[{"id":"arxiv-2608.24651","title":"AICON: An operational global machine learning weather forecasting model","authors":["Tobias Goecke","Marek Jacob","Florian Prill","Michael Denhard","Felix Fundel","Jan Keller","Roland Potthast","Hendrik Reich","Britta Seegebrecht","Sven Ulbrich","Arianna Valmassoi","Sabrina Wahl"],"date":"2026-08-25","year":2026,"venue_type":"preprint","ids":{"arxiv":"2608.24651","openalex":"W7204225272"},"links":{"paper":"https://arxiv.org/abs/2608.24651","pdf":"https://arxiv.org/pdf/2608.24651"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"operational","method":["gnn"],"timescale":["short","medium"],"spatial":["global"],"data":["km-scale-sim","nwp-analysis"],"status":"operational","summary":"AICON is a 13 km graph-neural-network global model run operationally at DWD, competitive with operational ICON for near-surface variables.","significance":6,"score":34,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1038-s41586-026-10953-2","title":"Operational tropical cyclone forecasting with AI","authors":["Ferran Alet","Tom R. Andersson","Ilan Price","Stratis Markou","Andrew El-Kadi","Dominic Masters","Amy Li","Samier Merchant","Natalie Williams","Gregory Thornton","Ken MacKay","Olivia Graham","Akib Uddin","Ben Gaiarin","Devaja Shah","Elinor Kruse","Wallace Hogsett","David Zelinsky","John Cangialosi","Jonathan Martinez","James Franklin","Mark DeMaria","Kate Musgrave","Caroline L. Bain","Helen Titley","Jacklynn Stott","Remi Lam","Aaron Bell","Paul Komarek","Matthew Willson","Alvaro Sanchez-Gonzalez","Peter Battaglia"],"date":"2026-08-06","year":2026,"venue":"Nature","venue_type":"journal","ids":{"doi":"10.1038/s41586-026-10953-2","openalex":"W7196929311"},"links":{"paper":"https://doi.org/10.1038/s41586-026-10953-2"},"orgs":["colorado-state-university","google-deepmind","google-research","met-office","noaa"],"topic":"extremes-hazards","topics":["probabilistic-ensembles","global-medium-range"],"type":"model","method":[],"timescale":["medium"],"spatial":["global"],"data":["era5","other"],"status":"operational","summary":"Operational AI ensemble WeatherNext Cyclones predicts tropical cyclone track, intensity and size to 15 days, gaining about 1 day of lead time over leading operational models.","significance":8,"cited_by":1,"score":97,"highlight":true,"highlight_reason":"Nature paper on operational AI cyclone ensemble WeatherNext Cyclones, showing about one day lead-time gains over leading operational models in track and intensity.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2605.01126","title":"Extreme Weather Bench: A framework and benchmark for evaluation of high-impact weather","authors":["Amy McGovern","Taylor Mandelbaum","Daniel Rothenberg","Nicholas Loveday","Corey Potvin","Montgomery Flora","Linus Magnusson","Eric Gilleland","John Allen"],"date":"2026-05-01","year":2026,"venue_type":"preprint","ids":{"arxiv":"2605.01126","openalex":"W7160254805"},"links":{"paper":"https://arxiv.org/abs/2605.01126","pdf":"https://arxiv.org/pdf/2605.01126"},"orgs":[],"topic":"benchmarks-data-eval","topics":["extremes-hazards"],"type":"benchmark","method":[],"timescale":["short","medium"],"spatial":["global","regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Extreme Weather Bench is an open community benchmark of case studies, observations and impact metrics for verifying AI and NWP models on high-impact weather.","significance":6,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2604.16922","title":"ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis","authors":["Hao Wang","Jindong Han","Wei Fan","Hao Liu"],"date":"2026-01-01","year":2026,"venue":"Findings of the Association for Computational Linguistics: ACL 2026","venue_type":"preprint","ids":{"arxiv":"2604.16922","doi":"10.18653/v1/2026.findings-acl.1067","openalex":"W7166818636"},"links":{"paper":"https://arxiv.org/abs/2604.16922","pdf":"https://arxiv.org/pdf/2604.16922","code":"https://github.com/usail-hkust/ClimAgent"},"orgs":[],"topic":"llms-agents","topics":["climate-analysis-attribution"],"type":"model","method":["llm"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"ClimAgent is an LLM agent framework that runs end-to-end climate science analyses, introducing ClimaBench and a 40% gain over baseline LLM solutions.","significance":4,"cited_by":1,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2511.20109","title":"CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows","authors":["Chenyue Li","Hyeonjae Kim","Wen Deng","Mengxi Jin","Wen Huang","Mengqian Lu","Binhang Yuan"],"date":"2025-11-25","year":2025,"venue_type":"preprint","ids":{"arxiv":"2511.20109","openalex":"W7106816661"},"links":{"paper":"https://arxiv.org/abs/2511.20109","pdf":"https://arxiv.org/pdf/2511.20109","code":"https://github.com/Relaxed-System-Lab/ClimateAgent"},"orgs":[],"topic":"llms-agents","topics":["benchmarks-data-eval"],"type":"model","method":["llm"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A multi-agent LLM framework completes climate data workflows with 100% task completion on an 85-task benchmark, beating a GPT-5 baseline.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2510.04017","title":"Zephyrus: An Agentic Framework for Weather Science","authors":["Sumanth Varambally","Marshall Fisher","Jas Thakker","Yiwei Chen","Zhirui Xia","Yasaman Jafari","Ruijia Niu","Manas Jain","Veeramakali Vignesh Manivannan","Zachary Novack","Luyu Han","Srikar Eranky","Salva Rühling Cachay","Taylor Berg-Kirkpatrick","Duncan Watson-Parris","Yi-An Ma","Rose Yu"],"date":"2025-10-05","year":2025,"venue_type":"preprint","ids":{"arxiv":"2510.04017","openalex":"W4416373925"},"links":{"paper":"https://arxiv.org/abs/2510.04017","pdf":"https://arxiv.org/pdf/2510.04017","code":"https://github.com/Rose-STL-Lab/Zephyrus"},"orgs":[],"topic":"llms-agents","topics":["benchmarks-data-eval"],"type":"model","method":["llm"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Zephyrus is an LLM agent with a weather-data environment and ZephyrusBench, outperforming text-only baselines by up to 44 points in correctness.","significance":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2509.18994","title":"An update to ECMWF's machine-learned weather forecast model AIFS","authors":["Gabriel Moldovan","Ewan Pinnington","Ana Prieto Nemesio","Simon Lang","Zied Ben Bouallègue","Jesper Dramsch","Mihai Alexe","Mario Santa Cruz","Sara Hahner","Harrison Cook","Helen Theissen","Mariana Clare","Cathal O'Brien","Jan Polster","Linus Magnusson","Gert Mertes","Florian Pinault","Baudouin Raoult","Patricia de Rosnay","Richard Forbes","Matthew Chantry"],"date":"2025-09-23","year":2025,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"arxiv":"2509.18994","doi":"10.5194/gmd-19-4703-2026","openalex":"W7163046362"},"links":{"paper":"https://arxiv.org/abs/2509.18994","pdf":"https://arxiv.org/pdf/2509.18994"},"orgs":["ecmwf"],"topic":"global-medium-range","topics":[],"type":"operational","method":[],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"operational","summary":"Updates ECMWF's AIFS with bounding layers for physical consistency, better precipitation and new variables; operational at ECMWF since February 2025.","significance":7,"cited_by":9,"score":73,"highlight":true,"highlight_reason":"Documents the operational ECMWF AIFS upgrade with bounding layers that improve precipitation and new variables; important reference for operational ML forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2509.13523","title":"AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions","authors":["Väinö Hatanpää","Eugene Ku","Jason Stock","Murali Emani","Sam Foreman","Chunyong Jung","Sandeep Madireddy","Tung Nguyen","Varuni Sastry","Ray A. O. Sinurat","Sam Wheeler","Huihuo Zheng","Troy Arcomano","Venkatram Vishwanath","Rao Kotamarthi"],"date":"2025-09-16","year":2025,"venue":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","venue_type":"preprint","ids":{"arxiv":"2509.13523","doi":"10.1145/3712285.3772094","openalex":"W4416203801"},"links":{"paper":"https://arxiv.org/abs/2509.13523","pdf":"https://arxiv.org/pdf/2509.13523"},"orgs":["ai2","argonne","ucla","university-of-chicago"],"topic":"infra-software","topics":["global-medium-range"],"type":"model","method":["diffusion","transformer"],"timescale":["medium","seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"AERIS is a 1.3 to 80B parameter Swin diffusion transformer reaching 10.2 ExaFLOPS on Aurora, stable to 90-day forecasts and outperforming IFS ENS.","significance":7,"cited_by":3,"score":63,"highlight":true,"highlight_reason":"Scales diffusion transformers to 80B parameters at 0.25° with exaflop performance, beating IFS ENS and stable to seasonal scales.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2509.12490","title":"SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators","authors":["James P. C. Duncan","Elynn Wu","Surya Dheeshjith","Adam Subel","Troy Arcomano","Spencer K. Clark","Brian Henn","Anna Kwa","Jeremy McGibbon","W. Andre Perkins","William Gregory","Carlos Fernandez-Granda","Julius Busecke","Oliver Watt-Meyer","William J. Hurlin","Alistair Adcroft","Laure Zanna","Christopher Bretherton"],"date":"2025-09-15","year":2025,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"arxiv":"2509.12490","doi":"10.1029/2025gl119340","openalex":"W4415315983"},"links":{"paper":"https://arxiv.org/abs/2509.12490","pdf":"https://arxiv.org/pdf/2509.12490"},"orgs":["ai2","columbia-leap","noaa","nyu-m2lines","princeton-university"],"topic":"climate-emulation","topics":[],"type":"model","method":[],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"SamudrACE is a coupled atmosphere-ocean ML emulator giving stable centuries-long runs at 1 degree with realistic ENSO variability absent in uncoupled mode.","significance":7,"cited_by":3,"score":63,"highlight":true,"highlight_reason":"First stable coupled atmosphere-ocean ML climate emulator over centuries with ENSO; major step for ML climate modelling.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2507.12144","title":"FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale","authors":["Boris Bonev","Thorsten Kurth","Ankur Mahesh","Mauro Bisson","Jean Kossaifi","Karthik Kashinath","Anima Anandkumar","William D. Collins","Michael S. Pritchard","Alexander Keller"],"date":"2025-07-16","year":2025,"venue_type":"preprint","ids":{"arxiv":"2507.12144","openalex":"W4414985038"},"links":{"paper":"https://arxiv.org/abs/2507.12144","pdf":"https://arxiv.org/pdf/2507.12144"},"orgs":[],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["cnn","other"],"timescale":["medium","s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"FourCastNet 3 is a spherical-CNN probabilistic ensemble model that rivals diffusion models, forecasts 8-60x faster, and stays calibrated and spectrally realistic to 60 days.","significance":6,"cited_by":3,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2507.05658","title":"HRRRCast: a data-driven emulator for regional weather forecasting at convection allowing scales","authors":["Daniel Abdi","Isidora Jankov","Paul Madden","Vanderlei Vargas","Timothy A. Smith","Sergey Frolov","Montgomery Flora","Corey Potvin"],"date":"2025-07-08","year":2025,"venue":"Artificial Intelligence for the Earth Systems, Vol. 5, No. 2, 2026, Article 250061","venue_type":"journal","ids":{"arxiv":"2507.05658","doi":"10.1175/aies-d-25-0061.1","openalex":"W4416060956"},"links":{"paper":"https://arxiv.org/abs/2507.05658","pdf":"https://arxiv.org/pdf/2507.05658"},"orgs":["colorado-state-university","noaa","university-of-oklahoma"],"topic":"regional-km-scale","topics":["probabilistic-ensembles"],"type":"model","method":["cnn","diffusion","gnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"research","summary":"HRRRCast is a ResNet-based emulator of the HRRR convection-allowing model over CONUS, with DDIM ensembles that beat HRRR at the 20 dBZ reflectivity threshold.","significance":4,"cited_by":4,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2506.10772","title":"Skillful joint probabilistic weather forecasting from marginals","authors":["Ferran Alet","Ilan Price","Andrew El-Kadi","Dominic Masters","Stratis Markou","Tom R. Andersson","Jacklynn Stott","Remi Lam","Matthew Willson","Alvaro Sanchez-Gonzalez","Peter Battaglia"],"date":"2025-06-12","year":2025,"venue_type":"preprint","ids":{"arxiv":"2506.10772","openalex":"W4417355657"},"links":{"paper":"https://arxiv.org/abs/2506.10772","pdf":"https://arxiv.org/pdf/2506.10772"},"orgs":[],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"FGN generates ensembles through learned model perturbations trained on per-location CRPS, achieving state-of-the-art probabilistic skill and skillful ensemble tropical cyclone tracks.","significance":6,"cited_by":4,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2505.06474","title":"Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere","authors":["Noah D. Brenowitz","Tao Ge","Akshay Subramaniam","Peter Manshausen","Aayush Gupta","David M. Hall","Morteza Mardani","Arash Vahdat","Karthik Kashinath","Michael S. Pritchard"],"date":"2025-05-10","year":2025,"venue_type":"preprint","ids":{"arxiv":"2505.06474","openalex":"W4417512511"},"links":{"paper":"https://arxiv.org/abs/2505.06474","pdf":"https://arxiv.org/pdf/2505.06474"},"orgs":[],"topic":"climate-emulation","topics":["foundation-models","extremes-hazards"],"type":"model","method":["diffusion","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["era5","cmip","km-scale-sim"],"status":"research","summary":"cBottle is a generative diffusion emulator of global 5 km climate simulations and reanalysis on HEALPix, avoiding autoregressive rollout and reaching 12.5M-pixel resolution.","significance":6,"cited_by":1,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2505.04802","title":"ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling","authors":["Xiao Wang","Jong-Youl Choi","Takuya Kurihaya","Isaac Lyngaas","Hong-Jun Yoon","Xi Xiao","David Pugmire","Ming Fan","Nasik M. Nafi","Aristeidis Tsaris","Ashwin M. Aji","Maliha Hossain","Mohamed Wahib","Dali Wang","Peter Thornton","Prasanna Balaprakash","Moetasim Ashfaq","Dan Lu"],"date":"2025-05-07","year":2025,"venue":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","venue_type":"preprint","ids":{"arxiv":"2505.04802","doi":"10.1145/3712285.3771989","openalex":"W4416146665"},"links":{"paper":"https://arxiv.org/abs/2505.04802","pdf":"https://arxiv.org/pdf/2505.04802"},"orgs":["ornl"],"topic":"foundation-models","topics":["infra-software"],"type":"model","method":["transformer"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"ORBIT-2 is a 10-billion-parameter ViT downscaling foundation model reaching 0.9 km global resolution on 65,536 GPUs with R² of 0.98–0.99 on 7 km benchmarks.","significance":5,"cited_by":4,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2504.09340","title":"Building Machine Learning Limited Area Models: Kilometer-Scale Weather Forecasting in Realistic Settings","authors":["Simon Adamov","Joel Oskarsson","Leif Denby","Tomas Landelius","Kasper Hintz","Simon Christiansen","Irene Schicker","Carlos Osuna","Fredrik Lindsten","Oliver Fuhrer","Sebastian Schemm"],"date":"2025-04-12","year":2025,"venue_type":"preprint","ids":{"arxiv":"2504.09340","openalex":"W4415156407"},"links":{"paper":"https://arxiv.org/abs/2504.09340","pdf":"https://arxiv.org/pdf/2504.09340","code":"https://github.com/joeloskarsson/neural-lam-dev"},"orgs":[],"topic":"regional-km-scale","topics":["global-medium-range"],"type":"model","method":["gnn"],"timescale":["medium"],"spatial":["regional"],"data":["era5","nwp-analysis","stations"],"status":"research","summary":"Kilometre-scale graph-based limited-area models for Denmark and Switzerland, driven by flexible boundary forcing, match or beat the NWP baseline for key surface variables.","significance":5,"cited_by":1,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2503.23953","title":"Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data","authors":["Chris Kent","Adam A. Scaife","Nick J. Dunstone","Doug Smith","Steven C. Hardiman","Tom Dunstan","Oliver Watt-Meyer"],"date":"2025-03-31","year":2025,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"arxiv":"2503.23953","doi":"10.1038/s41612-025-01198-3","openalex":"W4413523434"},"links":{"paper":"https://arxiv.org/abs/2503.23953","pdf":"https://arxiv.org/pdf/2503.23953"},"orgs":["ai2","met-office"],"topic":"s2s-seasonal","topics":["climate-emulation","global-medium-range"],"type":"evaluation","method":["other"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"ACE2 produces skilful winter seasonal forecasts from SST-persisted initialisation, reaching NAO correlation 0.47 over 1993–2016, comparable to a physics-based model.","significance":6,"cited_by":19,"score":59,"highlight":true,"highlight_reason":"Shows ACE2 emulator has skilful seasonal NAO prediction, hinting ML weather models can serve seasonal forecasting; notable signal-to-noise finding.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1038-s41467-025-56573-8","title":"Artificial intelligence for modeling and understanding extreme weather and climate events","authors":["Gustau Camps-Valls","Miguel-Ángel Fernández-Torres","Kai-Hendrik Cohrs","Adrian Höhl","Andrea Castelletti","Aytac Pacal","Claire Robin","Francesco Martinuzzi","Ioannis Papoutsis","Ioannis Prapas","Jorge Pérez-Aracil","Katja Weigel","Maria Gonzalez-Calabuig","Markus Reichstein","Martin Rabel","Matteo Giuliani","Miguel D. Mahecha","Oana-Iuliana Popescu","Oscar J. Pellicer-Valero","Said Ouala","Sancho Salcedo-Sanz","Sebastian Sippel","Spyros Kondylatos","Tamara Happé","Tristan Williams"],"date":"2025-02-24","year":2025,"venue":"Nature Communications","venue_type":"journal","ids":{"doi":"10.1038/s41467-025-56573-8","openalex":"W4407870507"},"links":{"paper":"https://doi.org/10.1038/s41467-025-56573-8"},"orgs":["inria","mpi-biogeochemistry","tum"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Nature Communications review of AI for modeling and understanding extreme weather and climate events; abstract absent, judged from title and venue.","significance":4,"cited_by":309,"score":56,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2502.07532","title":"Diffusion-LAM: Probabilistic Limited Area Weather Forecasting with Diffusion","authors":["Erik Larsson","Joel Oskarsson","Tomas Landelius","Fredrik Lindsten"],"date":"2025-02-11","year":2025,"venue_type":"preprint","ids":{"arxiv":"2502.07532","openalex":"W4407424958"},"links":{"paper":"https://arxiv.org/abs/2502.07532","pdf":"https://arxiv.org/pdf/2502.07532"},"orgs":[],"topic":"regional-km-scale","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Diffusion-LAM is a conditional diffusion model that generates probabilistic limited-area forecasts from boundary conditions, demonstrated on the MEPS regional ensemble dataset.","significance":4,"cited_by":2,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2412.15832","title":"AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score","authors":["Simon Lang","Mihai Alexe","Mariana C. A. Clare","Christopher Roberts","Rilwan Adewoyin","Zied Ben Bouallègue","Matthew Chantry","Jesper Dramsch","Peter D. Dueben","Sara Hahner","Pedro Maciel","Ana Prieto-Nemesio","Cathal O'Brien","Florian Pinault","Jan Polster","Baudouin Raoult","Steffen Tietsche","Martin Leutbecher"],"date":"2024-12-20","year":2024,"venue":"npj Artificial Intelligence","venue_type":"journal","ids":{"arxiv":"2412.15832","doi":"10.1038/s44387-026-00073-7","openalex":"W7127046044"},"links":{"paper":"https://arxiv.org/abs/2412.15832","pdf":"https://arxiv.org/pdf/2412.15832"},"orgs":["ecmwf"],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["transformer","other"],"timescale":["medium","s2s"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"operational","summary":"AIFS-CRPS trains an ML ensemble model on a CRPS-based loss, outperforming the IFS ensemble for most medium-range variables and competing at subseasonal lead times.","significance":8,"cited_by":31,"score":77,"highlight":true,"highlight_reason":"ECMWF's CRPS-trained ensemble AIFS, outperforming IFS ENS and later operational; key reference for ensemble ML forecasting without diffusion.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2412.15687","title":"GraphDOP: Towards skilful data-driven medium-range weather forecasts learnt and initialised directly from observations","authors":["Mihai Alexe","Eulalie Boucher","Peter Lean","Ewan Pinnington","Patrick Laloyaux","Anthony McNally","Simon Lang","Matthew Chantry","Chris Burrows","Marcin Chrust","Florian Pinault","Ethel Villeneuve","Niels Bormann","Sean Healy"],"date":"2024-12-20","year":2024,"venue_type":"preprint","ids":{"arxiv":"2412.15687","openalex":"W4405715399"},"links":{"paper":"https://arxiv.org/abs/2412.15687","pdf":"https://arxiv.org/pdf/2412.15687"},"orgs":[],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["gnn"],"timescale":["medium"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"GraphDOP is an ECMWF graph model trained and initialised only from satellite and conventional observations, giving skilful forecasts up to five days ahead.","significance":6,"cited_by":3,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2412.12971","title":"ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting","authors":["Guillaume Couairon","Renu Singh","Anastase Charantonis","Christian Lessig","Claire Monteleoni"],"date":"2024-12-17","year":2024,"venue":"Science Advances","venue_type":"journal","ids":{"arxiv":"2412.12971","doi":"10.1126/sciadv.adx2372","openalex":"W7155213685"},"links":{"paper":"https://arxiv.org/abs/2412.12971","pdf":"https://arxiv.org/pdf/2412.12971","code":"https://github.com/INRIA/geoarches"},"orgs":["ecmwf","inria"],"topic":"probabilistic-ensembles","topics":[],"type":"model","method":["transformer","diffusion"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"ArchesWeather is a transformer deterministic model, and ArchesWeatherGen a flow-matching ensemble that beats IFS ENS and NeuralGCM on WeatherBench headline variables at academic compute cost.","significance":6,"cited_by":5,"score":89,"highlight":true,"highlight_reason":"Efficient academic-scale deterministic plus flow-matching generative model beating IFS ENS and NeuralGCM at 1.5°; useful recipe for probabilistic ML forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2412.11973","title":"Neural general circulation models optimized to predict satellite-based precipitation observations","authors":["Janni Yuval","Ian Langmore","Dmitrii Kochkov","Stephan Hoyer"],"date":"2024-12-16","year":2024,"venue":"Science Advances","venue_type":"journal","ids":{"arxiv":"2412.11973","doi":"10.1126/sciadv.adv6891","openalex":"W7119133558"},"links":{"paper":"https://arxiv.org/abs/2412.11973","pdf":"https://arxiv.org/pdf/2412.11973"},"orgs":["google-research"],"topic":"hybrid-parameterization","topics":["observations-remote-sensing"],"type":"model","method":["differentiable"],"timescale":["climate"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A NeuralGCM-based hybrid model trained on satellite precipitation cuts climate-model precipitation biases and beats the ECMWF ensemble at mid-range forecasts.","significance":6,"cited_by":8,"score":79,"highlight":true,"highlight_reason":"NeuralGCM trained directly on satellite precipitation improves extremes and the diurnal cycle over GCMs and ERA5. It shows that hybrid models can learn from observations.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2412.04418","title":"ACE2-SOM: Coupling an ML atmospheric emulator to a slab ocean and learning the sensitivity of climate to changed CO$_2$","authors":["Spencer K. Clark","Oliver Watt-Meyer","Anna Kwa","Jeremy McGibbon","Brian Henn","W. Andre Perkins","Elynn Wu","Lucas M. Harris","Christopher S. Bretherton"],"date":"2024-12-05","year":2024,"venue":"Journal of Geophysical Research: Machine Learning and Computation","venue_type":"journal","ids":{"arxiv":"2412.04418","doi":"10.1029/2024jh000575","openalex":"W4414672403"},"links":{"paper":"https://arxiv.org/abs/2412.04418","pdf":"https://arxiv.org/pdf/2412.04418"},"orgs":["ai2","noaa"],"topic":"climate-emulation","topics":[],"type":"model","method":["neural-operator"],"timescale":["climate"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"Couples the ACE2 emulator to a slab ocean and trains it across CO2 levels, reproducing equilibrium warming but violating energy conservation in transient runs.","significance":5,"cited_by":9,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2411.11268","title":"ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses","authors":["Oliver Watt-Meyer","Brian Henn","Jeremy McGibbon","Spencer K. Clark","Anna Kwa","W. Andre Perkins","Elynn Wu","Lucas Harris","Christopher S. Bretherton"],"date":"2024-11-18","year":2024,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"arxiv":"2411.11268","doi":"10.1038/s41612-025-01090-0","openalex":"W4410856408"},"links":{"paper":"https://arxiv.org/abs/2411.11268","pdf":"https://arxiv.org/pdf/2411.11268"},"orgs":["ai2","noaa"],"topic":"climate-emulation","topics":["s2s-seasonal"],"type":"model","method":["neural-operator"],"timescale":["s2s","seasonal","decadal"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"ACE2 is a 450M-parameter emulator that conserves dry air and moisture, runs about 1500 simulated years per day, and reproduces El Niño responses over 80 years.","significance":7,"cited_by":37,"score":63,"highlight":true,"highlight_reason":"ACE2 is a stable, mass-conserving climate emulator that reproduces El Niño responses and 80-year trends at about 1500 simulated years per day. It is a strong step for ML climate emulation.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2411.05420","title":"WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning","authors":["Xiangyu Zhao","Zhiwang Zhou","Wenlong Zhang","Yihao Liu","Xiangyu Chen","Junchao Gong","Hao Chen","Ben Fei","Shiqi Chen","Wanli Ouyang","Xiao-Ming Wu","Lei Bai"],"date":"2024-11-08","year":2024,"venue_type":"preprint","ids":{"arxiv":"2411.05420","openalex":"W4404389581"},"links":{"paper":"https://arxiv.org/abs/2411.05420","pdf":"https://arxiv.org/pdf/2411.05420"},"orgs":["shanghai-ai-lab"],"topic":"foundation-models","topics":["post-processing"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"WeatherGFM is a generalist weather foundation model using in-context visual prompting to handle up to ten weather tasks, including forecasting, super-resolution and post-processing.","significance":4,"cited_by":1,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-gmd-17-7915-2024","title":"Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast","authors":["Leonardo Olivetti","Gabriele Messori"],"date":"2024-11-07","year":2024,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-17-7915-2024","openalex":"W4404143263"},"links":{"paper":"https://doi.org/10.5194/gmd-17-7915-2024"},"orgs":[],"topic":"extremes-hazards","topics":["global-medium-range","benchmarks-data-eval"],"type":"evaluation","method":["transformer","gnn"],"timescale":["medium","short"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Comparison of Pangu-Weather, GraphCast and IFS HRES finds data-driven models mostly beat IFS on global RMSE for 1-10 day forecasts and compete on temperature and wind extremes.","significance":5,"cited_by":41,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2410.19882","title":"Recommendations for Comprehensive and Independent Evaluation of Machine Learning-Based Earth System Models","authors":["Paul A. Ullrich","Elizabeth A. Barnes","William D. Collins","Katherine Dagon","Shiheng Duan","Joshua Elms","Jiwoo Lee","L. Ruby Leung","Dan Lu","Maria J. Molina","Travis A. O'Brien","Finn O. Rebassoo"],"date":"2024-10-24","year":2024,"venue":"Journal of Geophysical Research: Machine Learning and Computation","venue_type":"journal","ids":{"arxiv":"2410.19882","doi":"10.1029/2024jh000496","openalex":"W4408457719"},"links":{"paper":"https://arxiv.org/abs/2410.19882","pdf":"https://arxiv.org/pdf/2410.19882"},"orgs":["colorado-state-university","lbnl-nersc","ncar","ornl","uc-berkeley"],"topic":"benchmarks-data-eval","topics":["climate-emulation","xai-uq-physics"],"type":"position","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Five recommendations for standardized, independent evaluation of ML-based Earth system models, stressing physical consistency for climate projections without historical analogues.","significance":4,"cited_by":8,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2410.14932","title":"Can AI weather models predict out-of-distribution gray swan tropical cyclones?","authors":["Y. Qiang Sun","Pedram Hassanzadeh","Mohsen Zand","Ashesh Chattopadhyay","Jonathan Weare","Dorian S. Abbot"],"date":"2024-10-19","year":2024,"venue":"Proceedings of the National Academy of Sciences","venue_type":"journal","ids":{"arxiv":"2410.14932","doi":"10.1073/pnas.2420914122","openalex":"W4410535525"},"links":{"paper":"https://arxiv.org/abs/2410.14932","pdf":"https://arxiv.org/pdf/2410.14932"},"orgs":["nyu-m2lines","university-of-chicago"],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"evaluation","method":["neural-operator"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"FourCastNet trained without Category 3-5 cyclones cannot forecast Category 5 storms, showing AI weather models fail to extrapolate to unseen extremes.","significance":7,"cited_by":51,"score":58,"highlight":true,"highlight_reason":"Shows FourCastNet cannot extrapolate to unseen Category 5 cyclones when trained without strong storms. This is a key limit on AI forecasting of gray swan extremes.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2410.07472","title":"Exploring the design space of deep-learning-based weather forecasting systems","authors":["Shoaib Ahmed Siddiqui","Jean Kossaifi","Boris Bonev","Christopher Choy","Jan Kautz","David Krueger","Kamyar Azizzadenesheli"],"date":"2024-10-09","year":2024,"venue_type":"preprint","ids":{"arxiv":"2410.07472","openalex":"W4403364907"},"links":{"paper":"https://arxiv.org/abs/2410.07472","pdf":"https://arxiv.org/pdf/2410.07472"},"orgs":["nvidia","university-of-cambridge"],"topic":"infra-software","topics":[],"type":"evaluation","method":["transformer","cnn","gnn","neural-operator"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Systematic study of design choices for DL weather models finds fixed-grid architectures beat grid-invariant ones, proposes a hybrid, and shows multi-step fine-tuning is essential.","significance":5,"cited_by":3,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2410.05431","title":"Continuous Ensemble Weather Forecasting with Diffusion models","authors":["Martin Andrae","Tomas Landelius","Joel Oskarsson","Fredrik Lindsten"],"date":"2024-10-07","year":2024,"venue_type":"preprint","ids":{"arxiv":"2410.05431","openalex":"W4403346255"},"links":{"paper":"https://arxiv.org/abs/2410.05431","pdf":"https://arxiv.org/pdf/2410.05431","code":"https://github.com/martinandrae/Continuous-Ensemble-Forecasting"},"orgs":[],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["diffusion"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Continuous Ensemble Forecasting samples diffusion ensemble trajectories in parallel without autoregressive rollout, achieving competitive global forecasts at arbitrary temporal resolution.","significance":4,"cited_by":1,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2410.01776","title":"Dynamical-generative downscaling of climate model ensembles","authors":["Ignacio Lopez-Gomez","Zhong Yi Wan","Leonardo Zepeda-Núñez","Tapio Schneider","John Anderson","Fei Sha"],"date":"2024-10-02","year":2024,"venue":"Proceedings of the National Academy of Sciences","venue_type":"journal","ids":{"arxiv":"2410.01776","doi":"10.1073/pnas.2420288122","openalex":"W4409795612"},"links":{"paper":"https://arxiv.org/abs/2410.01776","pdf":"https://arxiv.org/pdf/2410.01776"},"orgs":["caltech","google-research"],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"model","method":["diffusion","physics-constrained"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Combining RCM dynamical downscaling with diffusion refinement lets large CMIP6 ensembles be downscaled cheaply, giving better uncertainty bounds than BCSD and smaller dynamical ensembles.","significance":6,"cited_by":60,"score":79,"highlight":true,"highlight_reason":"Combines RCM downscaling to an intermediate resolution with diffusion refinement, which makes downscaling large CMIP6 ensembles affordable and gives better uncertainty bounds than BCSD.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2409.18529","title":"Robustness of AI-based weather forecasts in a changing climate","authors":["Thomas Rackow","Nikolay Koldunov","Christian Lessig","Irina Sandu","Mihai Alexe","Matthew Chantry","Mariana Clare","Jesper Dramsch","Florian Pappenberger","Xabier Pedruzo-Bagazgoitia","Steffen Tietsche","Thomas Jung"],"date":"2024-09-27","year":2024,"venue_type":"preprint","ids":{"arxiv":"2409.18529","openalex":"W4403798800"},"links":{"paper":"https://arxiv.org/abs/2409.18529","pdf":"https://arxiv.org/pdf/2409.18529"},"orgs":["ecmwf"],"topic":"xai-uq-physics","topics":[],"type":"evaluation","method":[],"timescale":["medium","climate"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"Shows weather-trained ML models forecast skillfully across pre-industrial, present-day and +2.9K climates, though two models show global-mean drift biases toward their training climate.","significance":6,"cited_by":3,"score":59,"highlight":true,"highlight_reason":"Shows AI weather models forecast skillfully in pre-industrial and warmer climates but drift toward present-day temperatures, which bears directly on using them for climate work.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2409.16247","title":"A Deep Learning Earth System Model for Efficient Simulation of the Observed Climate","authors":["Nathaniel Cresswell-Clay","Bowen Liu","Dale Durran","Zihui Liu","Zachary I. Espinosa","Raul Moreno","Matthias Karlbauer"],"date":"2024-09-24","year":2024,"venue":"AGU Advances, 6, e2025AV001706","venue_type":"journal","ids":{"arxiv":"2409.16247","doi":"10.1029/2025av001706","openalex":"W4413501898"},"links":{"paper":"https://arxiv.org/abs/2409.16247","pdf":"https://arxiv.org/pdf/2409.16247"},"orgs":["iap-cas","university-of-washington"],"topic":"climate-emulation","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["climate","seasonal"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"DLESyM, a deep learning Earth system model, simulates 1000-year observed climate without drift, matching CMIP6 variability at a fraction of the cost.","significance":5,"cited_by":18,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2409.13598","title":"Prithvi WxC: Foundation Model for Weather and Climate","authors":["Johannes Schmude","Sujit Roy","Will Trojak","Johannes Jakubik","Daniel Salles Civitarese","Shraddha Singh","Julian Kuehnert","Kumar Ankur","Aman Gupta","Christopher E Phillips","Romeo Kienzler","Daniela Szwarcman","Vishal Gaur","Rajat Shinde","Rohit Lal","Arlindo Da Silva","Jorge Luis Guevara Diaz","Anne Jones","Simon Pfreundschuh","Amy Lin","Aditi Sheshadri","Udaysankar Nair","Valentine Anantharaj","Hendrik Hamann","Campbell Watson","Manil Maskey","Tsengdar J Lee","Juan Bernabe Moreno","Rahul Ramachandran"],"date":"2024-09-20","year":2024,"venue_type":"preprint","ids":{"arxiv":"2409.13598","openalex":"W4403775115"},"links":{"paper":"https://arxiv.org/abs/2409.13598","pdf":"https://arxiv.org/pdf/2409.13598"},"orgs":[],"topic":"foundation-models","topics":["downscaling","extremes-hazards"],"type":"model","method":["transformer"],"timescale":["short","medium"],"spatial":["global","regional"],"data":["era5"],"status":"research","summary":"Prithvi WxC is a 2.3-billion-parameter MERRA-2 foundation model that transfers to forecasting, downscaling, gravity-wave parameterization and extreme-event tasks.","significance":6,"cited_by":11,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2409.09371","title":"WeatherReal: A Benchmark Based on In-Situ Observations for Evaluating Weather Models","authors":["Weixin Jin","Jonathan Weyn","Pengcheng Zhao","Siqi Xiang","Jiang Bian","Zuliang Fang","Haiyu Dong","Hongyu Sun","Kit Thambiratnam","Qi Zhang"],"date":"2024-09-14","year":2024,"venue_type":"preprint","ids":{"arxiv":"2409.09371","openalex":"W4403667177"},"links":{"paper":"https://arxiv.org/abs/2409.09371","pdf":"https://arxiv.org/pdf/2409.09371"},"orgs":[],"topic":"benchmarks-data-eval","topics":["observations-remote-sensing"],"type":"benchmark","method":[],"timescale":["medium"],"spatial":["global"],"data":["stations","era5"],"status":"research","summary":"Introduces WeatherReal, a benchmark from global in-situ surface observations showing reanalysis-trained AI models diverge from station data for temperature, wind and precipitation.","significance":5,"cited_by":1,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2409.02891","title":"Regional data-driven weather modeling with a global stretched-grid","authors":["Thomas Nils Nipen","Håvard Homleid Haugen","Magnus Sikora Ingstad","Even Marius Nordhagen","Aram Farhad Shafiq Salihi","Paulina Tedesco","Ivar Ambjørn Seierstad","Jørn Kristiansen","Simon Lang","Mihai Alexe","Jesper Dramsch","Baudouin Raoult","Gert Mertes","Matthew Chantry"],"date":"2024-09-04","year":2024,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2409.02891","doi":"10.1175/aies-d-25-0001.1","openalex":"W4416121871"},"links":{"paper":"https://arxiv.org/abs/2409.02891","pdf":"https://arxiv.org/pdf/2409.02891"},"orgs":["ecmwf","met-norway"],"topic":"regional-km-scale","topics":["global-medium-range"],"type":"model","method":["gnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","nwp-analysis","stations"],"status":"research","summary":"Graph-based stretched-grid model refines a global AI model to 2.5 km over the Nordics, beating the MEPS ensemble mean for 2 m temperature but underestimating extremes.","significance":6,"cited_by":16,"score":59,"highlight":true,"highlight_reason":"Stretched-grid GNN extending AIFS gives 2.5 km regional forecasts over the Nordics, beating MEPS on 2 m temperature; the approach underpins later Anemoi regional systems.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1126-sciadv.adl3242","title":"Machine learning–based extreme event attribution","authors":["Jared T. Trok","Elizabeth A. Barnes","Frances V. Davenport","Noah S. Diffenbaugh"],"date":"2024-08-23","year":2024,"venue":"Science Advances","venue_type":"journal","ids":{"doi":"10.1126/sciadv.adl3242","openalex":"W4401724841"},"links":{"paper":"https://doi.org/10.1126/sciadv.adl3242"},"orgs":["colorado-state-university","stanford"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"A CNN generates dynamically consistent counterfactual extreme heat events, estimating the 2023 southcentral North America heat was 1.18–1.42°C warmer due to warming.","significance":4,"cited_by":57,"score":46,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1038-s41558-024-02095-y","title":"Pushing the frontiers in climate modelling and analysis with machine learning","authors":["Veronika Eyring","William D. Collins","Pierre Gentine","Elizabeth A. Barnes","Marcelo Barreiro","Tom Beucler","Marc Bocquet","Christopher S. Bretherton","Hannah M. Christensen","Katherine Dagon","David John Gagne","David Hall","Dorit Hammerling","Stephan Hoyer","Fernando Iglesias-Suarez","Ignacio Lopez-Gomez","Marie C. McGraw","Gerald A. Meehl","Maria J. Molina","Claire Monteleoni","Juliane Mueller","Michael S. Pritchard","David Rolnick","Jakob Runge","Philip Stier","Oliver Watt-Meyer","Katja Weigel","Rose Yu","Laure Zanna"],"date":"2024-08-23","year":2024,"venue":"Nature Climate Change","venue_type":"journal","ids":{"doi":"10.1038/s41558-024-02095-y","openalex":"W4401806513"},"links":{"paper":"https://doi.org/10.1038/s41558-024-02095-y"},"orgs":["ai2","caltech","colorado-state-university","columbia-leap","google-research","inria","lbnl-nersc","ncar","nvidia","nyu-m2lines","uc-berkeley","university-of-oxford"],"topic":"climate-emulation","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Nature Climate Change perspective on machine learning in climate modelling and analysis; abstract absent, judged from title and venue.","significance":5,"cited_by":167,"score":85,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2408.10958","title":"Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modeling","authors":["Jaideep Pathak","Yair Cohen","Piyush Garg","Peter Harrington","Noah Brenowitz","Dale Durran","Morteza Mardani","Arash Vahdat","Shaoming Xu","Karthik Kashinath","Michael Pritchard"],"date":"2024-08-20","year":2024,"venue":"Science Advances","venue_type":"journal","ids":{"arxiv":"2408.10958","doi":"10.1126/sciadv.adv0423","openalex":"W7126248709"},"links":{"paper":"https://arxiv.org/abs/2408.10958","pdf":"https://arxiv.org/pdf/2408.10958"},"orgs":["nvidia"],"topic":"regional-km-scale","topics":[],"type":"model","method":["diffusion"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis","km-scale-sim"],"status":"research","summary":"StormCast, a generative diffusion emulator of the 3 km HRRR convection-allowing model, gives competitive 1-6 hour radar reflectivity skill with realistic cold pools and power spectra.","significance":7,"cited_by":12,"score":83,"highlight":true,"highlight_reason":"StormCast is a diffusion model emulating HRRR at 3 km with competitive 1-6 h skill; a leading step for regional km-scale ML prediction.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2408.09627","title":"Machine Learning for the Physics of Climate","authors":["Annalisa Bracco","Julien Brajard","Henk A. Dijkstra","Pedram Hassanzadeh","Christian Lessig","Claire Monteleoni"],"date":"2024-08-19","year":2024,"venue":"Nature Reviews Physics","venue_type":"journal","ids":{"arxiv":"2408.09627","doi":"10.1038/s42254-024-00776-3","openalex":"W4404226779"},"links":{"paper":"https://arxiv.org/abs/2408.09627","pdf":"https://arxiv.org/pdf/2408.09627"},"orgs":["ecmwf","inria","lbnl-nersc","university-of-chicago"],"topic":"hybrid-parameterization","topics":[],"type":"review","method":[],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Review of ML across climate physics, covering observation reconstruction, subgrid parameterization, causal inference and climate and weather prediction.","significance":4,"cited_by":76,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2408.06400","title":"MetMamba: Regional Weather Forecasting with Spatial-Temporal Mamba Model","authors":["Haoyu Qin","Yungang Chen","Qianchuan Jiang","Pengchao Sun","Xiancai Ye","Chao Lin"],"date":"2024-08-12","year":2024,"venue_type":"preprint","ids":{"arxiv":"2408.06400","openalex":"W4402426830"},"links":{"paper":"https://arxiv.org/abs/2408.06400","pdf":"https://arxiv.org/pdf/2408.06400"},"orgs":[],"topic":"regional-km-scale","topics":["global-medium-range"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"MetMamba uses a Mamba state-space backbone for regional forecasting, outperforming attention and neural operator backbones and enabling coupled limited-area training with a global host.","significance":4,"cited_by":1,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2408.05472","title":"FuXi Weather: A data-to-forecast machine learning system for global weather","authors":["Xiuyu Sun","Xiaohui Zhong","Xiaoze Xu","Yuanqing Huang","Hao Li","J. David Neelin","Deliang Chen","Jie Feng","Wei Han","Libo Wu","Yuan Qi"],"date":"2024-08-10","year":2024,"venue":"Nature Communications","venue_type":"journal","ids":{"arxiv":"2408.05472","doi":"10.1038/s41467-025-62024-1","openalex":"W4412522531"},"links":{"paper":"https://arxiv.org/abs/2408.05472","pdf":"https://arxiv.org/pdf/2408.05472"},"orgs":["cma","fudan-university","nuist","tsinghua-university","ucla"],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":[],"timescale":["medium"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"FuXi Weather is an ML system that assimilates multi-satellite observations and produces 10-day global forecasts, outperforming ECMWF HRES in observation-sparse regions like central Africa.","significance":8,"cited_by":31,"score":87,"highlight":true,"highlight_reason":"FuXi Weather assimilates satellite data end-to-end in a ML cycle and beats HRES at some lead times; a major step toward independence from NWP.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2408.03100","title":"Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operators","authors":["Ankur Mahesh","William Collins","Boris Bonev","Noah Brenowitz","Yair Cohen","Joshua Elms","Peter Harrington","Karthik Kashinath","Thorsten Kurth","Joshua North","Travis OBrien","Michael Pritchard","David Pruitt","Mark Risser","Shashank Subramanian","Jared Willard"],"date":"2024-08-06","year":2024,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"arxiv":"2408.03100","doi":"10.5194/gmd-18-5575-2025","openalex":"W4413992135"},"links":{"paper":"https://arxiv.org/abs/2408.03100","pdf":"https://arxiv.org/pdf/2408.03100"},"orgs":["lbnl-nersc","nvidia","uc-berkeley"],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["neural-operator"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"A 1.1-billion-parameter SFNO ensemble with bred vectors and perturbed parameters passes spectral tests and is calibrated, setting up ML huge ensembles of 1,000+ members.","significance":7,"cited_by":17,"score":63,"highlight":true,"highlight_reason":"SFNO-based calibrated ensemble design enabling huge ML ensembles for extremes; important for probabilistic ML forecasting and tail-risk studies.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2407.14158","title":"Machine learning emulation of precipitation from km-scale UK regional climate simulations using a diffusion model","authors":["Henry Addison","Elizabeth Kendon","Suman Ravuri","Laurence Aitchison","Peter AG Watson"],"date":"2024-07-19","year":2024,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2407.14158","doi":"10.1029/2025ms005140","openalex":"W7134167274"},"links":{"paper":"https://arxiv.org/abs/2407.14158","pdf":"https://arxiv.org/pdf/2407.14158"},"orgs":["met-office","nvidia"],"topic":"downscaling","topics":["climate-emulation"],"type":"model","method":["diffusion"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","km-scale-sim"],"status":"research","summary":"A diffusion model (CPMGEM) emulates 2.2 km UK convection-permitting precipitation from 60 km GCM inputs, reproducing extremes up to about 100-year return times at much lower cost.","significance":5,"cited_by":6,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2407.06100","title":"Leveraging data-driven weather models for improving numerical weather prediction skill through large-scale spectral nudging","authors":["Syed Zahid Husain","Leo Separovic","Jean-François Caron","Rabah Aider","Mark Buehner","Stéphane Chamberland","Ervig Lapalme","Ron McTaggart-Cowan","Christopher Subich","Paul A. Vaillancourt","Jing Yang","Ayrton Zadra"],"date":"2024-07-08","year":2024,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"arxiv":"2407.06100","doi":"10.1175/waf-d-24-0139.1","openalex":"W4412526239"},"links":{"paper":"https://arxiv.org/abs/2407.06100","pdf":"https://arxiv.org/pdf/2407.06100"},"orgs":["eccc"],"topic":"hybrid-parameterization","topics":["global-medium-range"],"type":"model","method":["gnn"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Hybrid NWP-AI system spectrally nudges GEM toward GraphCast large scales, improving prediction skill and tropical cyclone tracks while keeping physically consistent fine scales.","significance":4,"cited_by":12,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2407.00124","title":"Stable Machine-Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection-Permitting Simulations","authors":["Zeyuan Hu","Akshay Subramaniam","Zhiming Kuang","Jerry Lin","Sungduk Yu","Walter M. Hannah","Noah D. Brenowitz","Josh Romero","Michael S. Pritchard"],"date":"2024-06-28","year":2024,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2407.00124","doi":"10.1029/2024ms004618","openalex":"W4412173901"},"links":{"paper":"https://arxiv.org/abs/2407.00124","pdf":"https://arxiv.org/pdf/2407.00124"},"orgs":["nvidia"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A U-Net emulator of embedded cloud-resolving models gives a stable 5-year hybrid climate run with realistic cloud condensate and a 0.96 mm/day precipitation RMSE.","significance":6,"cited_by":15,"score":59,"highlight":true,"highlight_reason":"Stable multi-year hybrid climate run with an ML subgrid parameterization learned from MMF, with real geography and cloud condensate; a notable step for ML parameterization.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2406.16947","title":"Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scales","authors":["Peter Manshausen","Yair Cohen","Peter Harrington","Jaideep Pathak","Mike Pritchard","Piyush Garg","Morteza Mardani","Karthik Kashinath","Simon Byrne","Noah Brenowitz"],"date":"2024-06-19","year":2024,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2406.16947","doi":"10.1029/2024ms004505","openalex":"W4415620306"},"links":{"paper":"https://arxiv.org/abs/2406.16947","pdf":"https://arxiv.org/pdf/2406.16947"},"orgs":["nvidia","university-of-oxford"],"topic":"data-assimilation","topics":["regional-km-scale"],"type":"model","method":["diffusion"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Score-based diffusion data assimilation at km scale assimilates 40 sparse weather stations, lowering held-out station RMSE by 10% versus HRRR.","significance":5,"cited_by":18,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2406.11217","title":"WeatherQA: Can Multimodal Language Models Reason about Severe Weather?","authors":["Chengqian Ma","Zhanxiang Hua","Alexandra Anderson-Frey","Vikram Iyer","Xin Liu","Lianhui Qin"],"date":"2024-06-17","year":2024,"venue_type":"preprint","ids":{"arxiv":"2406.11217","openalex":"W4399794948"},"links":{"paper":"https://arxiv.org/abs/2406.11217","pdf":"https://arxiv.org/pdf/2406.11217","code":"https://github.com/chengqianma/WeatherQA"},"orgs":["ai2","university-of-washington"],"topic":"llms-agents","topics":["extremes-hazards","benchmarks-data-eval"],"type":"benchmark","method":["llm"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["radar","nwp-analysis","other"],"status":"research","summary":"WeatherQA is a multimodal benchmark of 8,000+ image-text pairs for severe convective weather reasoning; GPT-4o shows a substantial gap to human forecasters.","significance":4,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2023gl107377","title":"On Some Limitations of Current Machine Learning Weather Prediction Models","authors":["Massimo Bonavita"],"date":"2024-06-14","year":2024,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl107377","openalex":"W4399668152"},"links":{"paper":"https://doi.org/10.1029/2023gl107377"},"orgs":["ecmwf"],"topic":"xai-uq-physics","topics":[],"type":"evaluation","method":["gnn","transformer","cnn"],"timescale":["short","medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Shows Pangu-Weather, FourCastNet and GraphCast fail to reproduce sub-synoptic and mesoscale phenomena, lacking physical consistency versus physics-based models.","significance":6,"cited_by":151,"score":69,"highlight":true,"highlight_reason":"Influential ECMWF critique showing leading ML models miss mesoscale features and physical consistency; important caveat for evaluating ML skill.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2406.05019","title":"Predictability Limit of the 2021 Pacific Northwest Heatwave from Deep-Learning Sensitivity Analysis","authors":["P. Trent Vonich","Gregory J. Hakim"],"date":"2024-06-07","year":2024,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"arxiv":"2406.05019","doi":"10.1029/2024gl110651","openalex":"W4403085937"},"links":{"paper":"https://arxiv.org/abs/2406.05019","pdf":"https://arxiv.org/pdf/2406.05019"},"orgs":["university-of-washington"],"topic":"xai-uq-physics","topics":[],"type":"application","method":["gnn","differentiable"],"timescale":["medium"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Backpropagation through GraphCast optimizes initial conditions, cutting 10-day Pacific Northwest heatwave errors over 90% and extending predictability to about 23 days.","significance":4,"cited_by":30,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2406.01465","title":"AIFS -- ECMWF's data-driven forecasting system","authors":["Simon Lang","Mihai Alexe","Matthew Chantry","Jesper Dramsch","Florian Pinault","Baudouin Raoult","Mariana C. A. Clare","Christian Lessig","Michael Maier-Gerber","Linus Magnusson","Zied Ben Bouallègue","Ana Prieto Nemesio","Peter D. Dueben","Andrew Brown","Florian Pappenberger","Florence Rabier"],"date":"2024-06-03","year":2024,"venue_type":"preprint","ids":{"arxiv":"2406.01465","openalex":"W4399401448"},"links":{"paper":"https://arxiv.org/abs/2406.01465","pdf":"https://arxiv.org/pdf/2406.01465"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["gnn","transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"operational","summary":"AIFS is ECMWF's operational GNN-transformer forecast system, trained on ERA5 and operational analyses, with skilled upper-air, surface and tropical cyclone forecasts run publicly.","significance":9,"cited_by":86,"score":46,"highlight":true,"highlight_reason":"ECMWF's operational data-driven AIFS, a GNN-transformer model running alongside IFS with open data; a key reference for operational ML weather forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2406.00390","title":"AI-based data assimilation: Learning the functional of analysis estimation","authors":["Jan D. Keller","Roland Potthast"],"date":"2024-06-01","year":2024,"venue_type":"preprint","ids":{"arxiv":"2406.00390","openalex":"W4399355701"},"links":{"paper":"https://arxiv.org/abs/2406.00390","pdf":"https://arxiv.org/pdf/2406.00390"},"orgs":["dwd"],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"pre-operational","summary":"AI-Var trains a neural network to minimise the variational DA cost function directly, producing accurate initial conditions without pre-existing analysis datasets in proof-of-concept tests.","significance":4,"cited_by":5,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2405.16297","title":"LUCIE: A Lightweight Uncoupled ClImate Emulator with long-term stability and physical consistency for O(1000)-member ensembles","authors":["Haiwen Guan","Troy Arcomano","Ashesh Chattopadhyay","Romit Maulik"],"date":"2024-05-25","year":2024,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2405.16297","doi":"10.1029/2025ms005152","openalex":"W4415960043"},"links":{"paper":"https://arxiv.org/abs/2405.16297","pdf":"https://arxiv.org/pdf/2405.16297"},"orgs":["argonne"],"topic":"climate-emulation","topics":[],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["era5"],"status":"research","summary":"LUCIE, a lightweight ERA5-trained emulator trained on 2 years of data, stays stable and climatologically consistent for 100-year, 100-member simulations on one GPU.","significance":5,"cited_by":4,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2405.13063","title":"A Foundation Model for the Earth System","authors":["Cristian Bodnar","Wessel P. Bruinsma","Ana Lucic","Megan Stanley","Anna Vaughan","Johannes Brandstetter","Patrick Garvan","Maik Riechert","Jonathan A. Weyn","Haiyu Dong","Jayesh K. Gupta","Kit Thambiratnam","Alexander T. Archibald","Chun-Chieh Wu","Elizabeth Heider","Max Welling","Richard E. Turner","Paris Perdikaris"],"date":"2024-05-20","year":2024,"venue":"Nature","venue_type":"journal","ids":{"arxiv":"2405.13063","doi":"10.1038/s41586-025-09005-y","openalex":"W4410551352"},"links":{"paper":"https://arxiv.org/abs/2405.13063","pdf":"https://arxiv.org/pdf/2405.13063"},"orgs":["alan-turing-institute","microsoft-research","silurian","university-of-cambridge"],"topic":"foundation-models","topics":["global-medium-range","applications-impacts"],"type":"model","method":["transformer"],"timescale":["short","medium"],"spatial":["global","regional"],"data":["era5","nwp-analysis","other"],"status":"research","summary":"Aurora is a large Earth-system foundation model trained on over a million hours of data that beats operational systems for air quality, waves, cyclone tracks and high-resolution weather.","significance":8,"cited_by":257,"score":97,"highlight":true,"highlight_reason":"Aurora, a Nature foundation model for the Earth system, beats operational systems on air quality, waves, cyclone tracks and high-resolution weather; a major contribution.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2405.05925","title":"FuXi-ENS: A machine learning model for medium-range ensemble weather forecasting","authors":["Xiaohui Zhong","Lei Chen","Hao Li","Roberto Buizza","Jun Liu","Jie Feng","Zijian Zhu","Xu Fan","Kan Dai","Jing-jia Luo","Jie Wu","Bo Lu"],"date":"2024-05-09","year":2024,"venue":"Science Advances","venue_type":"journal","ids":{"arxiv":"2405.05925","doi":"10.1126/sciadv.adu2854","openalex":"W4415748430"},"links":{"paper":"https://arxiv.org/abs/2405.05925","pdf":"https://arxiv.org/pdf/2405.05925"},"orgs":["cma","fudan-university","nuist"],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["gan-vae"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"FuXi-ENS, a VAE-based ensemble trained with CRPS and KL loss at 0.25°, beats ECMWF ENS in CRPS on 98.1% of 360 variable and lead time combinations.","significance":7,"cited_by":16,"score":83,"highlight":true,"highlight_reason":"0.25° global ML ensemble model trained with CRPS plus a VAE, competitive with ECMWF ENS; important for probabilistic ML forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2405.03376","title":"CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer","authors":["Tao Han","Zhenghao Chen","Song Guo","Wanghan Xu","Lei Bai"],"date":"2024-05-06","year":2024,"venue_type":"preprint","ids":{"arxiv":"2405.03376"},"links":{"paper":"https://arxiv.org/abs/2405.03376","pdf":"https://arxiv.org/pdf/2405.03376","code":"https://github.com/taohan10200/CRA5"},"orgs":[],"topic":"infra-software","topics":[],"type":"benchmark","method":["transformer","gan-vae"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"CRA5 compresses 226 TB of ERA5 to 0.7 TB (over 300x) with a VAE transformer codec, and models trained on it match original-data forecast accuracy.","significance":5,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2404.19630","title":"Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction","authors":["Jared D. Willard","Peter Harrington","Shashank Subramanian","Ankur Mahesh","Travis A. O'Brien","William D. Collins"],"date":"2024-04-30","year":2024,"venue":"23rd Conference on Artificial Intelligence for Environmental Science. Jan 2024. Abstract #437874","venue_type":"journal","ids":{"arxiv":"2404.19630","doi":"10.1175/aies-d-24-0061.1","openalex":"W4409428784"},"links":{"paper":"https://arxiv.org/abs/2404.19630","pdf":"https://arxiv.org/pdf/2404.19630"},"orgs":["lbnl-nersc","uc-berkeley"],"topic":"infra-software","topics":[],"type":"evaluation","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A minimally modified SwinV2 trained on ERA5 beats IFS, and ablations on loss, model size and multi-step fine-tuning show which training choices matter.","significance":4,"cited_by":11,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2404.17652","title":"Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Events","authors":["Olivier C. Pasche","Jonathan Wider","Zhongwei Zhang","Jakob Zscheischler","Sebastian Engelke"],"date":"2024-04-26","year":2024,"venue":"Artificial Intelligence for the Earth Systems 4(1), e240033 (2025)","venue_type":"journal","ids":{"arxiv":"2404.17652","doi":"10.1175/aies-d-24-0033.1","openalex":"W4404960134"},"links":{"paper":"https://arxiv.org/abs/2404.17652","pdf":"https://arxiv.org/pdf/2404.17652"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"evaluation","method":[],"timescale":["short","medium"],"spatial":["regional","global"],"data":["nwp-analysis","era5"],"status":"research","summary":"Compares GraphCast, Pangu-Weather, FourCastNet and HRES on three extreme events, finding ML models weaker on heatwave aggregates but better on a winter storm.","significance":4,"cited_by":34,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2404.14712","title":"ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability","authors":["Xiao Wang","Siyan Liu","Aristeidis Tsaris","Jong-Youl Choi","Ashwin Aji","Ming Fan","Wei Zhang","Junqi Yin","Moetasim Ashfaq","Dan Lu","Prasanna Balaprakash"],"date":"2024-04-23","year":2024,"venue":"SC24: International Conference for High Performance Computing, Networking, Storage and Analysis","venue_type":"preprint","ids":{"arxiv":"2404.14712","doi":"10.1109/sc41406.2024.00007","openalex":"W4405387414"},"links":{"paper":"https://arxiv.org/abs/2404.14712","pdf":"https://arxiv.org/pdf/2404.14712"},"orgs":["ornl"],"topic":"foundation-models","topics":["infra-software"],"type":"model","method":["transformer"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"ORBIT scales a vision transformer to 113 billion parameters for Earth system prediction, sustaining 1.6 exaFLOPS on 49,152 GPUs of the Frontier supercomputer.","significance":5,"cited_by":16,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2404.13227","title":"Machine learning for climate physics and simulations","authors":["Ching-Yao Lai","Pedram Hassanzadeh","Aditi Sheshadri","Maike Sonnewald","Raffaele Ferrari","Venkatramani Balaji"],"date":"2024-04-20","year":2024,"venue":"Annual Review of Condensed Matter Physics","venue_type":"journal","ids":{"arxiv":"2404.13227","doi":"10.1146/annurev-conmatphys-043024-114758","openalex":"W4404734447"},"links":{"paper":"https://arxiv.org/abs/2404.13227","pdf":"https://arxiv.org/pdf/2404.13227"},"orgs":["mit","stanford","university-of-chicago"],"topic":"hybrid-parameterization","topics":["climate-analysis-attribution","climate-emulation"],"type":"review","method":["classical-ml","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["cmip","era5","other"],"status":"research","summary":"Review of ML for climate physics and climate simulations, arguing physics knowledge and interpretability are essential in the small-data, non-stationary regime of long-term climate projection.","significance":4,"cited_by":34,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2404.08522","title":"Fuxi-DA: A Generalized Deep Learning Data Assimilation Framework for Assimilating Satellite Observations","authors":["Xiaoze Xu","Xiuyu Sun","Wei Han","Xiaohui Zhong","Lei Chen","Zhiqiu Gao","Hao Li"],"date":"2024-04-12","year":2024,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"arxiv":"2404.08522","doi":"10.1038/s41612-025-01039-3","openalex":"W4409835711"},"links":{"paper":"https://arxiv.org/abs/2404.08522","pdf":"https://arxiv.org/pdf/2404.08522"},"orgs":["cma","fudan-university","nuist"],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["transformer","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"FuXi-DA is a deep learning data assimilation framework that assimilates FY-4B AGRI satellite radiances, reducing analysis errors and improving forecasts.","significance":5,"cited_by":32,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-aies-d-23-0066.1","title":"Enhancing Regional Climate Downscaling through Advances in Machine Learning","authors":["Neelesh Rampal","Sanaa Hobeichi","Peter B. Gibson","Jorge Baño-Medina","Gab Abramowitz","Tom Beucler","Jose González-Abad","William Chapman","Paula Harder","José Manuel Gutiérrez"],"date":"2024-04-01","year":2024,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-23-0066.1","openalex":"W4392550838"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0066.1"},"orgs":["ncar"],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"review","method":[],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Review of machine learning for empirical climate downscaling, covering out-of-distribution generalization, extremes, and a proposed evaluation framework for downscaling algorithms.","significance":4,"cited_by":88,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2404.00411","title":"Aardvark weather: end-to-end data-driven weather forecasting","authors":["Anna Vaughan","Stratis Markou","Will Tebbutt","James Requeima","Wessel P. Bruinsma","Tom R. Andersson","Michael Herzog","Nicholas D. Lane","Matthew Chantry","J. Scott Hosking","Richard E. Turner"],"date":"2024-03-30","year":2024,"venue":"Nature","venue_type":"journal","ids":{"arxiv":"2404.00411","doi":"10.1038/s41586-025-08897-0","openalex":"W4408657432"},"links":{"paper":"https://arxiv.org/abs/2404.00411","pdf":"https://arxiv.org/pdf/2404.00411"},"orgs":["alan-turing-institute","ecmwf","google-deepmind","microsoft-research","university-of-cambridge"],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global","local"],"data":["other","stations"],"status":"research","summary":"End-to-end model ingests raw observations to produce global and station forecasts, beating operational NWP on several variables using 8% of input data.","significance":8,"cited_by":104,"score":97,"highlight":true,"highlight_reason":"Nature paper replacing the whole NWP pipeline, from raw observations to forecasts, with an end-to-end ML system at far lower compute; major paradigm shift.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-gmd-17-2347-2024","title":"Advances and prospects of deep learning for medium-range extreme weather forecasting","authors":["Leonardo Olivetti","Gabriele Messori"],"date":"2024-03-21","year":2024,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-17-2347-2024","openalex":"W4393041535"},"links":{"paper":"https://doi.org/10.5194/gmd-17-2347-2024"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":[],"timescale":["medium"],"spatial":["global"],"data":[],"status":"research","summary":"Reviews deep learning medium-range forecasts and shows leading models struggle with extremes, proposing a workflow for extreme-event forecasting models.","significance":4,"cited_by":48,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2403.13458","title":"Uncertainty quantification for data-driven weather models","authors":["Christopher Bülte","Nina Horat","Julian Quinting","Sebastian Lerch"],"date":"2024-03-20","year":2024,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2403.13458","doi":"10.1175/aies-d-24-0049.1","openalex":"W4408812456"},"links":{"paper":"https://arxiv.org/abs/2403.13458","pdf":"https://arxiv.org/pdf/2403.13458"},"orgs":["kit"],"topic":"xai-uq-physics","topics":["global-medium-range"],"type":"evaluation","method":["classical-ml","other"],"timescale":["medium"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Compares uncertainty quantification methods for Pangu-Weather ensembles over Europe; ML post-hoc UQ gives skill up to 5 days beyond ECMWF ENS.","significance":4,"cited_by":20,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2401.16254","title":"YingLong-weather: AI-Based Limited Area Models for Forecasting of Non-precipitation Surface Meteorological Variables","authors":["Pengbo Xu","Xiaogu Zheng","Tianyan Gao","Yu Wang","Junping Yin","Juan Zhang","Xuanze Zhang","San Luo","Zhonglei Wang","Zhimin Zhang","Xiaoguang Hu","Xiaoxu Chen"],"date":"2024-01-29","year":2024,"venue":"Communications Earth &amp; Environment","venue_type":"journal","ids":{"arxiv":"2401.16254","doi":"10.1038/s43247-025-02347-5","openalex":"W4410413805"},"links":{"paper":"https://arxiv.org/abs/2401.16254","pdf":"https://arxiv.org/pdf/2401.16254"},"orgs":["baidu","cma"],"topic":"regional-km-scale","topics":["applications-impacts","global-medium-range"],"type":"model","method":["transformer","cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","km-scale-sim"],"status":"research","summary":"YingLong is a 3 km AI limited-area model that beats WRF-ARW on surface wind speed in two domains while running much faster, using Pangu-Weather boundaries.","significance":4,"cited_by":19,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2402.00059","title":"FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting","authors":["Tao Han","Song Guo","Fenghua Ling","Kang Chen","Junchao Gong","Jingjia Luo","Junxia Gu","Kan Dai","Wanli Ouyang","Lei Bai"],"date":"2024-01-28","year":2024,"venue_type":"preprint","ids":{"arxiv":"2402.00059","openalex":"W4391513958"},"links":{"paper":"https://arxiv.org/abs/2402.00059","pdf":"https://arxiv.org/pdf/2402.00059"},"orgs":["cma","nuist","shanghai-ai-lab"],"topic":"global-medium-range","topics":["regional-km-scale"],"type":"model","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"First data-driven global model at 0.09 degree resolution, initialized by transfer from a low-resolution model, outperforming IFS-HRES in 2022 hindcasts.","significance":6,"cited_by":9,"score":59,"highlight":true,"highlight_reason":"First data-driven global forecast at 0.09° resolution, built by transferring from a low-resolution model; claims to beat IFS-HRES.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2401.15305","title":"A Practical Probabilistic Benchmark for AI Weather Models","authors":["Noah D. Brenowitz","Yair Cohen","Jaideep Pathak","Ankur Mahesh","Boris Bonev","Thorsten Kurth","Dale R. Durran","Peter Harrington","Michael S. Pritchard"],"date":"2024-01-27","year":2024,"venue":"Geophysical Research Letters, 52, e2024GL113656 (2025)","venue_type":"journal","ids":{"arxiv":"2401.15305","doi":"10.1029/2024gl113656","openalex":"W4409263600"},"links":{"paper":"https://arxiv.org/abs/2401.15305","pdf":"https://arxiv.org/pdf/2401.15305"},"orgs":["lbnl-nersc","nvidia","uc-berkeley"],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"evaluation","method":["neural-operator","transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Lagged ensembles give a parameter-free probabilistic comparison showing GraphCast and Pangu tie on CRPS, and that multi-step losses hurt probabilistic skill.","significance":6,"cited_by":30,"score":59,"highlight":true,"highlight_reason":"Lagged-ensemble method enables fair probabilistic comparison of AI weather models; shows multi-step losses hurt probabilistic skill.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2401.09646","title":"ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change","authors":["David Thulke","Yingbo Gao","Petrus Pelser","Rein Brune","Rricha Jalota","Floris Fok","Michael Ramos","Ian van Wyk","Abdallah Nasir","Hayden Goldstein","Taylor Tragemann","Katie Nguyen","Ariana Fowler","Andrew Stanco","Jon Gabriel","Jordan Taylor","Dean Moro","Evgenii Tsymbalov","Juliette de Waal","Evgeny Matusov","Mudar Yaghi","Mohammad Shihadah","Hermann Ney","Christian Dugast","Jonathan Dotan","Daniel Erasmus"],"date":"2024-01-17","year":2024,"venue_type":"preprint","ids":{"arxiv":"2401.09646","doi":"10.18154/rwth-2025-05396","openalex":"W4391045944"},"links":{"paper":"https://arxiv.org/abs/2401.09646","pdf":"https://arxiv.org/pdf/2401.09646"},"orgs":[],"topic":"llms-agents","topics":[],"type":"model","method":["llm"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"ClimateGPT is a domain-specific language model for synthesizing climate-change research text; it does not model the atmosphere or climate system directly.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2401.05932","title":"DiffDA: a Diffusion Model for Weather-scale Data Assimilation","authors":["Langwen Huang","Lukas Gianinazzi","Yuejiang Yu","Peter D. Dueben","Torsten Hoefler"],"date":"2024-01-11","year":2024,"venue_type":"preprint","ids":{"arxiv":"2401.05932","openalex":"W4390833509"},"links":{"paper":"https://arxiv.org/abs/2401.05932","pdf":"https://arxiv.org/pdf/2401.05932"},"orgs":[],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["diffusion","gnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"DiffDA adapts the pretrained GraphCast network as a diffusion backbone to assimilate sparse observations at 0.25 degree, losing at most 24 hours of lead time versus state-of-the-art analyses.","significance":5,"cited_by":9,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1038-s43247-023-01199-1","title":"Local climate services for all, courtesy of large language models","authors":["Nikolay Koldunov","Thomas Jung"],"date":"2024-01-05","year":2024,"venue":"Communications Earth &amp; Environment","venue_type":"journal","ids":{"doi":"10.1038/s43247-023-01199-1","openalex":"W4390598749"},"links":{"paper":"https://doi.org/10.1038/s43247-023-01199-1"},"orgs":[],"topic":"llms-agents","topics":[],"type":"position","method":["llm"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Discusses using large language models for local climate services; the abstract is absent, so the classification relies on the title only.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2406.14798","title":"Probabilistic Emulation of a Global Climate Model with Spherical DYffusion","authors":["Salva Rühling Cachay","Brian Henn","Oliver Watt-Meyer","Christopher S. Bretherton","Rose Yu"],"date":"2024-01-01","year":2024,"venue":"Advances in Neural Information Processing Systems 37","venue_type":"preprint","ids":{"arxiv":"2406.14798","doi":"10.52202/079017-4052","openalex":"W4415800707"},"links":{"paper":"https://arxiv.org/abs/2406.14798","pdf":"https://arxiv.org/pdf/2406.14798","code":"https://github.com/Rose-STL-Lab/spherical-dyffusion"},"orgs":[],"topic":"climate-emulation","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion","neural-operator"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"DYffusion combined with a spherical Fourier neural operator emulates a coarse FV3GFS climate model, producing stable 100-year probabilistic ensemble simulations at low cost.","significance":6,"cited_by":3,"score":34,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2406.04759","title":"Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks","authors":["Joel Oskarsson","Tomas Landelius","Marc Peter Deisenroth","Fredrik Lindsten"],"date":"2024-01-01","year":2024,"venue":"Advances in Neural Information Processing Systems 37","venue_type":"preprint","ids":{"arxiv":"2406.04759","doi":"10.52202/079017-1316","openalex":"W4415798127"},"links":{"paper":"https://arxiv.org/abs/2406.04759","pdf":"https://arxiv.org/pdf/2406.04759","code":"https://github.com/mllam/neural-lam"},"orgs":[],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["gnn","other"],"timescale":["medium"],"spatial":["global","regional"],"data":["era5"],"status":"research","summary":"Graph-EFM is a hierarchical graph latent-variable model that generates arbitrarily large spatially coherent ensembles in one forward pass per step, matching deterministic error levels.","significance":5,"cited_by":9,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2402.00712","title":"ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction","authors":["Juan Nathaniel","Yongquan Qu","Tung Nguyen","Sungduk Yu","Julius Busecke","Aditya Grover","Pierre Gentine"],"date":"2024-01-01","year":2024,"venue":"Advances in Neural Information Processing Systems 37","venue_type":"preprint","ids":{"arxiv":"2402.00712","doi":"10.52202/079017-1386","openalex":"W4415797737"},"links":{"paper":"https://arxiv.org/abs/2402.00712","pdf":"https://arxiv.org/pdf/2402.00712"},"orgs":[],"topic":"benchmarks-data-eval","topics":["s2s-seasonal"],"type":"benchmark","method":["transformer","other"],"timescale":["s2s"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"ChaosBench is a physics-based S2S benchmark showing weather-scale AI models collapse to climatology, with ensembles and physics constraints suggested to extend skill.","significance":5,"cited_by":7,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2312.15796","title":"GenCast: Diffusion-based ensemble forecasting for medium-range weather","authors":["Ilan Price","Alvaro Sanchez-Gonzalez","Ferran Alet","Tom R. Andersson","Andrew El-Kadi","Dominic Masters","Timo Ewalds","Jacklynn Stott","Shakir Mohamed","Peter Battaglia","Remi Lam","Matthew Willson"],"date":"2023-12-25","year":2023,"venue":"Nature","venue_type":"journal","ids":{"arxiv":"2312.15796","doi":"10.1038/s41586-024-08252-9","openalex":"W4405031167"},"links":{"paper":"https://arxiv.org/abs/2312.15796","pdf":"https://arxiv.org/pdf/2312.15796"},"orgs":["google-deepmind","google-research"],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["diffusion"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"GenCast, a diffusion ensemble trained on reanalysis, beats ECMWF ENS on 97.4% of 1320 targets, with better tropical cyclone and wind power prediction, in 8 minutes.","significance":9,"cited_by":443,"score":100,"highlight":true,"highlight_reason":"GenCast: diffusion-based ensemble beats ECMWF ENS on 97.4% of targets, a state-of-the-art probabilistic ML weather model in Nature.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2312.12462","title":"Towards an end-to-end artificial intelligence driven global weather forecasting system","authors":["Kun Chen","Lei Bai","Fenghua Ling","Peng Ye","Tao Chen","Hang Fan","Hao Chen","Yi Xiao","Kang Chen","Tao Han","Jing-Jia Luo","Wanli Ouyang"],"date":"2023-12-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2312.12462","openalex":"W4390091490"},"links":{"paper":"https://arxiv.org/abs/2312.12462","pdf":"https://arxiv.org/pdf/2312.12462"},"orgs":["fudan-university","nuist","shanghai-ai-lab"],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["transformer","cnn"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis","stations","satellite"],"status":"research","summary":"Adas is an AI data assimilation model that, combined with FengWu, forms an end-to-end AI forecast system with skill comparable to IFS.","significance":6,"cited_by":12,"score":59,"highlight":true,"highlight_reason":"FengWu-Adas builds an end-to-end AI assimilation and forecast system with IFS-comparable skill; useful progress toward fully AI forecasting pipelines.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2312.12455","title":"FengWu-4DVar: Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilation","authors":["Yi Xiao","Lei Bai","Wei Xue","Kang Chen","Tao Han","Wanli Ouyang"],"date":"2023-12-16","year":2023,"venue_type":"preprint","ids":{"arxiv":"2312.12455","openalex":"W4390091486"},"links":{"paper":"https://arxiv.org/abs/2312.12455","pdf":"https://arxiv.org/pdf/2312.12455"},"orgs":["shanghai-ai-lab","tsinghua-university"],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["transformer","differentiable"],"timescale":["short"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Couples the FengWu forecast model with 4D-Var using autodifferentiation instead of adjoints, producing cyclic analyses from simulated observations.","significance":6,"cited_by":13,"score":59,"highlight":true,"highlight_reason":"Couples FengWu with 4DVar using autodiff instead of adjoints, a solid step toward cycling AI-based assimilation and forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2312.09926","title":"FuXi-S2S: A machine learning model that outperforms conventional global subseasonal forecast models","authors":["Lei Chen","Xiaohui Zhong","Hao Li","Jie Wu","Bo Lu","Deliang Chen","Shang-Ping Xie","Libo Wu","Qingchen Chao","Chensen Lin","Zixin Hu","Yuan Qi"],"date":"2023-12-15","year":2023,"venue":"Nature Communications","venue_type":"journal","ids":{"arxiv":"2312.09926","doi":"10.1038/s41467-024-50714-1","openalex":"W4401112323"},"links":{"paper":"https://arxiv.org/abs/2312.09926","pdf":"https://arxiv.org/pdf/2312.09926"},"orgs":["cma","fudan-university"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["transformer"],"timescale":["s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Machine learning S2S model outperforms ECMWF's S2S system for precipitation and OLR up to 42 days, extending MJO prediction skill from 30 to 36 days.","significance":7,"cited_by":105,"score":93,"highlight":true,"highlight_reason":"First ML model to beat ECMWF S2S on precipitation and OLR, extending skillful MJO prediction to 36 days; major subseasonal advance.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2312.06734","title":"DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting","authors":["Demin Yu","Xutao Li","Yunming Ye","Baoquan Zhang","Chuyao Luo","Kuai Dai","Rui Wang","Xunlai Chen"],"date":"2023-12-11","year":2023,"venue":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","venue_type":"preprint","ids":{"arxiv":"2312.06734","doi":"10.1109/cvpr52733.2024.02622","openalex":"W4402754191"},"links":{"paper":"https://arxiv.org/abs/2312.06734","pdf":"https://arxiv.org/pdf/2312.06734","code":"https://github.com/DeminYu98/DiffCast"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["diffusion"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"DiffCast decomposes precipitation into deterministic motion and stochastic residuals via residual diffusion, reducing blurring and position errors on four radar datasets.","significance":4,"cited_by":82,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2312.03876","title":"Scaling transformer neural networks for skillful and reliable medium-range weather forecasting","authors":["Tung Nguyen","Rohan Shah","Hritik Bansal","Troy Arcomano","Romit Maulik","Veerabhadra Kotamarthi","Ian Foster","Sandeep Madireddy","Aditya Grover"],"date":"2023-12-06","year":2023,"venue":"Advances in Neural Information Processing Systems 37","venue_type":"preprint","ids":{"arxiv":"2312.03876","doi":"10.52202/079017-2196","openalex":"W4415797118"},"links":{"paper":"https://arxiv.org/abs/2312.03876","pdf":"https://arxiv.org/pdf/2312.03876","code":"https://github.com/tung-nd/stormer"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Stormer, a plain transformer with randomized forecast training, beats leading models beyond 7 days on WeatherBench 2 using far less data and compute, and scales well.","significance":6,"cited_by":44,"score":34,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2312.02658","title":"Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán","authors":["Andrew J. Charlton-Perez","Helen F. Dacre","Simon Driscoll","Suzanne L. Gray","Ben Harvey","Natalie J. Harvey","Kieran M. R. Hunt","Robert W. Lee","Ranjini Swaminathan","Remy Vandaele","Ambrogio Volonté"],"date":"2023-12-05","year":2023,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"arxiv":"2312.02658","doi":"10.1038/s41612-024-00638-w","openalex":"W4395010148"},"links":{"paper":"https://arxiv.org/abs/2312.02658","pdf":"https://arxiv.org/pdf/2312.02658"},"orgs":["university-of-reading"],"topic":"extremes-hazards","topics":["global-medium-range","benchmarks-data-eval"],"type":"evaluation","method":["transformer","gnn"],"timescale":["medium"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Case study of Storm Ciarán finds FourCastNet, Pangu, and GraphCast capture synoptic structure but underestimate peak winds and miss fine warning-relevant features.","significance":4,"cited_by":82,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-gmd-16-6433-2023","title":"Machine learning for numerical weather and climate modelling: a review","authors":["Catherine O. de Burgh-Day","Tennessee Leeuwenburg"],"date":"2023-11-14","year":2023,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-6433-2023","openalex":"W4388660896"},"links":{"paper":"https://doi.org/10.5194/gmd-16-6433-2023"},"orgs":["bom-australia"],"topic":"global-medium-range","topics":["climate-emulation"],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Chronological review of machine learning in weather and climate modelling, from solvers and parameterization emulation to full ML forecast models, with ethics and future directions.","significance":6,"cited_by":178,"score":44,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2311.07222","title":"Neural General Circulation Models for Weather and Climate","authors":["Dmitrii Kochkov","Janni Yuval","Ian Langmore","Peter Norgaard","Jamie Smith","Griffin Mooers","Milan Klöwer","James Lottes","Stephan Rasp","Peter Düben","Sam Hatfield","Peter Battaglia","Alvaro Sanchez-Gonzalez","Matthew Willson","Michael P. Brenner","Stephan Hoyer"],"date":"2023-11-13","year":2023,"venue":"Nature","venue_type":"journal","ids":{"arxiv":"2311.07222","doi":"10.1038/s41586-024-07744-y","openalex":"W4400880443"},"links":{"paper":"https://arxiv.org/abs/2311.07222","pdf":"https://arxiv.org/pdf/2311.07222"},"orgs":["ecmwf","google-deepmind","google-research","mit"],"topic":"hybrid-parameterization","topics":["global-medium-range","climate-emulation"],"type":"model","method":["physics-constrained","differentiable","other"],"timescale":["medium","climate"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"NeuralGCM couples a differentiable dynamical solver with ML components, matching ML and ECMWF ensemble skill for 1-15 day forecasts and stable multi-decade climate runs.","significance":9,"cited_by":448,"score":100,"highlight":true,"highlight_reason":"NeuralGCM: first hybrid differentiable-dynamics plus ML GCM matching top ML and ENS for weather and stable multidecade climate runs; landmark in Nature.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.66108-mna.v2i3.54","title":"Techniques Leveraging from Artificial Intelligence for the Prediction of Climate Change in Pakistan: A Systematic Literature Review","authors":["Sameen Fatima","Aniqa Dilawari"],"date":"2023-10-31","year":2023,"venue":"Machines and Algorithms","venue_type":"journal","ids":{"doi":"10.66108/mna.v2i3.54","openalex":"W7216497304"},"links":{"paper":"https://doi.org/10.66108/mna.v2i3.54","pdf":"https://knovell.org/MnA/index.php/ojs/article/download/54/37"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":[],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Systematic review of machine learning, deep learning and IoT methods for weather and climate prediction in Pakistan, motivated by agricultural and climate risks.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15215197","title":"Assessment of Deep Learning-Based Nowcasting Using Weather Radar in South Korea","authors":["Seong-Sim Yoon","Hongjoon Shin","Jae‐Yeong Heo","Kwang-Bae Choi"],"date":"2023-10-31","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15215197","openalex":"W4388077113"},"links":{"paper":"https://doi.org/10.3390/rs15215197"},"orgs":[],"topic":"nowcasting","topics":[],"type":"evaluation","method":["cnn","rnn","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Compares RainNet, ConvLSTM U-Net, recursive U-Net and GAN nowcasting on South Korean S-band radar, with RainNet reaching CSI 0.826 at 0.1 mm/h.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jas-d-23-0058.1","title":"Quantifying the Environmental Effects on Tropical Cyclone Intensity Change Using a Simple Dynamically Based Dynamical System Model","authors":["Jing Xu","Yuqing Wang","Chi Yang"],"date":"2023-10-31","year":2023,"venue":"Journal of the Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1175/jas-d-23-0058.1","openalex":"W4388043931"},"links":{"paper":"https://doi.org/10.1175/jas-d-23-0058.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atsc/80/12/JAS-D-23-0058.1.pdf"},"orgs":["cma"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"ML-derived ventilation parameters in a simple dynamical model show deep-layer vertical wind shear dominates tropical cyclone weakening across basins during 1982–2021.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.20187","title":"Self-Supervised Pre-Training for Precipitation Post-Processor","authors":["Sojung An","Junha Lee","Jiyeon Jang","Inchae Na","Wooyeon Park","Sujeong You"],"date":"2023-10-31","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.20187","openalex":"W4388184458"},"links":{"paper":"https://arxiv.org/abs/2310.20187","pdf":"https://arxiv.org/pdf/2310.20187"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Self-supervised encoder pretraining on atmospheric variables, then transfer to a labelled precipitation task, improves regional NWP precipitation correction over other approaches.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.20174","title":"GraphTransformers for Geospatial Forecasting of Hurricane Trajectories","authors":["Pallavi Banerjee","Satyaki Chakraborty"],"date":"2023-10-31","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.20174"},"links":{"paper":"https://arxiv.org/abs/2310.20174","pdf":"https://arxiv.org/pdf/2310.20174"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["transformer","gnn"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Graph Transformer exploits an emergent graph among geospatial points to improve six-hourly hurricane trajectory prediction on HURDAT over a standard Transformer baseline.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.20168","title":"Understanding and Visualizing Droplet Distributions in Simulations of Shallow Clouds","authors":["Justus C. Will","Andrea M. Jenney","Kara D. Lamb","Michael S. Pritchard","Colleen Kaul","Po-Lun Ma","Kyle Pressel","Jacob Shpund","Marcus van Lier-Walqui","Stephan Mandt"],"date":"2023-10-31","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.20168"},"links":{"paper":"https://arxiv.org/abs/2310.20168","pdf":"https://arxiv.org/pdf/2310.20168"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Uses VAE latent spaces to visualize droplet size distributions from bin-microphysics cloud simulations, showing similar spectrum evolution across aerosol levels at different paces.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21608-pserj.2023.242830.1270","title":"Using GNSS Observations for Tropospheric Delay Prediction Using Artificial Intelligence","authors":["Ahmed A. Sedeek"],"date":"2023-10-30","year":2023,"venue":"Port-Said Engineering Research Journal","venue_type":"journal","ids":{"doi":"10.21608/pserj.2023.242830.1270","openalex":"W4388613534"},"links":{"paper":"https://doi.org/10.21608/pserj.2023.242830.1270","pdf":"https://pserj.journals.ekb.eg/article_323834_05d20538048e80a606adda7f20486cb9.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Neural network predicts GNSS zenith tropospheric and wet delay from GNSS and meteorological data, reaching 5 mm (ZTD) and 3.6 mm (ZWD) error for water-vapour estimates.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20937-atm.53258","title":"Using a hybrid approach for wind power forecasting in Northwestern Mexico","authors":["Yanet Díaz Esteban","C.A. Lopez-Villalobos","Instituto de Energías Renovables, Universidad Nacional Autónoma de México, Privada Xochicalco s/n, Col. Azteca, 62588 Temixco, Morelos, México.","C. Ochoa","nstituto de Ciencias de la Atmósfera y Cambio Climático, Universidad Nacional Autónoma de México, Circuito de la Investigación Científica s/n, Ciudad Universitaria, 04510 Ciudad de México, México.","Rosario Romero‐Centeno","nstituto de Ciencias de la Atmósfera y Cambio Climático, Universidad Nacional Autónoma de México, Circuito de la Investigación Científica s/n, Ciudad Universitaria, 04510 Ciudad de México, México.","Ignacio Arturo Quintanar","nstituto de Ciencias de la Atmósfera y Cambio Climático, Universidad Nacional Autónoma de México, Circuito de la Investigación Científica s/n, Ciudad Universitaria, 04510 Ciudad de México, México."],"date":"2023-10-30","year":2023,"venue":"Atmósfera","venue_type":"journal","ids":{"doi":"10.20937/atm.53258","openalex":"W4388017696"},"links":{"paper":"https://doi.org/10.20937/atm.53258","pdf":"https://www.revistascca.unam.mx/atm/index.php/atm/article/download/53258/47000"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Hybrid WRF-plus-neural-network model forecasts 24-hour-ahead wind power at a northwestern Mexico farm, with 6.97% hourly NMAPE, outperforming decision trees and SVR.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.19932","title":"Sim2Real for Environmental Neural Processes","authors":["Jonas Scholz","Tom R. Andersson","Anna Vaughan","James Requeima","Richard E. Turner"],"date":"2023-10-30","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.19932","openalex":"W4388183375"},"links":{"paper":"https://arxiv.org/abs/2310.19932","pdf":"https://arxiv.org/pdf/2310.19932"},"orgs":["microsoft-research","university-of-cambridge"],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"model","method":["cnn","other"],"timescale":[],"spatial":["regional","local"],"data":["era5","stations"],"status":"research","summary":"Sim2Real pre-trains a ConvCNP on reanalysis and fine-tunes on German weather stations, outperforming reanalysis-only or station-only training for surface air temperature interpolation.","significance":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.19515","title":"Transformer-based nowcasting of radar composites from satellite images for severe weather","authors":["Çağlar Küçük","Apostolos Giannakos","Stefan Schneider","Alexander Jann"],"date":"2023-10-30","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.19515"},"links":{"paper":"https://arxiv.org/abs/2310.19515","pdf":"https://arxiv.org/pdf/2310.19515"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"Transformer nowcasts radar composites up to two hours ahead from geostationary satellite data, with lightning and infrared channels proving key features in severe weather.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.19385","title":"Gradient-free online learning of subgrid-scale dynamics with neural emulators","authors":["Hugo Frezat","Ronan Fablet","Guillaume Balarac","Julien Le Sommer"],"date":"2023-10-30","year":2023,"venue":"Journal of Advances in Modeling Earth Systems: Volume 18, Issue 8 (August 2026)","venue_type":"journal","ids":{"arxiv":"2310.19385","doi":"10.1029/2023ms004140"},"links":{"paper":"https://arxiv.org/abs/2310.19385","pdf":"https://arxiv.org/pdf/2310.19385"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Trains neural subgrid parametrizations with a posteriori losses via a neural emulator that propagates gradients through non-differentiable solvers, tested on Lorenz-96 and quasi-geostrophic systems.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15215169","title":"Enhancing Rainfall Nowcasting Using Generative Deep Learning Model with Multi-Temporal Optical Flow","authors":["Ji-Hoon Ha","Hyesook Lee"],"date":"2023-10-29","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15215169","openalex":"W4388017790"},"links":{"paper":"https://doi.org/10.3390/rs15215169","pdf":"https://www.mdpi.com/2072-4292/15/21/5169/pdf?version=1698661558"},"orgs":["kma"],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Combines multi-temporal optical flow with a conditional GAN for radar rainfall nowcasting, improving accuracy over MAPLE for 0–3 h lead times.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14111620","title":"Hybrid Post-Processing on GEFSv12 Reforecast for Summer Maximum Temperature Ensemble Forecasts with an Extended-Range Time Scale over Taiwan","authors":["M. M. Nageswararao","Yuejian Zhu","Vijay S. Tallapragada","Meng-Shih Chen"],"date":"2023-10-29","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14111620","openalex":"W4388159608"},"links":{"paper":"https://doi.org/10.3390/atmos14111620","pdf":"https://www.mdpi.com/2073-4433/14/11/1620/pdf?version=1698748120"},"orgs":["noaa","ncar"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"Hybrid ANN plus quantile-mapping post-processing of GEFSv12 reforecasts reduces warm bias and improves summer Tmax and extreme-day forecasts over Taiwan at extended ranges.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003446","title":"Uncertainty Quantification When Learning Dynamical Models and Solvers With Variational Methods","authors":["Nicolas Lafon","Ronan Fablet","Philippe Naveau"],"date":"2023-10-29","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003446","openalex":"W4323049798"},"links":{"paper":"https://doi.org/10.1029/2022ms003446","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003446"},"orgs":[],"topic":"data-assimilation","topics":["xai-uq-physics"],"type":"model","method":["gan-vae","differentiable"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"End-to-end variational Bayes neural scheme jointly learns a trainable solver and Gaussian posterior for data assimilation with uncertainty, tested on Lorenz-63 and river flow.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.18703","title":"Detangling the role of climate in vegetation productivity with an explainable convolutional neural network","authors":["Ricardo Barros Lourenço","Michael J. Smith","Sylvia Smullin","Umangi Jain","Alemu Gonsamo","Arthur Ouaknine"],"date":"2023-10-28","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.18703"},"links":{"paper":"https://arxiv.org/abs/2310.18703","pdf":"https://arxiv.org/pdf/2310.18703"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Uses a V-Net to predict leaf area index from climate variables for future vegetation productivity, with outputs consistent with Earth observation LAI product standards.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.169841550.08343114-v1","title":"Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts","authors":["Luke Conibear","Ashley E. Payne","Allison E Reed Harris","Tyler C. McCandless","Steven J. Brey","Kushal Keshavamurthy","Maxfield E Green","Stylianos Flampouris","Luke Thomas Peffers"],"date":"2023-10-27","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.169841550.08343114/v1","openalex":"W4387971817"},"links":{"paper":"https://doi.org/10.22541/essoar.169841550.08343114/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.169841550.08343114"},"orgs":["tomorrow-io","amazon"],"topic":"post-processing","topics":["probabilistic-ensembles","regional-km-scale"],"type":"model","method":["other"],"timescale":["short","medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"operational","summary":"Operational multi-task neural network post-processes HRRR forecasts with a CRPS loss, improving RMSE by 3–25% and CRPS by 31–45% over HRRR.","significance":5,"cited_by":1,"score":40,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0090.1","title":"Exploring the Use of Machine Learning to Improve Vertical Profiles of Temperature and Moisture","authors":["Katherine Haynes","Jason Stock","Jack Dostalek","Charles W. Anderson","Imme Ebert‐Uphoff"],"date":"2023-10-27","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0090.1","openalex":"W4387972375"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0090.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/aies/3/1/AIES-D-22-0090.1.pdf"},"orgs":["colorado-state-university"],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","satellite"],"status":"research","summary":"A residual U-Net postprocesses RAP forecasts with satellite data, improving dewpoint profiles and CAPE by up to 40% with well-calibrated uncertainty for severe-weather forecasting.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.heliyon.2023.e21479","title":"Direct and indirect short-term aggregated turbine- and farm-level wind power forecasts integrating several NWP sources","authors":["Ghali Yakoub","Sathyajith Mathew","J. B. Leal"],"date":"2023-10-27","year":2023,"venue":"Heliyon","venue_type":"journal","ids":{"doi":"10.1016/j.heliyon.2023.e21479","openalex":"W4388190017"},"links":{"paper":"https://doi.org/10.1016/j.heliyon.2023.e21479"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Combining three NWP sources with ML wind-downscaling reduces Nordic wind power forecast errors by 8-30%, with turbine-level aggregation improving accuracy by 10-15%.","significance":2,"cited_by":14,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.17829","title":"Hybrid Optical Turbulence Models Using Machine Learning and Local Measurements","authors":["Christopher Jellen","Charles Nelson","John Burkhardt","Cody Brownell"],"date":"2023-10-27","year":2023,"venue":"Applied Optics 62, no. 18 (2023): 4880-4890","venue_type":"journal","ids":{"arxiv":"2310.17829","doi":"10.1364/ao.487280"},"links":{"paper":"https://arxiv.org/abs/2310.17829","pdf":"https://arxiv.org/pdf/2310.17829"},"orgs":[],"topic":"applications-impacts","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Gradient-boosted hybrid models combining macro-meteorological baselines with local observations cut optical turbulence error by 29% with one day of data and 68% with 180 days.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-3491099-v1","title":"Assessment of Rainfall and Climate Change Patterns in the City of Kigali via Machine Learning and IPCC Codex Models and their Impact on Heavy Storms","authors":["Hussein Bizimana","Abdüsselam Altunkaynak","Robert M. Kalin","Emmanuel Rukundo","Mathieu Mbati Mugunga","Osman Sönmez","Gamze Tuncer","Abdulkadir Baycan"],"date":"2023-10-26","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-3491099/v1","openalex":"W4388200869"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-3491099/v1","pdf":"https://www.researchsquare.com/article/rs-3491099/latest.pdf"},"orgs":[],"topic":"local-forecasting","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["stations","cmip"],"status":"research","summary":"Genetic-fuzzy GENOFIS model beats ANFIS and SVM for Kigali rainfall prediction using 1991–2023 gauge data, combined with downscaled climate-change scenarios.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl105747","title":"Can Artificial Intelligence‐Based Weather Prediction Models Simulate the Butterfly Effect?","authors":["T. Selz","G. C. Craig"],"date":"2023-10-26","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl105747","openalex":"W4388205020"},"links":{"paper":"https://doi.org/10.1029/2023gl105747"},"orgs":[],"topic":"xai-uq-physics","topics":["global-medium-range"],"type":"evaluation","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Finds an AI weather model fails to reproduce rapid early growth of small initial perturbations, implying falsely unlimited predictability unless perturbations are large.","significance":5,"cited_by":82,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-gmd-2023-187","title":"A deep learning method for convective weather forecasting: CNN-BiLSTM-AM (version 1.0)","authors":["Jianbin Zhang","Zhiqiu Gao","Yubin Li","Yuncong Jiang"],"date":"2023-10-25","year":2023,"venue_type":"other","ids":{"doi":"10.5194/gmd-2023-187","openalex":"W4387940001"},"links":{"paper":"https://doi.org/10.5194/gmd-2023-187"},"orgs":["nuist","iap-cas"],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"CNN-BiLSTM-attention model forecasts convective and heavy precipitation from GFS data, reaching threat score 0.336 versus 0.252 for forecasters.","significance":3,"cited_by":0,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl105175","title":"CNN‐Based ENSO Forecasts With a Focus on SSTA Zonal Pattern and Physical Interpretation","authors":["Ming Sun","Lin Chen","Tim Li","Jing‐Jia Luo"],"date":"2023-10-25","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl105175","openalex":"W4387937917"},"links":{"paper":"https://doi.org/10.1029/2023gl105175"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A CNN with cosine-distance loss predicts equatorial Pacific SST zonal patterns up to 16 months ahead, outperforming dynamical models, with physically interpreted ENSO precursors.","significance":4,"cited_by":36,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.19822","title":"FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model","authors":["Xiaohui Zhong","Lei Chen","Jun Liu","Chensen Lin","Yuan Qi","Hao Li"],"date":"2023-10-25","year":2023,"venue":"Science China Earth Sciences","venue_type":"journal","ids":{"arxiv":"2310.19822","doi":"10.1007/s11430-023-1427-x","openalex":"W4403554789"},"links":{"paper":"https://arxiv.org/abs/2310.19822","pdf":"https://arxiv.org/pdf/2310.19822"},"orgs":["fudan-university"],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["diffusion","transformer"],"timescale":["short"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"A denoising diffusion model restores fine-scale detail in FuXi 5-day forecasts, improving extreme precipitation and wind over HRES, but not TC intensity.","significance":4,"cited_by":43,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2310.16741","title":"Stochastic Latent Transformer: Efficient Modelling of Stochastically Forced Zonal Jets","authors":["Ira J. S. Shokar","Rich R. Kerswell","Peter H. Haynes"],"date":"2023-10-25","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.16741","doi":"10.1029/2023ms004177"},"links":{"paper":"https://arxiv.org/abs/2310.16741","pdf":"https://arxiv.org/pdf/2310.16741"},"orgs":[],"topic":"climate-emulation","topics":["hybrid-parameterization"],"type":"model","method":["transformer","gan-vae"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"A stochastic latent transformer emulates a stochastically forced zonal jet model with CRPS training, giving a five-order-of-magnitude speedup for large ensemble generation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su152115209","title":"Application of Wavelet Transform for Bias Correction and Predictor Screening of Climate Data","authors":["Aida Hosseini Baghanam","Vahid Nourani","Ehsan Norouzi","Amirreza Tabataba Vakili","Hüseyin Gökçekuş"],"date":"2023-10-24","year":2023,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su152115209","openalex":"W4387907549"},"links":{"paper":"https://doi.org/10.3390/su152115209","pdf":"https://www.mdpi.com/2071-1050/15/21/15209/pdf?version=1698138858"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Wavelet-based bias correction outperforms quantile mapping for climate model precipitation in Iran, with wavelet-ANN predictor screening for downscaling.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15215084","title":"Spatial Downscaling of Near-Surface Air Temperature Based on Deep Learning Cross-Attention Mechanism","authors":["Zhanfei Shen","Chunxiang Shi","Runping Shen","Ruian Tie","Lingling Ge"],"date":"2023-10-24","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15215084","openalex":"W4387908692"},"links":{"paper":"https://doi.org/10.3390/rs15215084","pdf":"https://www.mdpi.com/2072-4292/15/21/5084/pdf?version=1698148105"},"orgs":["nuist"],"topic":"downscaling","topics":[],"type":"model","method":["transformer","cnn"],"timescale":[],"spatial":["regional"],"data":["other","stations"],"status":"research","summary":"SNCA-CLDASSD, a Swin cross-attention network with DEM input, downscales CLDAS air temperature from 0.05° to 0.01° and beats interpolation and super-resolution baselines in mountains.","significance":3,"cited_by":14,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tia.2023.3327035","title":"Overview of Day-Ahead Solar Power Forecasts Based on Weather Classifications and a Case Study in Taiwan","authors":["Yuan‐Kang Wu","Quoc‐Thang Phan","You-Jing Zhong"],"date":"2023-10-24","year":2023,"venue":"IEEE Transactions on Industry Applications","venue_type":"journal","ids":{"doi":"10.1109/tia.2023.3327035","openalex":"W4387917807"},"links":{"paper":"https://doi.org/10.1109/tia.2023.3327035"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["transformer","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares weather-pattern clustering schemes for day-ahead PV power forecasts in Taiwan; Transformer with weather classification gives the best deterministic and probabilistic accuracy.","significance":2,"cited_by":37,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.16015","title":"Physically Explainable Deep Learning for Convective Initiation Nowcasting Using GOES-16 Satellite Observations","authors":["Da Fan","Steven J. Greybush","David John Gagne","Eugene E. Clothiaux"],"date":"2023-10-24","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.16015","doi":"10.1175/aies-d-23-0098.1"},"links":{"paper":"https://arxiv.org/abs/2310.16015","pdf":"https://arxiv.org/pdf/2310.16015"},"orgs":[],"topic":"nowcasting","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Object-based probabilistic deep learning on GOES-16 infrared imagery predicts convection initiation up to 1 hour ahead, beating logistic regression, with explanations of moisture and cloud drivers.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.15912","title":"Climate Change Impact on Agricultural Land Suitability: An Interpretable Machine Learning-Based Eurasia Case Study","authors":["Valeriy Shevchenko","Daria Taniushkina","Aleksander Lukashevich","Aleksandr Bulkin","Roland Grinis","Kirill Kovalev","Veronika Narozhnaia","Nazar Sotiriadi","Alexander Krenke","Yury Maximov"],"date":"2023-10-24","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.15912"},"links":{"paper":"https://arxiv.org/abs/2310.15912","pdf":"https://arxiv.org/pdf/2310.15912"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Interpretable machine learning projects how climate change under emission scenarios will degrade agricultural land suitability across Central Eurasia, highlighting key climate drivers.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ad0607","title":"Investigating permafrost carbon dynamics in Alaska with artificial intelligence","authors":["Bradley A. Gay","Andreas E Züfle","Neal J. Pastick","Amanda Armstrong","Jennifer D. Watts","Paul Alan Dirmeyer","Kimberley Rain Miner","Konrad Wessels","John J Qu","Charles E. Miller"],"date":"2023-10-23","year":2023,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ad0607","openalex":"W4387868774"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ad0607","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ad0607/pdf"},"orgs":["nasa","caltech"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["decadal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"GeoCryoAI, a CNN-RNN hybrid, models Alaskan permafrost active layer thickness and CO2/CH4 fluxes, with a 1.327 cm ALT RMSE over 1969–2022.","significance":2,"cited_by":16,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.58445-rars.618","title":"Comparative Analysis and the Progression of Different Machine Learning Models in the field of Meteorology","authors":["Sriram Yerramsetty"],"date":"2023-10-21","year":2023,"venue_type":"other","ids":{"doi":"10.58445/rars.618","openalex":"W4387846799"},"links":{"paper":"https://doi.org/10.58445/rars.618","pdf":"https://research-archive.org/index.php/rars/preprint/download/618/989/773"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares logistic regression, MLP and SVM for next-day rain prediction, showing how accuracy changes with training data volume.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2023.130375","title":"An explainable two-stage machine learning approach for precipitation forecast","authors":["Ali Ulvi Galip Şenocak","M. Tuğrul Yılmaz","Sinan Kalkan","İsmail Yücel","Muhammad Amjad"],"date":"2023-10-21","year":2023,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2023.130375","openalex":"W4387843871"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2023.130375"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Proposes an explainable two-stage classification-then-regression ML post-processor for daily station precipitation, improving on single-stage black-box baselines.","significance":3,"cited_by":36,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-5895-2023","title":"Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning","authors":["Daehyeon Han","Jungho Im","Yeji Shin","Juhyun Lee"],"date":"2023-10-20","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-5895-2023","openalex":"W4387817337"},"links":{"paper":"https://doi.org/10.5194/gmd-16-5895-2023","pdf":"https://gmd.copernicus.org/articles/16/5895/2023/gmd-16-5895-2023.pdf"},"orgs":["kma"],"topic":"nowcasting","topics":[],"type":"evaluation","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Tests 24 schemes for deep-learning radar nowcasting in South Korea, finding U-Net beats ConvLSTM and balanced MSE loss helps heavy rain.","significance":3,"cited_by":19,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4108-ew.4195","title":"Big Data and Machine Learning Framework for Temperature Forecasting","authors":["A Mekala","Bhaskar Kamal Baishya","Kamarajugadda Tulasi Vigneswara Rao","Deepak Annasaheb Vidhate","Vinayak A. Drave","P. Vishnu Prasanth"],"date":"2023-10-20","year":2023,"venue":"EAI Endorsed Transactions on Energy Web","venue_type":"journal","ids":{"doi":"10.4108/ew.4195","openalex":"W4387811293"},"links":{"paper":"https://doi.org/10.4108/ew.4195","pdf":"https://publications.eai.eu/index.php/ew/article/download/4195/2618"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses an artificial neural network on historical weather variables to forecast temperature, with a framework claimed to outperform traditional methods.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.107068","title":"All-weather precipitable water vapor map reconstruction using data fusion and machine learning-based spatial downscaling","authors":["Yongchao Ma","Tong Liu","Zhibin Yu","Chaowei Jiang","Guochang Xu","Zhiping Lǚ"],"date":"2023-10-20","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.107068","openalex":"W4387826386"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.107068"},"orgs":[],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Fuses multiple data sources with machine-learning spatial downscaling to reconstruct all-weather precipitable water vapour maps; no abstract available, so results are unverified.","significance":3,"cited_by":27,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.15615","title":"Super-resolved rainfall prediction with physics-aware deep learning","authors":["J. F. Amieva","A. Austoni","M. A. Brovelli","L. Ansalone","P. Naylor","F. Serva","B. Le Saux"],"date":"2023-10-20","year":2023,"venue":"Proceedings of the 2023 conference on Big Data from Space","venue_type":"journal","ids":{"arxiv":"2310.15615","doi":"10.2760/46796"},"links":{"paper":"https://arxiv.org/abs/2310.15615","pdf":"https://arxiv.org/pdf/2310.15615"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"A physics-aware ConvLSTM followed by a U-Net predicts km-scale rainfall occurrence from satellite radiances up to 4 hours ahead for the weather4cast challenge.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2023.1250201","title":"Precipitation forecasting: from geophysical aspects to machine learning applications","authors":["Ewerton Cristhian Lima de Oliveira","Antônio Vasconcelos Nogueira Neto","Ana Paula Paes dos Santos","Claudia Priscila Wanzeler da Costa","Julio Cezar Gonçalves de Freitas","Pedro Walfir Martins e Souza Filho","Rafael de Lima Rocha","Ronnie Cley de Oliveira Alves","Vânia dos Santos Franco","Eduardo Costa de Carvalho","Renata Gonçalves Tedeschi"],"date":"2023-10-19","year":2023,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2023.1250201","openalex":"W4387779021"},"links":{"paper":"https://doi.org/10.3389/fclim.2023.1250201"},"orgs":[],"topic":"nowcasting","topics":[],"type":"review","method":["other"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Reviews precipitation forecasting, covering rainfall physics and the growing role of machine learning methods, with discussion of computational challenges.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2023.3325628","title":"Preformer: Simple and Efficient Design for Precipitation Nowcasting With Transformers","authors":["Qizhao Jin","Xinbang Zhang","Xinyu Xiao","Ying Wang","Shiming Xiang","Chunhong Pan"],"date":"2023-10-19","year":2023,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2023.3325628","openalex":"W4387789870"},"links":{"paper":"https://doi.org/10.1109/lgrs.2023.3325628"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Preformer, a streamlined transformer with encoder-translator-decoder design, achieves state-of-the-art precipitation nowcasting with the fewest parameters among compared models.","significance":4,"cited_by":12,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.13161","title":"A Distributed Approach to Meteorological Predictions: Addressing Data Imbalance in Precipitation Prediction Models through Federated Learning and GANs","authors":["Elaheh Jafarigol","Theodore Trafalis"],"date":"2023-10-19","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.13161"},"links":{"paper":"https://arxiv.org/abs/2310.13161","pdf":"https://arxiv.org/pdf/2310.13161"},"orgs":[],"topic":"local-forecasting","topics":["benchmarks-data-eval"],"type":"model","method":["gan-vae","classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies SMOTE and GAN augmentation with federated learning to classify rare weather events in imbalanced tabular station data; no headline numbers given.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.66032-2221-2574-2023-1-3-20-28","title":"Neural network tasks for short-term forecasting according to results of microwave radiometric sounding of the atmosphere","authors":["Федосеева Елена Валерьевна","I. N. Rostokin","Georgy G. Shchukin","Ростокина Елена Анатольевна","M. A. Matyukov","Холодов Иван Юрьевич"],"date":"2023-10-18","year":2023,"venue":"Radio Engineering and Telecommunication System","venue_type":"journal","ids":{"doi":"10.66032/2221-2574-2023-1-3-20-28","openalex":"W7160314747"},"links":{"paper":"https://doi.org/10.66032/2221-2574-2023-1-3-20-28"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"pre-operational","summary":"A neural network trained on tri-band VHF radiometric sounding data forecasts short-term ground-layer temperature, humidity and precipitation from daily measurements.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.8369201","title":"CCClim - A machine-learning powered cloud class climatology","authors":["Arndt Kaps","Axel Lauer","Veronika Eyring"],"date":"2023-10-18","year":2023,"venue":"HAL (Le Centre pour la Communication Scientifique Directe)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.8369201","openalex":"W4393680432"},"links":{"paper":"https://doi.org/10.5281/zenodo.8369201","pdf":"https://hal.science/hal-04638041v1/document"},"orgs":[],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Machine-learning-derived 1° global climatology of eight WMO cloud types from ESA Cloud_cci retrievals, almost gapless from 1982 to 2016.","significance":4,"cited_by":5,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15203650","title":"RLNformer: A Rainfall Levels Nowcasting Model Based on Conv1D_Transformer for the Northern Xinjiang Area of China","authors":["Yulong Liu","Shuxian Liu","Juepu Chen"],"date":"2023-10-18","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15203650","openalex":"W4387737908"},"links":{"paper":"https://doi.org/10.3390/w15203650"},"orgs":[],"topic":"local-forecasting","topics":["nowcasting"],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A Conv1D-Transformer predicts 3-hour rainfall levels in northern Xinjiang from 24 hours of station data, a regional semi-arid case study.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.12387","title":"Learning to Optimise Climate Sensor Placement using a Transformer","authors":["Chen Wang","Victoria Huang","Gang Chen","Hui Ma","Bryce Chen","Jochen Schmidt"],"date":"2023-10-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.12387"},"links":{"paper":"https://arxiv.org/abs/2310.12387","pdf":"https://arxiv.org/pdf/2310.12387"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["reinforcement-learning","transformer"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Uses deep reinforcement learning with a transformer policy to learn improvement heuristics for climate sensor placement, comparing favourably with existing solvers.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.12088","title":"Improving probabilistic wind speed forecasting using M-Rice distribution and spatial data integration","authors":["Roberta Baggio","Jean-François Muzy"],"date":"2023-10-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.12088"},"links":{"paper":"https://arxiv.org/abs/2310.12088","pdf":"https://arxiv.org/pdf/2310.12088"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","era5"],"status":"research","summary":"A neural network predicts parametric wind speed distributions, with the M-Rice distribution outperforming alternatives and ERA5 neighbour data improving 6-hour station forecasts.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.11001","title":"Spatially-resolved hyperlocal weather prediction and anomaly detection using IoT sensor networks and machine learning techniques","authors":["Anita B. Agarwal","Rohit Rajesh","Nitin Arul"],"date":"2023-10-17","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.11001"},"links":{"paper":"https://arxiv.org/abs/2310.11001","pdf":"https://arxiv.org/pdf/2310.11001"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"IoT sensor networks with unsupervised learning give hyperlocal short-term forecasts of temperature, pressure and humidity, and flag anomalous weather patterns in real time.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15204981","title":"Cloud-to-Ground and Intra-Cloud Nowcasting Lightning Using a Semantic Segmentation Deep Learning Network","authors":["Ling Fan","Changhai Zhou"],"date":"2023-10-16","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15204981","openalex":"W4387667840"},"links":{"paper":"https://doi.org/10.3390/rs15204981","pdf":"https://www.mdpi.com/2072-4292/15/20/4981/pdf?version=1697451679"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Light3DUnet, a 3D U-Net on radar reflectivity, nowcasts cloud-to-ground and intra-cloud lightning within one hour over central China.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4596","title":"Investigating transformer‐based models for spatial downscaling and correcting biases of near‐surface temperature and wind‐speed forecasts","authors":["Xiaohui Zhong","Du Fei","Lei Chen","Zhibin Wang","Hao Li"],"date":"2023-10-14","year":2023,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4596","openalex":"W4387642293"},"links":{"paper":"https://doi.org/10.1002/qj.4596"},"orgs":["fudan-university","alibaba-damo"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["transformer"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"SwinIR and Uformer transformers downscale and bias-correct ECMWF HRES 2 m temperature and 10 m wind to 0.01°, outperforming UNet and RCAN baselines.","significance":3,"cited_by":47,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4592","title":"Identifying and characterising trapped lee waves using deep learning techniques","authors":["Jonathan Coney","Leif Denby","Andrew N Ross","He Wang","Simon Vosper","Van Niekerk","Tom Dunstan","Neil P. Hindley"],"date":"2023-10-14","year":2023,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4592","openalex":"W4387640835"},"links":{"paper":"https://doi.org/10.1002/qj.4592","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/qj.4592"},"orgs":["ecmwf","met-office"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","km-scale-sim"],"status":"research","summary":"A deep-learning segmentation model with transfer learning from synthetic fields detects and characterises trapped lee waves hazardous to aviation, faster than spectral methods.","significance":3,"cited_by":4,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-computers12100206","title":"The Potential of Machine Learning for Wind Speed and Direction Short-Term Forecasting: A Systematic Review","authors":["Décio Alves","Fábio Mendonça","Sheikh Shanawaz Mostafa","Fernando Morgado‐Dias"],"date":"2023-10-13","year":2023,"venue":"Computers","venue_type":"journal","ids":{"doi":"10.3390/computers12100206","openalex":"W4387616626"},"links":{"paper":"https://doi.org/10.3390/computers12100206","pdf":"https://www.mdpi.com/2073-431X/12/10/206/pdf?version=1697190646"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml","rnn"],"timescale":["nowcast","short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Systematic review of 23 studies finds deep learning outperforms traditional methods for short-term wind speed and direction forecasting, with mean MAE of 0.56 m/s.","significance":3,"cited_by":38,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3321963","title":"SpatioTemporal Inference Network for Precipitation Nowcasting With Multimodal Fusion","authors":["Qizhao Jin","Xinbang Zhang","Xinyu Xiao","Ying Wang","Gaofeng Meng","Shiming Xiang","Chunhong Pan"],"date":"2023-10-13","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3321963","openalex":"W4387623850"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3321963","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10285341.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"STIN uses spatiotemporally-aware convolutions to fuse temperature, humidity and wind with precipitation for nowcasting, improving on shared-kernel baselines.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.8276","title":"Application of deep learning algorithms to correct bias in CMIP6 simulations of surface air temperature over the Indian monsoon core region","authors":["A. Sabarinath","A. Naga Rajesh","Sachin S. Gunthe","T. V. Lakshmi Kumar"],"date":"2023-10-13","year":2023,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.8276","openalex":"W4387617059"},"links":{"paper":"https://doi.org/10.1002/joc.8276"},"orgs":[],"topic":"post-processing","topics":[],"type":"application","method":["cnn","rnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"CNN-1D and CNN-LSTM bias correction reduces CMIP6 surface air temperature warm bias over India's monsoon core to 0.35°C RMSE in the historical period.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.09392","title":"Machine Learning Estimation of Maximum Vertical Velocity from Radar","authors":["Randy J. Chase","Amy McGovern","Cameron Homeyer","Peter Marinescu","Corey Potvin"],"date":"2023-10-13","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.09392","doi":"10.1175/aies-d-23-0095.1"},"links":{"paper":"https://arxiv.org/abs/2310.09392","pdf":"https://arxiv.org/pdf/2310.09392"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["radar","km-scale-sim"],"status":"research","summary":"U-Nets retrieve storm maximum vertical velocity from 3D radar reflectivity with probabilistic outputs, reaching R² above 0.65 on WoFS simulations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.09162","title":"Quantum Machine Learning in Climate Change and Sustainability: a Review","authors":["Amal Nammouchi","Andreas Kassler","Andreas Theorachis"],"date":"2023-10-13","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.09162"},"links":{"paper":"https://arxiv.org/abs/2310.09162","pdf":"https://arxiv.org/pdf/2310.09162"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Survey of quantum machine learning for climate change, covering energy, climate data forecasting, monitoring and hazard prediction, with open challenges.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15204938","title":"Spatio-Temporal Alignment and Track-To-Velocity Module for Tropical Cyclone Forecast","authors":["Xiaoyi Geng","Zili Liu","Zhenwei Shi"],"date":"2023-10-12","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15204938","openalex":"W4387581158"},"links":{"paper":"https://doi.org/10.3390/rs15204938","pdf":"https://www.mdpi.com/2072-4292/15/20/4938/pdf?version=1697118127"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"TC-TrajGRU fuses track time series with meteorological fields for 12-hour tropical cyclone track forecasts that are comparable to official forecasts.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.08495","title":"Characterizing climate pathways using feature importance on echo state networks","authors":["Katherine Goode","Daniel Ries","Kellie McClernon"],"date":"2023-10-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.08495"},"links":{"paper":"https://arxiv.org/abs/2310.08495","pdf":"https://arxiv.org/pdf/2310.08495"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["rnn","classical-ml"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Feature-importance methods for echo state networks identify climate pathways, applied to reanalysis data around the 1991 Pinatubo eruction as a proxy for stratospheric aerosol injection.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15203548","title":"Empowering Greenhouse Cultivation: Dynamic Factors and Machine Learning Unite for Advanced Microclimate Prediction","authors":["Wei Sun","Fi‐John Chang"],"date":"2023-10-11","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15203548","openalex":"W4387530505"},"links":{"paper":"https://doi.org/10.3390/w15203548","pdf":"https://www.mdpi.com/2073-4441/15/20/3548/pdf?version=1697024726"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"A hybrid dynamic-factor, random forest and neural network model predicts greenhouse temperature, humidity, PAR and CO2 at multiple horizons, beating LSTM and BPNN baselines.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-023-44286-1","title":"Predicting maximum temperatures over India 10-days ahead using machine learning models","authors":["J. V. Ratnam","Swadhin Kumar Behera","Masami Nonaka","Patrick Martineau","Kalpesh Ravindra Patil"],"date":"2023-10-11","year":2023,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-023-44286-1","openalex":"W4387529214"},"links":{"paper":"https://doi.org/10.1038/s41598-023-44286-1","pdf":"https://www.nature.com/articles/s41598-023-44286-1.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"evaluation","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"AdaBoost with MLP base predicts India's March–June Tmax anomalies 10 days ahead, matching CFS reforecast skill in April–May but not in March or June.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.07437","title":"A Branched Deep Convolutional Network for Forecasting the Occurrence of Hazes in Paris using Meteorological Maps with Different Characteristic Spatial Scales","authors":["Chien Wang"],"date":"2023-10-11","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.07437"},"links":{"paper":"https://arxiv.org/abs/2310.07437","pdf":"https://arxiv.org/pdf/2310.07437"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["era5","stations"],"status":"pre-operational","summary":"A branched deep CNN forecasts Paris haze and low-visibility occurrence from multi-decadal meteorological maps, with blind forecasts for 2021 and 2022 showing reasonable skill.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-23-0025.1","title":"Deep Learning Parameterization of Vertical Wind Velocity Variability via Constrained Adversarial Training","authors":["Donifan Barahona","Katherine H. Breen","Heike Kalesse‐Los","Johannes Röttenbacher"],"date":"2023-10-10","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-23-0025.1","openalex":"W4387502517"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0025.1"},"orgs":["nasa"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["gan-vae","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim","era5","satellite"],"status":"research","summary":"An adversarially trained deep learning parameterization of subgrid vertical wind variability reproduces observed statistics and can run online in large-scale atmospheric models.","significance":4,"cited_by":4,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3322343","title":"Deep Learning for Near-Surface Air Temperature Estimation From FengYun 4A Satellite Data","authors":["Shanmin Yang","Ren Qing","Ningfang Zhou","Yan Zhang","Xi Wu"],"date":"2023-10-09","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3322343","openalex":"W4387449178"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3322343","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10274655.pdf"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["transformer"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","stations"],"status":"research","summary":"TaNet, a transformer, estimates near-surface air temperature from FengYun-4A imagery, reaching correlation 0.990 with ERA5 and 0.959 with stations.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.06045","title":"Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model","authors":["Yingkai Sha","Ryan A. Sobash","David John Gagne"],"date":"2023-10-09","year":2023,"venue":"Artificial Intelligence for the Earth Systems, 3(2), p.e230094 (2024)","venue_type":"journal","ids":{"arxiv":"2310.06045","doi":"10.1175/aies-d-23-0094.1"},"links":{"paper":"https://arxiv.org/abs/2310.06045","pdf":"https://arxiv.org/pdf/2310.06045"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards","probabilistic-ensembles"],"type":"model","method":["gan-vae","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"research","summary":"Conditional GANs generate synthetic ensemble members from HRRR convection-allowing forecasts, and a CNN turns them into severe weather probabilities with up to 20% Brier skill score gain.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.05691","title":"Climate-sensitive Urban Planning through Optimization of Tree Placements","authors":["Simon Schrodi","Ferdinand Briegel","Max Argus","Andreas Christen","Thomas Brox"],"date":"2023-10-09","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.05691","openalex":"W4387560296"},"links":{"paper":"https://arxiv.org/abs/2310.05691","pdf":"https://arxiv.org/pdf/2310.05691"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["other"],"timescale":["short","climate"],"spatial":["local"],"data":["other"],"status":"research","summary":"Neural networks emulate mean radiant temperature to guide an optimization of urban tree placement that reduces heat stress during heatwaves and over decades.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.05517","title":"WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correction","authors":["Binqing Wu","Weiqi Chen","Wengwei Wang","Bingqing Peng","Liang Sun","Ling Chen"],"date":"2023-10-09","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.05517"},"links":{"paper":"https://arxiv.org/abs/2310.05517","pdf":"https://arxiv.org/pdf/2310.05517"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["gnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"GNN-based local bias correction of NWP forecasts exploits meteorological and spatial dependencies, improving RMSE by 4.75% over the best baseline.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.04808","title":"Combining UPerNet and ConvNeXt for Contrails Identification to reduce Global Warming","authors":["Zhenkuan Wang"],"date":"2023-10-07","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.04808"},"links":{"paper":"https://arxiv.org/abs/2310.04808","pdf":"https://arxiv.org/pdf/2310.04808","code":"https://github.com/biluko/2023GRIC.git"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"UPerNet with ConvNeXt segments aircraft contrails in GOES-16 infrared false-colour imagery, ranking in the top 5% of a competition.","significance":2,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-3397684-v1","title":"Deep Learning Based Cyclone Intensity Estimation","authors":["Samhita Kothandaraman","Shreyash Salunke","Vedant Bhatkar","Jagruti Jadhav"],"date":"2023-10-06","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-3397684/v1","openalex":"W4387410558"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-3397684/v1","pdf":"https://www.researchsquare.com/article/rs-3397684/latest.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A capsule neural network estimates tropical cyclone intensity from INSAT-3D satellite images; the abstract reports no quantitative accuracy.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s43247-023-01011-0","title":"A machine learning approach to rapidly project climate responses under a multitude of net-zero emission pathways","authors":["Vassili Kitsios","T. Okane","David Newth"],"date":"2023-10-06","year":2023,"venue":"Communications Earth & Environment","venue_type":"journal","ids":{"doi":"10.1038/s43247-023-01011-0","openalex":"W4387408477"},"links":{"paper":"https://doi.org/10.1038/s43247-023-01011-0","pdf":"https://www.nature.com/articles/s43247-023-01011-0.pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"QuickClim uses machine learning to cheaply emulate climate simulations across many net-zero concentration pathways, quantifying uncertainty and pathway sensitivity.","significance":4,"cited_by":22,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15194824","title":"Machine Learning-Based Calibrated Model for Forecast Vienna Mapping Function 3 Zenith Wet Delay","authors":["Feijuan Li","Junyu Li","Lilong Liu","Liangke Huang","Lv Zhou","Hongchang He"],"date":"2023-10-05","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15194824","openalex":"W4387373324"},"links":{"paper":"https://doi.org/10.3390/rs15194824","pdf":"https://www.mdpi.com/2072-4292/15/19/4824/pdf?version=1696478687"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["nwp-analysis","stations"],"status":"research","summary":"An XGBoost calibration of the VMF3-FC zenith wet delay forecast cuts bias by 93% and RMSE by 6% versus the operational product, validated on 492 radiosondes.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.03499","title":"IceCloudNet: Cirrus and mixed-phase cloud prediction from SEVIRI input learned from sparse supervision","authors":["Kai Jeggle","Mikolaj Czerkawski","Federico Serva","Bertrand Le Saux","David Neubauer","Ulrike Lohmann"],"date":"2023-10-05","year":2023,"venue":"NeurIPS 2023 Workshop: Tackling Climate Change with Machine Learning","venue_type":"journal","ids":{"arxiv":"2310.03499","openalex":"W4387433351"},"links":{"paper":"https://arxiv.org/abs/2310.03499","pdf":"https://arxiv.org/pdf/2310.03499"},"orgs":["eth-zurich"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A CNN trained on SEVIRI satellite imagery and DARDAR lidar retrievals provides a geostationary observational constraint on cirrus and mixed-phase ice cloud microphysics.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.03261","title":"Climate Change and Future Food Security: Predicting the Extent of Cropland Gain or Degradation","authors":["Tanushkina Daria","Shevchenko Valeriy","Lukashevich Aleksander","Bulkin Aleksandr","Grinis Roland","Kovalev Kirill","Narozhnaia Veronika","Sotiriadi Nazar","Krenke Alexander","Maximov Yury"],"date":"2023-10-05","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.03261","openalex":"W4387432246"},"links":{"paper":"https://arxiv.org/abs/2310.03261","pdf":"https://arxiv.org/pdf/2310.03261"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"ML on CMIP5 projections forecasts crop productivity: rice output falls 10% in Vietnam and 14% in Thailand, but rises 11% in the Philippines by 2026.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.08790","title":"A comparison of data-driven reduced order models for the simulation of mesoscale atmospheric flow","authors":["Arash Hajisharifi","Michele Girfoglio","Annalisa Quaini","Gianluigi Rozza"],"date":"2023-10-05","year":2023,"venue":"Finite Elements in Analysis and Design","venue_type":"journal","ids":{"arxiv":"2307.08790","doi":"10.1016/j.finel.2023.104050","openalex":"W4387388093"},"links":{"paper":"https://doi.org/10.1016/j.finel.2023.104050"},"orgs":[],"topic":"regional-km-scale","topics":[],"type":"evaluation","method":["other"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Compares data-driven reduced-order models for simulating mesoscale atmospheric flow; the abstract is missing, so the ML contribution is uncertain.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.03180","title":"Accessing Convective Hazards Frequency Shift with Climate Change using Physics-Informed Machine Learning","authors":["Mikhail Mozikov","Ilya Makarov","Alexandr Bulkin","Daria Taniushkina","Roland Grinis","Yury Maximov"],"date":"2023-10-04","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.03180","openalex":"W4387427593"},"links":{"paper":"https://arxiv.org/abs/2310.03180","pdf":"https://arxiv.org/pdf/2310.03180"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml","physics-constrained"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Physics-informed neural network uses climate projections and landscape features to map projected changes in intense rainfall, hail and strong-wind frequency for climate adaptation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.02932","title":"Assessing Large Language Models on Climate Information","authors":["Jannis Bulian","Mike S. Schäfer","Afra Amini","Heidi Lam","Massimiliano Ciaramita","Ben Gaiarin","Michelle Chen Hübscher","Christian Buck","Niels G. Mede","Markus Leippold","Nadine Strauß"],"date":"2023-10-04","year":2023,"venue":"Proceedings of the 41st International Conference on Machine Learning (ICML), 2024","venue_type":"journal","ids":{"arxiv":"2310.02932"},"links":{"paper":"https://arxiv.org/abs/2310.02932","pdf":"https://arxiv.org/pdf/2310.02932"},"orgs":[],"topic":"llms-agents","topics":[],"type":"evaluation","method":["llm"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Framework and AI-assisted rating protocol show LLM climate answers have a significant gap between surface presentation and epistemological quality.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2310.02676","title":"PostRainBench: A comprehensive benchmark and a new model for precipitation forecasting","authors":["Yujin Tang","Jiaming Zhou","Xiang Pan","Zeying Gong","Junwei Liang"],"date":"2023-10-04","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.02676","openalex":"W4387427374"},"links":{"paper":"https://arxiv.org/abs/2310.02676","pdf":"https://arxiv.org/pdf/2310.02676","code":"https://github.com/yyyujintang/PostRainBench"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"benchmark","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"PostRainBench and CAMT post-process NWP for precipitation, with the first deep model beating NWP on heavy-rain CSI by 15.6–31.8%.","significance":4,"cited_by":1,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tia.2023.3321863","title":"Adaptive Feature Selection and GCN With Optimal Graph Structure-Based Ultra-Short-Term Wind Farm Cluster Power Forecasting Method","authors":["Honglai Xu","Yiran Zhang","Zhao Zhen","Fei Xu","Fei Wang"],"date":"2023-10-03","year":2023,"venue":"IEEE Transactions on Industry Applications","venue_type":"journal","ids":{"doi":"10.1109/tia.2023.3321863","openalex":"W4387303296"},"links":{"paper":"https://doi.org/10.1109/tia.2023.3321863"},"orgs":["tsinghua-university"],"topic":"applications-impacts","topics":[],"type":"model","method":["gnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Adaptive MRMR feature selection with conditional mutual information builds an optimal graph for GCN wind-farm cluster power forecasts from NWP data, cutting cost while improving accuracy.","significance":2,"cited_by":38,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.02074","title":"ACE: A fast, skillful learned global atmospheric model for climate prediction","authors":["Oliver Watt-Meyer","Gideon Dresdner","Jeremy McGibbon","Spencer K. Clark","Brian Henn","James Duncan","Noah D. Brenowitz","Karthik Kashinath","Michael S. Pritchard","Boris Bonev","Matthew E. Peters","Christopher S. Bretherton"],"date":"2023-10-03","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.02074","openalex":"W4387356266"},"links":{"paper":"https://arxiv.org/abs/2310.02074","pdf":"https://arxiv.org/pdf/2310.02074"},"orgs":["ai2","nvidia","uc-berkeley"],"topic":"climate-emulation","topics":[],"type":"model","method":["neural-operator"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"ACE is a 200M-parameter autoregressive emulator that stays stable for 100 years, reproduces a 100 km reference model's climate, and runs about 100x faster.","significance":7,"cited_by":27,"score":63,"highlight":true,"highlight_reason":"ACE is a stable 100-year ML atmospheric climate emulator that nearly conserves moisture, an important early step for ML climate models.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2310.01944","title":"Artificial Intelligence for Prediction of Climate Extremes: State of the art, challenges and future perspectives","authors":["Stefano Materia","Lluís Palma García","Chiem van Straaten","Sungmin O","Antonios Mamalakis","Leone Cavicchia","Dim Coumou","Paolo De Luca","Marlene Kretschmer","Markus G. Donat"],"date":"2023-10-03","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.01944","openalex":"W4387356099"},"links":{"paper":"https://arxiv.org/abs/2310.01944","pdf":"https://arxiv.org/pdf/2310.01944"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"review","method":[],"timescale":["s2s","seasonal"],"spatial":[],"data":[],"status":"research","summary":"Review of AI methods for predicting climate extremes such as heatwaves, droughts and heavy rain, covering hybrid AI-climate-model approaches, challenges and future perspectives.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.01853","title":"Score-based Data Assimilation for a Two-Layer Quasi-Geostrophic Model","authors":["François Rozet","Gilles Louppe"],"date":"2023-10-03","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.01853"},"links":{"paper":"https://arxiv.org/abs/2310.01853","pdf":"https://arxiv.org/pdf/2310.01853"},"orgs":[],"topic":"data-assimilation","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Score-based data assimilation with a memory-efficient score network is tested on a two-layer quasi-geostrophic atmosphere-like model, demonstrating scalability to high-dimensional geophysical systems.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-27669645.2023.2262127","title":"Optimised weighted mean temperature model based on generalised regression neural network","authors":["Junyu Li","Mingyun Hu","Lilong Liu","Chaolong Yao","Liangke Huang","Tengxu Zhang","Lv Zhou","Fade Chen"],"date":"2023-10-02","year":2023,"venue":"All Earth","venue_type":"journal","ids":{"doi":"10.1080/27669645.2023.2262127","openalex":"W4387264698"},"links":{"paper":"https://doi.org/10.1080/27669645.2023.2262127"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","era5","stations"],"status":"research","summary":"A generalised regression neural network corrects GRAPES and ERA5 weighted mean temperature, nearly removing bias and cutting RMSE by 19–21% for GNSS water vapour.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.eswa.2023.121907","title":"Machine-learning-based short-term forecasting of daily precipitation in different climate regions across the contiguous United States","authors":["Mohammad Valipour","Helaleh Khoshkam","Sayed Mohyeddin Bateni","Changhyun Jun"],"date":"2023-10-02","year":2023,"venue":"Expert Systems with Applications","venue_type":"journal","ids":{"doi":"10.1016/j.eswa.2023.121907","openalex":"W4387246662"},"links":{"paper":"https://doi.org/10.1016/j.eswa.2023.121907"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Machine learning models forecast short-term daily precipitation across contiguous US climate regions; the abstract is missing, so the method and gains are unverified.","significance":2,"cited_by":30,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.01690","title":"Forecasting Tropical Cyclones with Cascaded Diffusion Models","authors":["Pritthijit Nath","Pancham Shukla","Shuai Wang","César Quilodrán-Casas"],"date":"2023-10-02","year":2023,"venue_type":"preprint","ids":{"arxiv":"2310.01690","openalex":"W4387355792"},"links":{"paper":"https://arxiv.org/abs/2310.01690","pdf":"https://arxiv.org/pdf/2310.01690","code":"https://github.com/nathzi1505/forecast-diffmodels"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["diffusion","cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Cascaded diffusion models forecast tropical cyclone tracks and precipitation up to 36 hours from satellite and atmospheric data, running in 30 minutes on a single GPU.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.63581-jocpes.v3i2.04","title":"Predictive Maintenance for Automatic Weather Station (AWS) Based on Anomaly Detection Using Autoencoder: A Literature Review","authors":["Muhammad Hamdan Afif","Daffa Aly Meganendra"],"date":"2023-10-01","year":2023,"venue":"Journal of Computation Physics and Earth Science (JoCPES)","venue_type":"journal","ids":{"doi":"10.63581/jocpes.v3i2.04","openalex":"W4410074550"},"links":{"paper":"https://doi.org/10.63581/jocpes.v3i2.04","pdf":"https://journal.physan.org/index.php/jocpes/article/download/40/10"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Autoencoder-based anomaly detection is proposed to flag faulty automatic weather station data for predictive maintenance, a low-novelty study with no quantitative results given.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15194799","title":"Sofia Airport Visibility Estimation with Two Machine-Learning Techniques","authors":["Nikolay Penov","Guergana Guerova"],"date":"2023-10-01","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15194799","openalex":"W4387262675"},"links":{"paper":"https://doi.org/10.3390/rs15194799","pdf":"https://www.mdpi.com/2072-4292/15/19/4799/pdf?version=1696151847"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml","rnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random forest and LSTM estimate Sofia airport visibility from 11 surface meteorological variables, with regression post-processing improving skill for fog detection.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21917-ijsc.2023.0449","title":"ANT COLONY OPTIMISATION COUPLED WITH CHAOTIC DATA MINING FOR ENHANCED WEATHER PREDICTION ANALYSIS","authors":["Santhosh J","Govind Hanmantrao Balde","Rajesh Kumar A","Chandra Mouli Venkata Srinivas Akana"],"date":"2023-10-01","year":2023,"venue":"ICTACT Journal on Soft Computing","venue_type":"journal","ids":{"doi":"10.21917/ijsc.2023.0449","openalex":"W4403770161"},"links":{"paper":"https://doi.org/10.21917/ijsc.2023.0449"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Ant colony optimisation tunes decision-tree and neural data-mining models for weather prediction, claiming accuracy gains without specific quantitative results.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0081.1","title":"Machine Learning for Nonorographic Gravity Waves in a Climate Model","authors":["Steven C. Hardiman","Adam A. Scaife","Van Niekerk","Rachel Prudden","Aled Owen","Samantha V. Adams","Tom Dunstan","Nick Dunstone","Sam Madge"],"date":"2023-10-01","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0081.1","openalex":"W4387343040"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0081.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/4/AIES-D-22-0081.1.pdf"},"orgs":["met-office"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["other","cmip"],"status":"research","summary":"Neural network emulates the Met Office nonorographic gravity wave scheme using only two of six inputs, and reproduces QBO and ENSO-linked gravity wave variability in a climate model.","significance":4,"cited_by":10,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-5.0156999","title":"Constraining chaos: Enforcing dynamical invariants in the training of reservoir computers","authors":["Jason A. Platt","Stephen Gregory Penny","Timothy A. Smith","Tse‐Chun Chen","Henry D. I. Abarbanel"],"date":"2023-10-01","year":2023,"venue":"Chaos An Interdisciplinary Journal of Nonlinear Science","venue_type":"journal","ids":{"doi":"10.1063/5.0156999","openalex":"W4387299563"},"links":{"paper":"https://doi.org/10.1063/5.0156999","pdf":"https://www.osti.gov/servlets/purl/2246611"},"orgs":["noaa"],"topic":"xai-uq-physics","topics":["global-medium-range"],"type":"model","method":["rnn","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Reservoir computers trained to enforce dynamical invariants gain longer, more stable forecasts with limited data on Lorenz 96 and a quasi-geostrophic atmosphere model.","significance":3,"cited_by":10,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023ms003715","title":"Updates on Model Hierarchies for Understanding and Simulating the Climate System: A Focus on Data‐Informed Methods and Climate Change Impacts","authors":["Laura Mansfield","Aman Gupta","Adam C. Burnett","Brian Green","Catherine Wilka","Aditi Sheshadri"],"date":"2023-10-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2023ms003715","openalex":"W4387817541"},"links":{"paper":"https://doi.org/10.1029/2023ms003715","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023MS003715"},"orgs":["stanford"],"topic":"climate-emulation","topics":[],"type":"review","method":[],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Perspective on climate model hierarchies since 2016, highlighting the rapid growth of machine learning in climate modelling and model use for climate risk decisions.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023ea002906","title":"spateGAN: Spatio‐Temporal Downscaling of Rainfall Fields Using a cGAN Approach","authors":["Luca Glawion","Julius Polz","Harald Günter Kunstmann","Benjamin Fersch","Christian Chwala"],"date":"2023-10-01","year":2023,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2023ea002906","openalex":"W4387666384"},"links":{"paper":"https://doi.org/10.1029/2023ea002906","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023EA002906"},"orgs":["kit"],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"spateGAN, a conditional GAN, downscales coarse German radar rainfall from 32 km/1 h to 2 km/10 min, with FSS of 0.6 for intensities over 15 mm/h.","significance":4,"cited_by":36,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003596","title":"Using Convolutional Neural Network to Emulate Seasonal Tropical Cyclone Activity","authors":["Dan Fu","Ping Chang","Xue Liu"],"date":"2023-10-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003596","openalex":"W4387308870"},"links":{"paper":"https://doi.org/10.1029/2022ms003596"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal","climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5","cmip","nwp-analysis"],"status":"research","summary":"Transfer-learned CNN ensemble emulates seasonal tropical cyclone activity from large-scale fields, with skill on operational forecasts and projected global TC decline under warming.","significance":4,"cited_by":12,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003508","title":"An Ensemble of Neural Networks for Moist Physics Processes, Its Generalizability and Stable Integration","authors":["Yilun Han","Guang Jun Zhang","Yong Wang"],"date":"2023-10-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003508","openalex":"W4387574884"},"links":{"paper":"https://doi.org/10.1029/2022ms003508"},"orgs":["tsinghua-university"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Ensemble of 32-layer residual CNNs emulates superparameterized convection and clouds, runs stably for 5 years in CAM5, and generalizes to a +4K warmer climate.","significance":4,"cited_by":24,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003475","title":"Detection and Attribution of Climate Change Using a Neural Network","authors":["Constantin Bône","Guillaume Gastineau","Sylvie Thiria","Patrick Gallinari","Carlos Mejía"],"date":"2023-10-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003475","openalex":"W4387579482"},"links":{"paper":"https://doi.org/10.1029/2022ms003475","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003475"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"CNN-based backward optimization attributes 1900-2014 global temperature change to forcings without assuming additivity, with uncertainty estimates compared to regularized optimal fingerprinting.","significance":4,"cited_by":11,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.60087-jklst.vol2.n2.p113","title":"Leveraging Deep Learning for Climate Change Prediction Models : A Dive into Cutting-Edge Techniques","authors":["Gowrisankar Krishnamoorthy","Sai Mani Krishna Sistla"],"date":"2023-09-30","year":2023,"venue":"Journal of Knowledge Learning and Science Technology","venue_type":"journal","ids":{"doi":"10.60087/jklst.vol2.n2.p113","openalex":"W4391793199"},"links":{"paper":"https://doi.org/10.60087/jklst.vol2.n2.p113","pdf":"https://jklst.org/index.php/home/article/download/117/92"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Proposes deep ensembles to improve uncertainty in deep-learning statistical downscaling of climate projections, tested with pseudo-reality experiments for non-stationary future climates.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.169603607.70953547-v1","title":"“Seeing” beneath the clouds - machine-learning-based reconstruction of North African dust events","authors":["Franz Kanngießer","Stephanie Fiedler"],"date":"2023-09-29","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.169603607.70953547/v1","openalex":"W4387159105"},"links":{"paper":"https://doi.org/10.22541/essoar.169603607.70953547/v1"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Uses a neural network trained on reanalysis and cloud masks to inpaint cloud-obscured SEVIRI satellite dust plumes over North Africa, recovering up to 15% of summertime observations.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.17370","title":"Graph-based Neural Weather Prediction for Limited Area Modeling","authors":["Joel Oskarsson","Tomas Landelius","Fredrik Lindsten"],"date":"2023-09-29","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.17370","openalex":"W4387294484"},"links":{"paper":"https://arxiv.org/abs/2309.17370","pdf":"https://arxiv.org/pdf/2309.17370","code":"https://github.com/joeloskarsson/neural-lam"},"orgs":[],"topic":"regional-km-scale","topics":["global-medium-range"],"type":"model","method":["gnn"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Adapts graph-based neural weather prediction to limited-area modelling with a multi-scale hierarchical extension, validated on a Nordic regional model.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos14101501","title":"Estimating Daily Temperatures over Andhra Pradesh, India, Using Artificial Neural Networks","authors":["Gubbala China Satyanarayana","Sambasivarao Velivelli","Peddi Yasaswini","Meer Mohammed Ali"],"date":"2023-09-28","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14101501","openalex":"W4387177450"},"links":{"paper":"https://doi.org/10.3390/atmos14101501","pdf":"https://www.mdpi.com/2073-4433/14/10/1501/pdf?version=1695969895"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Uses neural networks to correct GFDL-ESM2G CMIP5 surface air temperature over Andhra Pradesh against IMD observations, with RMSE of 0.97–1.33 °C.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20944-preprints202309.1966.v1","title":"Hybrid Model of VMD and LSTM for Next-Hour Wind Speed Forecasting in a Hot Desert Climate","authors":["Ghadah Alkhayat","Syed Hamid Hasan","Rashid Mehmood"],"date":"2023-09-28","year":2023,"venue":"Preprints.org","venue_type":"preprint","ids":{"doi":"10.20944/preprints202309.1966.v1","openalex":"W4387184748"},"links":{"paper":"https://doi.org/10.20944/preprints202309.1966.v1","pdf":"https://www.preprints.org/manuscript/202309.1966/v1/download"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn","other"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A variational mode decomposition plus LSTM hybrid forecasts next-hour wind speed in Saudi Arabia with 61–74% skill, outperforming other hybrid and deep models.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s44274-023-00014-0","title":"A perceptible stacking ensemble model for air temperature prediction in a tropical climate zone","authors":["Tajrian Mollick","Galib Hashmi","Saifur Rahman Sabuj"],"date":"2023-09-28","year":2023,"venue":"Discover Environment","venue_type":"journal","ids":{"doi":"10.1007/s44274-023-00014-0","openalex":"W4387139970"},"links":{"paper":"https://doi.org/10.1007/s44274-023-00014-0","pdf":"https://link.springer.com/content/pdf/10.1007/s44274-023-00014-0.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Stacks linear regression, ridge, SVR, random forest and LightGBM to forecast next-day temperatures at Cox's Bazar, Bangladesh, with R² up to 0.965.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.16177","title":"Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles","authors":["Jerry Lin","Sungduk Yu","Liran Peng","Tom Beucler","Eliot Wong-Toi","Zeyuan Hu","Pierre Gentine","Margarita Geleta","Mike Pritchard"],"date":"2023-09-28","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.16177"},"links":{"paper":"https://arxiv.org/abs/2309.16177","pdf":"https://arxiv.org/pdf/2309.16177"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"evaluation","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Builds a semi-automated pipeline for O(100)-member ensembles of ML subgrid parameterization runs, showing offline error reductions can have opposite effects on online error and stability.","significance":6,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-3375438-v1","title":"Application of Maximum Overlap Discrete Wavelet Transform and Machine Learning to Improved Daily Rainfall Prediction Modeling","authors":["Kübra Küllahcı","Abdüsselam Altunkaynak"],"date":"2023-09-27","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-3375438/v1","openalex":"W4387096811"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-3375438/v1","pdf":"https://www.researchsquare.com/article/rs-3375438/latest.pdf"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"MODWT wavelet decomposition combined with machine learning improves daily rainfall forecasts three days ahead at three Turkish stations, judged by MSE and Nash-Sutcliffe efficiency.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-23-0044.1","title":"The Development and Initial Capabilities of ThunderCast, a Deep Learning Model for Thunderstorm Nowcasting in the United States","authors":["Stephanie M. Ortland","Michael J. Pavolonis","John L. Cintineo"],"date":"2023-09-27","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-23-0044.1","openalex":"W4387078817"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0044.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/aop/AIES-D-23-0044.1/AIES-D-23-0044.1.pdf"},"orgs":["noaa"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"U-Net nowcasts convection initiation and thunderstorms over the continental US within 60 min from GOES-16 imagery, with MRMS radar targets.","significance":4,"cited_by":2,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.15689","title":"Further analysis of cGAN: A system for Generative Deep Learning Post-processing of Precipitation","authors":["Fenwick Cooper","Andrew T. T. McRae","Matthew Chantry","Bobby Antonio","T. N. Palmer"],"date":"2023-09-27","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.15689","openalex":"W4387158672"},"links":{"paper":"http://arxiv.org/abs/2309.15689","pdf":"https://arxiv.org/pdf/2309.15689"},"orgs":[],"topic":"post-processing","topics":["downscaling","probabilistic-ensembles"],"type":"model","method":["gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["era5","radar","nwp-analysis"],"status":"research","summary":"Trains a conditional GAN on ERA5 to generate downscaled 1 km precipitation ensembles over UK and US regions, competitive with IFS ensembles at 8–16 h lead.","significance":4,"cited_by":0,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.15400","title":"Interpretable AI-Driven Discovery of Terrain-Precipitation Relationships for Enhanced Climate Insights","authors":["Hao Xu","Yuntian Chen","Zhenzhong Zeng","Nina Li","Jian Li","Dongxiao Zhang"],"date":"2023-09-27","year":2023,"venue":"Nexus, 2(1), 2025","venue_type":"journal","ids":{"arxiv":"2309.15400","doi":"10.1016/j.ynexs.2024.100045"},"links":{"paper":"https://arxiv.org/abs/2309.15400","pdf":"https://arxiv.org/pdf/2309.15400"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"A genetic-algorithm plus geographically weighted regression framework finds explicit terrain-precipitation equations that beat empirical models and support fine-scale precipitation downscaling under future climate.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023wr035088","title":"Intercomparison of Deep Learning Architectures for the Prediction of Precipitation Fields With a Focus on Extremes","authors":["Noelia Otero","Pascal Horton"],"date":"2023-09-26","year":2023,"venue":"Water Resources Research","venue_type":"journal","ids":{"doi":"10.1029/2023wr035088","openalex":"W4387055315"},"links":{"paper":"https://doi.org/10.1029/2023wr035088","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023WR035088"},"orgs":[],"topic":"benchmarks-data-eval","topics":["extremes-hazards","xai-uq-physics"],"type":"evaluation","method":["cnn"],"timescale":[],"spatial":["regional"],"data":[],"status":"research","summary":"Compares deep learning architectures for European precipitation, including extremes; a two-level U-Net matches deeper versions at lower cost, with layer-wise relevance attribution.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12665-023-11191-9","title":"Forecasting precipitation based on teleconnections using machine learning approaches across different precipitation regimes","authors":["Jalil Helali","Milad Nouri","Mehdi Mohammadi Ghaleni","Seyed Asaad Hosseini","Farshad Safarpour","Azim Shirdeli","Parisa Paymard","Zahra Kalantari"],"date":"2023-09-26","year":2023,"venue":"Environmental Earth Sciences","venue_type":"journal","ids":{"doi":"10.1007/s12665-023-11191-9","openalex":"W4387059168"},"links":{"paper":"https://doi.org/10.1007/s12665-023-11191-9"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning models forecast precipitation from teleconnection indices across different precipitation regimes, an approach for seasonal-scale rainfall prediction.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.15207","title":"Balancing Computational Efficiency and Forecast Error in Machine Learning-based Time-Series Forecasting: Insights from Live Experiments on Meteorological Nowcasting","authors":["Elin Törnquist","Wagner Costa Santos","Timothy Pogue","Nicholas Wingle","Robert A. Caulk"],"date":"2023-09-26","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.15207","openalex":"W4387156791"},"links":{"paper":"https://arxiv.org/abs/2309.15207","pdf":"https://arxiv.org/pdf/2309.15207"},"orgs":[],"topic":"local-forecasting","topics":["nowcasting"],"type":"evaluation","method":["classical-ml","rnn","transformer"],"timescale":["short","nowcast"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"pre-operational","summary":"Live experiments with XGBoost, MLP, Transformer and LSTM nowcast temperature, wind and cloud cover; a variance-horizon method cuts compute by over 50% and concept-drift retraining cuts it by up to 90%.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.14780","title":"Transferring climate change physical knowledge","authors":["Francesco Immorlano","Veronika Eyring","Thomas le Monnier de Gouville","Gabriele Accarino","Donatello Elia","Stephan Mandt","Giovanni Aloisio","Pierre Gentine"],"date":"2023-09-26","year":2023,"venue":"Proc. Natl. Acad. Sci. U.S.A. 122 (15) e2413503122, 2025","venue_type":"journal","ids":{"arxiv":"2309.14780","doi":"10.1073/pnas.2413503122"},"links":{"paper":"https://arxiv.org/abs/2309.14780","pdf":"https://arxiv.org/pdf/2309.14780"},"orgs":[],"topic":"climate-analysis-attribution","topics":["climate-emulation"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Transfer learning merges Earth system model simulations with historical observations to cut the spread of 21st-century global temperature projections by more than 50%.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5815-ijisa.2023.05.05","title":"Machine Learning for Weather Forecasting: XGBoost vs SVM vs Random Forest in Predicting Temperature for Visakhapatnam","authors":["Deep Karan Singh","Nisha Rawat"],"date":"2023-09-25","year":2023,"venue":"International Journal of Intelligent Systems and Applications","venue_type":"journal","ids":{"doi":"10.5815/ijisa.2023.05.05","openalex":"W4387029677"},"links":{"paper":"https://doi.org/10.5815/ijisa.2023.05.05","pdf":"https://www.mecs-press.org/ijisa/ijisa-v15-n5/IJISA-V15-N5-5.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares XGBoost, SVM and Random Forest for daily maximum and minimum temperature at Visakhapatnam; no single model dominates.","significance":1,"cited_by":7,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23198065","title":"MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network","authors":["Shengchun Wang","Tianyang Wang","Sihong Wang","Zixiong Fang","Jingui Huang","Zuxi Zhou"],"date":"2023-09-25","year":2023,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23198065","openalex":"W4387021375"},"links":{"paper":"https://doi.org/10.3390/s23198065","pdf":"https://www.mdpi.com/1424-8220/23/19/8065/pdf?version=1695624654"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A multi-layer attention module improves ConvRNN radar echo extrapolation, preserving high-intensity echoes and long-term skill on HKO-7 and HMB radar datasets.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-23-0070.1","title":"Lagrangian Analysis of Tropical Cyclone Intensification Simulated by General Circulation Models Compared with Observations","authors":["Chanwoo Song","Sungsu Park","Siyun Kim","Juwon Kim"],"date":"2023-09-25","year":2023,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-23-0070.1","openalex":"W4387018941"},"links":{"paper":"https://doi.org/10.1175/jcli-d-23-0070.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/clim/36/24/JCLI-D-23-0070.1.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"Machine learning on GCM and ERA5 environmental variables identifies humidity convergence and CAPE as key predictors of tropical cyclone intensification rates.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-023-42356-y","title":"Machine learning-based optimal crop selection system in smart agriculture","authors":["Sita Rani","Amit Kumar Mishra","Aman Kataria","Saurav Mallik","Hong HQ Qin"],"date":"2023-09-25","year":2023,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-023-42356-y","openalex":"W4387019227"},"links":{"paper":"https://doi.org/10.1038/s41598-023-42356-y","pdf":"https://www.nature.com/articles/s41598-023-42356-y.pdf"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Pairs LSTM-RNN weather forecasting with a Random Forest for crop selection, reporting 5-8% RMSE on temperature and rainfall and 97% crop-selection accuracy.","significance":2,"cited_by":113,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.107032","title":"Deep-learning post-processing of short-term station precipitation based on NWP forecasts","authors":["Qi Liu","Xiao Lou","Zhongwei Yan","Yajie Qi","Yuchao Jin","Shuang Yu","Xiaoliang Yang","Deming Zhao","Jiangjiang Xia"],"date":"2023-09-25","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.107032","openalex":"W4387008172"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.107032"},"orgs":["iap-cas","cma"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"CNN post-processing of ECMWF-HRES forecasts at 390 North China stations raises threat scores by up to 296% at high precipitation thresholds.","significance":3,"cited_by":36,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijeecs.v32.i2.pp1187-1198","title":"Rainfall analysis and prediction using ensemble learning for Karnataka State","authors":["Govardhana Meti","Ravikumar Guralamata Krishnegowda","Gudihalli Savitha Swamy"],"date":"2023-09-24","year":2023,"venue":"Indonesian Journal of Electrical Engineering and Computer Science","venue_type":"journal","ids":{"doi":"10.11591/ijeecs.v32.i2.pp1187-1198","openalex":"W4386995224"},"links":{"paper":"https://doi.org/10.11591/ijeecs.v32.i2.pp1187-1198","pdf":"https://ijeecs.iaescore.com/index.php/IJEECS/article/download/33421/17744"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A stacking ensemble of machine learning models estimates annual rainfall for Karnataka state using 1901–2015 station records.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.15214","title":"Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling","authors":["Morteza Mardani","Noah Brenowitz","Yair Cohen","Jaideep Pathak","Chieh-Yu Chen","Cheng-Chin Liu","Arash Vahdat","Mohammad Amin Nabian","Tao Ge","Akshay Subramaniam","Karthik Kashinath","Jan Kautz","Mike Pritchard"],"date":"2023-09-24","year":2023,"venue":"Communications Earth &amp; Environment","venue_type":"journal","ids":{"arxiv":"2309.15214","doi":"10.1038/s43247-025-02042-5","openalex":"W4407884014"},"links":{"paper":"https://arxiv.org/abs/2309.15214","pdf":"https://arxiv.org/pdf/2309.15214"},"orgs":["nvidia"],"topic":"downscaling","topics":[],"type":"model","method":["diffusion","cnn"],"timescale":[],"spatial":["regional","local"],"data":["era5","km-scale-sim"],"status":"research","summary":"Two-step UNet plus diffusion residual model downscales 25 km reanalysis to 2 km over Taiwan, recovering spectra and sharpening fronts and typhoon structures.","significance":7,"cited_by":121,"score":73,"highlight":true,"highlight_reason":"CorrDiff introduces a residual diffusion approach to km-scale downscaling that underpins NVIDIA's later work, and it is a significant generative downscaling result.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2309.14358","title":"Prediction of Tropical Pacific Rain Rates with Over-parameterized Neural Networks","authors":["Hojun You","Jiayi Wang","Raymond K. W. Wong","Courtney Schumacher","R. Saravanan","Mikyoung Jun"],"date":"2023-09-23","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.14358"},"links":{"paper":"https://arxiv.org/abs/2309.14358","pdf":"https://arxiv.org/pdf/2309.14358"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Over-parameterized neural networks predict GPM radar tropical Pacific rain-rate distributions from MERRA-2 profiles, capturing heavy tails better than other machine learning methods.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.13330","title":"Predicting Temperature of Major Cities Using Machine Learning and Deep Learning","authors":["Wasiou Jaharabi","MD Ibrahim Al Hossain","Rownak Tahmid","Md. Zuhayer Islam","T. M. Saad Rayhan"],"date":"2023-09-23","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.13330","openalex":"W4387074987"},"links":{"paper":"https://arxiv.org/abs/2309.13330","pdf":"https://arxiv.org/pdf/2309.13330"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM, ARIMA, SARIMA and Prophet are applied to historical temperature series for major cities to forecast future temperature trends; methods are standard and evaluation is limited.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.13211","title":"Interpretable structural model error discovery from sparse assimilation increments using spectral bias-reduced neural networks: A quasi-geostrophic turbulence test case","authors":["Rambod Mojgani","Ashesh Chattopadhyay","Pedram Hassanzadeh"],"date":"2023-09-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.13211","doi":"10.1029/2023ms004033"},"links":{"paper":"https://arxiv.org/abs/2309.13211","pdf":"https://arxiv.org/pdf/2309.13211"},"orgs":[],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"MEDIDA uses sparse equation discovery with random Fourier features to learn Earth system model errors from sparse analysis increments in a quasi-geostrophic test case.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.13207","title":"Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications","authors":["John S. Schreck","David John Gagne","Charlie Becker","William E. Chapman","Kim Elmore","Da Fan","Gabrielle Gantos","Eliot Kim","Dhamma Kimpara","Thomas Martin","Maria J. Molina","Vanessa M. Pryzbylo","Jacob Radford","Belen Saavedra","Justin Willson","Christopher Wirz"],"date":"2023-09-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.13207","doi":"10.1175/aies-d-23-0093.1"},"links":{"paper":"https://arxiv.org/abs/2309.13207","pdf":"https://arxiv.org/pdf/2309.13207","code":"https://github.com/ai2es/miles-guess"},"orgs":[],"topic":"xai-uq-physics","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Evidential deep learning gives one-model aleatoric and epistemic uncertainty for winter precipitation type and surface flux regression, matching ensemble accuracy; releases the MILES-GUESS package.","significance":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7218291290","title":"Revolutionizing Rain Prediction: Deep Learning-Powered TensorFlow Solution for Meteorology and Emergency Management","authors":["Prakaash A. S.","K. Kalaivani","K. C. Rajheshwari","P. Dhanalakshmi","T. A. Mohanaprakash"],"date":"2023-09-21","year":2023,"venue":"International Journal of Intelligent Systems and Applications in Engineering","venue_type":"journal","ids":{"openalex":"W7218291290"},"links":{"paper":"https://ijisae.org/index.php/IJISAE/article/view/3617","pdf":"https://ijisae.org/index.php/IJISAE/article/download/3617/2236"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"CNN-LSTM model predicts rainfall from meteorological variables and is claimed to beat statistical methods, though the abstract gives no quantitative results.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-23-0099.1","title":"Subseasonal Features of the Indian Monsoon","authors":["Lun Dai","Tat Fan Cheng","Bin Wang","Mengqian Lu"],"date":"2023-09-21","year":2023,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-23-0099.1","openalex":"W4386928379"},"links":{"paper":"https://doi.org/10.1175/jcli-d-23-0099.1"},"orgs":[],"topic":"climate-analysis-attribution","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Self-organizing map identifies six subseasonal Indian monsoon stages and two wind-based indices for subseasonal monitoring and forecasting.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-16-4165-2023","title":"Retrieval of surface solar irradiance from satellite imagery using machine learning: pitfalls and perspectives","authors":["Hadrien Verbois","Yves‐Marie Saint‐Drenan","Vadim Becquet","Benoît Gschwind","Philippe Blanc"],"date":"2023-09-19","year":2023,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-16-4165-2023","openalex":"W4386849793"},"links":{"paper":"https://doi.org/10.5194/amt-16-4165-2023","pdf":"https://amt.copernicus.org/articles/16/4165/2023/amt-16-4165-2023.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"MLP retrieval of surface solar irradiance from MSG imagery can beat a physical method but depends strongly on training-set similarity, highlighting pitfalls.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2023-8828093","title":"Daily Variation and Regional Differences in Wind Power Output during Heat and Cold Wave Days in China","authors":["Yang Liu","Jie Bai"],"date":"2023-09-19","year":2023,"venue":"International Transactions on Electrical Energy Systems","venue_type":"journal","ids":{"doi":"10.1155/2023/8828093","openalex":"W4386855735"},"links":{"paper":"https://doi.org/10.1155/2023/8828093","pdf":"https://downloads.hindawi.com/journals/itees/2023/8828093.pdf"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"A stacking ensemble ML model projects heat and cold wave days in China to 2060, showing wind power output falls during heat waves and rises during cold waves.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.10867","title":"Dynamical Tests of a Deep-Learning Weather Prediction Model","authors":["Gregory J. Hakim","Sanjit Masanam"],"date":"2023-09-19","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2309.10867","doi":"10.1175/aies-d-23-0090.1","openalex":"W4398139677"},"links":{"paper":"https://arxiv.org/abs/2309.10867","pdf":"https://arxiv.org/pdf/2309.10867"},"orgs":["university-of-washington"],"topic":"xai-uq-physics","topics":[],"type":"evaluation","method":["transformer"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Classical dynamical experiments show Pangu-Weather reproduces Matsuno-Gill responses, polar lows and hurricane development, suggesting it encodes realistic atmospheric physics.","significance":4,"cited_by":44,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2309.10808","title":"AI Foundation Models for Weather and Climate: Applications, Design, and Implementation","authors":["S. Karthik Mukkavilli","Daniel Salles Civitarese","Johannes Schmude","Johannes Jakubik","Anne Jones","Nam Nguyen","Christopher Phillips","Sujit Roy","Shraddha Singh","Campbell Watson","Raghu Ganti","Hendrik Hamann","Udaysankar Nair","Rahul Ramachandran","Kommy Weldemariam"],"date":"2023-09-19","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.10808","openalex":"W4386942610"},"links":{"paper":"https://arxiv.org/abs/2309.10808","pdf":"https://arxiv.org/pdf/2309.10808"},"orgs":["ibm-research","kit","nasa"],"topic":"foundation-models","topics":["global-medium-range","downscaling"],"type":"position","method":["transformer","physics-constrained"],"timescale":["nowcast","short","medium"],"spatial":["global","regional"],"data":["era5","nwp-analysis","other"],"status":"research","summary":"Review and perspective arguing that transformer-based weather and climate foundation models are mature enough to build, outlining criteria for downscaling, wildfire and hurricane tasks.","significance":4,"cited_by":15,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2309.10231","title":"Multi-fidelity climate model parameterization for better generalization and extrapolation","authors":["Mohamed Aziz Bhouri","Liran Peng","Michael S. Pritchard","Pierre Gentine"],"date":"2023-09-19","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.10231","openalex":"W4386907286"},"links":{"paper":"https://arxiv.org/abs/2309.10231","pdf":"https://arxiv.org/pdf/2309.10231"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-emulation","probabilistic-ensembles"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Multi-fidelity randomized prior networks combine physical parameterizations and storm-resolving runs to extrapolate to +4K warming, yielding more skillful climate projections with uncertainty.","significance":4,"cited_by":2,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35957-jatisi.v10i3.5376","title":"Enhancing Weather Prediction Using Stacked Long Short-Term Memory Networks","authors":["Mohammad Diqi","Hamzah Hamzah","SRI HASTA MULYANI"],"date":"2023-09-18","year":2023,"venue":"JATISI (Jurnal Teknik Informatika dan Sistem Informasi)","venue_type":"journal","ids":{"doi":"10.35957/jatisi.v10i3.5376","openalex":"W7218581412"},"links":{"paper":"https://doi.org/10.35957/jatisi.v10i3.5376"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Stacked LSTM forecasts hourly Denpasar weather (temperature, pressure, humidity, wind) from 20 years of station data, reporting average R² of 0.87 and RMSE of 0.035.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.10172","title":"Enhancing wind field resolution in complex terrain through a knowledge-driven machine learning approach","authors":["Jacob Wulff Wold","Florian Stadtmann","Adil Rasheed","Mandar Tabib","Omer San","Jan-Tore Horn"],"date":"2023-09-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.10172"},"links":{"paper":"https://arxiv.org/abs/2309.10172","pdf":"https://arxiv.org/pdf/2309.10172"},"orgs":[],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"ESRGAN-inspired network upscales coarse wind fields to high-resolution 3D flow over complex terrain at a Norwegian wind farm, outperforming trilinear interpolation.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.09336","title":"Unleashing the Power of Dynamic Mode Decomposition and Deep Learning for Rainfall Prediction in North-East India","authors":["Paleti Nikhil Chowdary","Sathvika P","Pranav U","Rohan S","Sowmya V","Gopalakrishnan E A","Dhanya M"],"date":"2023-09-17","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.09336"},"links":{"paper":"https://arxiv.org/abs/2309.09336","pdf":"https://arxiv.org/pdf/2309.09336"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM outperforms Dynamic Mode Decomposition for daily rainfall forecasting from 118 years of station records in North-East India.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.09067","title":"MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer","authors":["Fudong Lin","Summer Crawford","Kaleb Guillot","Yihe Zhang","Yan Chen","Xu Yuan","Li Chen","Shelby Williams","Robert Minvielle","Xiangming Xiao","Drew Gholson","Nicolas Ashwell","Tri Setiyono","Brenda Tubana","Lu Peng","Magdy Bayoumi","Nian-Feng Tzeng"],"date":"2023-09-16","year":2023,"venue":"ICCV 2023","venue_type":"journal","ids":{"arxiv":"2309.09067"},"links":{"paper":"https://arxiv.org/abs/2309.09067","pdf":"https://arxiv.org/pdf/2309.09067"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"model","method":["transformer"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"MMST-ViT transformer predicts US county crop yields from satellite images and weather, capturing short-term weather and long-term climate change effects with three metrics improved.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.09024","title":"Explainable Offline-Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave-QBO Testbed in the Small-data Regime","authors":["Hamid A. Pahlavan","Pedram Hassanzadeh","M. Joan Alexander"],"date":"2023-09-16","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.09024","doi":"10.1029/2023gl106324"},"links":{"paper":"https://arxiv.org/abs/2309.09024","pdf":"https://arxiv.org/pdf/2309.09024"},"orgs":[],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["cnn","physics-constrained"],"timescale":["climate"],"spatial":["local"],"data":["other"],"status":"research","summary":"Online re-training of two layers of a gravity-wave CNN via ensemble Kalman inversion yields realistic QBOs in a 1D model when offline small-data training fails.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.08694","title":"Processing of global solar irradiance and ground-based infrared sky images for solar nowcasting and intra-hour forecasting applications","authors":["Guillermo Terrén-Serrano","Manel Martínez‐Ramón"],"date":"2023-09-16","year":2023,"venue":"Solar Energy","venue_type":"journal","ids":{"arxiv":"2101.08694","doi":"10.1016/j.solener.2023.111968","openalex":"W3193111049"},"links":{"paper":"https://doi.org/10.1016/j.solener.2023.111968"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"ML-assisted physical models extract cloud features from sky-imager and irradiance data for intra-hour solar nowcasting, reducing hardware supervision needs for solar energy.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15184551","title":"Machine Learning-Based Estimation of Hourly GNSS Precipitable Water Vapour","authors":["Zohreh Adavi","Babak Ghassemi","Robert Weber","Natalia Hanna"],"date":"2023-09-15","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15184551","openalex":"W4386838147"},"links":{"paper":"https://doi.org/10.3390/rs15184551","pdf":"https://www.mdpi.com/2072-4292/15/18/4551/pdf?version=1695031517"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random Forest and ANN estimate hourly GNSS precipitable water vapour across Austria without meteorological inputs, with a single-hidden-layer ANN slightly outperforming other models.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15184536","title":"MCSPF-Net: A Precipitation Forecasting Method Using Multi-Channel Cloud Observations of FY-4A Satellite by 3D Convolution Neural Network","authors":["Yuhang Jiang","Feng Gao","Shaoqing Zhang","Wei Xin Cheng","Chang Liu","Shudong Wang"],"date":"2023-09-15","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15184536","openalex":"W4386780324"},"links":{"paper":"https://doi.org/10.3390/rs15184536","pdf":"https://www.mdpi.com/2072-4292/15/18/4536/pdf?version=1694762999"},"orgs":["cma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"3D CNN forecasts precipitation 4 h ahead from FY-4A multichannel satellite imagery, beating NWP on critical success index (0.25 vs 0.21).","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1145-3616384","title":"Evaluation of Dependency Structure for Multivariate Weather Predictors Using Copulas","authors":["Samuel Chege Maina","Dorcas Gicuku Mwigereri","Jonathan A. Weyn","Lester W. Mackey","Millicent Ochieng"],"date":"2023-09-15","year":2023,"venue":"ACM Journal on Computing and Sustainable Societies","venue_type":"journal","ids":{"doi":"10.1145/3616384","openalex":"W4386773830"},"links":{"paper":"https://doi.org/10.1145/3616384","pdf":"https://dl.acm.org/doi/pdf/10.1145/3616384"},"orgs":["microsoft-research"],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Vine copulas model dependence among weather variables at three African sites, proposed as a dependency layer for subseasonal forecast calibration.","significance":2,"cited_by":3,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.08567","title":"Charting the Realms of Mesoscale Cloud Organisation using Unsupervised Learning","authors":["Leif Denby"],"date":"2023-09-15","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.08567"},"links":{"paper":"https://arxiv.org/abs/2309.08567","pdf":"https://arxiv.org/pdf/2309.08567"},"orgs":[],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"An unsupervised neural network manifold maps the continuum of mesoscale shallow cloud organisation, showing organisation alters albedo by about ±1.4% beyond cloud-fraction changes.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.08473","title":"On some limitations of data-driven weather forecasting models","authors":["Massimo Bonavita"],"date":"2023-09-15","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.08473","openalex":"W4386839776"},"links":{"paper":"https://arxiv.org/abs/2309.08473","pdf":"https://arxiv.org/pdf/2309.08473"},"orgs":["ecmwf"],"topic":"xai-uq-physics","topics":["global-medium-range"],"type":"evaluation","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis","era5"],"status":"research","summary":"Analysis of Pangu-Weather shows its forecasts lack the fidelity and physical consistency of physics-based models, suggesting part of its deterministic skill advantage comes from these peculiarities.","significance":4,"cited_by":6,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.00425","title":"Propagation pathways of Indo-Pacific rainfall extremes are modulated by Pacific sea surface temperatures","authors":["Felix Strnad","Jakob Schlör","Ruth Geen","Niklas Boers","Bedartha Goswami"],"date":"2023-09-15","year":2023,"venue":"Nature Communications","venue_type":"journal","ids":{"arxiv":"2302.00425","doi":"10.1038/s41467-023-41400-9","openalex":"W4386782305"},"links":{"paper":"https://doi.org/10.1038/s41467-023-41400-9","pdf":"https://www.nature.com/articles/s41467-023-41400-9.pdf"},"orgs":["tum","pik"],"topic":"climate-analysis-attribution","topics":["s2s-seasonal"],"type":"model","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Unsupervised learning finds three propagation modes of Indo-Pacific rainfall extremes linked to Pacific SST, with early warning skill up to four weeks ahead.","significance":4,"cited_by":26,"score":46,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1515-jag-2023-0035","title":"A proposed neural network model for obtaining precipitable water vapor","authors":["Hadeer Al-Eshmawy","Mohamed Amin Abdelfatah","Gamal El-Fiky"],"date":"2023-09-14","year":2023,"venue":"Journal of Applied Geodesy","venue_type":"journal","ids":{"doi":"10.1515/jag-2023-0035","openalex":"W4386735689"},"links":{"paper":"https://doi.org/10.1515/jag-2023-0035"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","era5"],"status":"research","summary":"An ANN estimates precipitable water vapour over Egypt from surface meteorology, reaching RMS 0.21 mm and outperforming eight empirical models including ERA5.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-23-0017.1","title":"Improving Precipitation Nowcasting for High-Intensity Events Using Deep Generative Models with Balanced Loss and Temperature Data: A Case Study in the Netherlands","authors":["Charlotte Cambier van Nooten","Koert Schreurs","Jasper S. Wijnands","Hidde Leijnse","Maurice J. Schmeits","Kirien Whan","Yuliya Shapovalova"],"date":"2023-09-14","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-23-0017.1","openalex":"W4386740901"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0017.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/aop/AIES-D-23-0017.1/AIES-D-23-0017.1.pdf"},"orgs":["knmi"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"A deep generative nowcasting model with a balanced loss and temperature input extends skillful heavy-rain nowcasts over the Netherlands to 60-minute lead times.","significance":4,"cited_by":12,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.06833","title":"Agnostic detection of large-scale weather patterns in the northern hemisphere: from blockings to teleconnections","authors":["Sebastian Springer","Vera Melinda Galfi","Alessandro Laio","Valerio Lucarini"],"date":"2023-09-13","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.06833","doi":"10.1038/s41612-024-00659-5"},"links":{"paper":"https://arxiv.org/abs/2309.06833","pdf":"https://arxiv.org/pdf/2309.06833"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Unsupervised Markov-state analysis of 500 hPa heights identifies Northern Hemisphere winter blocking and teleconnection-like regimes with stronger dynamical grounding than EOFs.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15183244","title":"Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach","authors":["Pavan Kumar Yeditha","Anusha Ganapathiraju","Siva Sai Syam Nandikanti","Maheswaran Rathinasamy"],"date":"2023-09-12","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15183244","openalex":"W4386628916"},"links":{"paper":"https://doi.org/10.3390/w15183244","pdf":"https://www.mdpi.com/2073-4441/15/18/3244/pdf?version=1694516277"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Wavelet-decomposed deep learning forecasts monthly Indian precipitation from lagged rainfall and teleconnections; beats single-scale models.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app131810221","title":"Automated Aviation Wind Nowcasting: Exploring Feature-Based Machine Learning Methods","authors":["Décio Alves","Fábio Mendonça","Sheikh Shanawaz Mostafa","Fernando Morgado‐Dias"],"date":"2023-09-12","year":2023,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app131810221","openalex":"W4386687670"},"links":{"paper":"https://doi.org/10.3390/app131810221","pdf":"https://www.mdpi.com/2076-3417/13/18/10221/pdf?version=1694503610"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Feature engineering and selection for airport wind nowcasts 2–20 min ahead; wind speed MAPE reaches 0.35–0.63%, but direction remains hard.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2023.477","title":"Predicting rainfall response to climate change and uncertainty analysis: Introducing a novel downscaling CMIP6 models technique based on the stacking ensemble machine learning","authors":["Mahdi Valikhan Anaraki","Mojtaba Kadkhodazadeh","Amirreza Morshed-Bozorgdel","Saeed Farzin"],"date":"2023-09-12","year":2023,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2023.477","openalex":"W4386692412"},"links":{"paper":"https://doi.org/10.2166/wcc.2023.477","pdf":"https://iwaponline.com/jwcc/article-pdf/14/10/3671/1314064/jwc0143671.pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Proposes a stacking ensemble of machine learning algorithms to statistically downscale three CMIP6 GCMs for rainfall at two Iranian basins under SSP scenarios.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jclepro.2023.138793","title":"Wind power plants hybridised with solar power: A generation forecast perspective","authors":["António Couto","Ana I. Estanqueiro"],"date":"2023-09-12","year":2023,"venue":"Journal of Cleaner Production","venue_type":"journal","ids":{"doi":"10.1016/j.jclepro.2023.138793","openalex":"W4386648405"},"links":{"paper":"https://doi.org/10.1016/j.jclepro.2023.138793"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Neural-network forecasts of hybrid wind-solar plant output use NWP feature selection to cut forecast error by about 4% and raise market revenue.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.8250","title":"Synoptic circulation patterns of urban floods for the city of Hyderabad","authors":["Azharuddin Mohammed","Satish Kumar Regonda"],"date":"2023-09-12","year":2023,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.8250","openalex":"W4386626058"},"links":{"paper":"https://doi.org/10.1002/joc.8250"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Self-organizing maps classify synoptic circulation patterns behind Hyderabad urban flood rainfall, identifying 35 atmospheric river events and their moisture sources.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.07174","title":"HurriCast: Synthetic Tropical Cyclone Track Generation for Hurricane Forecasting","authors":["Shouwei Gao","Meiyan Gao","Yuepeng Li","Wenqian Dong"],"date":"2023-09-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.07174"},"links":{"paper":"https://arxiv.org/abs/2309.07174","pdf":"https://arxiv.org/pdf/2309.07174"},"orgs":[],"topic":"extremes-hazards","topics":["climate-emulation"],"type":"model","method":["classical-ml","other"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Hybrid ARIMA, K-means and autoencoder method generates synthetic North Atlantic tropical cyclone tracks and intensities from HURDAT2 for risk assessment.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.07173","title":"Using Unsupervised and Supervised Learning and Digital Twin for Deep Convective Ice Storm Classification","authors":["Jason Swope","Steve Chien","Emily Dunkel","Xavier Bosch-Lluis","Qing Yue","William Deal"],"date":"2023-09-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.07173"},"links":{"paper":"https://arxiv.org/abs/2309.07173","pdf":"https://arxiv.org/pdf/2309.07173"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","km-scale-sim"],"status":"research","summary":"Classifies simulated radiometer bands into deep convective ice-storm cloud types using WRF digital twin data and ML classifiers, with over 80% accuracy on the tropical set.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.06212","title":"Long-term drought prediction using deep neural networks based on geospatial weather data","authors":["Alexander Marusov","Vsevolod Grabar","Yury Maximov","Nazar Sotiriadi","Alexander Bulkin","Alexey Zaytsev"],"date":"2023-09-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.06212"},"links":{"paper":"https://arxiv.org/abs/2309.06212","pdf":"https://arxiv.org/pdf/2309.06212"},"orgs":[],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["transformer","rnn"],"timescale":["s2s","seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"EarthFormer transformer forecasts Palmer Drought Severity Index up to six months ahead, while ConvLSTM performs better at longer lead times, using open monthly climate data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.169447444.44778188-v1","title":"UNetKF: Ensemble U-Net Kalman Filter","authors":["Feiyu Lu"],"date":"2023-09-11","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.169447444.44778188/v1","openalex":"W4386594858"},"links":{"paper":"https://doi.org/10.22541/essoar.169447444.44778188/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.169447444.44778188"},"orgs":["noaa","ncar","princeton-university"],"topic":"data-assimilation","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"U-Net predicts flow-dependent covariances for an Ensemble Kalman Filter in a quasi-geostrophic model, matching 3DVar and EnKF for ensemble sizes up to 80.","significance":4,"cited_by":0,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2311.06253","title":"Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Mesh","authors":["Matthias Karlbauer","Nathaniel Cresswell-Clay","Dale R. Durran","Raul A. Moreno","Thorsten Kurth","Boris Bonev","Noah Brenowitz","Martin V. Butz"],"date":"2023-09-11","year":2023,"venue":"Journal of Advances in Modeling Earth Systems, 16, e2023MS004021","venue_type":"journal","ids":{"arxiv":"2311.06253","doi":"10.1029/2023ms00402"},"links":{"paper":"https://arxiv.org/abs/2311.06253","pdf":"https://arxiv.org/pdf/2311.06253"},"orgs":[],"topic":"global-medium-range","topics":["climate-emulation"],"type":"model","method":["cnn","rnn"],"timescale":["medium","climate"],"spatial":["global"],"data":["era5"],"status":"research","summary":"DLWP-HPX uses a HEALPix mesh and GRU-augmented U-Net with fewer variables at 110 km, reaching skill about one day behind Pangu-Weather and GraphCast at one week and stable one-year rollouts.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.05828","title":"Exploring Geometric Deep Learning For Precipitation Nowcasting","authors":["Shan Zhao","Sudipan Saha","Zhitong Xiong","Niklas Boers","Xiao Xiang Zhu"],"date":"2023-09-11","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.05828"},"links":{"paper":"https://arxiv.org/abs/2309.05828","pdf":"https://arxiv.org/pdf/2309.05828"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A temporal graph convolutional network with learned adjacency predicts radar-based precipitation over the Trento area, reducing smoothing and improving error measures over CNN baselines.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15184447","title":"Statistical Downscaling of SEVIRI Land Surface Temperature to WRF Near-Surface Air Temperature Using a Deep Learning Model","authors":["Afshin Afshari","Julian Vogel","Ganesh Chockalingam"],"date":"2023-09-09","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15184447","openalex":"W4386602211"},"links":{"paper":"https://doi.org/10.3390/rs15184447","pdf":"https://www.mdpi.com/2072-4292/15/18/4447/pdf?version=1694405898"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","km-scale-sim"],"status":"research","summary":"A 3D-convolution U-Net downscales SEVIRI land surface temperature to hourly 1 km WRF air temperature, with MAE 1.36 °C versus 1.49 °C for ridge regression.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.envint.2023.108196","title":"Grading surface urban heat island and investigating factor weight based on interpretable deep learning model across global cities","authors":["Kangning Li","Yunhao Chen","Jinbao Jiang"],"date":"2023-09-09","year":2023,"venue":"Environment International","venue_type":"journal","ids":{"doi":"10.1016/j.envint.2023.108196","openalex":"W4386573890"},"links":{"paper":"https://doi.org/10.1016/j.envint.2023.108196"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"Clusters global cities into five surface urban heat island grades and uses an interpretable TabNet model to weight the drivers of each grade.","significance":3,"cited_by":28,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10115-023-01955-x","title":"Long-term prediction of daily solar irradiance using Bayesian deep learning and climate simulation data","authors":["Firas Gerges","Michel C. Boufadel","Elie R. Bou-Zeid","Hani H. Nassif","Jason T. L. Wang"],"date":"2023-09-09","year":2023,"venue":"Knowledge and Information Systems","venue_type":"journal","ids":{"doi":"10.1007/s10115-023-01955-x","openalex":"W4386574529"},"links":{"paper":"https://doi.org/10.1007/s10115-023-01955-x"},"orgs":["princeton-university"],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["decadal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Bayesian deep learning forecasts long-term daily solar irradiance from climate simulation outputs for energy applications.","significance":2,"cited_by":14,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15184431","title":"DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network","authors":["Xi Kan","Zhengsong Lu","Yonghong Zhang","Linglong Zhu","Kenny Thiam Choy Lim Kam Sian","Jiangeng Wang","Xu Liu","Zhou Zhou","Haixiao Cao"],"date":"2023-09-08","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15184431","openalex":"W4387391605"},"links":{"paper":"https://doi.org/10.3390/rs15184431","pdf":"https://www.mdpi.com/2072-4292/15/18/4431/pdf?version=1694414958"},"orgs":["nuist","cma"],"topic":"observations-remote-sensing","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"DSRSS-Net jointly super-resolves and segments FY-4A imagery for snow-cover mapping on the Tibetan Plateau, improving classification accuracy by 4.45% over MOD10A1.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.04452","title":"Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks","authors":["Kevin Höhlein","Benedikt Schulz","Rüdiger Westermann","Sebastian Lerch"],"date":"2023-09-08","year":2023,"venue":"Artificial Intelligence for the Earth Systems, 2023","venue_type":"journal","ids":{"arxiv":"2309.04452","doi":"10.1175/aies-d-23-0070.1"},"links":{"paper":"https://arxiv.org/abs/2309.04452","pdf":"https://arxiv.org/pdf/2309.04452"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Permutation-invariant neural networks postprocess raw ensemble forecasts as unordered member sets, achieving state-of-the-art calibrated distributions for surface temperature and wind gusts.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.37595-mediainfo.v22i2.180","title":"Sistem Prakiraan Cuaca Berbasis Android dengan Metode Jaringan Syaraf Tiruan Backpropagation","authors":["Adi Arga Arifnur","Jefril Rahmadoni","Ullya Mega Wahyuni"],"date":"2023-09-07","year":2023,"venue":"Media Informatika","venue_type":"journal","ids":{"doi":"10.37595/mediainfo.v22i2.180","openalex":"W4386468014"},"links":{"paper":"https://doi.org/10.37595/mediainfo.v22i2.180","pdf":"https://journal.likmi.ac.id/index.php/media-informatika/article/download/180/99"},"orgs":[],"topic":"local-forecasting","topics":["infra-software"],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"An Arduino and Android weather station uses a backpropagation neural network on temperature and humidity, reaching a 78.6% forecast success rate on 14 trials.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-22-0137.1","title":"Deep Learning–Based Summertime Turbulence Intensity Estimation Using Satellite Observations","authors":["Yoonjin Lee","Soo‐Hyun Kim","Yoo‐Jeong Noh","Jung‐Hoon Kim"],"date":"2023-09-07","year":2023,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-22-0137.1","openalex":"W4386497166"},"links":{"paper":"https://doi.org/10.1175/jtech-d-22-0137.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atot/40/11/JTECH-D-22-0137.1.pdf"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"U-Net models estimate aviation turbulence intensity at three altitude layers from GOES-16 ABI imagery; U-Net3+ matches pilot reports best.","significance":3,"cited_by":18,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023jd038927","title":"Regional Variability in the Environmental Controls of Precipitation Regimes in the Tropics","authors":["Samson Hagos","Zhe Feng","Sheng‐Lun Tai","Jingyi Chen"],"date":"2023-09-07","year":2023,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2023jd038927","openalex":"W4386525961"},"links":{"paper":"https://doi.org/10.1029/2023jd038927","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023JD038927"},"orgs":[],"topic":"climate-analysis-attribution","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"A simple ML model links PW, CIN and wind shear to tropical rain-regime transitions, with a PW above 60 mm threshold, proposed as a convection trigger.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl104539","title":"Soil Moisture Dominates the Forest Productivity Decline During the 2022 China Compound Drought‐Heatwave Event","authors":["Dayang Zhao","Zhaoying Zhang","Yongguang Zhang"],"date":"2023-09-07","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl104539","openalex":"W4386512038"},"links":{"paper":"https://doi.org/10.1029/2023gl104539","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023GL104539"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Machine learning attributes the 2022 China compound drought-heatwave forest productivity decline mainly to soil moisture rather than VPD, identifying a tipping point.","significance":3,"cited_by":73,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-3310465-v1","title":"Machine learning for uncertainty quantification in climate precipitation prediction over South America","authors":["Vinicius Schmidt Monego","Juliana Aparecida Anochi","Haroldo Fraga de Campos Velho"],"date":"2023-09-05","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-3310465/v1","openalex":"W4386465478"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-3310465/v1","pdf":"https://www.researchsquare.com/article/rs-3310465/latest.pdf"},"orgs":[],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Applies machine learning with uncertainty quantification to climate precipitation predictions over South America; the abstract is missing, so details are limited.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20944-preprints202309.0156.v1","title":"Improving Precipitation Forecasting in Jilin Province Using Deep Learning and Gaussian Noise","authors":["Yibo Zhang","Wang Chengcheng","Wang Pengcheng","Zhang Lu","Yu Qingbo","Hui Xu","Maofa Wang"],"date":"2023-09-05","year":2023,"venue":"Preprints.org","venue_type":"preprint","ids":{"doi":"10.20944/preprints202309.0156.v1","openalex":"W4386413054"},"links":{"paper":"https://doi.org/10.20944/preprints202309.0156.v1","pdf":"https://www.preprints.org/manuscript/202309.0156/v1/download"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn","transformer","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Stacked-LSTM beats Transformer and SVR for precipitation at 56 Jilin stations; Gaussian noise augmentation improves robustness and zero-rain prediction.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41558-023-01769-3","title":"Harnessing AI and computing to advance climate modelling and prediction","authors":["Tapio Schneider","Swadhin Behera","Giulio Boccaletti","Clara Deser","Kerry Emanuel","Raffaele Ferrari","L. Ruby Leung","Ning Lin","Thomas Müller","Antonio Navarra","Ousmane Ndiaye","Andrew Stuart","Joseph Tribbia","Toshio Yamagata"],"date":"2023-09-05","year":2023,"venue":"Nature Climate Change","venue_type":"journal","ids":{"doi":"10.1038/s41558-023-01769-3","openalex":"W4386465713"},"links":{"paper":"https://doi.org/10.1038/s41558-023-01769-3"},"orgs":["caltech","mit","ncar","princeton-university"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"position","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Nature Climate Change perspective on combining AI and computing for climate modelling and prediction; abstract absent, judged from title and venue.","significance":4,"cited_by":85,"score":71,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s00484-023-02544-x","title":"Impacts of meteorological variables and machine learning algorithms on rice yield prediction in Korea","authors":["Subin Ha","Yong-Tak Kim","Eun‐Soon Im","Jina Hur","Sera Jo","Yong-Seok Kim","Kyo‐Moon Shim"],"date":"2023-09-05","year":2023,"venue":"International Journal of Biometeorology","venue_type":"journal","ids":{"doi":"10.1007/s00484-023-02544-x","openalex":"W4386413101"},"links":{"paper":"https://doi.org/10.1007/s00484-023-02544-x"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning models link meteorological variables to rice yield in Korea, with the best algorithm identified for crop yield prediction.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.8241","title":"The efficacy of tropical and extratropical predictors for long‐lead El Niño‐Southern Oscillation prediction: A study using a machine learning algorithm","authors":["Wanjiao Song","Jin‐Yi Yu","Tao Lian"],"date":"2023-09-05","year":2023,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.8241","openalex":"W4386480706"},"links":{"paper":"https://doi.org/10.1002/joc.8241","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.8241"},"orgs":["cma"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"An LSTM forecasts the Oceanic Niño Index 18 months ahead, with the extratropical western North Pacific predictor giving the best skill and beating linear regression.","significance":4,"cited_by":1,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.02615","title":"Generative Algorithms for Fusion of Physics-Based Wildfire Spread Models with Satellite Data for Initializing Wildfire Forecasts","authors":["Bryan Shaddy","Deep Ray","Angel Farguell","Valentina Calaza","Jan Mandel","James Haley","Kyle Hilburn","Derek V. Mallia","Adam Kochanski","Assad Oberai"],"date":"2023-09-05","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.02615"},"links":{"paper":"https://arxiv.org/abs/2309.02615","pdf":"https://arxiv.org/pdf/2309.02615"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["gan-vae","physics-constrained"],"timescale":["short"],"spatial":["regional"],"data":["satellite","km-scale-sim"],"status":"research","summary":"A conditional Wasserstein GAN trained on WRF-SFIRE simulations infers wildfire arrival times from satellite detections, achieving a 0.81 Sorensen coefficient for fire perimeters.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.02600","title":"Comparative Evaluation of Metaheuristic Algorithms for Hyperparameter Selection in Short-Term Weather Forecasting","authors":["Anuvab Sen","Arul Rhik Mazumder","Dibyarup Dutta","Udayon Sen","Pathikrit Syam","Sandipan Dhar"],"date":"2023-09-05","year":2023,"venue":"Proceedings of the 15th International Joint Conference on Computational Intelligence (2023)","venue_type":"journal","ids":{"arxiv":"2309.02600","doi":"10.5220/0012187300003595"},"links":{"paper":"https://arxiv.org/abs/2309.02600","pdf":"https://arxiv.org/pdf/2309.02600"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["rnn","other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Compares genetic algorithm, differential evolution and particle swarm tuning of ANN, LSTM and GRU hyperparameters for short-term weather forecasting, with no headline numeric gain given.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.02248","title":"Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Network","authors":["Smit Marvaniya","Jitendra Singh","Nicolas Galichet","Fred Ochieng Otieno","Geeth De Mel","Kommy Weldemariam"],"date":"2023-09-05","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.02248","openalex":"W4386557962"},"links":{"paper":"https://arxiv.org/abs/2309.02248","pdf":"https://arxiv.org/pdf/2309.02248"},"orgs":["ibm-research"],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":[],"data":["other"],"status":"research","summary":"Modular neural network encodes uncertain seasonal climate forecasts for supply-chain demand forecasting, reducing error by 13% to 17% versus existing methods.","significance":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14091396","title":"Modeling of Precipitation Prediction Based on Causal Analysis and Machine Learning","authors":["Hongchen Li","Ming Li"],"date":"2023-09-04","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14091396","openalex":"W4386423282"},"links":{"paper":"https://doi.org/10.3390/atmos14091396","pdf":"https://www.mdpi.com/2073-4433/14/9/1396/pdf?version=1693882005"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"Random Forest and BP networks with causally screened circulation predictors forecast western China precipitation 1, 3 and 6 months ahead, improving 1- and 3-month skill over an institute's forecasts.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ejrh.2023.101523","title":"Assessing the impacts of climate change on precipitation through a hybrid method of machine learning and discrete wavelet transform techniques, case study: Cork, Ireland","authors":["Sogol Moradian","Gregório Iglesias","Ciarán Broderick","Agnieszka I. Olbert"],"date":"2023-09-04","year":2023,"venue":"Journal of Hydrology Regional Studies","venue_type":"journal","ids":{"doi":"10.1016/j.ejrh.2023.101523","openalex":"W4386463742"},"links":{"paper":"https://doi.org/10.1016/j.ejrh.2023.101523"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Combines machine learning and wavelet simulations with reweighting to bias-correct CMIP6 NEX-GDDP precipitation for Cork, projecting a decline to about 116–119 mm/month by 2076–2100.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.01424","title":"Expanding Mars Climate Modeling: Interpretable Machine Learning for Modeling MSL Relative Humidity","authors":["Nour Abdelmoneim","Dattaraj B. Dhuri","Dimitra Atri","Germán Martínez"],"date":"2023-09-04","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.01424","openalex":"W4386556652"},"links":{"paper":"https://arxiv.org/abs/2309.01424","pdf":"https://arxiv.org/pdf/2309.01424"},"orgs":["nyu-m2lines"],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Uses an interpretable neural network trained on Mars Planetary Climate Model outputs to predict Gale Crater relative humidity with R² of 0.92, emulating a local climate variable.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7217807433","title":"Heat Wave Prediction Using Recurrent Neural Networks Based on Deep Learning","authors":["Sarita Byagar","Araddhana Arvind Deshmukh","Kirti Wanjale","Vinod S. Wadne","Nidhi Ranjan","Rupali Gangarde"],"date":"2023-09-03","year":2023,"venue":"International Journal of Intelligent Systems and Applications in Engineering","venue_type":"journal","ids":{"openalex":"W7217807433"},"links":{"paper":"https://ijisae.org/index.php/IJISAE/article/view/3496","pdf":"https://ijisae.org/index.php/IJISAE/article/download/3496/2092"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM predicts local heatwave occurrence from historical temperature, humidity and wind data, outperforming traditional statistical models in accuracy and F1.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.62486-latia202576","title":"Role of Artificial Intelligence in Disseminating Climate Information Services in Africa","authors":["Petros Chavula","Fredrick Kayusi"],"date":"2023-09-03","year":2023,"venue":"LatIA","venue_type":"journal","ids":{"doi":"10.62486/latia202576","openalex":"W4408953989"},"links":{"paper":"https://doi.org/10.62486/latia202576","pdf":"https://latia.ageditor.uy/index.php/latia/article/download/76/250"},"orgs":[],"topic":"applications-impacts","topics":["llms-agents"],"type":"review","method":["classical-ml","llm"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"pre-operational","summary":"Reviews how AI, including ML and NLP, can improve climate information services and drought early warning in Africa, with sub-Saharan case studies.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asoc.2023.110799","title":"A granular sigmoid extreme learning machine and its application in a weather forecast","authors":["Hailiang Jiang","Yumin Chen","Hongbo Jiang","Yue Ni","Huijun Su"],"date":"2023-09-03","year":2023,"venue":"Applied Soft Computing","venue_type":"journal","ids":{"doi":"10.1016/j.asoc.2023.110799","openalex":"W4386401794"},"links":{"paper":"https://doi.org/10.1016/j.asoc.2023.110799"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Proposes a granular sigmoid extreme learning machine applied to weather forecasting; abstract unavailable, so details are unverified.","significance":1,"cited_by":17,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.01247","title":"Evaluation of forecasts by a global data-driven weather model with and without probabilistic post-processing at Norwegian stations","authors":["John Bjørnar Bremnes","Thomas N. Nipen","Ivar A. Seierstad"],"date":"2023-09-03","year":2023,"venue":"Nonlinear Processes in Geophysics","venue_type":"journal","ids":{"arxiv":"2309.01247","doi":"10.5194/npg-31-247-2024","openalex":"W4399993230"},"links":{"paper":"https://arxiv.org/abs/2309.01247","pdf":"https://arxiv.org/pdf/2309.01247"},"orgs":["met-norway"],"topic":"post-processing","topics":["global-medium-range","applications-impacts"],"type":"evaluation","method":["other"],"timescale":["medium"],"spatial":["local"],"data":["era5","stations","nwp-analysis"],"status":"research","summary":"Evaluates Pangu-Weather against ECMWF and MEPS at 183 Norwegian stations; probabilistic post-processing helps global models most, though MEPS remains best.","significance":3,"cited_by":7,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.61186-jgit.11.2.1","title":"Tropical Storm Path Prediction Using Long Short-Term Memory Model, Similarity Measurement of Trajectories and Contextual Information","authors":["Sahar Farmanifard","Ali Asghar Alesheikh","Mohammad Sharif","Danial Alizadeh"],"date":"2023-09-01","year":2023,"venue":"Journal of Geospatial Information Technology","venue_type":"journal","ids":{"doi":"10.61186/jgit.11.2.1","openalex":"W4394997841"},"links":{"paper":"https://doi.org/10.61186/jgit.11.2.1","pdf":"http://jgit.kntu.ac.ir/files/site1/user_files_71dd47/msharif-A-11-888-1-bb7d15c.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"An LSTM with wind speed and storm direction context predicts North Atlantic tropical cyclone tracks at 3 to 12 hours, cutting path error by a reported 1.9 to 4.5 km.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21608-ajmris.2023.317449","title":"NEW WEATHER FORECASTING APPLICATIONS","authors":["Mohamed Gamal Shouman"],"date":"2023-09-01","year":2023,"venue":"Alexandria Journal of Managerial Research & Information Systems","venue_type":"journal","ids":{"doi":"10.21608/ajmris.2023.317449","openalex":"W4387038510"},"links":{"paper":"https://doi.org/10.21608/ajmris.2023.317449","pdf":"https://ajmris.journals.ekb.eg/article_317449_cdd5e65a9c10c6ff4281dd267debe5e8.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Proposes ANN-based weather forecasting apps claiming high accuracy up to 1460 days ahead, but methods and validation are weakly described.","significance":0,"cited_by":2,"score":0,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15407-pp2023.03.091","title":"Deeplearning-based approach to improving numerical weather forecasts","authors":["А.Yu. Doroshenko","Vitalii Shpyg","Roman Kushnirenko"],"date":"2023-09-01","year":2023,"venue":"PROBLEMS IN PROGRAMMING","venue_type":"journal","ids":{"doi":"10.15407/pp2023.03.091","openalex":"W4388827505"},"links":{"paper":"https://doi.org/10.15407/pp2023.03.091","pdf":"https://pp.isofts.kiev.ua/index.php/ojs1/article/download/585/635"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural network corrects COSMO 2 m temperature forecast errors at eight Kyiv-region stations, improving forecasts in over 50% of cases.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14042-j.cnki.32.1309.2023.05.003","title":"Radar rainfall nowcasting and flood forecasting based on deep learning","authors":["Jianzhu LI","Leijing Li","Ping Feng","Ruoyi Tang"],"date":"2023-09-01","year":2023,"venue":"DOAJ (DOAJ: Directory of Open Access Journals)","venue_type":"preprint","ids":{"doi":"10.14042/j.cnki.32.1309.2023.05.003","openalex":"W7158829235"},"links":{"paper":"https://doi.org/10.14042/j.cnki.32.1309.2023.05.003"},"orgs":[],"topic":"nowcasting","topics":[],"type":"application","method":["cnn","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"U-Net variants nowcast radar rainfall one hour ahead and feed HEC-HMS flood models; TransAtt-Unet keeps simulated peak errors under 20%.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.12785-ijcds-140167","title":"A Machine Learning-Based Approach for Meteorological Big Data Analysis to Improve Weather Forecast","authors":["Abderrahim El Mhouti","Mohamed Abdelmonem Fahim","Asmae Bahbah","Yassine El Borji","Adil Souf","Ayoub Aoulalay","Chaimae Ouazri"],"date":"2023-09-01","year":2023,"venue":"International Journal of Computing and Digital Systems","venue_type":"journal","ids":{"doi":"10.12785/ijcds/140167","openalex":"W4386356812"},"links":{"paper":"https://doi.org/10.12785/ijcds/140167","pdf":"https://journal.uob.edu.bh:443/bitstream/123456789/5172/3/IJCDS140167.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Random Projection dimensionality reduction with Decision Tree and Naive Bayes on web-scraped weather data is claimed to improve forecast accuracy.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023ea002909","title":"Reconstructing and Nowcasting the Rainfall Field by a CML Network","authors":["Peng Zhang","Xichuan Liu","Mingzhong Zou"],"date":"2023-09-01","year":2023,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2023ea002909","openalex":"W4386533256"},"links":{"paper":"https://doi.org/10.1029/2023ea002909","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023EA002909"},"orgs":["cma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other","stations"],"status":"research","summary":"LSTM nowcasts 10-minute rainfall fields reconstructed from 26 commercial microwave links, reaching correlation 0.91 at one minute and falling to 0.20 at ten.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ea002743","title":"Fast Gaussian Process Emulation of Mars Global Climate Model","authors":["Marc Tunnell","Nathaniel Bowman","Erin Carrier"],"date":"2023-09-01","year":2023,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2022ea002743","openalex":"W4387008385"},"links":{"paper":"https://doi.org/10.1029/2022ea002743"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A Gaussian process surrogate emulates the NASA Mars Global Climate Model in minutes instead of weeks for sensitivity studies.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.tcrr.2023.09.003","title":"Recent advances in seasonal and multi-annual tropical cyclone forecasting","authors":["Yuhei Takaya","Louis‐Philippe Caron","Eric S. Blake","François Bonnardot","Nicolas Bruneau","Joanne Camp","Johnny C. L. Chan","Paul Gregory","Jhordanne J. Jones","Nam-Young Kang","Philip J. Klotzbach","Yuriy Kuleshov","Marie-Dominique Leroux","Julia F. Lockwood","Hiroyuki Murakami","Akio Nishimura","D. R. Pattanaik","Tom J. Philp","Yohan Ruprich‐Robert","Ralf Toumi","Frédéric Vitart","Seong‐Hee Won","Ruifen Zhan"],"date":"2023-09-01","year":2023,"venue":"Tropical Cyclone Research and Review","venue_type":"journal","ids":{"doi":"10.1016/j.tcrr.2023.09.003","openalex":"W4386813576"},"links":{"paper":"https://doi.org/10.1016/j.tcrr.2023.09.003"},"orgs":["noaa","ncar","met-office","meteo-france","colorado-state-university","cma","jma","bom-australia"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"review","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["nwp-analysis"],"status":"operational","summary":"Reviews seasonal and multi-annual tropical cyclone forecasting, including emerging ML/AI methods, ENSO-neutral predictability and landfall skill gaps relative to user needs.","significance":3,"cited_by":21,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.2144","title":"Projection of future precipitation change using CMIP6 multimodel ensemble based on fusion of multiple machine learning algorithms: A case in Hanjiang River Basin, China","authors":["Dong Wang","Jiahong Liu","Qinghua Luan","Weiwei Shao","Xiaoran Fu","Hao Eric Wang","Yanling Gu"],"date":"2023-09-01","year":2023,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.2144","openalex":"W4386890269"},"links":{"paper":"https://doi.org/10.1002/met.2144","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.2144"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Fuses random forest, KNN, extra trees and GBDT into a CMIP6 multimodel ensemble for Hanjiang Basin precipitation, reaching correlation 0.88 and Taylor skill 0.764.","significance":2,"cited_by":34,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.00314","title":"ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction","authors":["Wenxuan Zhang","Xuechao Zou","Li Wu","Xiaoying Wang","Jianqiang Huang","Junliang Xing"],"date":"2023-09-01","year":2023,"venue_type":"preprint","ids":{"arxiv":"2309.00314"},"links":{"paper":"https://arxiv.org/abs/2309.00314","pdf":"https://arxiv.org/pdf/2309.00314"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Proposes an asymmetric receptive field autoencoder for spatiotemporal prediction and releases RainBench, a radar echo dataset for precipitation nowcasting, with state-of-the-art results.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.17762-ijritcc.v11i9s.7741","title":"AIWFF: A Machine Learning based Framework for Automatic Weather Forecasting","authors":["K Sowjanya Bharathi","Boddu Sekhar Babu"],"date":"2023-08-31","year":2023,"venue":"International Journal on Recent and Innovation Trends in Computing and Communication","venue_type":"journal","ids":{"doi":"10.17762/ijritcc.v11i9s.7741","openalex":"W4386963393"},"links":{"paper":"https://doi.org/10.17762/ijritcc.v11i9s.7741","pdf":"https://ijritcc.org/index.php/ijritcc/article/download/7741/6394"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Framework combining random forest, linear and decision-tree regressors with feature selection for general weather forecasting; no quantitative results reported.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-23-0012.1","title":"Estimating Full Longwave and Shortwave Radiative Transfer with Neural Networks of Varying Complexity","authors":["Ryan Lagerquist","David D. Turner","Imme Ebert‐Uphoff","Jebb Q. Stewart"],"date":"2023-08-31","year":2023,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-23-0012.1","openalex":"W4386325634"},"links":{"paper":"https://doi.org/10.1175/jtech-d-23-0012.1"},"orgs":["noaa","colorado-state-university"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["nwp-analysis","era5"],"status":"pre-operational","summary":"U-Net++ and U-Net3+ networks emulate full shortwave and longwave RRTM radiation in GFSv16, running 7510 and 90 times faster with reliable heating rates.","significance":4,"cited_by":10,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-23-0034.1","title":"Precipitation Vertical Structure Characterization: A Feature-Based Approach","authors":["Malarvizhi Arulraj","Veljko Petković","Ralph R. Ferraro","Huan Meng"],"date":"2023-08-31","year":2023,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-23-0034.1","openalex":"W4386307996"},"links":{"paper":"https://doi.org/10.1175/jhm-d-23-0034.1"},"orgs":["noaa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"Convolutional autoencoders with clustering classify 3D MRMS radar reflectivity profiles into 18 precipitation-structure clusters linked to HRRR environmental conditions.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20944-preprints202308.2068.v1","title":"Application Raindrop Size Distribution Base on LSTM in Precipitation Forecasting in Guizhou","authors":["Fuzeng Wang","An Xue-Jiao","Wang Qiu-Song","GU Xiao-ping","Li Zi-Xin"],"date":"2023-08-30","year":2023,"venue":"Preprints.org","venue_type":"preprint","ids":{"doi":"10.20944/preprints202308.2068.v1","openalex":"W4386331822"},"links":{"paper":"https://doi.org/10.20944/preprints202308.2068.v1","pdf":"https://www.preprints.org/frontend/manuscript/17bb63c9780ef66553821df48c46a0ea/download_pub"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"LSTM uses raindrop size distribution with radar and gauge data to predict Guizhou precipitation 0–180 min, with 60-min correlations near 0.93.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-22-0142.1","title":"Spatially Explicit Correction of Simulated Urban Air Temperatures Using Crowdsourced Data","authors":["Oscar Brousse","Charles H. Simpson","Owain A. Kenway","Alberto Martilli","E. Scott Krayenhoff","Andrea Zonato","Clare Heaviside"],"date":"2023-08-30","year":2023,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-22-0142.1","openalex":"W4386276054"},"links":{"paper":"https://doi.org/10.1175/jamc-d-22-0142.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/apme/aop/JAMC-D-22-0142.1/JAMC-D-22-0142.1.pdf"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other","stations"],"status":"research","summary":"Machine learning corrects WRF urban air-temperature biases per grid cell using 402 crowdsourced personal weather stations over London.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41586-023-06474-x","title":"Anthropogenic fingerprints in daily precipitation revealed by deep learning","authors":["Yoo-Geun Ham","Jeong-Hwan Kim","Seung-Ki Min","Daehyun Kim","Tim Li","Axel Timmermann","Malte F. Stuecker"],"date":"2023-08-30","year":2023,"venue":"Nature","venue_type":"journal","ids":{"doi":"10.1038/s41586-023-06474-x","openalex":"W4386268841"},"links":{"paper":"https://doi.org/10.1038/s41586-023-06474-x"},"orgs":["nuist","university-of-washington"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip","stations"],"status":"research","summary":"A CNN trained on daily precipitation from climate models detects emerging anthropogenic signals in observed rainfall since the mid-2010s.","significance":5,"cited_by":105,"score":60,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2023gl104174","title":"Old Dog, New Trick: Reservoir Computing Advances Machine Learning for Climate Modeling","authors":["Christopher S. Bretherton"],"date":"2023-08-30","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl104174","openalex":"W4386274382"},"links":{"paper":"https://doi.org/10.1029/2023gl104174"},"orgs":["ai2"],"topic":"climate-emulation","topics":["hybrid-parameterization"],"type":"position","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Commentary on reservoir-computing hybrid models coupling ML to a coarse climate model and SST predictor, arguing ML could disrupt conventional climate modeling.","significance":3,"cited_by":4,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.16073","title":"3D-Var Data Assimilation using a Variational Autoencoder","authors":["Boštjan Melinc","Žiga Zaplotnik"],"date":"2023-08-30","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.16073","doi":"10.1002/qj.4708"},"links":{"paper":"https://arxiv.org/abs/2308.16073","pdf":"https://arxiv.org/pdf/2308.16073"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"VAE-based 3D-Var assimilates simulated temperature observations in a learned latent space, yielding flow-dependent background covariances across tropical and extratropical regions.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.15560","title":"WeatherBench 2: A benchmark for the next generation of data-driven global weather models","authors":["Stephan Rasp","Stephan Hoyer","Alexander Merose","Ian Langmore","Peter Battaglia","Tyler Russel","Alvaro Sanchez-Gonzalez","Vivian Yang","Rob Carver","Shreya Agrawal","Matthew Chantry","Zied Ben Bouallegue","Peter Dueben","Carla Bromberg","Jared Sisk","Luke Barrington","Aaron Bell","Fei Sha"],"date":"2023-08-29","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2308.15560","doi":"10.1029/2023ms004019","openalex":"W4399779937"},"links":{"paper":"https://arxiv.org/abs/2308.15560","pdf":"https://arxiv.org/pdf/2308.15560"},"orgs":["ecmwf","google-deepmind","google-research"],"topic":"benchmarks-data-eval","topics":["global-medium-range"],"type":"benchmark","method":[],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"WeatherBench 2 provides an open evaluation framework, training and ground-truth data, and baselines for data-driven global 1-14 day forecasts.","significance":8,"cited_by":238,"score":77,"highlight":true,"highlight_reason":"WeatherBench 2 is the standard benchmark and evaluation framework for data-driven global medium-range models, and nearly all ML weather papers use it.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos14091355","title":"Ten-Meter Wind Speed Forecast Correction in Southwest China Based on U-Net Neural Network","authors":["Tao Xiang","Xiefei Zhi","Weijun Guo","Yang Lyu","Yan Ji","Yanhe Zhu","Yanan Yin","Jiawen Huang"],"date":"2023-08-28","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14091355","openalex":"W4386255803"},"links":{"paper":"https://doi.org/10.3390/atmos14091355","pdf":"https://www.mdpi.com/2073-4433/14/9/1355/pdf?version=1693277191"},"orgs":["nuist"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"U-Net calibrates GEFS 10-m wind forecasts over Southwest China, raising the share of errors under 0.5 m/s by 46-50% at day 1 and beating CNN and linear baselines.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.14547","title":"Deep graphical regression for jointly moderate and extreme Australian wildfires","authors":["Daniela Cisneros","Jordan Richards","Ashok Dahal","Luigi Lombardo","Raphaël Huser"],"date":"2023-08-28","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.14547"},"links":{"paper":"https://arxiv.org/abs/2308.14547","pdf":"https://arxiv.org/pdf/2308.14547"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["gnn","classical-ml"],"timescale":[],"spatial":["regional","local"],"data":["other"],"status":"research","summary":"Graph convolutional networks with extended generalized Pareto distributions model monthly Australian wildfire spread, including extremes, for hazard assessment.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14091349","title":"Downscaling Daily Satellite-Based Precipitation Estimates Using MODIS Cloud Optical and Microphysical Properties in Machine-Learning Models","authors":["Sergio Callaú Medrano","Frédéric Satgé","Jorge Molina‐Carpio","Ramiro Pillco Zolá","Marie‐Paule Bonnet"],"date":"2023-08-27","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14091349","openalex":"W4386238411"},"links":{"paper":"https://doi.org/10.3390/atmos14091349","pdf":"https://www.mdpi.com/2073-4433/14/9/1349/pdf?version=1693279154"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random forest downscales daily IMERG precipitation from 10 km to 1 km using MODIS cloud properties, cutting RMSE by 29% against gauges.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.13983","title":"Interpolation of mountain weather forecasts by machine learning","authors":["Kazuma Iwase","Tomoyuki Takenawa"],"date":"2023-08-27","year":2023,"venue":"Journal of Information Processing, Volume 32, 873--880 (2024)","venue_type":"journal","ids":{"arxiv":"2308.13983","doi":"10.2197/ipsjjip.32.873"},"links":{"paper":"https://arxiv.org/abs/2308.13983","pdf":"https://arxiv.org/pdf/2308.13983"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"LightGBM interpolates plains forecasts and observations to improve temperature and precipitation forecasts in Japanese mountain areas, with partial RMSE gains.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su151712914","title":"A Comprehensive Review on Machine Learning Techniques for Forecasting Wind Flow Pattern","authors":["K. R. Sri Preethaa","Akila Muthuramalingam","Yuvaraj Natarajan","Gitanjali Wadhwa","Ahmed Abdi Yusuf Ali"],"date":"2023-08-26","year":2023,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su151712914","openalex":"W4386222374"},"links":{"paper":"https://doi.org/10.3390/su151712914","pdf":"https://www.mdpi.com/2071-1050/15/17/12914/pdf?version=1693048958"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":["short","medium"],"spatial":[],"data":["other"],"status":"research","summary":"Review of machine learning methods for wind flow and wind-power forecasting, covering ensembles, SVR and neural networks, with future directions.","significance":2,"cited_by":33,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en16176208","title":"Smart Urban Wind Power Forecasting: Integrating Weibull Distribution, Recurrent Neural Networks, and Numerical Weather Prediction","authors":["Navid Shirzadi","Fuzhan Nasiri","Ramanunni Parakkal Menon","Pilar Monsalvete","Anton K. Kaifel","Ursula Eicker"],"date":"2023-08-26","year":2023,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en16176208","openalex":"W4386223800"},"links":{"paper":"https://doi.org/10.3390/en16176208","pdf":"https://www.mdpi.com/1996-1073/16/17/6208/pdf?version=1693199938"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"LSTM with a Weibull wind-speed distribution, combined with NWP, forecasts Montreal wind 48 h ahead, cutting RMSE 13–31% versus plain LSTM.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.13830","title":"The Sampling Method for Optimal Precursors of ENSO Events","authors":["Bin Shi","Junjie Ma"],"date":"2023-08-26","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.13830","openalex":"W4386270150"},"links":{"paper":"https://arxiv.org/abs/2308.13830","pdf":"https://arxiv.org/pdf/2308.13830"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Sampling-based CNOP method finds ENSO optimal precursors in the Zebiak-Cane model without an adjoint, matching adjoint results with parallelizable samples.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15174188","title":"Estimation of Tropical Cyclone Intensity via Deep Learning Techniques from Satellite Cloud Images","authors":["Biao Tong","Jiyang Fu","Yaxue Deng","Yongjun Huang","Pak Wai Chan","Yuncheng He"],"date":"2023-08-25","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15174188","openalex":"W4386168289"},"links":{"paper":"https://doi.org/10.3390/rs15174188","pdf":"https://www.mdpi.com/2072-4292/15/17/4188/pdf?version=1692966303"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["transformer","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Vision Transformer and CNN regressors estimate tropical cyclone intensity from satellite cloud images, and a fused two-stage strategy gives the best accuracy.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.13280","title":"AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learning","authors":["Christian Lessig","Ilaria Luise","Bing Gong","Michael Langguth","Scarlet Stadtler","Martin Schultz"],"date":"2023-08-25","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.13280"},"links":{"paper":"https://arxiv.org/abs/2308.13280","pdf":"https://arxiv.org/pdf/2308.13280"},"orgs":[],"topic":"foundation-models","topics":["probabilistic-ensembles"],"type":"model","method":["transformer"],"timescale":["short","medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Stochastic, task-independent atmosphere model learned by self-supervised representation learning; skillful for nowcasting, interpolation, model correction and downscaling without task-specific training.","significance":6,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.22541-essoar.169290554.48887852-v1","title":"Improving Seasonal Forecast of Summer Precipitation in Southeastern China using CycleGAN Deep Learning Bias Correction","authors":["Song Yang","Fenghua Ling","Lei Bai","Jing‐Jia Luo"],"date":"2023-08-24","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.169290554.48887852/v1","openalex":"W4386147724"},"links":{"paper":"https://doi.org/10.22541/essoar.169290554.48887852/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.169290554.48887852"},"orgs":["shanghai-ai-lab","nuist"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["gan-vae"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"CycleGAN bias correction of NUIST-CFS summer precipitation forecasts in southeastern China outperforms quantile mapping and better captures extreme precipitation frequency and intensity.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41612-023-00451-x","title":"Lightning nowcasting with aerosol-informed machine learning and satellite-enriched dataset","authors":["Ge Song","Siwei Li","Jia Xing"],"date":"2023-08-24","year":2023,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"doi":"10.1038/s41612-023-00451-x","openalex":"W4386142292"},"links":{"paper":"https://doi.org/10.1038/s41612-023-00451-x","pdf":"https://www.nature.com/articles/s41612-023-00451-x.pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"LightGBM with aerosol features and GLM satellite data nowcasts hourly CONUS lightning at 0.25°, reaching 94.3% accuracy and 75% probability of detection.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5370-kiee.2023.72.8.904","title":"Prediction of a Floating Photovoltaic Generation Utilizing KMA Weather Forecast","authors":["Ogeuk Kwon","Hyunpyo Hong","Hyunsik Jo","Hanju Cha"],"date":"2023-08-22","year":2023,"venue":"The Transactions of The Korean Institute of Electrical Engineers","venue_type":"journal","ids":{"doi":"10.5370/kiee.2023.72.8.904","openalex":"W4386064579"},"links":{"paper":"https://doi.org/10.5370/kiee.2023.72.8.904"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"LSTM forecasts hourly floating PV output from KMA weather forecasts at two Korean sites, meeting the 5% error threshold.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.169272242.27053871-v1","title":"Enhancing climate predictions with combination of dynamical model and artificial neural network","authors":["Zikang He","Julien Brajard","Yiguo Wang","Xidong Wang","Zheqi Shen"],"date":"2023-08-22","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.169272242.27053871/v1","openalex":"W4386070303"},"links":{"paper":"https://doi.org/10.22541/essoar.169272242.27053871/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.169272242.27053871"},"orgs":["lbnl-nersc"],"topic":"hybrid-parameterization","topics":["s2s-seasonal"],"type":"model","method":["other"],"timescale":["short","medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Hybrid model uses an ANN trained on analysis increments to correct errors in a coupled ocean-atmosphere model (MAOOAM), improving prediction skill across lead times.","significance":3,"cited_by":2,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-023-04592-0","title":"A high-precision prediction method for coarse grids based on deep learning and the Weather Research and Forecasting model","authors":["Junyi He","Xinyu Liu","Hanqing Wang","Dongnan Zhu","Zhenming Liu"],"date":"2023-08-22","year":2023,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-023-04592-0","openalex":"W4386055516"},"links":{"paper":"https://doi.org/10.1007/s00704-023-04592-0","pdf":"https://www.researchsquare.com/article/rs-2568065/latest.pdf"},"orgs":[],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Deep learning method improves WRF predictions on coarse grids; the abstract is unavailable, so the approach is inferred from the title only.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.11854","title":"Finding the Perfect Fit: Applying Regression Models to ClimateBench v1.0","authors":["Anmol Chaure","Ashok Kumar Behera","Sudip Bhattacharya"],"date":"2023-08-22","year":2023,"venue":"International Journal of Computer Applications 185(29):31-39, August 2023","venue_type":"journal","ids":{"arxiv":"2308.11854","doi":"10.5120/ijca2023923042","openalex":"W4386135165"},"links":{"paper":"https://arxiv.org/abs/2308.11854","pdf":"https://arxiv.org/pdf/2308.11854"},"orgs":[],"topic":"climate-emulation","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Evaluates Gaussian process, SVR and kernel ridge regression emulators on ClimateBench; GP performs best but is computationally expensive.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.10909","title":"Global Warming In Ghana's Major Cities Based on Statistical Analysis of NASA's POWER Over 3-Decades","authors":["Joshua Attih"],"date":"2023-08-20","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.10909"},"links":{"paper":"https://arxiv.org/abs/2308.10909","pdf":"https://arxiv.org/pdf/2308.10909"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Linear trends and XGBoost analyse three decades of POWER temperature data in four Ghanaian cities, finding local warming, with Accra warming most.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15162979","title":"Potential of Artificial Intelligence-Based Techniques for Rainfall Forecasting in Thailand: A Comprehensive Review","authors":["Muhammad Waqas","Usa Wannasingha Humphries","Angkool Wangwongchai","Porntip Dechpichai","Shakeel Ahmad"],"date":"2023-08-18","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15162979","openalex":"W4385985206"},"links":{"paper":"https://doi.org/10.3390/w15162979","pdf":"https://www.mdpi.com/2073-4441/15/16/2979/pdf?version=1692350721"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml","rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Reviews AI and deep learning rainfall forecasting studies for Thailand from 2000 to 2022, concluding hybrid ANN-wavelet models are most promising.","significance":2,"cited_by":94,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.rsase.2023.101048","title":"Prediction of maximum air temperature for defining heat wave in Rajasthan and Karnataka states of India using machine learning approach","authors":["Gourav Suthar","Saurabh Singh","Nivedita Kaul","Sumit Khandelwal","Rajat Prakash Singhal"],"date":"2023-08-18","year":2023,"venue":"Remote Sensing Applications Society and Environment","venue_type":"journal","ids":{"doi":"10.1016/j.rsase.2023.101048","openalex":"W4385989261"},"links":{"paper":"https://doi.org/10.1016/j.rsase.2023.101048"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Machine learning predicts maximum air temperature to define heatwaves in Rajasthan and Karnataka, India; the abstract is unavailable, so details are from the title only.","significance":2,"cited_by":28,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.10995","title":"Deep Learning Techniques in Extreme Weather Events: A Review","authors":["Shikha Verma","Kuldeep Srivastava","Akhilesh Tiwari","Shekhar Verma"],"date":"2023-08-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.10995","openalex":"W4386113878"},"links":{"paper":"https://arxiv.org/abs/2308.10995","pdf":"https://arxiv.org/pdf/2308.10995"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":[],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Review surveys deep learning for extreme weather, covering thunderstorms, precipitation, droughts, heatwaves, cold waves and tropical cyclones, and discusses open limitations.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.09827","title":"Probabilistic Rainfall Downscaling: Joint Generalized Neural Models with Censored Spatial Gaussian Copula","authors":["David Huk","Rilwan A. Adewoyin","Ritabrata Dutta"],"date":"2023-08-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.09827","openalex":"W7221011829"},"links":{"paper":"http://arxiv.org/abs/2308.09827","pdf":"https://arxiv.org/pdf/2308.09827"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Joint generalised neural networks combined with a censored latent Gaussian copula produce spatially coherent probabilistic rainfall downscaling from coarse weather variables over the UK.","significance":4,"cited_by":0,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-esd-14-817-2023","title":"Understanding pattern scaling errors across a range of emissions pathways","authors":["Christopher Wells","Lawrence Jackson","Amanda C. Maycock","Piers M. de F. Forster"],"date":"2023-08-17","year":2023,"venue":"Earth System Dynamics","venue_type":"journal","ids":{"doi":"10.5194/esd-14-817-2023","openalex":"W4385950693"},"links":{"paper":"https://doi.org/10.5194/esd-14-817-2023"},"orgs":[],"topic":"climate-emulation","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["global","regional"],"data":["cmip"],"status":"research","summary":"Decomposes pattern scaling errors from the MESMER emulator into scenario pattern and timeseries components, showing timeseries error is about 20% for high emissions but comparable to pattern error for low emissions.","significance":3,"cited_by":25,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.08794","title":"Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces","authors":["Miguel Liu-Schiaffini","Clare E. Singer","Nikola Kovachki","Sze Chai Leung","Hyunji Jane Bae","Kamyar Azizzadenesheli","Anima Anandkumar"],"date":"2023-08-17","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.08794"},"links":{"paper":"https://arxiv.org/abs/2308.08794","pdf":"https://arxiv.org/pdf/2308.08794"},"orgs":[],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"model","method":["neural-operator","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Recurrent neural operator with conformal prediction forecasts tipping points, including a stratocumulus cloud cover climate tipping point, using physics-constraint deviations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10291-023-01526-1","title":"A precipitation forecast model with a neural network and improved GPT3 model for Japan","authors":["Song Li","Nan Jiang","Tianhe Xu","Yan Liang Xu","Honglei Yang","Zhen Zhang","Ao Guo","Yuhao Wu"],"date":"2023-08-16","year":2023,"venue":"GPS Solutions","venue_type":"journal","ids":{"doi":"10.1007/s10291-023-01526-1","openalex":"W4385876878"},"links":{"paper":"https://doi.org/10.1007/s10291-023-01526-1","pdf":"https://www.researchsquare.com/article/rs-2658716/latest.pdf"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Neural network combined with an improved GPT3 model forecasts Japanese precipitation from GNSS-derived atmospheric data; abstract unavailable, so details are limited.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.11465","title":"Understanding the complex dynamics of climate change in south-west Australia using Machine Learning","authors":["Alka Yadav","Sourish Das","K. Shuvo Bakar","Anirban Chakraborti"],"date":"2023-08-16","year":2023,"venue":"Physica A Statistical Mechanics and its Applications","venue_type":"journal","ids":{"arxiv":"2302.11465","doi":"10.1016/j.physa.2023.129139","openalex":"W4385880672"},"links":{"paper":"https://doi.org/10.1016/j.physa.2023.129139","pdf":"https://arxiv.org/pdf/2302.11465"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":[],"timescale":["climate"],"spatial":["regional"],"data":[],"status":"research","summary":"Applies machine learning to analyse complex climate change dynamics in south-west Australia; no abstract was available, so the classification is based on the title only.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-isprs-archives-xlviii-m-1-2023-537-2023","title":"IMPROVING THE ACCURACY OF SATELLITE-BASED NEAR SURFACE AIR TEMPERATURE AND PRECIPITATION PRODUCTS","authors":["Çağrı Hasan Karaman","Zuhal Akyürek"],"date":"2023-08-15","year":2023,"venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","venue_type":"journal","ids":{"doi":"10.5194/isprs-archives-xlviii-m-1-2023-537-2023","openalex":"W4385834959"},"links":{"paper":"https://doi.org/10.5194/isprs-archives-xlviii-m-1-2023-537-2023","pdf":"https://isprs-archives.copernicus.org/articles/XLVIII-M-1-2023/537/2023/isprs-archives-XLVIII-M-1-2023-537-2023.pdf"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","satellite","stations"],"status":"research","summary":"Random Forest spatial interpolation with satellite covariates downscales reanalysis and satellite air temperature and precipitation products over Turkey, with AgERA5 and MSWEP the best products.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-2023-158","title":"Deep-learning statistical downscaling of precipitation in the middle reaches of the Yellow River: A Residual in Residual Dense Block based network","authors":["He Fu","Jianing Guo","Chenguang Deng","Heng Liu","Jie Wu","Zhengguo Shi","Cailing Wang","Xiaoning Xie"],"date":"2023-08-15","year":2023,"venue_type":"other","ids":{"doi":"10.5194/gmd-2023-158","openalex":"W4385835973"},"links":{"paper":"https://doi.org/10.5194/gmd-2023-158"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn","gan-vae"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"RRDBNet residual-in-residual dense network statistically downscales Yellow River precipitation and improves extreme precipitation over regression and deep baselines.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.48175-ijarsct-12461","title":"Maharashtra Rainfall Prediction using Machine Learning","authors":["Prof T. P. Raju","T Akhilesh Naidu","Herambh Jatadhar","Shraddha Manerao","Ashish Armarkar"],"date":"2023-08-15","year":2023,"venue":"International Journal of Advanced Research in Science Communication and Technology","venue_type":"journal","ids":{"doi":"10.48175/ijarsct-12461","openalex":"W4385835831"},"links":{"paper":"https://doi.org/10.48175/ijarsct-12461","pdf":"https://doi.org/10.48175/ijarsct-12461"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Genetic-algorithm feature extraction for Maharashtra rainfall prediction, with claimed efficiency gains over traditional systems but no quantitative results.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-23-0023.1","title":"Machine Learning–Adjusted WRF Forecasts to Support Wind Energy Needs in Black Start Operations","authors":["Kyle K. Hugeback","William A. Gallus","Hugo Nestor Villegas Pico"],"date":"2023-08-15","year":2023,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-23-0023.1","openalex":"W4385847250"},"links":{"paper":"https://doi.org/10.1175/waf-d-23-0023.1"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["rnn","classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine learning corrects WRF hub-height wind forecasts for black-start operations, cutting day-2 wind MSE by over 90% with a multioutput network and nowcasting with LSTM.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-023-06912-6","title":"On the use of convolutional neural networks for downscaling daily temperatures over southern South America in a climate change scenario","authors":["Rocío Balmaceda-Huarte","Jorge Baño‐Medina","Matias Ezequiel Olmo","María Laura Bettolli"],"date":"2023-08-15","year":2023,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-023-06912-6","openalex":"W4385839268"},"links":{"paper":"https://doi.org/10.1007/s00382-023-06912-6"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Applies CNN statistical downscaling to daily temperatures over southern South America under climate change scenarios.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.06733","title":"Precipitation nowcasting with generative diffusion models","authors":["Andrea Asperti","Fabio Merizzi","Alberto Paparella","Giorgio Pedrazzi","Matteo Angelinelli","Stefano Colamonaco"],"date":"2023-08-13","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.06733"},"links":{"paper":"https://arxiv.org/abs/2308.06733","pdf":"https://arxiv.org/pdf/2308.06733"},"orgs":[],"topic":"nowcasting","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Generative ensemble diffusion produces precipitation scenarios over Central Europe from ERA5 data, outperforming U-Net baselines after a learned post-processing step.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.06708","title":"Generating observation guided ensembles for data assimilation with denoising diffusion probabilistic model","authors":["Yuuichi Asahi","Yuta Hasegawa","Naoyuki Onodera","Takashi Shimokawabe","Hayato Shiba","Yasuhiro Idomura"],"date":"2023-08-13","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.06708"},"links":{"paper":"https://arxiv.org/abs/2308.06708","pdf":"https://arxiv.org/pdf/2308.06708"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["diffusion"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Uses denoising diffusion models to generate pseudo-ensembles for ensemble data assimilation, outperforming standard ensemble methods when the simulation model is imperfect.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ecoinf.2023.102261","title":"Applying deep learning to predict SST variation and tropical cyclone patterns that influence coral bleaching","authors":["Yuan‐Chien Lin","Shan-Non Feng","Chun-Yeh Lai","Hsiao‐Ting Tseng","Chun‐Wei Huang"],"date":"2023-08-12","year":2023,"venue":"Ecological Informatics","venue_type":"journal","ids":{"doi":"10.1016/j.ecoinf.2023.102261","openalex":"W4385776125"},"links":{"paper":"https://doi.org/10.1016/j.ecoinf.2023.102261"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Deep learning is applied to predict sea-surface temperature variability and tropical cyclone patterns linked to coral bleaching; classified from the title only, as the abstract is missing.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su151612261","title":"Evaluation of Tropical Cyclone Disaster Loss Using Machine Learning Algorithms with an eXplainable Artificial Intelligence Approach","authors":["Shuxian Liu","Yang Liu","Zhigang Chu","Kun Yang","Guanlan Wang","Lisheng Zhang","Yuanda Zhang"],"date":"2023-08-11","year":2023,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su151612261","openalex":"W4385760445"},"links":{"paper":"https://doi.org/10.3390/su151612261","pdf":"https://www.mdpi.com/2071-1050/15/16/12261/pdf?version=1691733159"},"orgs":["nuist","cma"],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"LightGBM with SHAP explanations predicts tropical cyclone disaster loss grades in China with 0.86 accuracy, with rainfall and wind as the main drivers.","significance":2,"cited_by":22,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-au.169173769.98893974-v1","title":"Rough Set Theory and Association Rule Mining for Detecting Interactions and Improving Machine Learning Predictions for Weather Prediction in Kenya.","authors":["Isaac Kega","Lawrence Nderu","Ronald Waweru Mwangi","Dennis Njagi"],"date":"2023-08-11","year":2023,"venue_type":"other","ids":{"doi":"10.22541/au.169173769.98893974/v1","openalex":"W4385765270"},"links":{"paper":"https://doi.org/10.22541/au.169173769.98893974/v1","pdf":"https://www.authorea.com/doi/pdf/10.22541/au.169173769.98893974"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Rough set reducts and association rules create binary features that improve classifiers for Kenyan farm weather from Wunderground data; no numbers in abstract.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-22-0693.1","title":"Multidecadal Oceanic Modulation of Summer Precipitation in North China in 1200-Year Global Climate Simulations","authors":["Xuan Tong","Zhongwei Yan","Wen Zhou","Jiangjiang Xia","Xiao‐Wei Quan"],"date":"2023-08-11","year":2023,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-22-0693.1","openalex":"W4385758380"},"links":{"paper":"https://doi.org/10.1175/jcli-d-22-0693.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/clim/36/17/JCLI-D-22-0693.1.pdf"},"orgs":["fudan-university","iap-cas"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Explainable CNN on 1200-year simulations attributes North China summer precipitation variability to PDO and AMO sea surface temperature patterns, with 96-98% accuracy.","significance":3,"cited_by":4,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl104228","title":"Obukhov Length Estimation From Spaceborne Radars","authors":["Owen O’Driscoll","Alexis Aurelien Mouche","Bertrand Chapron","Marcel Kleinherenbrink","Paco López‐Dekker"],"date":"2023-08-10","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl104228","openalex":"W4385723915"},"links":{"paper":"https://doi.org/10.1029/2023gl104228","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023GL104228"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Machine learning on SAR-derived features estimates atmospheric surface-layer Obukhov length, explaining about 80% of variance for convective scenes.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23167047","title":"Informer-Based Temperature Prediction Using Observed and Numerical Weather Prediction Data","authors":["Jimin Jun","Hong Kook Kim"],"date":"2023-08-09","year":2023,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23167047","openalex":"W4385697379"},"links":{"paper":"https://doi.org/10.3390/s23167047","pdf":"https://www.mdpi.com/1424-8220/23/16/7047/pdf?version=1691574221"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["transformer"],"timescale":["short","medium"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Informer transformer fuses station observations with LDAPS NWP for 6–336 h temperature forecasts, lowering RMSE by 0.25 °C versus CNN-BLSTM.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15163948","title":"Machine Learning Applied to a Dual-Polarized Sentinel-1 Image for Wind Retrieval of Tropical Cyclones","authors":["Yuyi Hu","Weizeng Shao","Wei Shen","Yuhang Zhou","Xingwei Jiang"],"date":"2023-08-09","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15163948","openalex":"W4385698284"},"links":{"paper":"https://doi.org/10.3390/rs15163948","pdf":"https://www.mdpi.com/2072-4292/15/16/3948/pdf?version=1691582779"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"XGBoost trained on dual-polarized Sentinel-1 SAR collocated with SFMR and SMAP retrieves tropical cyclone surface winds with 2.53 m/s RMSE up to 70 m/s.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl104370","title":"TAFFNet: Time‐Aware Adaptive Feature Fusion Network for Very Short‐Term Precipitation Forecasts","authors":["Jingnan Wang","Xiaodong Wang","Jiping Guan","Lifeng Zhang","Jie Zhou"],"date":"2023-08-08","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl104370","openalex":"W4385658256"},"links":{"paper":"https://doi.org/10.1029/2023gl104370","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023GL104370"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"TAFFNet adaptively fuses radar echoes with NWP using time-aware weighting, improving 0–12 h precipitation forecasts and storm initiation and dissipation.","significance":4,"cited_by":10,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.04391","title":"Calibrated Forecasts of Quasi-Periodic Climate Processes with Deep Echo State Networks and Penalized Quantile Regression","authors":["Matthew Bonas","Christopher K. Wikle","Stefano Castruccio"],"date":"2023-08-08","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.04391"},"links":{"paper":"https://arxiv.org/abs/2308.04391","pdf":"https://arxiv.org/pdf/2308.04391"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep echo state networks with penalized quantile regression forecast quasi-periodic ocean-driven multi-year climate events, with calibrated uncertainty from fast ensembles.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.03985","title":"Fourier neural operator for real-time simulation of 3D dynamic urban microclimate","authors":["Wenhui Peng","Shaoxiang Qin","Senwen Yang","Jianchun Wang","Xue Liu","Liangzhu Leon Wang"],"date":"2023-08-08","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.03985"},"links":{"paper":"https://arxiv.org/abs/2308.03985","pdf":"https://arxiv.org/pdf/2308.03985"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["neural-operator"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"A Fourier neural operator emulates CFD simulations of 3D urban wind fields, predicting in milliseconds and generalizing to unseen wind directions.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33480-jitk.v9i1.4203","title":"RAINFALL PREDICTION USING MULTIPLE LINEAR REGRESSION ALGORITHM","authors":["Mulia Sulistiyono","Budy Satria","Acihmah Sidauruk","Raditya Wardhana"],"date":"2023-08-07","year":2023,"venue":"JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer)","venue_type":"journal","ids":{"doi":"10.33480/jitk.v9i1.4203","openalex":"W4385634029"},"links":{"paper":"https://doi.org/10.33480/jitk.v9i1.4203","pdf":"https://ejournal.nusamandiri.ac.id/index.php/jitk/article/download/4203/1062"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Multiple linear regression predicts Yogyakarta daily rainfall from temperature, humidity, wind and sunshine, reaching an R2 of only 12.99%.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.adapen.2023.100150","title":"Advances in solar forecasting: Computer vision with deep learning","authors":["Quentin Paletta","Guillermo Terrén-Serrano","Yuhao Nie","Binghui Li","Jacob Bieker","Wenqi Zhang","Laurent Dubus","Soumyabrata Dev","Cong Feng"],"date":"2023-08-07","year":2023,"venue":"Advances in Applied Energy","venue_type":"journal","ids":{"doi":"10.1016/j.adapen.2023.100150","openalex":"W4385638612"},"links":{"paper":"https://doi.org/10.1016/j.adapen.2023.100150","pdf":"https://ars.els-cdn.com/content/image/1-s2.0-S266679242300029X-gr001_lrg.jpg"},"orgs":["university-of-cambridge","stanford"],"topic":"applications-impacts","topics":["nowcasting"],"type":"review","method":["cnn"],"timescale":["nowcast","short"],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"Review of deep learning solar forecasting from sky cameras, satellites and weather stations that tracks cloud displacement, outlining gaps relative to NWP.","significance":3,"cited_by":158,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.04460","title":"The Compatibility between the Pangu Weather Forecasting Model and Meteorological Operational Data","authors":["Wencong Cheng","Yan Yan","Jiangjiang Xia","Qi Liu","Chang Qu","Zhigang Wang"],"date":"2023-08-07","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.04460","openalex":"W4385749727"},"links":{"paper":"https://arxiv.org/abs/2308.04460","pdf":"https://arxiv.org/pdf/2308.04460"},"orgs":["iap-cas"],"topic":"global-medium-range","topics":[],"type":"evaluation","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Case studies show Pangu-Weather runs stably from several operational NWP analyses as initial conditions, and better initial conditions improve its forecast skill.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.106947","title":"Seasonal prediction of summer extreme precipitation frequencies over Southwest China based on machine learning","authors":["Yanbo Nie","Jianqi Sun","Jiehua Ma"],"date":"2023-08-05","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.106947","openalex":"W4385605327"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.106947"},"orgs":["iap-cas"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning seasonal prediction of summer extreme precipitation frequency over Southwest China; classified from the title only, as the abstract is missing.","significance":3,"cited_by":18,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2023.1136346","title":"A study of deep learning algorithm usage in predicting building loss ratio due to typhoons: the case of southern part of the Korean Peninsula","authors":["Ji-Myong Kim","Junseo Bae","Manik Das Adhikari","Sang‐Guk Yum"],"date":"2023-08-04","year":2023,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2023.1136346","openalex":"W4385579893"},"links":{"paper":"https://doi.org/10.3389/feart.2023.1136346","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2023.1136346/pdf"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A deep neural network predicts typhoon-caused building loss ratios in southern Korea, outperforming multiple regression on MAE, RMSE and R2.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3233-jifs-224543","title":"Blizzard prediction in antarctic meteorological data using deep learning techniques","authors":["V.S. Samy","Veena Thenkanidiyoor"],"date":"2023-08-04","year":2023,"venue":"Journal of Intelligent & Fuzzy Systems","venue_type":"journal","ids":{"doi":"10.3233/jifs-224543","openalex":"W4385575861"},"links":{"paper":"https://doi.org/10.3233/jifs-224543"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM-based blizzard prediction on Antarctic polar station data; reported accuracies of 49.6% and 55.2% are low and the evaluation is weakly documented.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-2752-5295-aced60","title":"Assessing decadal variability of subseasonal forecasts of opportunity using explainable AI","authors":["Marybeth C Arcodia","Elizabeth A. Barnes","Kirsten J. Mayer","Jiwoo Lee","Ana C. Ordoñez","Min‐Seop Ahn"],"date":"2023-08-04","year":2023,"venue":"Environmental Research Climate","venue_type":"journal","ids":{"doi":"10.1088/2752-5295/aced60","openalex":"W4385568832"},"links":{"paper":"https://doi.org/10.1088/2752-5295/aced60","pdf":"https://iopscience.iop.org/article/10.1088/2752-5295/aced60/pdf"},"orgs":["nasa","ncar","colorado-state-university"],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["s2s"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"Neural networks with explainable AI identify decadal variability in tropically driven subseasonal precipitation skill in CESM2 and confirm the relationships in ERA5 reanalysis.","significance":4,"cited_by":12,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2023.1149566","title":"A radiative transfer deep learning model coupled into WRF with a generic fortran torch adaptor","authors":["Bin Mu","Lu Chen","Shijin Yuan","Bo Qin"],"date":"2023-08-03","year":2023,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2023.1149566","openalex":"W4385547939"},"links":{"paper":"https://doi.org/10.3389/feart.2023.1149566","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2023.1149566/pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":["infra-software"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A Fortran Torch Adaptor couples deep learning radiation emulators into WRF, achieving 50x to 300x GPU speedups and better forecasts than feedforward networks.","significance":4,"cited_by":13,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.169109567.78839949-v1","title":"Revisiting Machine Learning Approaches for Short- and Longwave Radiation Inference in Weather and Climate Models, Part I: Offline Performance","authors":["Guillaume Bertoli","Fırat Özdemir","Fernando Pérez‐Cruz"],"date":"2023-08-03","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.169109567.78839949/v1","openalex":"W4385515680"},"links":{"paper":"https://doi.org/10.22541/essoar.169109567.78839949/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.169109567.78839949"},"orgs":["eth-zurich","sdsc"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["rnn","cnn","classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Compares random forest and neural network emulators of ICON's ecRad radiation; neural nets show top-of-atmosphere bias, and a recurrent design with flux normalisation performs best.","significance":4,"cited_by":3,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl104668","title":"Accelerating Atmospheric Gravity Wave Simulations Using Machine Learning: Kelvin‐Helmholtz Instability and Mountain Wave Sources Driving Gravity Wave Breaking and Secondary Gravity Wave Generation","authors":["Wenjun Dong","David C. Fritts","Alan Z. Liu","Thomas Lund","Hanli Liu","Jonathan Brian Snively"],"date":"2023-08-02","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl104668","openalex":"W4385483134"},"links":{"paper":"https://doi.org/10.1029/2023gl104668","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023GL104668"},"orgs":["ncar"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["neural-operator","physics-constrained"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"CAMNet, a physics-informed neural operator trained on high-resolution simulations, accelerates 2-D gravity wave and secondary wave simulations on GPUs, capturing key dynamics.","significance":4,"cited_by":11,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.01868","title":"Multi-variable Hard Physical Constraints for Climate Model Downscaling","authors":["Jose González-Abad","Álex Hernández-García","Paula Harder","David Rolnick","José Manuel Gutiérrez"],"date":"2023-08-02","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.01868"},"links":{"paper":"https://arxiv.org/abs/2308.01868","pdf":"https://arxiv.org/pdf/2308.01868"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Introduces multi-variable hard constraints so deep-learning downscaled climate variables keep physical relationships, demonstrated on temperature downscaling from GCM output.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3103-s1068373923080022","title":"Sea Surface Wind Speed Retrieval from MTVZA-GYa Data","authors":["Elizaveta V. Zabolotskikh","S. M. Azarov","M. A. Zhivotovskaya"],"date":"2023-08-01","year":2023,"venue":"Russian Meteorology and Hydrology","venue_type":"journal","ids":{"doi":"10.3103/s1068373923080022","openalex":"W4389389215"},"links":{"paper":"https://doi.org/10.3103/s1068373923080022"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Neural network retrieves sea-surface wind speed from the MTVZA-GYa microwave radiometer, matching AMSR2 with 1.6 m/s RMS difference and mapping tropical cyclone winds.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s43017-023-00468-z","title":"Deep learning and a changing economy in weather and climate prediction","authors":["Peter Bauer","Peter Dueben","Matthew Chantry","Francisco Doblas-Reyes","Torsten Hoefler","Amy McGovern","Bjorn Stevens"],"date":"2023-08-01","year":2023,"venue":"Nature Reviews Earth &amp; Environment","venue_type":"journal","ids":{"doi":"10.1038/s43017-023-00468-z","openalex":"W4385455137"},"links":{"paper":"https://doi.org/10.1038/s43017-023-00468-z"},"orgs":["ecmwf","eth-zurich","mpi-meteorology","university-of-oklahoma"],"topic":"global-medium-range","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Nature Reviews review of deep learning's impact on weather and climate prediction; abstract absent, judged from title and venue.","significance":5,"cited_by":33,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2023ef003531","title":"Downscaling CORDEX Through Deep Learning to Daily 1 km Multivariate Ensemble in Complex Terrain","authors":["Dánnell Quesada‐Chacón","Jorge Baño‐Medina","Klemens Barfus","Christian Bernhofer"],"date":"2023-08-01","year":2023,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2023ef003531","openalex":"W4386102314"},"links":{"paper":"https://doi.org/10.1029/2023ef003531","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023EF003531"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5","stations"],"status":"pre-operational","summary":"Deep-learning perfect-prognosis downscaling of CORDEX-EUR11 yields a daily 1 km multivariate ensemble for Saxony through 2100 with validated transfer functions.","significance":4,"cited_by":17,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ef003211","title":"Connecting Large‐Scale Meteorological Patterns to Extratropical Cyclones in CMIP6 Climate Models Using Self‐Organizing Maps","authors":["Michelle J. Gore","Colin M. Zarzycki","Melissa Gervais"],"date":"2023-08-01","year":2023,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2022ef003211","openalex":"W4386070579"},"links":{"paper":"https://doi.org/10.1029/2022ef003211","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EF003211"},"orgs":[],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Self-organizing maps link large-scale patterns to extratropical cyclones and show CMIP6 models produce too few cyclones and too zonal patterns over northeastern US.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s41976-023-00089-6","title":"MPM-Net: a Data-Driven Approach for Forecasting Indian Heatwave and Cold Wave Events Using Dehazing and Ensemble Learning Technique","authors":["Raj Kumari","R Mahaveerakannan"],"date":"2023-08-01","year":2023,"venue":"Remote Sensing in Earth Systems Sciences","venue_type":"journal","ids":{"doi":"10.1007/s41976-023-00089-6","openalex":"W4385456087"},"links":{"paper":"https://doi.org/10.1007/s41976-023-00089-6"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Proposes MPM-Net, combining dehazing and ensemble learning to forecast Indian heatwave and cold wave events; the abstract is missing, so details are limited.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10489-023-04824-w","title":"A flexible and lightweight deep learning weather forecasting model","authors":["Gabriel Zenkner","S. Navarro-Martinez"],"date":"2023-08-01","year":2023,"venue":"Applied Intelligence","venue_type":"journal","ids":{"doi":"10.1007/s10489-023-04824-w","openalex":"W4385472497"},"links":{"paper":"https://doi.org/10.1007/s10489-023-04824-w","pdf":"https://link.springer.com/content/pdf/10.1007/s10489-023-04824-w.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Bi-LSTM models forecast London temperature and humidity 24–72 h ahead from station history, reaching about 1.45 °C RMSE at Kew Gardens.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-hyp.14954","title":"Monthly precipitation prediction at regional scale using deep convolutional neural networks","authors":["Lingling Ni","Dong Wang","Vijay Pal Singh","Jianfeng Wu","Xiaoyan Chen","Yuwei Tao","Xiaobin Zhu","Jianguo Jiang","Xiankui Zeng"],"date":"2023-08-01","year":2023,"venue":"Hydrological Processes","venue_type":"journal","ids":{"doi":"10.1002/hyp.14954","openalex":"W4385635981"},"links":{"paper":"https://doi.org/10.1002/hyp.14954"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["s2s","seasonal"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"UNet-RegPre CNN predicts regional monthly precipitation in China with skill comparable to CFSv2 and identifies summer monsoon precursors.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-hess-2023-158","title":"Comparison of four machine learning models for forecasting daily reference evaporation based on public weather forecast data","authors":["Yunfeng Liang","Dongpu Feng","Zhaojun Sun"],"date":"2023-07-31","year":2023,"venue_type":"other","ids":{"doi":"10.5194/hess-2023-158","openalex":"W4385417782"},"links":{"paper":"https://doi.org/10.5194/hess-2023-158"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"Compares four ML models trained on public weather forecasts versus observations for one-day-ahead reference evapotranspiration; forecast-trained models perform better.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23156832","title":"A Deep Learning-Based Algorithm for Identifying Precipitation Clouds Using Fengyun-4A Satellite Observation Data","authors":["Guangyi Ma","Jie Huang","Yonghong Zhang","Linglong Zhu","Kenny Thiam Choy Lim Kam Sian","Yixin Feng","Tianming Yu"],"date":"2023-07-31","year":2023,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23156832","openalex":"W4385461486"},"links":{"paper":"https://doi.org/10.3390/s23156832","pdf":"https://www.mdpi.com/1424-8220/23/15/6832/pdf?version=1690863909"},"orgs":["nuist"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A CNN (PCINet) identifies day and night precipitation clouds from FY-4A imagery, outperforming five segmentation baselines and enabling near-real-time monitoring.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-jmse11081529","title":"El Niño Index Prediction Based on Deep Learning with STL Decomposition","authors":["Ningmeng Chen","Cheng Su","Sensen Wu","Yuanyuan Wang"],"date":"2023-07-31","year":2023,"venue":"Journal of Marine Science and Engineering","venue_type":"journal","ids":{"doi":"10.3390/jmse11081529","openalex":"W4385429653"},"links":{"paper":"https://doi.org/10.3390/jmse11081529","pdf":"https://www.mdpi.com/2077-1312/11/8/1529/pdf?version=1690800538"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"STL decomposition with temporal convolutional networks forecasts the Niño index over multiple steps, capturing ENSO trend and peak intensity for 1992–2022.","significance":3,"cited_by":16,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00202-023-01945-w","title":"Optimal design of renewable energy based hybrid system considering weather forecasting using machine learning techniques","authors":["Bandana Sharma","Mohammad Rizwan","Priyanka Anand"],"date":"2023-07-31","year":2023,"venue":"Electrical Engineering","venue_type":"journal","ids":{"doi":"10.1007/s00202-023-01945-w","openalex":"W4385429724"},"links":{"paper":"https://doi.org/10.1007/s00202-023-01945-w"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Optimal sizing of a renewable hybrid energy system that uses machine learning weather forecasts as an input; abstract unavailable.","significance":1,"cited_by":16,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15153767","title":"An ENSO Prediction Model Based on Backtracking Multiple Initial Values: Ordinary Differential Equations–Memory Kernel Function","authors":["Qianrong Ma","Yingxiao Sun","Shiquan Wan","Yu Gu","Yang Bai","Jiayi Mu"],"date":"2023-07-28","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15153767","openalex":"W4385422628"},"links":{"paper":"https://doi.org/10.3390/rs15153767","pdf":"https://www.mdpi.com/2072-4292/15/15/3767/pdf?version=1690795773"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["s2s","seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"A hybrid ODE and memory-kernel model using backtracked initial values reaches 24-month ENSO index lead predictions and about 18 months of verified skill.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-23-0020.1","title":"Can Machine Learning Models Be a Suitable Tool for Predicting Central European Cold Winter Weather on Subseasonal to Seasonal Time Scales?","authors":["Selina M. Kiefer","Sebastian Lerch","Patrick Ludwig","Joaquim Ginete Pinto"],"date":"2023-07-28","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-23-0020.1","openalex":"W4385350660"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0020.1"},"orgs":["kit"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Quantile regression forests and random forest classifiers give skillful 14–28 day probabilistic forecasts of central European winter 2-m temperatures and cold waves, beating climatology.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-01431161.2023.2235641","title":"Tropical cyclone detection by combining wavelet transform with deep learning using infrared satellite images","authors":["Changjiang Zhang","Liu Zhang","Leiming Ma","Xiaoqin Lu"],"date":"2023-07-28","year":2023,"venue":"International Journal of Remote Sensing","venue_type":"journal","ids":{"doi":"10.1080/01431161.2023.2235641","openalex":"W4385344390"},"links":{"paper":"https://doi.org/10.1080/01431161.2023.2235641"},"orgs":["cma"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"WEY-TCNet combines wavelet fusion and YOLOX with channel attention to detect tropical cyclones in Fengyun-2D infrared images, reaching 91.5% mAP versus 86.7% baseline.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.oceaneng.2023.115435","title":"Application of a deep learning-based discrete weather data continuousization model in ship route optimization","authors":["Zhizheng Wu","Shengzheng Wang","Qiumeng Yuan","Naiyuan Lou","Siyuan Qiu","Bo Li","Xiuzhi Chen"],"date":"2023-07-28","year":2023,"venue":"Ocean Engineering","venue_type":"journal","ids":{"doi":"10.1016/j.oceaneng.2023.115435","openalex":"W4385373213"},"links":{"paper":"https://doi.org/10.1016/j.oceaneng.2023.115435"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep learning converts discrete weather data into continuous fields for ship route optimization; abstract unavailable.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.15727","title":"AI for Anticipatory Action: Moving Beyond Climate Forecasting","authors":["Benjamin Q. Huynh","Mathew V. Kiang"],"date":"2023-07-28","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.15727","doi":"10.1609/aaaiss.v2i1.27652"},"links":{"paper":"https://arxiv.org/abs/2307.15727","pdf":"https://arxiv.org/pdf/2307.15727"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":[],"status":"research","summary":"Reviews how machine learning weather and climate forecasts can support anticipatory action in disaster response, identifying gaps between forecasting and impact prediction.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-2794460-v1","title":"Tenki Weather Prediction Model","authors":["Chellappan Thangappan Manimegalai","Kali Muthu"],"date":"2023-07-27","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-2794460/v1","openalex":"W4385291353"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-2794460/v1","pdf":"https://www.researchsquare.com/article/rs-2794460/latest.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Describes a sensor and machine-learning system for real-time local weather monitoring and forecasting; little technical detail or evaluation given.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-aceb0a","title":"Downscaling ERA5 wind speed data: a machine learning approach considering topographic influences","authors":["Wenxuan Hu","Yvonne Scholz","Madhura Yeligeti","Lueder von Bremen","Deng Ying"],"date":"2023-07-27","year":2023,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/aceb0a","openalex":"W4385297181"},"links":{"paper":"https://doi.org/10.1088/1748-9326/aceb0a","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/aceb0a/pdf"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Machine learning downscales ERA5 wind speed from about 31 km to 1 km in complex terrain using station data and topographic metrics, aimed at energy applications.","significance":3,"cited_by":39,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.14857","title":"Generative convective parametrization of dry atmospheric boundary layer","authors":["Florian Heyder","Juan Pedro Mellado","Jörg Schumacher"],"date":"2023-07-27","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.14857","openalex":"W4385373044"},"links":{"paper":"https://arxiv.org/abs/2307.14857","pdf":"https://arxiv.org/pdf/2307.14857"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"A GAN-based convective boundary layer parametrization, trained on DNS with Deardorff self-similarity, reproduces buoyancy and vertical velocity statistics and thermal organization.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.14654","title":"Machine Learning based Parameter Sensitivity of Regional Climate Models -- A Case Study of the WRF Model for Heat Extremes over Southeast Australia","authors":["P. Jyoteeshkumar Reddy","Sandeep Chinta","Richard Matear","John Taylor","Harish Baki","Marcus Thatcher","Jatin Kala","Jason Sharples"],"date":"2023-07-27","year":2023,"venue":"Environ. Res. Lett. 19 (2024) 014010","venue_type":"journal","ids":{"arxiv":"2307.14654","doi":"10.1088/1748-9326/ad0eb0"},"links":{"paper":"https://arxiv.org/abs/2307.14654","pdf":"https://arxiv.org/pdf/2307.14654"},"orgs":[],"topic":"xai-uq-physics","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"ML-surrogate Sobol analysis of WRF physics parameters for southeast Australian heat extremes finds only three of 24 parameters matter.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl104406","title":"Deep Learning Improves GFS Wintertime Precipitation Forecast Over Southeastern China","authors":["Danyi Sun","Wenyu Huang","Zifan Yang","Yong Ming Luo","Jing‐Jia Luo","Jonathon S. Wright","Haohuan Fu","Bin Wang"],"date":"2023-07-26","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl104406","openalex":"W4385272292"},"links":{"paper":"https://doi.org/10.1029/2023gl104406","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023GL104406"},"orgs":["tsinghua-university","nuist"],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"DABU-Net, a data-augmented deep learning correction of GFS wintertime precipitation over southeastern China, cuts RMSE by 19–25% at 24–72 h.","significance":4,"cited_by":18,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.14285","title":"Emerging Statistical Machine Learning Techniques for Extreme Temperature Forecasting in U.S. Cities","authors":["Kameron B. Kinast","Ernest Fokoué"],"date":"2023-07-26","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.14285"},"links":{"paper":"https://arxiv.org/abs/2307.14285","pdf":"https://arxiv.org/pdf/2307.14285"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["decadal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares ARIMA, exponential smoothing, MLP and Gaussian processes for extreme temperature in five US cities; MLP performs best and projects temperatures to 2030.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46947-joaasr542023682","title":"Rain Fall Prediction using Ada Boost Machine Learning Ensemble Algorithm","authors":["P. Senthil Kumar","M Swathi"],"date":"2023-07-24","year":2023,"venue":"JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH","venue_type":"journal","ids":{"doi":"10.46947/joaasr542023682","openalex":"W4385214504"},"links":{"paper":"https://doi.org/10.46947/joaasr542023682","pdf":"http://www.joaasr.com/index.php/joaasr/article/download/682/211"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"AdaBoost ensemble classifies rainfall from 1901–2015 Indian station data, claiming better accuracy than SVM; no numbers given in abstract.","significance":1,"cited_by":6,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10584-023-03585-2","title":"Extreme events in the multi-proxy South Pacific drought atlas","authors":["Philippa Higgins","Jonathan Palmer","Martin S. Andersen","CHRIS S. M. TURNEY","Fiona M. Johnson"],"date":"2023-07-24","year":2023,"venue":"Climatic Change","venue_type":"journal","ids":{"doi":"10.1007/s10584-023-03585-2","openalex":"W4385191258"},"links":{"paper":"https://doi.org/10.1007/s10584-023-03585-2","pdf":"https://link.springer.com/content/pdf/10.1007/s10584-023-03585-2.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Multi-proxy drought atlas reconstructs southwest Pacific drought back to 1640 and uses Isolation Forest to flag extreme El Niño-linked droughts.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30865-mib.v7i3.6173","title":"Penerapan Algorimta Backpropagation Untuk Prakiraan Cuaca Harian Dibandingkan Dengan Support Vector Machine dan Logistic Regression","authors":["Ayu Zulfiani","Chairani Fauzi"],"date":"2023-07-23","year":2023,"venue":"JURNAL MEDIA INFORMATIKA BUDIDARMA","venue_type":"journal","ids":{"doi":"10.30865/mib.v7i3.6173","openalex":"W4401051190"},"links":{"paper":"https://doi.org/10.30865/mib.v7i3.6173"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Backpropagation neural network predicts classified daily rainfall at a Lampung station, outperforming SVM and logistic regression on light-rain recall.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.12032","title":"Flight Contrail Segmentation via Augmented Transfer Learning with Novel SR Loss Function in Hough Space","authors":["Junzi Sun","Esther Roosenbrand"],"date":"2023-07-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.12032"},"links":{"paper":"https://arxiv.org/abs/2307.12032","pdf":"https://arxiv.org/pdf/2307.12032","code":"https://github.com/junzis/contrail-net"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Few-shot transfer learning with a novel Hough-space SR loss segments flight contrails in satellite imagery for climate-impact monitoring.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15143627","title":"Spatiotemporal Variations of Global Human-Perceived Heatwave Risks and their Driving Factors Based on Machine Learning","authors":["Yuwei Wang","Na Zhao"],"date":"2023-07-21","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15143627","openalex":"W4385069085"},"links":{"paper":"https://doi.org/10.3390/rs15143627","pdf":"https://www.mdpi.com/2072-4292/15/14/3627/pdf?version=1689913412"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["era5","satellite"],"status":"research","summary":"Random forest analysis of 2000–2020 global human-perceived heatwave risk using heat index shows rising high-risk areas and identifies aspect and land use as main drivers.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.8190","title":"Comparison of machine learning statistical downscaling and regional climate models for temperature, precipitation, wind speed, humidity and radiation over Europe under present conditions","authors":["Alfonso Hernanz","Carlos Correa","Marta Domínguez","Esteban Rodríguez‐Guisado","Ernesto Rodríguez Camino"],"date":"2023-07-21","year":2023,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.8190","openalex":"W4385065610"},"links":{"paper":"https://doi.org/10.1002/joc.8190"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations","other"],"status":"research","summary":"Compares a machine-learning statistical downscaling model with six EURO-CORDEX regional climate models over Europe; the ML model scores better on most metrics before bias correction.","significance":4,"cited_by":16,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14071174","title":"Classification of Weather Conditions Based on Supervised Learning for Swedish Cities","authors":["Mohamad Safia","R. Abbas","Mohammad Aslani"],"date":"2023-07-20","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14071174","openalex":"W4385069115"},"links":{"paper":"https://doi.org/10.3390/atmos14071174","pdf":"https://www.mdpi.com/2073-4433/14/7/1174/pdf?version=1689858910"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Compares ANN, SVM, random forest and KNN for weather-condition classification in Swedish cities; the ANN performs best and beats Weatherstack's own forecasts.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2023.1223154","title":"Improved forecasting of extreme hurricane events by integrating spatio-temporal CNN-RF learning of tropical cyclone characteristics","authors":["Javier Martínez-Amaya","Nicolas Longépé","Verònica Nieves","Jordi Muñoz-Marı́"],"date":"2023-07-20","year":2023,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2023.1223154","openalex":"W4385068565"},"links":{"paper":"https://doi.org/10.3389/feart.2023.1223154"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A CNN plus random forest hybrid using brightness temperature features improves severe hurricane prediction by 12% up to 3 days ahead.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jas-d-22-0208.1","title":"Diagnosing Tropical Cyclone Intensity Variations from the Surface Wind Field Evolution","authors":["Léo Vinour","Swen Jullien","Alexis Aurelien Mouche"],"date":"2023-07-20","year":2023,"venue":"Journal of the Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1175/jas-d-22-0208.1","openalex":"W4384934600"},"links":{"paper":"https://doi.org/10.1175/jas-d-22-0208.1"},"orgs":[],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Surface wind asymmetry descriptors from 1-km tropical cyclone simulations, classified by machine learning, improve intensification prediction skill by 11% to about 75%.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.10843","title":"Global Precipitation Nowcasting of Integrated Multi-satellitE Retrievals for GPM: A U-Net Convolutional LSTM Architecture","authors":["Reyhaneh Rahimi","Praveen Ravirathinam","Ardeshir Ebtehaj","Ali Behrangi","Jackson Tan","Vipin Kumar"],"date":"2023-07-20","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.10843"},"links":{"paper":"https://arxiv.org/abs/2307.10843","pdf":"https://arxiv.org/pdf/2307.10843"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"A U-Net ConvLSTM nowcasts near-global IMERG precipitation every 30 minutes up to 4 hours; a classification-loss variant better predicts rates above 8 mm/hr.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.10580","title":"Intelligent model for offshore China sea fog forecasting","authors":["Yanfei Xiang","Qinghong Zhang","Mingqing Wang","Ruixue Xia","Yang Kong","Xiaomeng Huang"],"date":"2023-07-20","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.10580","openalex":"W4385001472"},"links":{"paper":"https://arxiv.org/abs/2307.10580","pdf":"https://arxiv.org/pdf/2307.10580"},"orgs":["tsinghua-university"],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Ensemble learning with focal loss improves 60-hour sea fog forecasts over WRF and NOAA FSL baselines off the Yangtze estuary, raising detection and cutting false alarms.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1126-sciadv.adf2758","title":"Toward machine-assisted tuning avoiding the underestimation of uncertainty in climate change projections","authors":["F. Hourdin","Brady S. Ferster","Julie Deshayes","Juliette Mignot","Ionela Musat","Daniel Williamson"],"date":"2023-07-19","year":2023,"venue":"Science Advances","venue_type":"journal","ids":{"doi":"10.1126/sciadv.adf2758","openalex":"W4384818614"},"links":{"paper":"https://doi.org/10.1126/sciadv.adf2758","pdf":"https://www.science.org/doi/pdf/10.1126/sciadv.adf2758?download=true"},"orgs":[],"topic":"climate-emulation","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Uses machine-learning emulators to select climate model parameter configurations, showing that conventional tuning underestimates warming uncertainty while matching present-day observations.","significance":5,"cited_by":49,"score":40,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.10128","title":"The rise of data-driven weather forecasting","authors":["Zied Ben-Bouallegue","Mariana C A Clare","Linus Magnusson","Estibaliz Gascon","Michael Maier-Gerber","Martin Janousek","Mark Rodwell","Florian Pinault","Jesper S Dramsch","Simon T K Lang","Baudouin Raoult","Florence Rabier","Matthieu Chevallier","Irina Sandu","Peter Dueben","Matthew Chantry","Florian Pappenberger"],"date":"2023-07-19","year":2023,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"arxiv":"2307.10128","doi":"10.1175/bams-d-23-0162.1","openalex":"W4392284590"},"links":{"paper":"https://arxiv.org/abs/2307.10128","pdf":"https://arxiv.org/pdf/2307.10128"},"orgs":["ecmwf"],"topic":"benchmarks-data-eval","topics":[],"type":"evaluation","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Compares PanguWeather with ECMWF IFS and finds comparable skill for global and extreme metrics, with forecast smoothness and bias drift as drawbacks.","significance":6,"cited_by":212,"score":69,"highlight":true,"highlight_reason":"This ECMWF study gives an early operational-style comparison of Pangu-Weather and IFS, and it is influential in the community for showing how to verify ML models.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1016-j.rse.2023.113723","title":"A deep learning-based framework for multi-source precipitation fusion","authors":["Keyhan Gavahi","Ehsan Foroumandi","Hamid Moradkhani"],"date":"2023-07-18","year":2023,"venue":"Remote Sensing of Environment","venue_type":"journal","ids":{"doi":"10.1016/j.rse.2023.113723","openalex":"W4384895629"},"links":{"paper":"https://doi.org/10.1016/j.rse.2023.113723","pdf":"https://www.sciencedirect.com/science/article/am/pii/S0034425723002742?via%3Dihub"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":[],"timescale":[],"spatial":[],"data":["satellite","stations"],"status":"research","summary":"Deep learning framework fuses multi-source satellite precipitation products; abstract unavailable, so classification relies on the title.","significance":3,"cited_by":107,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ejrh.2023.101477","title":"The skill of statistical downscaling in future climate with high-resolution climate models as pseudo-reality","authors":["Santiago Mendoza Paz","Patrick Willems"],"date":"2023-07-18","year":2023,"venue":"Journal of Hydrology Regional Studies","venue_type":"journal","ids":{"doi":"10.1016/j.ejrh.2023.101477","openalex":"W4385540543"},"links":{"paper":"https://doi.org/10.1016/j.ejrh.2023.101477","pdf":"https://ars.els-cdn.com/content/image/1-s2.0-S2214581823001647-ga1_lrg.jpg"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml","other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Evaluates 21 statistical downscaling methods, including ML, against a 4 km pseudo-reality for Belgian extreme rainfall, recommending an ensemble of downscaling approaches.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10584-023-03532-1","title":"Machine learning and the quest for objectivity in climate model parameterization","authors":["Julie Jebeile","Vincent Lam","Mason Majszak","Tim Räz"],"date":"2023-07-18","year":2023,"venue":"Climatic Change","venue_type":"journal","ids":{"doi":"10.1007/s10584-023-03532-1","openalex":"W4384694629"},"links":{"paper":"https://doi.org/10.1007/s10584-023-03532-1","pdf":"https://link.springer.com/content/pdf/10.1007/s10584-023-03532-1.pdf"},"orgs":["meteo-france"],"topic":"hybrid-parameterization","topics":[],"type":"position","method":["other"],"timescale":["climate"],"spatial":["global"],"data":[],"status":"research","summary":"Argues machine learning in climate model parameterization still requires expert judgment, so it is no more objective than conventional tuning.","significance":3,"cited_by":17,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.09060","title":"Extreme heatwave sampling and prediction with analog Markov chain and comparisons with deep learning","authors":["George Miloshevich","Dario Lucente","Pascal Yiou","Freddy Bouchet"],"date":"2023-07-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.09060","openalex":"W4384808021"},"links":{"paper":"https://arxiv.org/abs/2307.09060","pdf":"https://arxiv.org/pdf/2307.09060"},"orgs":[],"topic":"extremes-hazards","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"An analog-based stochastic weather generator emulates prolonged European heatwaves and extends return-time estimates, though a CNN predicts better with long training data.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-asr-20-81-2023","title":"Decentralized forecasting of wind energy generation with an adaptive machine learning approach to support ancillary grid services","authors":["Lukas Holicki","Manuel Dröse","Gregor Schürmann","Marcus Letzel"],"date":"2023-07-17","year":2023,"venue":"Advances in science and research","venue_type":"journal","ids":{"doi":"10.5194/asr-20-81-2023","openalex":"W4384558759"},"links":{"paper":"https://doi.org/10.5194/asr-20-81-2023","pdf":"https://asr.copernicus.org/articles/20/81/2023/asr-20-81-2023.pdf"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"pre-operational","summary":"On-site adaptive probabilistic wind power forecasting combined with NWP forecasts improves short-term reliability for grid operation.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-23-0057.1","title":"Uncertainty Quantification of Deep Learning–Based Statistical Downscaling of Climatic Parameters","authors":["Vahid Nourani","Kasra Khodkar","Aida Hosseini Baghanam","Sameh A. Kantoush","İbrahim Demir"],"date":"2023-07-17","year":2023,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-23-0057.1","openalex":"W4384524063"},"links":{"paper":"https://doi.org/10.1175/jamc-d-23-0057.1"},"orgs":[],"topic":"downscaling","topics":["xai-uq-physics"],"type":"model","method":["rnn","classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Downscales CanESM5 temperature and precipitation at two Iranian stations with feedforward and LSTM networks, adding LUBE prediction intervals; LSTM gains about 55% higher NSE.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-23-0003.1","title":"Assessing Tropical Pacific–Induced Predictability of Southern California Precipitation Using a Novel Multi-Input Multioutput Autoencoder","authors":["Linsey Sara Passarella","Salil Mahajan"],"date":"2023-07-17","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-23-0003.1","openalex":"W4384524047"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0003.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/aies/2/4/AIES-D-23-0003.1.pdf"},"orgs":["ornl"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["rnn","other"],"timescale":["s2s"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Multi-input autoencoder index from tropical Pacific SST gives Southern California precipitation predictability up to 4 months, beating Niño-3.4.","significance":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s43762-023-00100-2","title":"AI-enabled strategies for climate change adaptation: protecting communities, infrastructure, and businesses from the impacts of climate change","authors":["Harshita Jain","Renu Dhupper","Anamika Shrivastava","Deepak Kumar","Maya Kumari"],"date":"2023-07-17","year":2023,"venue":"Computational Urban Science","venue_type":"journal","ids":{"doi":"10.1007/s43762-023-00100-2","openalex":"W4384526074"},"links":{"paper":"https://doi.org/10.1007/s43762-023-00100-2","pdf":"https://link.springer.com/content/pdf/10.1007/s43762-023-00100-2.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Review of AI for climate change adaptation covering vulnerability mapping, climate scenario simulation and risk assessment, plus ethical concerns.","significance":2,"cited_by":136,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7217947281","title":"Image Based Automated Weather Analysis Using Deep Learning for Decision Support to Remote Farmers","authors":["Jeen Retna Kumar R","Berakhah F. Stanley","Subha S.","Jim Reeves S.","Gold Beulah Patturose J.","P. Bini Palas"],"date":"2023-07-16","year":2023,"venue":"International Journal of Intelligent Systems and Applications in Engineering","venue_type":"journal","ids":{"openalex":"W7217947281"},"links":{"paper":"https://ijisae.org/index.php/IJISAE/article/view/3343","pdf":"https://ijisae.org/index.php/IJISAE/article/download/3343/1929"},"orgs":[],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN plus Bi-GRU classifies weather conditions from on-farm sky images to support farmers' decisions; no quantitative results given.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.08038","title":"Bivariate DeepKriging for Large-scale Spatial Interpolation of Wind Fields","authors":["Pratik Nag","Ying Sun","Brian J Reich"],"date":"2023-07-16","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.08038","openalex":"W4384644203"},"links":{"paper":"https://arxiv.org/abs/2307.08038","pdf":"https://arxiv.org/pdf/2307.08038"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Bivariate DeepKriging uses a spatially embedded DNN to interpolate wind fields at about 500,000 locations, beating cokriging and running roughly 20 times faster.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-023-3001-1","title":"Superiority of a Convolutional Neural Network Model over Dynamical Models in Predicting Central Pacific ENSO","authors":["Tingyu Wang","Ping Huang"],"date":"2023-07-15","year":2023,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-023-3001-1","openalex":"W4384408321"},"links":{"paper":"https://doi.org/10.1007/s00376-023-3001-1"},"orgs":["nuist","iap-cas"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"A convolutional neural network is reported to outperform dynamical models in predicting Central Pacific ENSO events.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.rser.2023.113528","title":"Accurately forecasting solar radiation distribution at both spatial and temporal dimensions simultaneously with fully-convolutional deep neural network model","authors":["Zhaohui Ruan","Weiwei Sun","Yuan Yuan","He-Ping Tan"],"date":"2023-07-14","year":2023,"venue":"Renewable and Sustainable Energy Reviews","venue_type":"journal","ids":{"doi":"10.1016/j.rser.2023.113528","openalex":"W4384276671"},"links":{"paper":"https://doi.org/10.1016/j.rser.2023.113528"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A fully convolutional network forecasts spatially distributed solar radiation over time, targeting renewable energy applications.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.106925","title":"Machine learning model to accurately estimate the planetary boundary layer height of Beijing urban area with ERA5 data","authors":["Kecheng Peng","Jinyuan Xin","Xiaoqian Zhu","Xiaoyuan Wang","Xiaoqun Cao","Yongjing Ma","Xinbing Ren","Dandan Zhao","Junji Cao","Zifa Wang"],"date":"2023-07-14","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.106925","openalex":"W4384297306"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.106925"},"orgs":["iap-cas"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["era5"],"status":"research","summary":"Machine learning model estimates urban Beijing planetary boundary layer height from ERA5 predictors.","significance":2,"cited_by":23,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.10052","title":"FaIRGP: A Bayesian Energy Balance Model for Surface Temperatures Emulation","authors":["Shahine Bouabid","Dino Sejdinovic","Duncan Watson-Parris"],"date":"2023-07-14","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.10052"},"links":{"paper":"https://arxiv.org/abs/2307.10052","pdf":"https://arxiv.org/pdf/2307.10052"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Bayesian Gaussian-process emulator obeying energy-balance equations emulates global and spatial surface temperature across scenarios, with interpretable parameters and uncertainty quantification.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-22-0175.1","title":"Unsupervised Clustering of Geostationary Satellite Cloud Properties for Estimating Precipitation Probabilities of Tropical Convective Clouds","authors":["Doyi Kim","Hee-Jae Kim","Yong‐Sang Choi"],"date":"2023-07-13","year":2023,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-22-0175.1","openalex":"W4384131273"},"links":{"paper":"https://doi.org/10.1175/jamc-d-22-0175.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/apme/62/8/JAMC-D-22-0175.1.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Self-organizing map clustering of geostationary cloud properties finds tropical cloud clusters with over 70% precipitation probability, e.g., CER ≥ 20 μm and CTT < 230 K.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-023-02511-3","title":"Comparison of data-driven methods for linking extreme precipitation events to local and large-scale meteorological variables","authors":["Nafsika Antoniadou","Hjalte Jomo Danielsen Sørup","Jonas Wied Pedersen","Ida Bülow Gregersen","Torben Schmith","Karsten Arnbjerg‐Nielsen"],"date":"2023-07-13","year":2023,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-023-02511-3","openalex":"W4384205570"},"links":{"paper":"https://doi.org/10.1007/s00477-023-02511-3","pdf":"https://link.springer.com/content/pdf/10.1007/s00477-023-02511-3.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["era5","stations"],"status":"research","summary":"Logistic regression matches machine learning for detecting extreme precipitation in Denmark from ERA5 predictors, with ROC AUC 0.86 versus 0.87 for the best ML model.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15143510","title":"A CatBoost-Based Model for the Intensity Detection of Tropical Cyclones over the Western North Pacific Based on Satellite Cloud Images","authors":["Wei Zhong","Deyuan Zhang","Yuan Sun","Qian Wang"],"date":"2023-07-12","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15143510","openalex":"W4384203046"},"links":{"paper":"https://doi.org/10.3390/rs15143510","pdf":"https://www.mdpi.com/2072-4292/15/14/3510/pdf?version=1689156986"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"CatBoost model estimates western North Pacific tropical cyclone intensity from FY-2 cloud-top brightness temperatures, achieving 3.74 m/s RMSE and beating prior CNN approaches.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40435-023-01250-1","title":"Precipitation prediction in several Chinese regions using machine learning methods","authors":["Yuyao Wang","Lijun Pei","Jiachen Wang"],"date":"2023-07-12","year":2023,"venue":"International Journal of Dynamics and Control","venue_type":"journal","ids":{"doi":"10.1007/s40435-023-01250-1","openalex":"W4384024598"},"links":{"paper":"https://doi.org/10.1007/s40435-023-01250-1"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies machine learning to predict precipitation in several Chinese regions; no abstract was provided, so the details are unclear.","significance":1,"cited_by":12,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13762-023-05092-4","title":"An efficient hybrid weather prediction model based on deep learning","authors":["Anıl Utku","Ümit Can"],"date":"2023-07-12","year":2023,"venue":"International Journal of Environmental Science and Technology","venue_type":"journal","ids":{"doi":"10.1007/s13762-023-05092-4","openalex":"W4384029651"},"links":{"paper":"https://doi.org/10.1007/s13762-023-05092-4"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Proposes a hybrid deep learning weather prediction model; abstract unavailable, so details and reported gains could not be verified.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-3785-2023","title":"Deep learning for stochastic precipitation generation – deep SPG v1.0","authors":["Leroy J. Bird","Matthew Walker","G. E. Bodeker","Isaac Campbell","Guangzhong Liu","Swapna Josmi Sam","Jared Lewis","Suzanne M. Rosier"],"date":"2023-07-11","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-3785-2023","openalex":"W4383982480"},"links":{"paper":"https://doi.org/10.5194/gmd-16-3785-2023","pdf":"https://gmd.copernicus.org/articles/16/3785/2023/gmd-16-3785-2023.pdf"},"orgs":[],"topic":"climate-emulation","topics":["local-forecasting"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Introduces a neural-network stochastic precipitation generator for New Zealand that reproduces daily and hourly statistics and captures climate-change drift; runs orders of magnitude faster than an RCM.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15143493","title":"Towards the Accurate Automatic Detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications","authors":["Mikhail Krinitskiy","A. A. Sprygin","Svyatoslav Elizarov","Alexandra Narizhnaya","Andrey Nikolaevich Shikhov","А. V. Chernokulsky"],"date":"2023-07-11","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15143493","openalex":"W4384067390"},"links":{"paper":"https://doi.org/10.3390/rs15143493","pdf":"https://www.mdpi.com/2072-4292/15/14/3493/pdf?version=1689158259"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"benchmark","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Presents a RetinaNet detector, labeled dataset and annotation tool for mesoscale convective systems in Meteosat SEVIRI imagery, achieving mAP 0.75.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3233-jifs-230483","title":"Aviation visibility forecasting by integrating Convolutional Neural Network and long short-term memory network","authors":["Chuen-Jyh Chen","Chieh-Ni Huang","S. M. Yang"],"date":"2023-07-11","year":2023,"venue":"Journal of Intelligent & Fuzzy Systems","venue_type":"journal","ids":{"doi":"10.3233/jifs-230483","openalex":"W4383956471"},"links":{"paper":"https://doi.org/10.3233/jifs-230483"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"CNN-LSTM hybrid forecasts aviation visibility, reducing RMSE to 2.68 and MAPE to 13.41% from LSTM alone.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40808-023-01835-x","title":"A review of the application of hybrid machine learning models to improve rainfall prediction","authors":["Sam-Quarcoo Dotse","Isaac Larbi","Andrew Manoba Limantol","Liyanage C. De Silva"],"date":"2023-07-11","year":2023,"venue":"Modeling Earth Systems and Environment","venue_type":"journal","ids":{"doi":"10.1007/s40808-023-01835-x","openalex":"W4383878889"},"links":{"paper":"https://doi.org/10.1007/s40808-023-01835-x"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Reviews hybrid machine learning models for rainfall prediction, summarizing methods and their reported accuracy gains.","significance":2,"cited_by":71,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15143466","title":"Multiscale Representation of Radar Echo Data Retrieved through Deep Learning from Numerical Model Simulations and Satellite Images","authors":["Mingming Zhu","Qi Liao","Lin Wu","Si Zhang","Zifa Wang","Xiaole Pan","Qizhong Wu","Yangang Wang","Debin Su"],"date":"2023-07-09","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15143466","openalex":"W4383819129"},"links":{"paper":"https://doi.org/10.3390/rs15143466","pdf":"https://www.mdpi.com/2072-4292/15/14/3466/pdf?version=1688894667"},"orgs":["iap-cas"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite","km-scale-sim"],"status":"research","summary":"U-Net reconstructs radar reflectivity from WRF simulations and Himawari-8 satellite data with 5.38 dBZ RMSE, revealing scale-separated atmospheric features.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.06840","title":"Ensemble learning for blending gridded satellite and gauge-measured precipitation data","authors":["Georgia Papacharalampous","Hristos Tyralis","Nikolaos Doulamis","Anastasios Doulamis"],"date":"2023-07-09","year":2023,"venue":"Remote Sensing 15 (2023) 4912","venue_type":"journal","ids":{"arxiv":"2307.06840","doi":"10.3390/rs15204912"},"links":{"paper":"https://arxiv.org/abs/2307.06840","pdf":"https://arxiv.org/pdf/2307.06840"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Proposes eleven stacking and ensemble learners that blend PERSIANN and IMERG satellite precipitation with gauge data over CONUS, improving monthly accuracy.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.04216","title":"Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Data","authors":["Hieu Le","Jian Tao"],"date":"2023-07-09","year":2023,"venue":"Computing&AI Connect, ISSN: 3006-4163; 2024, Vol. 1, Article ID: 2024001","venue_type":"journal","ids":{"arxiv":"2307.04216","doi":"10.69709/caic.2024.193132"},"links":{"paper":"https://arxiv.org/abs/2307.04216","pdf":"https://arxiv.org/pdf/2307.04216"},"orgs":[],"topic":"infra-software","topics":["benchmarks-data-eval"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Autoencoder lossy compression reaches ratio 140 on benchmarks and 200 on 500 years of CESM climate output with negligible reconstruction error.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.24014-coreit.v9i1.21713","title":"Efficiency of the Combination of Machine Learning Models in the Evaluation of Weather Parameters","authors":["Yannick Mubakilayi","Simon Ntumba","Pierre Katalay Kafunda","Salem Cimanga","Gracias Kabulu"],"date":"2023-07-08","year":2023,"venue":"Jurnal CoreIT Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi","venue_type":"journal","ids":{"doi":"10.24014/coreit.v9i1.21713","openalex":"W4395100190"},"links":{"paper":"https://doi.org/10.24014/coreit.v9i1.21713","pdf":"https://ejournal.uin-suska.ac.id/index.php/coreit/article/download/21713/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Boosting ensemble of machine learning models predicts multiple meteorological parameters from measurements; no quantitative results given.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023jd039154","title":"Projection of Future Fire Emissions Over the Contiguous US Using Explainable Artificial Intelligence and CMIP6 Models","authors":["Sing‐Chun Wang","Lai-Yung Ruby Leung","Yun Qian"],"date":"2023-07-06","year":2023,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2023jd039154","openalex":"W4383342079"},"links":{"paper":"https://doi.org/10.1029/2023jd039154","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023JD039154"},"orgs":[],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"application","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Neural network with SHAP projects US fire PM2.5 emissions to rise 4–75% by mid-century under SSP5-8.5, driven by warming and drying.","significance":3,"cited_by":30,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su151310609","title":"A Novel Machine Learning Approach for Solar Radiation Estimation","authors":["Hasna Hissou","Said Benkirane","Azidine Guezzaz","Mourade Azrour","Abderrahim Beni‐Hssane"],"date":"2023-07-05","year":2023,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su151310609","openalex":"W4383376752"},"links":{"paper":"https://doi.org/10.3390/su151310609","pdf":"https://www.mdpi.com/2071-1050/15/13/10609/pdf?version=1688556296"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Proposes a machine-learning approach to estimate solar radiation from meteorological inputs, aimed at renewable energy planning and climate studies.","significance":2,"cited_by":83,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ace463","title":"Comparison of a novel machine learning approach with dynamical downscaling for Australian precipitation","authors":["Nidhi Nishant","Sanaa Hobeichi","Steven C. Sherwood","Gab Abramowitz","Yawen Shao","Craig H. Bishop","A. J. Pitman"],"date":"2023-07-05","year":2023,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ace463","openalex":"W4383218728"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ace463","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ace463/pdf"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["other"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"An MLP with a novel loss downscales Australian precipitation from 12–48 km to 5 km, outperforming dynamical downscaling on extremes with 15–85% lower bias at 12 km.","significance":4,"cited_by":29,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41586-023-06184-4","title":"Skilful nowcasting of extreme precipitation with NowcastNet","authors":["Yuchen Zhang","Mingsheng Long","Kaiyuan Chen","Lanxiang Xing","Ronghua Jin","Michael I. Jordan","Jianmin Wang"],"date":"2023-07-05","year":2023,"venue":"Nature","venue_type":"journal","ids":{"doi":"10.1038/s41586-023-06184-4","openalex":"W4383197616"},"links":{"paper":"https://doi.org/10.1038/s41586-023-06184-4"},"orgs":["cma","tsinghua-university","uc-berkeley"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn","physics-constrained"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"NowcastNet unifies advection physics with learned conditional generation for extreme precipitation nowcasts up to 3 hours, ranked first by meteorologists in 71% of cases.","significance":7,"cited_by":458,"score":68,"highlight":true,"highlight_reason":"NowcastNet unifies physical evolution and deep learning for extreme precipitation nowcasting, validated by meteorologists; influential Nature nowcasting work.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2307.02203","title":"Neural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensembles","authors":["Fatemeh Farokhmanesh","Kevin Höhlein","Christoph Neuhauser","Tobias Necker","Martin Weissmann","Takemasa Miyoshi","Rüdiger Westermann"],"date":"2023-07-05","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.02203"},"links":{"paper":"https://arxiv.org/abs/2307.02203","pdf":"https://arxiv.org/pdf/2307.02203"},"orgs":[],"topic":"xai-uq-physics","topics":["probabilistic-ensembles"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Neural field compactly represents non-linear mutual-information dependencies across a 1000-member weather forecast ensemble, enabling interactive volume-rendered visualization with lower memory and compute.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl103979","title":"A Customized Multi‐Scale Deep Learning Framework for Storm Nowcasting","authors":["Shangshang Yang","Huiling Yuan"],"date":"2023-07-03","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl103979","openalex":"W4383069610"},"links":{"paper":"https://doi.org/10.1029/2023gl103979","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023GL103979"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"Multi-scale deep learning framework with attention and a spatiotemporal loss improves 1-hour storm nowcast skill scores by 8.5–42.6% on SEVIR.","significance":4,"cited_by":21,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.04817","title":"A physics-constrained machine learning method for mapping gapless land surface temperature","authors":["Jun Ma","Huanfeng Shen","Menghui Jiang","Liupeng Lin","Chunlei Meng","Chao Zeng","Huifang Li","Penghai Wu"],"date":"2023-07-03","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.04817"},"links":{"paper":"https://arxiv.org/abs/2307.04817","pdf":"https://arxiv.org/pdf/2307.04817"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"A physics-constrained LightGBM model adds CLM surface energy balance inputs to remote sensing, giving more accurate and interpretable gapless land surface temperature.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0045.1","title":"TCDetect: A New Method of Detecting the Presence of Tropical Cyclones Using Deep Learning","authors":["Daniel Galea","Julian Martin Kunkel","Bryan Lawrence"],"date":"2023-07-01","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0045.1","openalex":"W4382932235"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0045.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/3/AIES-D-22-0045.1.pdf"},"orgs":["university-of-reading"],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Lightweight deep learning detects tropical cyclone presence during simulations for online data reduction, reaching 92% recall on held-out ERA-Interim years.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-5.0131929","title":"Memory-based parameterization with differentiable solver: Application to Lorenz ’96","authors":["Mohamed Aziz Bhouri","Pierre Gentine"],"date":"2023-07-01","year":2023,"venue":"Chaos An Interdisciplinary Journal of Nonlinear Science","venue_type":"journal","ids":{"doi":"10.1063/5.0131929","openalex":"W4383302406"},"links":{"paper":"https://doi.org/10.1063/5.0131929"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["rnn","differentiable"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Proposes memory-based neural network closures trained with a differentiable solver for Lorenz '96, giving more stable long-horizon forecasts than instantaneous parameterizations.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023ms003800","title":"Efficient Super‐Resolution of Near‐Surface Climate Modeling Using the Fourier Neural Operator","authors":["Peishi Jiang","Zhao Yang","Jiali Wang","Chenfu Huang","Pengfei Xue","TC Chakraborty","Xingyuan Chen","Yun Qian"],"date":"2023-07-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2023ms003800","openalex":"W4385076997"},"links":{"paper":"https://doi.org/10.1029/2023ms003800","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023MS003800"},"orgs":["argonne"],"topic":"downscaling","topics":["xai-uq-physics"],"type":"model","method":["neural-operator","physics-constrained"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Applies a Fourier neural operator with a Clausius–Clapeyron constraint for zero-shot super-resolution of WRF near-surface heat fields over the Great Lakes, reaching 1-km resolution.","significance":4,"cited_by":37,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.heliyon.2023.e18200","title":"An improved deep learning procedure for statistical downscaling of climate data","authors":["Ahmed M. S. Kheir","Abdelrazek Elnashar","Alaa Mosad","Ajit Govind"],"date":"2023-07-01","year":2023,"venue":"Heliyon","venue_type":"journal","ids":{"doi":"10.1016/j.heliyon.2023.e18200","openalex":"W4384937209"},"links":{"paper":"https://doi.org/10.1016/j.heliyon.2023.e18200","pdf":"http://www.cell.com/article/S2405844023054087/pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Applies a CNN to downscale CMIP6 CanESM5 temperatures over Egypt to 0.1°, projecting warming of 4.8 to 6.3 °C by 2100 under SSP scenarios.","significance":3,"cited_by":37,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12145-023-01037-0","title":"Random forest-based nowcast model for rainfall","authors":["Nita H. Shah","Anupam Priamvada","Bipasha Paul Shukla"],"date":"2023-07-01","year":2023,"venue":"Earth Science Informatics","venue_type":"journal","ids":{"doi":"10.1007/s12145-023-01037-0","openalex":"W4382796982"},"links":{"paper":"https://doi.org/10.1007/s12145-023-01037-0"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Random forest model for short-term rainfall nowcasting; abstract unavailable, so performance could not be assessed.","significance":1,"cited_by":11,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4521","title":"D‐vine‐copula‐based postprocessing of wind speed ensemble forecasts","authors":["David Jobst","Annette Möller","Jürgen Groß"],"date":"2023-07-01","year":2023,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4521","openalex":"W4383621501"},"links":{"paper":"https://doi.org/10.1002/qj.4521","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/qj.4521"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"D-vine copula quantile regression postprocesses 10 m wind ensembles at 60 German stations, outperforming gradient-boosted tEMOS globally.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.05505","title":"Reconfiguration of Amazon's Connectivity in the Climate System","authors":["Adam Giammarese","Jacob Brown","Nishant Malik"],"date":"2023-07-01","year":2023,"venue_type":"preprint","ids":{"arxiv":"2307.05505","doi":"10.1063/5.0165861"},"links":{"paper":"https://arxiv.org/abs/2307.05505","pdf":"https://arxiv.org/pdf/2307.05505"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional","global"],"data":["other"],"status":"research","summary":"Applies climate network analysis with manifold-learning embeddings to show the Amazon losing short-range and gaining long-range connectivity, with faster perturbation spread in recent decades.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5391-jkiis.2023.33.3.249","title":"Development of Real-Time Bias Correction Model for High-Resolution Weather Forecast Information of Mountainous Terrain Using Artificial Neural Network","authors":["Hyeong-Se Jeong","Sang-Sam Lee","Yong-Hee Lee","Yun-Am Seo"],"date":"2023-06-30","year":2023,"venue":"Journal of Korean institute of intelligent systems","venue_type":"journal","ids":{"doi":"10.5391/jkiis.2023.33.3.249","openalex":"W4383877464"},"links":{"paper":"https://doi.org/10.5391/jkiis.2023.33.3.249"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Sliding-window DNN bias correction of 100 m LDAPS forecasts at Pyeongchang reduces RMSE by 33% for temperature and 45% for wind speed.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-3611-2023","title":"Convective-gust nowcasting based on radar reflectivity and a deep learning algorithm","authors":["Haixia Xiao","Yaqiang Wang","Yu Zheng","Yuanyuan Zheng","Yuanyuan Zheng","Yuanyuan Zheng","Xiaoran Zhuang","Hongyan Wang","Gao Mei"],"date":"2023-06-30","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-3611-2023","openalex":"W4382791800"},"links":{"paper":"https://doi.org/10.5194/gmd-16-3611-2023","pdf":"https://gmd.copernicus.org/articles/16/3611/2023/gmd-16-3611-2023.pdf"},"orgs":["cma"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn","physics-constrained"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Physics-constrained deep learning (CGsNet) nowcasts convective wind gusts from radar at 0.01° and 6-minute resolution for 0-2 h, beating NWP-based nowcasting.","significance":4,"cited_by":12,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15233-gfz.2023.40.5","title":"Application of the Random Forest method on the observation dataset for visibility nowcasting","authors":["David Sládek"],"date":"2023-06-30","year":2023,"venue":"Geofizika","venue_type":"journal","ids":{"doi":"10.15233/gfz.2023.40.5","openalex":"W4382809545"},"links":{"paper":"https://doi.org/10.15233/gfz.2023.40.5","pdf":"https://hrcak.srce.hr/ojs/index.php/geofizika/article/download/26746/13965"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A random forest tuned on station observations forecasts three-hour visibility with about 78% accuracy and a 6% false alarm rate, relevant to aviation.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.13164-mendel.2023.1.007","title":"Predictive Model of the ENSO Phenomenon Based on Regression Trees","authors":["Indalecio Mendoza Uribe"],"date":"2023-06-30","year":2023,"venue":"MENDEL","venue_type":"journal","ids":{"doi":"10.13164/mendel.2023.1.007","openalex":"W4384565492"},"links":{"paper":"https://doi.org/10.13164/mendel.2023.1.007","pdf":"https://mendel-journal.org/index.php/mendel/article/download/210/195"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Regression trees predict ENSO phase over a 12-month window using 1950–2022 data, reporting RMSE of 0.13 for 2022; evaluation design is unclear.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-16-3257-2023","title":"Validation of a camera-based intra-hour irradiance nowcasting model using synthetic cloud data","authors":["Philipp Gregor","Tobias Zinner","Fabian Jakub","Bernhard Mayer"],"date":"2023-06-29","year":2023,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-16-3257-2023","openalex":"W4382721454"},"links":{"paper":"https://doi.org/10.5194/amt-16-3257-2023","pdf":"https://amt.copernicus.org/articles/16/3257/2023/amt-16-3257-2023.pdf"},"orgs":[],"topic":"nowcasting","topics":["data-assimilation"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"MACIN combines a CNN cloud detector with data assimilation to nowcast direct irradiance up to 20 minutes ahead, improving on persistence beyond one minute.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.17248","title":"TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures","authors":["Emmanuel Balogun","Ram Rajagopal","Arun Majumdar"],"date":"2023-06-29","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.17248"},"links":{"paper":"https://arxiv.org/abs/2306.17248","pdf":"https://arxiv.org/pdf/2306.17248"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A GAN conditioned on month, location and period generates hourly 2m air temperatures over North America from NLDAS data, reproducing diurnal cycles.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-essd-15-2635-2023","title":"The EUPPBench postprocessing benchmark dataset v1.0","authors":["Jonathan Demaeyer","Jonas Bhend","Sebastian Lerch","Cristina Primo","Bert Van Schaeybroeck","Aitor Atencia","Zied Ben Bouallègue","Jieyu Chen","Markus Dabernig","Gavin Evans","Jana Faganeli Pucer","Ben Hooper","Nina Horat","David Jobst","Janko Merše","Peter Mlakar","Annette Möller","Olivier Mestre","Maxime Taillardat","Stéphane Vannitsem"],"date":"2023-06-28","year":2023,"venue":"Earth System Science Data","venue_type":"journal","ids":{"doi":"10.5194/essd-15-2635-2023","openalex":"W4383056506"},"links":{"paper":"https://doi.org/10.5194/essd-15-2635-2023","code":"https://github.com/EUPP-benchmark/climetlab-eumetnet-postprocessing-benchmark"},"orgs":["dwd","ecmwf","kit","met-office","meteo-france","meteoswiss"],"topic":"benchmarks-data-eval","topics":["post-processing"],"type":"benchmark","method":["other"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Releases EUPPBench, a time-aligned forecast-observation dataset with evaluation methods and a first benchmark of 2 m temperature postprocessing.","significance":6,"cited_by":26,"score":69,"highlight":true,"highlight_reason":"Standardized open benchmark dataset for ML postprocessing of ensemble forecasts from major European centres; valuable community infrastructure.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-rs15133306","title":"Enhancing Spatial Variability Representation of Radar Nowcasting with Generative Adversarial Networks","authors":["Aofan Gong","Ruidong Li","Baoxiang Pan","Haonan Chen","Guangheng Ni","Mingxuan Chen"],"date":"2023-06-28","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15133306","openalex":"W4382369444"},"links":{"paper":"https://doi.org/10.3390/rs15133306","pdf":"https://www.mdpi.com/2072-4292/15/13/3306/pdf?version=1687932077"},"orgs":["tsinghua-university","colorado-state-university","iap-cas","cma"],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Attentional GAN with a spatial variability loss reduces the blurry effect in radar nowcasts and outperforms competing models on the test set and storm cases.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-drones7070428","title":"Hyper-Local Weather Predictions with the Enhanced General Urban Area Microclimate Predictions Tool","authors":["Kevin Allan Adkins","William Becker","Sricharan K. Ayyalasomayajula","Steven Lavenstein","Kleoniki Vlachou","D.O. Miller","Marc D. Compere","Avinash Muthu Krishnan","Nickolas D. Macchiarella"],"date":"2023-06-28","year":2023,"venue":"Drones","venue_type":"journal","ids":{"doi":"10.3390/drones7070428","openalex":"W4382726625"},"links":{"paper":"https://doi.org/10.3390/drones7070428","pdf":"https://www.mdpi.com/2504-446X/7/7/428/pdf?version=1688003859"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml","other"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","km-scale-sim"],"status":"pre-operational","summary":"GUMP combines ML sensor predictions with CFD flow fields to give hyper-local urban wind forecasts and a risk map for drone operations.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.15956","title":"Deep learning for post-processing global probabilistic forecasts on sub-seasonal time scales","authors":["Nina Horat","Sebastian Lerch"],"date":"2023-06-28","year":2023,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"arxiv":"2306.15956","doi":"10.1175/mwr-d-23-0150.1","openalex":"W4390704937"},"links":{"paper":"https://arxiv.org/abs/2306.15956","pdf":"https://arxiv.org/pdf/2306.15956"},"orgs":["kit"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"CNN post-processing of ECMWF ensemble means yields calibrated global tercile forecasts for weeks 3-6, outperforming recalibrated ECMWF sub-seasonal forecasts.","significance":4,"cited_by":26,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1080-01431161.2023.2221806","title":"Research on infrared hyperspectral remote sensing cloud detection method based on deep learning","authors":["Zhuoya Ni","Mengdie Wu","Qifeng Lu","Hongyuan Huo","Fu Wang"],"date":"2023-06-27","year":2023,"venue":"International Journal of Remote Sensing","venue_type":"journal","ids":{"doi":"10.1080/01431161.2023.2221806","openalex":"W4382249335"},"links":{"paper":"https://doi.org/10.1080/01431161.2023.2221806"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","rnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"End-to-end DNN, CNN and CNN-LSTM models detect clouds in FY-3D HIRAS infrared hyperspectral soundings, with CNN and CNN-LSTM reaching 0.96 accuracy.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s43017-023-00431-y","title":"Causal inference for time series","authors":["Jakob Runge","Andreas Gerhardus","Gherardo Varando","Veronika Eyring","Gustau Camps-Valls"],"date":"2023-06-27","year":2023,"venue":"Nature Reviews Earth &amp; Environment","venue_type":"journal","ids":{"doi":"10.1038/s43017-023-00431-y","openalex":"W4382281637"},"links":{"paper":"https://doi.org/10.1038/s43017-023-00431-y"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Review of causal inference methods for time series, showing how causal discovery and attribution tools apply to Earth system and climate data.","significance":5,"cited_by":302,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1016-j.jhydrol.2023.129866","title":"Using CNN framework to improve multi-GCM ensemble predictions of monthly precipitation at local areas: An application over China and comparison with other methods","authors":["Lei Sun","Yufeng Lan","Rongsheng Jiang"],"date":"2023-06-27","year":2023,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2023.129866","openalex":"W4382281490"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2023.129866"},"orgs":["cma"],"topic":"post-processing","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"CNN combines multi-GCM ensembles to improve monthly precipitation predictions at local scales over China compared with other methods.","significance":3,"cited_by":32,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1572-9494-ace17d","title":"Unpacking the black box of deep learning for identifying El Niño-Southern oscillation","authors":["Yu Xue Sun","Yusupjan Habibulla","Gaoke Hu","Jun Meng","Zhenghui Lu","Maoxin Liu","Xiaosong Chen"],"date":"2023-06-26","year":2023,"venue":"Communications in Theoretical Physics","venue_type":"journal","ids":{"doi":"10.1088/1572-9494/ace17d","openalex":"W4382073246"},"links":{"paper":"https://doi.org/10.1088/1572-9494/ace17d","pdf":"https://iopscience.iop.org/article/10.1088/1572-9494/ace17d/pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"CNN recognizes El Nino and La Nina phases with 86.4% validation accuracy, and weight analysis identifies the few active kernels driving the classification.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-10106049.2023.2227610","title":"Simulation of visible light at night from infrared measurements using deep learning technique","authors":["Junjie Yan","Jianhua Qu","Hongda An","He Zhang"],"date":"2023-06-26","year":2023,"venue":"Geocarto International","venue_type":"journal","ids":{"doi":"10.1080/10106049.2023.2227610","openalex":"W4382136592"},"links":{"paper":"https://doi.org/10.1080/10106049.2023.2227610","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/10106049.2023.2227610?download=true"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A deep neural network turns FY-4B infrared imagery into simulated night-time visible images with R² of 0.99, aiding night cloud and fog monitoring.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.14433","title":"A data-driven framework for dimensionality reduction and causal inference in climate fields","authors":["Fabrizio Falasca","Pavel Perezhogin","Laure Zanna"],"date":"2023-06-26","year":2023,"venue":"Physical Review E 109, 044202 (2024)","venue_type":"journal","ids":{"arxiv":"2306.14433","doi":"10.1103/physreve.109.044202"},"links":{"paper":"https://arxiv.org/abs/2306.14433","pdf":"https://arxiv.org/pdf/2306.14433"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Data-driven pattern reduction plus fluctuation-response causal inference, with a new null model, maps interventional causal links between regions in global monthly sea surface temperature fields.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.14070","title":"SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning","authors":["Pu Ren","N. Benjamin Erichson","Junyi Guo","Shashank Subramanian","Omer San","Zarija Lukic","Michael W. Mahoney"],"date":"2023-06-24","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.14070","openalex":"W4382322281"},"links":{"paper":"https://arxiv.org/abs/2306.14070","pdf":"https://arxiv.org/pdf/2306.14070"},"orgs":[],"topic":"benchmarks-data-eval","topics":["downscaling"],"type":"benchmark","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"SuperBench provides a super-resolution benchmark across fluids, cosmology and weather data, finding that deep SR methods miss fine-scale physics; weather is one of three domains.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.14066","title":"SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models","authors":["Lizao Li","Rob Carver","Ignacio Lopez-Gomez","Fei Sha","John Anderson"],"date":"2023-06-24","year":2023,"venue":"Science Advances","venue_type":"journal","ids":{"arxiv":"2306.14066","doi":"10.1126/sciadv.adk4489","openalex":"W4393319450"},"links":{"paper":"https://arxiv.org/abs/2306.14066","pdf":"https://arxiv.org/pdf/2306.14066"},"orgs":["google-research"],"topic":"probabilistic-ensembles","topics":["climate-emulation"],"type":"model","method":["diffusion"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"SEEDS uses diffusion models to emulate operational weather ensembles, generating thousands of realistic members cheaply with improved reliability and extreme-event probabilities after bias correction.","significance":6,"cited_by":101,"score":89,"highlight":true,"highlight_reason":"SEEDS uses diffusion models to cheaply generate large weather forecast ensembles that emulate operational ones. It is a solid step for probabilistic ML forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.22541-essoar.168748456.60017486-v1","title":"Learning Atmospheric Boundary Layer Turbulence","authors":["Sara Shamekh","Pierre Gentine"],"date":"2023-06-23","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.168748456.60017486/v1","openalex":"W4381743464"},"links":{"paper":"https://doi.org/10.22541/essoar.168748456.60017486/v1","pdf":"https://www.authorea.com/doi/pdf/10.22541/essoar.168748456.60017486"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["cnn","physics-constrained"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Physically constrained neural network with a 2D latent space predicts boundary-layer turbulent fluxes from LES data, outperforming the eddy-diffusivity mass-flux scheme.","significance":4,"cited_by":5,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-23-0018.1","title":"Improved Analog Ensemble Formulation for 3-Hourly Precipitation Forecasts","authors":["Julia Jeworrek","Gregory West","Roland B. Stull"],"date":"2023-06-23","year":2023,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-23-0018.1","openalex":"W4381736486"},"links":{"paper":"https://doi.org/10.1175/waf-d-23-0018.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/38/8/WAF-D-23-0018.1.pdf"},"orgs":[],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Analog ensemble variant that applies past analog errors reduces dry bias and improves heavy 3-hourly precipitation reliability over British Columbia, and can forecast record values.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0042.1","title":"Deriving Severe Hail Likelihood from Satellite Observations and Model Reanalysis Parameters Using a Deep Neural Network","authors":["Benjamin R. Scarino","Kyle F. Itterly","Kristopher M. Bedka","Cameron R. Homeyer","John Allen","Sarah D. Bang","Daniel J. Cecil"],"date":"2023-06-23","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0042.1","openalex":"W4381738390"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0042.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/4/AIES-D-22-0042.1.pdf"},"orgs":["nasa","university-of-oklahoma"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","radar"],"status":"research","summary":"A deep neural network combining GOES cloud-top satellite data with reanalysis parameters estimates severe hail likelihood, reaching CSI 0.511 against radar MESH.","significance":3,"cited_by":17,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl104151","title":"Observing Aerosol Primary Convective Invigoration and Its Meteorological Feedback","authors":["Lin Zang","Daniel Rosenfeld","Zengxin Pan","Feiyue Mao","Yannian Zhu","Xin Lü","Wei Yu Gong"],"date":"2023-06-23","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl104151","openalex":"W4381848324"},"links":{"paper":"https://doi.org/10.1029/2023gl104151","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023GL104151"},"orgs":[],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Neural network sensitivity analysis of observations separates aerosol primary convective invigoration (72% of cloud-top cooling) from meteorological effects in deep convection.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.13690","title":"Prediction of Deep Ice Layer Thickness Using Adaptive Recurrent Graph Neural Networks","authors":["Benjamin Zalatan","Maryam Rahnemoonfar"],"date":"2023-06-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.13690"},"links":{"paper":"https://arxiv.org/abs/2306.13690","pdf":"https://arxiv.org/pdf/2306.13690"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["gnn","rnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Adaptive recurrent graph networks infer historic snow accumulation from deep ice-layer thickness in airborne radar data, outperforming prior models in polar ice records.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.12873","title":"FuXi: A cascade machine learning forecasting system for 15-day global weather forecast","authors":["Lei Chen","Xiaohui Zhong","Feng Zhang","Yuan Cheng","Yinghui Xu","Yuan Qi","Hao Li"],"date":"2023-06-22","year":2023,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"arxiv":"2306.12873","doi":"10.1038/s41612-023-00512-1","openalex":"W4388728292"},"links":{"paper":"https://arxiv.org/abs/2306.12873","pdf":"https://arxiv.org/pdf/2306.12873"},"orgs":["fudan-university"],"topic":"global-medium-range","topics":["probabilistic-ensembles"],"type":"model","method":["transformer","cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"FuXi is a cascaded ML system giving 15-day global forecasts at 0.25 degrees, the first ML model to match the ECMWF ensemble mean at 15 days.","significance":8,"cited_by":360,"score":77,"highlight":true,"highlight_reason":"FuXi's cascaded design was the first ML system to match ECMWF ensemble mean skill at 15 days, and it became a key model.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-urbansci7030068","title":"Weather Forecasting Using Radial Basis Function Neural Network in Warangal, India","authors":["Venkataramana Veeramsetty","Prabhu Kiran","Munjampally Sushma","Surender Reddy Salkuti"],"date":"2023-06-21","year":2023,"venue":"Urban Science","venue_type":"journal","ids":{"doi":"10.3390/urbansci7030068","openalex":"W4381684843"},"links":{"paper":"https://doi.org/10.3390/urbansci7030068","pdf":"https://www.mdpi.com/2413-8851/7/3/68/pdf?version=1687340265"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Radial basis function neural network forecasts temperature and humidity in Warangal, India, from one year of station data and outperforms other ML models.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23135785","title":"LSTMAtU-Net: A Precipitation Nowcasting Model Based on ECSA Module","authors":["Huantong Geng","Xiaoyan Ge","Boyang Xie","Jinzhong Min","Xiaoran Zhuang"],"date":"2023-06-21","year":2023,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23135785","openalex":"W4381617817"},"links":{"paper":"https://doi.org/10.3390/s23135785","pdf":"https://www.mdpi.com/1424-8220/23/13/5785/pdf?version=1687655333"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"LSTMAtU-Net combines ConvLSTM with U-Net and an attention module to improve 0-2 hour radar precipitation nowcasts, especially for medium and high intensities.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14071057","title":"Comparison of Bias Correction Methods for Summertime Daily Rainfall in South Korea Using Quantile Mapping and Machine Learning Model","authors":["Ga‐Yeong Seo","Joong‐Bae Ahn"],"date":"2023-06-21","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14071057","openalex":"W4381687522"},"links":{"paper":"https://doi.org/10.3390/atmos14071057","pdf":"https://www.mdpi.com/2073-4433/14/7/1057/pdf?version=1687763892"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["rnn"],"timescale":[],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Compares quantile mapping with an LSTM bias correction of WRF summer rainfall over South Korea; LSTM best tracks interannual variability, but underestimates rain above 50 mm/day.","significance":3,"cited_by":33,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-3072958-v1","title":"Semantic Segmentation of Cloud Images captured with Horizon-Oriented Cameras for Nowcasting Applications","authors":["Bruno Juncklaus Martins","Juliana Marian Arrais","Allan Cerentini","Sylvio Luiz Mantelli Neto","Gilberto Perello Ricci Neto","Aldo von Wangenheim"],"date":"2023-06-21","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-3072958/v1","openalex":"W4381615565"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-3072958/v1","pdf":"https://www.researchsquare.com/article/rs-3072958/latest.pdf"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"U-Net with ResNet18 segments clouds in horizon-facing sky images with IoU 0.6, aimed at short-term cloud motion and solar power nowcasting.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20944-preprints202306.1492.v1","title":"Downscaling Seasonal Weather Forecasting with Generative Adversarial Networks","authors":["Georgios Gousios","Theano Mamouka","Paraskevi Vourlioti","Stylianos Kotsopoulos"],"date":"2023-06-21","year":2023,"venue":"Preprints.org","venue_type":"preprint","ids":{"doi":"10.20944/preprints202306.1492.v1","openalex":"W4381948702"},"links":{"paper":"https://doi.org/10.20944/preprints202306.1492.v1","pdf":"https://www.preprints.org/manuscript/202306.1492/v1/download"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"A GAN combined with a digital elevation model downscales seasonal temperature forecasts from 1° to 0.1° over Greece, with some over- and underestimation.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022jd038321","title":"Six Hundred Years of Reconstructed Atmospheric River Activity Along the US West Coast","authors":["Swatah Snigdha Borkotoky","Park Williams","Scott Steinschneider"],"date":"2023-06-21","year":2023,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2022jd038321","openalex":"W4381513400"},"links":{"paper":"https://doi.org/10.1029/2022jd038321","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022JD038321"},"orgs":["columbia-leap","ucla"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Neural networks classify US West Coast atmospheric river landfalls back to 1916, and tree-ring regression extends annual AR counts to 1400 CE.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-3407-2023","title":"SMLFire1.0: a stochastic machine learning (SML) model for wildfire activity in the western United States","authors":["Jatan Buch","Park Williams","Caroline S. Juang","Winslow D. Hansen","Pierre Gentine"],"date":"2023-06-19","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-3407-2023","openalex":"W4381165955"},"links":{"paper":"https://doi.org/10.5194/gmd-16-3407-2023"},"orgs":["columbia-leap","ucla"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Mixture density networks model monthly wildfire frequency and area burned across the western US, matching annual area burned with r = 0.85 observed.","significance":3,"cited_by":28,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-023-04532-y","title":"Statistical downscaling and projection of climatic extremes using machine learning algorithms","authors":["Junaid Maqsood","Hassan Afzaal","Aitazaz A. Farooque","Farhat Abbas","Xander Wang","Travis J. Esau"],"date":"2023-06-19","year":2023,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-023-04532-y","openalex":"W4381188755"},"links":{"paper":"https://doi.org/10.1007/s00704-023-04532-y"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Statistically downscales and projects climatic extremes using machine learning algorithms; abstract unavailable, so scope is inferred from the title.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.11161","title":"Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research","authors":["Chace Ashcraft","Jennifer Sleeman","Caroline Tang","Jay Brett","Anand Gnanadesikan"],"date":"2023-06-19","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.11161","openalex":"W4381573093"},"links":{"paper":"https://arxiv.org/abs/2306.11161","pdf":"https://arxiv.org/pdf/2306.11161"},"orgs":[],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Neuro-symbolic encoder-decoder translates climate questions into programs to direct deep learning simulations of AMOC tipping, aiming at explainability.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.11159","title":"A labeled dataset of cloud types using data from GOES-16 and CloudSat","authors":["Paula V. Romero Jure","Sergio Masuelli","Juan Bautista Cabral"],"date":"2023-06-19","year":2023,"venue":"2022 IEEE Biennial Congress of Argentina (ARGENCON), 2022, pp. 1-6","venue_type":"journal","ids":{"arxiv":"2306.11159","doi":"10.1109/argencon55245.2022.9940053"},"links":{"paper":"https://arxiv.org/abs/2306.11159","pdf":"https://arxiv.org/pdf/2306.11159"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A dataset pairs GOES-16 ABI multiband images with CloudSat cloud-type labels over South America, enabling supervised cloud classification with a simple neural network.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.11144","title":"Evaluating Loss Functions and Learning Data Pre-Processing for Climate Downscaling Deep Learning Models","authors":["Xingying Huang"],"date":"2023-06-19","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.11144","openalex":"W4381573060"},"links":{"paper":"https://arxiv.org/abs/2306.11144","pdf":"https://arxiv.org/pdf/2306.11144"},"orgs":["ncar"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"L2 loss outperforms L1 for imbalanced precipitation downscaling, and a learned nonlinear pre-processing function further improves accuracy in climate downscaling networks.","significance":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.10940","title":"TeleViT: Teleconnection-driven Transformers Improve Subseasonal to Seasonal Wildfire Forecasting","authors":["Ioannis Prapas","Nikolaos Ioannis Bountos","Spyros Kondylatos","Dimitrios Michail","Gustau Camps-Valls","Ioannis Papoutsis"],"date":"2023-06-19","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.10940"},"links":{"paper":"https://arxiv.org/abs/2306.10940","pdf":"https://arxiv.org/pdf/2306.10940","code":"https://github.com/Orion-Ai-Lab/TeleViT"},"orgs":[],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["transformer"],"timescale":["s2s"],"spatial":["global"],"data":["other"],"status":"research","summary":"Teleconnection-driven vision transformer forecasts global burned area up to four months ahead, with gains growing at longer lead times using climate indices.","significance":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.10619","title":"Towards Stability of Autoregressive Neural Operators","authors":["Michael McCabe","Peter Harrington","Shashank Subramanian","Jed Brown"],"date":"2023-06-18","year":2023,"venue":"Transactions on Machine Learning Research. November 2023","venue_type":"journal","ids":{"arxiv":"2306.10619","openalex":"W4381564169"},"links":{"paper":"https://arxiv.org/abs/2306.10619","pdf":"https://arxiv.org/pdf/2306.10619","code":"https://github.com/mikemccabe210/stabilizing_neural_operators"},"orgs":[],"topic":"xai-uq-physics","topics":["global-medium-range"],"type":"model","method":["neural-operator"],"timescale":["medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Architectural fixes to neural operators curb autoregressive error growth, giving lower long-horizon errors on Navier-Stokes, shallow water and a global weather forecasting system.","significance":4,"cited_by":2,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.10443","title":"Convolutional GRU Network for Seasonal Prediction of the El Niño-Southern Oscillation","authors":["Lingda Wang","Savana Ammons","Vera Mikyoung Hur","Ryan L. Sriver","Zhizhen Zhao"],"date":"2023-06-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.10443","openalex":"W4381552834"},"links":{"paper":"https://arxiv.org/abs/2306.10443","pdf":"https://arxiv.org/pdf/2306.10443"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A convolutional GRU encoder-decoder forecasts ENSO-region SST maps and the Niño 3.4 index, beating LIM, analog and RNN baselines in correlation, RMSE and useful prediction range on climate model data.","significance":4,"cited_by":2,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-023-06854-z","title":"Tendency-and-attention-informed deep learning for ENSO forecasts","authors":["Shen Qiao","Cuicui Zhang","Xuefeng Zhang","Kai Zhang","Hao Shan Shi","Sheng Li","Wei Hao"],"date":"2023-06-17","year":2023,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-023-06854-z","openalex":"W4380904986"},"links":{"paper":"https://doi.org/10.1007/s00382-023-06854-z","pdf":"https://www.researchsquare.com/article/rs-1733575/latest.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["transformer"],"timescale":["seasonal"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"Deep learning model combining tendency and attention mechanisms for ENSO forecasts; the abstract is missing, so skill figures are unavailable.","significance":4,"cited_by":7,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2308.06265","title":"Long-term Effects of Temperature Variations on Economic Growth: A Machine Learning Approach","authors":["Eugene Kharitonov","Oksana Zakharchuk","Lin Mei"],"date":"2023-06-17","year":2023,"venue_type":"preprint","ids":{"arxiv":"2308.06265"},"links":{"paper":"https://arxiv.org/abs/2308.06265","pdf":"https://arxiv.org/pdf/2308.06265"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["stations","other"],"status":"research","summary":"Machine learning on Berkeley Earth temperatures and World Bank GDP finds a significant relationship between average temperature and long-term GDP growth.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su15129668","title":"General Circulation Model Downscaling Using Interpolation—Machine Learning Model Combination—Case Study: Thailand","authors":["Chotirose Prathom","Paskorn Champrasert"],"date":"2023-06-16","year":2023,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su15129668","openalex":"W4380990630"},"links":{"paper":"https://doi.org/10.3390/su15129668","pdf":"https://www.mdpi.com/2071-1050/15/12/9668/pdf?version=1686913455"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional","local"],"data":["cmip","stations"],"status":"research","summary":"IDW-ANN combines interpolation with a neural network to downscale IPSL GCM temperature and precipitation to 1 km over Thailand under SSP scenarios.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15123138","title":"Weather Radar Echo Extrapolation with Dynamic Weight Loss","authors":["Yonghong Zhang","Sutong Geng","Wei Tian","Guangyi Ma","Huajun Zhao","Donglin Xie","Huanyu Lu","Kenny Thiam Choy Lim Kam Sian"],"date":"2023-06-15","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15123138","openalex":"W4380882504"},"links":{"paper":"https://doi.org/10.3390/rs15123138","pdf":"https://www.mdpi.com/2072-4292/15/12/3138/pdf?version=1686842524"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","physics-constrained"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Dynamic weight loss function added to ConvLSTM, ConvGRU, PredRNN and PredRNN++ reduces radar echo extrapolation MAE by up to 14.8% over 1 hour.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.eswa.2023.120701","title":"A context-aware hybrid deep learning model for the prediction of tropical cyclone trajectories","authors":["Sahar Farmanifard","Ali Asghar Alesheikh","Mohammad Sharif"],"date":"2023-06-15","year":2023,"venue":"Expert Systems with Applications","venue_type":"journal","ids":{"doi":"10.1016/j.eswa.2023.120701","openalex":"W4380742754"},"links":{"paper":"https://doi.org/10.1016/j.eswa.2023.120701"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Proposes a context-aware hybrid deep learning model for tropical cyclone track prediction; the abstract is missing, so results are unverified.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1364-oe.493818","title":"Physics constraint Deep Learning based radiative transfer model","authors":["Quanhua Liu","Xingming Liang"],"date":"2023-06-14","year":2023,"venue":"Optics Express","venue_type":"journal","ids":{"doi":"10.1364/oe.493818","openalex":"W4380627205"},"links":{"paper":"https://doi.org/10.1364/oe.493818"},"orgs":["noaa"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A physics-constrained deep learning radiative transfer model over oceans recovers correct Jacobians, enabling radiance sensitivities for satellite data assimilation.","significance":3,"cited_by":11,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0086.1","title":"A Review of Recent and Emerging Machine Learning Applications for Climate Variability and Weather Phenomena","authors":["María J. Molina","Travis Allen O'Brien","Gemma J. Anderson","Moetasim Ashfaq","Katrina E. Bennett","William D. Collins","Katherine Dagon","Juan Mario Restrepo","Paul Aaron Ullrich"],"date":"2023-06-14","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0086.1","openalex":"W4380611288"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0086.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/4/AIES-D-22-0086.1.pdf"},"orgs":["ncar","uc-berkeley","lbnl-nersc","ornl"],"topic":"climate-analysis-attribution","topics":["extremes-hazards","downscaling"],"type":"review","method":[],"timescale":[],"spatial":["global","regional"],"data":[],"status":"research","summary":"Review of ML for climate variability modes, extreme weather precursors, observation-model integration, downscaling and bias correction, aimed at domain scientists.","significance":4,"cited_by":51,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022jd038365","title":"Using Machine Learning With Partial Dependence Analysis to Investigate Coupling Between Soil Moisture and Near‐Surface Temperature","authors":["Jared T. Trok","Frances V. Davenport","Elizabeth A. Barnes","Noah S. Diffenbaugh"],"date":"2023-06-14","year":2023,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2022jd038365","openalex":"W4380442531"},"links":{"paper":"https://doi.org/10.1029/2022jd038365"},"orgs":["stanford","colorado-state-university"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"CNNs with partial dependence analysis reveal nonlinear soil moisture–temperature coupling across mid-latitude regions using reanalysis data.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.47672-ejt.1496","title":"AI Based Real-Time Weather Condition Prediction with Optimized Agricultural Resources","authors":["Nyakuri Pierre","Ishimwe Viviane","Uwimana Lambert","Ishimwe Viviane","Irakora Shadrack","Bakunzi Erneste","Nshimyumuremyi Schadrack","Ntawukuriryayo Alexis","Karanguza Francois","Habiyaremye Theogene"],"date":"2023-06-12","year":2023,"venue":"European Journal of Technology","venue_type":"journal","ids":{"doi":"10.47672/ejt.1496","openalex":"W4380358438"},"links":{"paper":"https://doi.org/10.47672/ejt.1496","pdf":"https://ajpojournals.org/journals/index.php/EJT/article/download/1496/1619"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"IoT and fuzzy-logic system predicts 24-hour farm rainfall from sensors and cut water use 55% in a two-hectare maize trial; ML role is modest.","significance":1,"cited_by":34,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.34753-hs.2022.3.230","title":"Experience of release of an avalanche bulletin for the mountain region of Ile Alatau","authors":["Viktor Blagovechshenskiy","V. V. Zhdanov","Tamara Gulyayeva"],"date":"2023-06-12","year":2023,"venue":"Гидросфера. Опасные процессы и явления.","venue_type":"journal","ids":{"doi":"10.34753/hs.2022.3.230","openalex":"W4400776403"},"links":{"paper":"https://doi.org/10.34753/hs.2022.3.230"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"operational","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"pre-operational","summary":"Kazakhstan avalanche bulletin uses a trained neural network on mountain weather station data, reaching 84-90% danger-level classification accuracy.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15123065","title":"Radar Echo Reconstruction in Oceanic Area via Deep Learning of Satellite Data","authors":["Xiaoqi Yu","Xiao Lou","Yan Yan","Zhongwei Yan","Wencong Cheng","Zhibin Wang","Deming Zhao","Jiangjiang Xia"],"date":"2023-06-12","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15123065","openalex":"W4380628757"},"links":{"paper":"https://doi.org/10.3390/rs15123065","pdf":"https://www.mdpi.com/2072-4292/15/12/3065/pdf?version=1686555771"},"orgs":["iap-cas","alibaba-damo"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"A U-Net reconstructs radar composite reflectivity over the ocean from satellite data, with interpretability showing cloud features matter most.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022jd037041","title":"A Deep‐Learning Ensemble Method to Detect Atmospheric Rivers and Its Application to Projected Changes in Precipitation Regime","authors":["Yuan Tian","Yang Zhao","Seok‐Woo Son","Jing‐Jia Luo","Seok‐Geun Oh","Yinjun Wang"],"date":"2023-06-10","year":2023,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2022jd037041","openalex":"W4380154462"},"links":{"paper":"https://doi.org/10.1029/2022jd037041","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022JD037041"},"orgs":["nuist","cma"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"An ensemble of 20 segmentation networks detects atmospheric rivers with 1.7–10.1% higher IoU; CMIP6 projections show AR-driven extreme precipitation rising under SSP5-8.5.","significance":4,"cited_by":77,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.scitotenv.2023.164734","title":"A novel artificial neural network methodology to produce high-resolution bioclimatic maps using Earth Observation data: A case study for Cyprus","authors":["Kostas Philippopoulos","Katerina G. Pantavou","Constantinos Cartalis","Ilias Agathangelidis","Thaleia Mavrakou","Anastasios Polydoros","Georgios K. Nikolopoulos"],"date":"2023-06-10","year":2023,"venue":"The Science of The Total Environment","venue_type":"journal","ids":{"doi":"10.1016/j.scitotenv.2023.164734","openalex":"W4380154103"},"links":{"paper":"https://doi.org/10.1016/j.scitotenv.2023.164734"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Uses an artificial neural network with Earth observation data to produce high-resolution bioclimatic maps for Cyprus; abstract unavailable, so scope is inferred from the title.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.06269","title":"DeepLCZChange: A Remote Sensing Deep Learning Model Architecture for Urban Climate Resilience","authors":["Wenlu Sun","Yao Sun","Chenying Liu","Conrad M Albrecht"],"date":"2023-06-09","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.06269"},"links":{"paper":"https://arxiv.org/abs/2306.06269","pdf":"https://arxiv.org/pdf/2306.06269"},"orgs":[],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"DeepLCZChange links airborne LiDAR urban structure to Landsat 8 surface temperature in New York, showing a cooling effect of urban forests.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15122171","title":"Spatio-Temporal Characteristics and Trend Prediction of Extreme Precipitation—Taking the Dongjiang River Basin as an Example","authors":["Ningning Li","Xiaohong Chen","Jing Qiu","Wenhui Li","Bikui Zhao"],"date":"2023-06-08","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15122171","openalex":"W4379988175"},"links":{"paper":"https://doi.org/10.3390/w15122171","pdf":"https://www.mdpi.com/2073-4441/15/12/2171/pdf?version=1686229391"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Analyzes 1979–2022 Dongjiang basin extreme precipitation trends and uses a BP neural network to simulate and predict them.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su15129289","title":"Prediction of Daily Temperature Based on the Robust Machine Learning Algorithms","authors":["Li Yu","Tongfei Li","Wei Lv","Zhiyao Liang","Junxian Wang"],"date":"2023-06-08","year":2023,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su15129289","openalex":"W4380083550"},"links":{"paper":"https://doi.org/10.3390/su15129289","pdf":"https://www.mdpi.com/2071-1050/15/12/9289/pdf?version=1686219260"},"orgs":["alibaba-damo"],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM and deep LSTM models forecast daily air temperature in Tabriz, Iran, from 1,097 observations, with the deep version reaching RMSE 0.08 °C.","significance":1,"cited_by":7,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.05420","title":"Scaling Spherical CNNs","authors":["Carlos Esteves","Jean-Jacques Slotine","Ameesh Makadia"],"date":"2023-06-08","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.05420","openalex":"W4380137121"},"links":{"paper":"https://arxiv.org/abs/2306.05420","pdf":"https://arxiv.org/pdf/2306.05420","code":"https://github.com/google-research/spherical-cnn"},"orgs":[],"topic":"global-medium-range","topics":["benchmarks-data-eval"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Scales spherical CNNs to large problems, reaching state of the art on QM9 and competitive results on several weather forecasting tasks; weather is a secondary target.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.05144","title":"Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean","authors":["Spyros Kondylatos","Ioannis Prapas","Gustau Camps-Valls","Ioannis Papoutsis"],"date":"2023-06-08","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.05144"},"links":{"paper":"https://arxiv.org/abs/2306.05144","pdf":"https://arxiv.org/pdf/2306.05144"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"benchmark","method":[],"timescale":["short"],"spatial":["regional"],"data":["era5","satellite","other"],"status":"research","summary":"Mesogeos is a 1 km daily Mediterranean wildfire datacube with meteorology and ignition records, plus ML tracks for danger forecasting and burned-area estimation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.05045","title":"Spain on Fire: A novel wildfire risk assessment model based on image satellite processing and atmospheric information","authors":["Helena Liz-López","Javier Huertas-Tato","Jorge Pérez-Aracil","Carlos Casanova-Mateo","Julia Sanz-Justo","David Camacho"],"date":"2023-06-08","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.05045"},"links":{"paper":"https://arxiv.org/abs/2306.05045","pdf":"https://arxiv.org/pdf/2306.05045"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"Wildfire Assessment Model uses a self-supervised CNN on atmospheric and greenness variables to estimate resources and burned area in Spain, improving baselines by up to 21%.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.18517-ijaseit.13.3.18377","title":"GRU and XGBoost Performance with Hyperparameter Tuning Using GridSearchCV and Bayesian Optimization on an IoT-Based Weather Prediction System","authors":["Hendri Darmawan","Mike Yuliana","Moch. Zen Samsono Hadi"],"date":"2023-06-07","year":2023,"venue":"International Journal on Advanced Science Engineering and Information Technology","venue_type":"journal","ids":{"doi":"10.18517/ijaseit.13.3.18377","openalex":"W4382700644"},"links":{"paper":"https://doi.org/10.18517/ijaseit.13.3.18377","pdf":"http://www.insightsociety.org/ojaseit/index.php/ijaseit/article/download/18377/3734"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"GRU and XGBoost, tuned and deployed on an IoT weather station, forecast local sensor readings and four-day rain; XGBoost wins regression, GRU wins classification.","significance":2,"cited_by":37,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tste.2023.3283242","title":"A Hybrid Model for Long-Term Wind Power Forecasting Utilizing NWP Subsequence Correction and Multi-Scale Deep Learning Regression Methods","authors":["Yu Chang","Han Yang","Yuxi Chen","Mingrui Zhou","Huabin Yang","Yan Wang","Yanru Zhang"],"date":"2023-06-07","year":2023,"venue":"IEEE Transactions on Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1109/tste.2023.3283242","openalex":"W4379528680"},"links":{"paper":"https://doi.org/10.1109/tste.2023.3283242"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Hybrid model corrects NWP wind speed with multi-scale deep learning for seven-day wind power forecasts, cutting MSE by 65% versus a state-of-the-art baseline.","significance":2,"cited_by":62,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asr.2023.05.057","title":"Downscaling of GPM satellite precipitation products based on machine learning method in complex terrain and limited observation area","authors":["Hao Wang","Zhi Li","Tao Zhang","Qingqing Chen","Xu Guo","Qiangyu Zeng","Jie Xiang"],"date":"2023-06-07","year":2023,"venue":"Advances in Space Research","venue_type":"journal","ids":{"doi":"10.1016/j.asr.2023.05.057","openalex":"W4379795797"},"links":{"paper":"https://doi.org/10.1016/j.asr.2023.05.057"},"orgs":["cma"],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Downscales GPM satellite precipitation from 0.1° to 1 km using a BP neural network with terrain and vegetation predictors, improving accuracy in complex terrain with sparse gauges.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40808-023-01799-y","title":"Trend analysis and forecasting of meteorological variables in the lower Thoubal river watershed, India using non-parametrical approach and machine learning models","authors":["Md Hibjur Rahaman","Tamal Kanti Saha","Md Masroor","Roshani","Haroon Sajjad"],"date":"2023-06-07","year":2023,"venue":"Modeling Earth Systems and Environment","venue_type":"journal","ids":{"doi":"10.1007/s40808-023-01799-y","openalex":"W4379619248"},"links":{"paper":"https://doi.org/10.1007/s40808-023-01799-y"},"orgs":[],"topic":"local-forecasting","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Non-parametric trend tests and machine learning models analyze and forecast meteorological variables in the Thoubal river watershed, India; the abstract is missing.","significance":2,"cited_by":40,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.07291","title":"An Ensemble Machine Learning Approach for Tropical Cyclone Detection Using ERA5 Reanalysis Data","authors":["Gabriele Accarino","Davide Donno","Francesco Immorlano","Donatello Elia","Giovanni Aloisio"],"date":"2023-06-07","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.07291","doi":"10.1029/2023ea003106"},"links":{"paper":"https://arxiv.org/abs/2306.07291","pdf":"https://arxiv.org/pdf/2306.07291"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"An ensemble of ML models trained on ERA5 jointly classifies and localizes tropical cyclone centres, detecting lower categories than those in training with improved localization over single models.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-23-0007.1","title":"Surrogate Downscaling of Mesoscale Wind Fields Using Ensemble Superresolution Convolutional Neural Networks","authors":["Tsuyoshi Thomas Sekiyama","Syugo Hayashi","Ryo Kaneko","Ken–ichi Fukui"],"date":"2023-06-06","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-23-0007.1","openalex":"W4379521063"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0007.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/aies/2/3/AIES-D-23-0007.1.pdf"},"orgs":["jma"],"topic":"downscaling","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"A 20-member SRCNN ensemble downscales 5 km surface winds to 1 km around Tokyo, with the ensemble mean beating the input winds all year.","significance":2,"cited_by":12,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.06079","title":"Deep Learning for Day Forecasts from Sparse Observations","authors":["Marcin Andrychowicz","Lasse Espeholt","Di Li","Samier Merchant","Alexander Merose","Fred Zyda","Shreya Agrawal","Nal Kalchbrenner"],"date":"2023-06-06","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.06079","openalex":"W4380551082"},"links":{"paper":"https://arxiv.org/abs/2306.06079","pdf":"https://arxiv.org/pdf/2306.06079"},"orgs":["google-research"],"topic":"nowcasting","topics":["data-assimilation"],"type":"model","method":["transformer","other"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["stations","radar","satellite","nwp-analysis"],"status":"operational","summary":"MetNet-3 learns from sparse and dense sensors to forecast precipitation, wind, temperature and dew point up to 24 hours ahead, beating HRRR and ENS over CONUS and running in Google Search.","significance":7,"cited_by":43,"score":73,"highlight":true,"highlight_reason":"MetNet-3 is an observation-trained regional model beating HRRR and ENS to 24h for multiple variables, and it was deployed in Google products.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2306.03838","title":"Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere","authors":["Boris Bonev","Thorsten Kurth","Christian Hundt","Jaideep Pathak","Maximilian Baust","Karthik Kashinath","Anima Anandkumar"],"date":"2023-06-06","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.03838","openalex":"W4379925125"},"links":{"paper":"https://arxiv.org/abs/2306.03838","pdf":"https://arxiv.org/pdf/2306.03838"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["neural-operator"],"timescale":["medium","climate"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Spherical Fourier Neural Operators avoid planar FFT artifacts and give stable year-long autoregressive atmospheric rollouts (1,460 steps) on the sphere.","significance":7,"cited_by":46,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos14060980","title":"Research on Radar Echo Extrapolation Method by Fusing Environment Grid Point Field Information","authors":["Yanqin Wen","Jun Zhang","Di Wang","Cong Wang","Ping Wang"],"date":"2023-06-05","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14060980","openalex":"W4379519001"},"links":{"paper":"https://doi.org/10.3390/atmos14060980","pdf":"https://www.mdpi.com/2073-4433/14/6/980/pdf?version=1685957233"},"orgs":[],"topic":"nowcasting","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","other"],"status":"research","summary":"A 3D CNN that fuses environmental grid fields with radar echoes raises CSI by 3.42% at 40 dBZ for convective extrapolation.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0072.1","title":"Machine Learning–Based Cloud Forecast Corrections for Fusions of Numerical Weather Prediction Model and Satellite Data","authors":["Chuyen Nguyen","Jason E. Nachamkin","David Sidoti","Jacob Gull","Adam Bienkowski","R. Bankert","Melinda L. Surratt"],"date":"2023-06-05","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0072.1","openalex":"W4379383811"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0072.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/aies/2/3/AIES-D-22-0072.1.pdf"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"UNet CNN fuses GOES-16 cloud observations with COAMPS forecasts to correct high-cloud forecasts at 3-12 h lead times, improving accuracy and sensitivity.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0062.1","title":"ARMing the Edge: Designing Edge Computing–Capable Machine Learning Algorithms to Target ARM Doppler Lidar Processing","authors":["Robert C. Jackson","Bhupendra Raut","Darío Demattíes","Scott Collis","Nicola Ferrier","Pete Beckman","Rajesh Sankaran","Yongho Kim","Seongha Park","Sean Shahkarami","Rob Newsom"],"date":"2023-06-05","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0062.1","openalex":"W4379389532"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0062.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/aies/2/4/AIES-D-22-0062.1.pdf"},"orgs":["argonne"],"topic":"observations-remote-sensing","topics":["infra-software"],"type":"application","method":["cnn","classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"ResNet50 classifier on an edge device classifies ARM Doppler lidar cloud and clear-air images with 97.6% and 94.7% accuracy.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-20964471.2023.2217576","title":"Generating high-resolution climate maps from sparse and irregular observations using a novel hybrid RBF network","authors":["Yue Han","Zhihua Zhang","M. James C. Crabbe"],"date":"2023-06-04","year":2023,"venue":"Big Earth Data","venue_type":"journal","ids":{"doi":"10.1080/20964471.2023.2217576","openalex":"W4379386436"},"links":{"paper":"https://doi.org/10.1080/20964471.2023.2217576","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/20964471.2023.2217576?needAccess=true&role=button"},"orgs":["university-of-oxford"],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"A hybrid RBF network downscales sparse station data into high-resolution precipitation, temperature and humidity maps for Bangladesh, outperforming MLR and kriging.","significance":3,"cited_by":0,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s41060-023-00397-6","title":"Downscaling daily wind speed with Bayesian deep learning for climate monitoring","authors":["Firas Gerges","Michel C. Boufadel","Elie R. Bou-Zeid","Hani H. Nassif","Jason T. L. Wang"],"date":"2023-06-04","year":2023,"venue":"International Journal of Data Science and Analytics","venue_type":"journal","ids":{"doi":"10.1007/s41060-023-00397-6","openalex":"W4379284926"},"links":{"paper":"https://doi.org/10.1007/s41060-023-00397-6","pdf":"https://www.researchsquare.com/article/rs-1999403/latest.pdf"},"orgs":["princeton-university"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":[],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Bayesian deep learning downscales daily wind speed for climate monitoring; the abstract is missing, so the scope is inferred from the title.","significance":2,"cited_by":13,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.168565419.96137434-v1","title":"Quantifying “climate distinguishability” after stratospheric aerosol injection using explainable artificial intelligence","authors":["Antonios Mamalakis","Elizabeth A. Barnes","James Wilson Hurrell"],"date":"2023-06-01","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.22541/essoar.168565419.96137434/v1","openalex":"W4378978926"},"links":{"paper":"https://doi.org/10.1029/2023gl106137","pdf":"https://www.authorea.com/doi/pdf/10.22541/essoar.168565419.96137434"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"application","method":["classical-ml","other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Explainable neural networks trained on Earth system model output quantify climate distinguishability after stratospheric aerosol injection, showing slower change under SAI.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tla.2023.10172135","title":"A GMDH Approach for Forecast Monthly Rainfall in Southeast of Para","authors":["Elton Rafael Alves","Márcio Nirlando Gomes Lopes","Fabricio Sales","Andson Balieiro","Adonis F. R. Leal"],"date":"2023-06-01","year":2023,"venue":"IEEE Latin America Transactions","venue_type":"journal","ids":{"doi":"10.1109/tla.2023.10172135","openalex":"W4382935733"},"links":{"paper":"https://doi.org/10.1109/tla.2023.10172135"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"GMDH model using lagged sea surface temperature predicts monthly rainfall in Pará, Brazil, with R 0.96 versus 0.82 for a multilayer perceptron.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003395","title":"Probing the Skill of Random Forest Emulators for Physical Parameterizations Via a Hierarchy of Simple CAM6 Configurations","authors":["Garrett C Limon","Christiane Jablonowski"],"date":"2023-06-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003395","openalex":"W4379744232"},"links":{"paper":"https://doi.org/10.1029/2022ms003395","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003395"},"orgs":[],"topic":"hybrid-parameterization","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["km-scale-sim","other"],"status":"research","summary":"Random forest emulators of CAM6 physics skill declines as model complexity rises across dry, moist, and extra-convection configurations, indicating limits for RF physics emulation.","significance":4,"cited_by":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.01112","title":"Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context","authors":["Oussama Boussif","Ghait Boukachab","Dan Assouline","Stefano Massaroli","Tianle Yuan","Loubna Benabbou","Yoshua Bengio"],"date":"2023-06-01","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.01112"},"links":{"paper":"https://arxiv.org/abs/2306.01112","pdf":"https://arxiv.org/pdf/2306.01112"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"A deep network combining satellite imagery with station series improves day-ahead solar irradiance forecasts and outputs per-step distributions, with zero-shot tests at unseen stations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46670-jsst.2023.32.3.164","title":"Development of a Weather Prediction Device Using Transformer Models and IoT Techniques","authors":["Iyapo Kamoru Olarewaju","Kyung Ki Kim"],"date":"2023-05-31","year":2023,"venue":"Journal of Sensor Science and Technology","venue_type":"journal","ids":{"doi":"10.46670/jsst.2023.32.3.164","openalex":"W4380538390"},"links":{"paper":"https://doi.org/10.46670/jsst.2023.32.3.164"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["transformer"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Describes an IoT weather prediction device built on transformer models; the abstract is missing, so results cannot be verified.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21776-ub.pengairan.2023.014.01.3","title":"Assessment of Drought Disasters (EDI) Based on ENSO and NOAA Climate Data Using ANN in Bondowoso Regency","authors":["Evid Zulhaqi","Gusfan Halik","Retno Utami Agung Wiyono"],"date":"2023-05-31","year":2023,"venue":"Jurnal Teknik Pengairan","venue_type":"journal","ids":{"doi":"10.21776/ub.pengairan.2023.014.01.3","openalex":"W4386640874"},"links":{"paper":"https://doi.org/10.21776/ub.pengairan.2023.014.01.3","pdf":"https://jurnalpengairan.ub.ac.id/index.php/jtp/article/download/670/424"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local","regional"],"data":["stations","other"],"status":"research","summary":"Backpropagation ANN statistically downscales ENSO and NOAA indices to monthly rainfall in Bondowoso, Indonesia, to drive EDI drought assessment with R2 of 0.97.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14445-23488549-ijece-v10i5p111","title":"Machine Learning based Predictive Assessments of Impacts of Influential Climatic Conditions for the Sustainable Productivity of Paddy Crops","authors":["S Thirumal","Latha R"],"date":"2023-05-31","year":2023,"venue":"International Journal of Electronics and Communication Engineering","venue_type":"journal","ids":{"doi":"10.14445/23488549/ijece-v10i5p111","openalex":"W4379535014"},"links":{"paper":"https://doi.org/10.14445/23488549/ijece-v10i5p111","pdf":"https://www.internationaljournalssrg.org/../IJECE/2023/Volume10-Issue5/IJECE-V10I5P111.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Multiplicative LSTM models project climate-change effects on paddy rice production in a region of interest; a regional application with limited methodological novelty.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0052.1","title":"Toward Operational Real-Time Identification of Frontal Boundaries Using Machine Learning","authors":["Andrew D. Justin","Colin Willingham","Amy McGovern","John T. Allen"],"date":"2023-05-31","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0052.1","openalex":"W4378837605"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0052.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/3/AIES-D-22-0052.1.pdf"},"orgs":["university-of-oklahoma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"pre-operational","summary":"Deep learning detects cold, warm, stationary and occluded fronts from ERA5 over the US, reaching CSI 0.60 for cold fronts and 0.71 for front/no-front.","significance":3,"cited_by":13,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3281727","title":"Transformer Aided Construction of a Long-term Tropical Cyclone Concentric Eyewalls Dataset","authors":["Xing Ling Huang","Ping Lu","Bo Zhang","Yanluan Lin","Xiaomeng Huang"],"date":"2023-05-31","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3281727","openalex":"W4378908392"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3281727","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10138781.pdf"},"orgs":["tsinghua-university"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"benchmark","method":["transformer"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Transformer detects concentric eyewalls in passive microwave imagery, producing a 30-year global dataset of 377 events with 92.9% precision and recall.","significance":4,"cited_by":5,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s43762-023-00096-9","title":"DownScaleBench for developing and applying a deep learning based urban climate downscaling- first results for high-resolution urban precipitation climatology over Austin, Texas","authors":["Manmeet Singh","Nachiketa Acharya","Sajad Jamshidi","Junfeng Jiao","Zong‐Liang Yang","Marc Coudert","Zach Baumer","Dev Niyogi"],"date":"2023-05-31","year":2023,"venue":"Computational Urban Science","venue_type":"journal","ids":{"doi":"10.1007/s43762-023-00096-9","openalex":"W4378908373"},"links":{"paper":"https://doi.org/10.1007/s43762-023-00096-9","pdf":"https://link.springer.com/content/pdf/10.1007/s43762-023-00096-9.pdf"},"orgs":["noaa"],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["local","regional"],"data":["satellite","stations"],"status":"research","summary":"DownScaleBench uses an iterative super-resolution CNN to produce 300 m urban precipitation from 10 km GsMAP data over Austin, improving on cubic interpolation.","significance":3,"cited_by":11,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13143-023-00330-8","title":"An Intercomparison of Deep-Learning Methods for Super-Resolution Bias-Correction (SRBC) of Indian Summer Monsoon Rainfall (ISMR) Using CORDEX-SA Simulations","authors":["Deveshwar Singh","Yunsoo Choi","Rijul Dimri","Masoud Ghahremanloo","Arman Pouyaei"],"date":"2023-05-31","year":2023,"venue":"Asia-Pacific Journal of Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s13143-023-00330-8","openalex":"W4378807603"},"links":{"paper":"https://doi.org/10.1007/s13143-023-00330-8"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Intercomparison of deep-learning super-resolution bias-correction methods for Indian summer monsoon rainfall in CORDEX South Asia simulations; the abstract is unavailable, so the classification relies on the title.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.58213-knbqvm64","title":"RainFall Prediction System for Mumbai","authors":["Aditya Nikhade","Rahul Khetale"],"date":"2023-05-30","year":2023,"venue":"Vidhyayana","venue_type":"journal","ids":{"doi":"10.58213/knbqvm64","openalex":"W7214488223"},"links":{"paper":"https://doi.org/10.58213/knbqvm64","pdf":"http://vidhyayanaejournal.org/index.php/journal/article/download/knbqvm64/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A random forest classifier predicts next-day rainfall in Mumbai from five years of local records, with no benchmark against other methods.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14060953","title":"Machine Learning for Fog-and-Low-Stratus Nowcasting from Meteosat SEVIRI Satellite Images","authors":["Driss Bari","Nabila Lasri","Rania Souri","Redouane Lguensat"],"date":"2023-05-30","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14060953","openalex":"W4378907784"},"links":{"paper":"https://doi.org/10.3390/atmos14060953","pdf":"https://www.mdpi.com/2073-4433/14/6/953/pdf?version=1685441821"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"U-Net and ConvLSTM models forecast fog and low stratus over Morocco 5 h ahead from Meteosat SEVIRI, beating optical flow on SSIM.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.18487","title":"Solar Irradiance Anticipative Transformer","authors":["Thomas M. Mercier","Tasmiat Rahman","Amin Sabet"],"date":"2023-05-29","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.18487"},"links":{"paper":"https://arxiv.org/abs/2305.18487","pdf":"https://arxiv.org/pdf/2305.18487"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"An anticipative vision transformer forecasts solar irradiance 15 minutes ahead from sky image sequences, reaching 21.45% forecast skill over smart persistence.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-acp-23-5867-2023","title":"Convective organization and 3D structure of tropical cloud systems deduced from synergistic A-Train observations and machine learning","authors":["Claudia J. Stubenrauch","Giulio Mandorli","Elizabeth Lemaitre"],"date":"2023-05-26","year":2023,"venue":"Atmospheric chemistry and physics","venue_type":"journal","ids":{"doi":"10.5194/acp-23-5867-2023","openalex":"W4378375671"},"links":{"paper":"https://doi.org/10.5194/acp-23-5867-2023","pdf":"https://acp.copernicus.org/articles/23/5867/2023/acp-23-5867-2023.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Neural networks trained on A-Train radar-lidar data add cloud height, layering and rain intensity to tropical cloud systems, enabling convective organization analysis for model evaluation.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2023.479","title":"Seasonal precipitation forecasting for water management in the Kosi Basin, India using large-scale climate predictors","authors":["Manjeet Singh Dhillon","Mohammed Sharif","Henrik Madsen","Flemming Jakobsen"],"date":"2023-05-26","year":2023,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2023.479","openalex":"W4378375212"},"links":{"paper":"https://doi.org/10.2166/wcc.2023.479","pdf":"https://iwaponline.com/jwcc/article-pdf/14/6/1868/1246158/jwc0141868.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Logistic regression on 14 large-scale climate predictors gives tercile seasonal precipitation forecasts for the Kosi Basin at 1–3 month leads.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11269-023-03528-7","title":"Improving Hybrid Models for Precipitation Forecasting by Combining Nonlinear Machine Learning Methods","authors":["Laleh Parviz","Kabir Rasouli","Ali Torabi Haghighi"],"date":"2023-05-26","year":2023,"venue":"Water Resources Management","venue_type":"journal","ids":{"doi":"10.1007/s11269-023-03528-7","openalex":"W4378472646"},"links":{"paper":"https://doi.org/10.1007/s11269-023-03528-7","pdf":"https://link.springer.com/content/pdf/10.1007/s11269-023-03528-7.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Ensembles combining GEP, SVR and GMDH improve hybrid precipitation forecasts at two Iranian stations, with MSE reduced by 67% at Rasht.","significance":2,"cited_by":30,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15680-ijirset.2023.1205500","title":"Innovative Machine Learning Applications in Weather Forecasting and Long-Term Climate Analysis","authors":["Prof. Pankaj Pali","Prof. Saurabh Verma"],"date":"2023-05-25","year":2023,"venue":"International Journal of Innovative Research in Science Engineering and Technology","venue_type":"journal","ids":{"doi":"10.15680/ijirset.2023.1205500","openalex":"W4401784518"},"links":{"paper":"https://doi.org/10.15680/ijirset.2023.1205500","pdf":"http://dx.doi.org/10.15680/ijirset.2023.1205500"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":[],"timescale":["short","climate"],"spatial":[],"data":[],"status":"research","summary":"Review of ML for weather prediction and climate analysis; claims a 97% accuracy model but gives no method detail to verify it.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0057.1","title":"Atmospheric Pattern–Based Predictions of S2S Sea Level Anomalies for Two Selected U.S. Locations","authors":["Cameron C. Lee","Scott Christopher Sheridan","Gregory Dusek","Douglas E. Pirhalla"],"date":"2023-05-25","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0057.1","openalex":"W4378175532"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0057.1"},"orgs":["noaa"],"topic":"s2s-seasonal","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Uses atmospheric circulation patterns as inputs to ANN models (NARX, PLANN) for monthly to 9-month sea level anomaly forecasts, outperforming post-processed NWP and climatology at US sites.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15112717","title":"Retrieval of Atmospheric Temperature Profile from Historical Data and Ground-Based Observations by Using a Machine Learning Algorithm","authors":["Hongkun Wang","Dong Liu","Yingwei Xia","Wanyi Xie","Yiren Wang"],"date":"2023-05-24","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15112717","openalex":"W4378072097"},"links":{"paper":"https://doi.org/10.3390/rs15112717","pdf":"https://www.mdpi.com/2072-4292/15/11/2717/pdf?version=1684905634"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"An MLP-CNN network retrieves atmospheric temperature profiles from ground measurements and historical observations, with low bias and RMSE at all altitudes.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en16114290","title":"Calibration of GFS Solar Irradiation Forecasts: A Case Study in Romania","authors":["Sergiu-Mihai Hategan","Nicoleta Stefu","Marius Paulescu"],"date":"2023-05-24","year":2023,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en16114290","openalex":"W4378228107"},"links":{"paper":"https://doi.org/10.3390/en16114290","pdf":"https://www.mdpi.com/1996-1073/16/11/4290/pdf?version=1684913560"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"An SVR and MLP ensemble calibrates GFS hourly solar irradiation forecasts in Romania, cutting normalized RMSE by about 16% using sky imagery.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-frwa.2023.1178114","title":"Deep learning of model- and reanalysis-based precipitation and pressure mismatches over Europe","authors":["Kaveh Patakchi Yousefi","Stefan J Kollet"],"date":"2023-05-24","year":2023,"venue":"Frontiers in Water","venue_type":"journal","ids":{"doi":"10.3389/frwa.2023.1178114","openalex":"W4377942240"},"links":{"paper":"https://doi.org/10.3389/frwa.2023.1178114"},"orgs":["juelich"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"UNet corrects TSMP European simulation mismatches against COSMO-REA6 for precipitation and pressure, improving RMSE by about 22%.","significance":3,"cited_by":14,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.15325","title":"Statistical post-processing of visibility ensemble forecasts","authors":["Sándor Baran","Mária Lakatos"],"date":"2023-05-24","year":2023,"venue":"Meteorological Applications 30 (2023), 1-18","venue_type":"journal","ids":{"arxiv":"2305.15325","doi":"10.1002/met.2157","openalex":"W4387982683"},"links":{"paper":"https://arxiv.org/abs/2305.15325","pdf":"https://arxiv.org/pdf/2305.15325"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares proportional-odds logistic regression and MLP classifiers for calibrating ECMWF visibility ensembles; POLR generally beats MLP and beats raw ensembles.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.15170","title":"Explaining heatwaves with machine learning","authors":["Sebastian Buschow","Jan Keller","Sabrina Wahl"],"date":"2023-05-24","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.15170","openalex":"W4378474118"},"links":{"paper":"https://arxiv.org/abs/2305.15170","pdf":"https://arxiv.org/pdf/2305.15170"},"orgs":["dwd"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A neural network with Shapley values on ERA5 predictors explains 70% of European heatwave variability, with upper-level geopotential the largest contributor at 27%.","significance":4,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.56726-irjmets39607","title":"PREDICTION OF CROP YIELD & WEATHER FORECASTING IN FARMLAND USING SENSOR DATA","authors":[],"date":"2023-05-23","year":2023,"venue":"International Research Journal of Modernization in Engineering Technology and Science","venue_type":"journal","ids":{"doi":"10.56726/irjmets39607","openalex":"W4377693468"},"links":{"paper":"https://doi.org/10.56726/irjmets39607","pdf":"http://dx.doi.org/10.56726/irjmets39607"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses farmland sensor data and ML to predict crop yield and generate local weather forecasts for farm management decisions.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-2737-2023","title":"CLGAN: a generative adversarial network (GAN)-based video prediction model for precipitation nowcasting","authors":["Yan Ji","Bing Gong","Michael Langguth","Amirpasha Mozaffari","Xiefei Zhi"],"date":"2023-05-23","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-2737-2023","openalex":"W4377821752"},"links":{"paper":"https://doi.org/10.5194/gmd-16-2737-2023","pdf":"https://gmd.copernicus.org/articles/16/2737/2023/gmd-16-2737-2023.pdf"},"orgs":["nuist","juelich"],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"CLGAN, a GAN with U-Net and LSTM generator, improves heavy-precipitation nowcasts up to 2 h over PredRNN-v2 and optical flow baselines.","significance":3,"cited_by":42,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.14452","title":"Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling","authors":["Qidong Yang","Alex Hernandez-Garcia","Paula Harder","Venkatesh Ramesh","Prasanna Sattegeri","Daniela Szwarcman","Campbell D. Watson","David Rolnick"],"date":"2023-05-23","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.14452"},"links":{"paper":"https://arxiv.org/abs/2305.14452","pdf":"https://arxiv.org/pdf/2305.14452"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["neural-operator"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A Fourier neural operator downscales ERA5 climate fields zero-shot to arbitrary unseen resolutions, outperforming CNN and GAN downscaling baselines.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.14244","title":"Federated Prompt Learning for Weather Foundation Models on Devices","authors":["Shengchao Chen","Guodong Long","Tao Shen","Jing Jiang","Chengqi Zhang"],"date":"2023-05-23","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.14244"},"links":{"paper":"https://arxiv.org/abs/2305.14244","pdf":"https://arxiv.org/pdf/2305.14244"},"orgs":[],"topic":"foundation-models","topics":["infra-software"],"type":"model","method":["gnn"],"timescale":["medium"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Federated prompt tuning of a frozen weather foundation model for on-device forecasting, using dynamic graphs to handle heterogeneity and cut communication cost.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-hess-27-1945-2023","title":"Statistical post-processing of precipitation forecasts using circulation classifications and spatiotemporal deep neural networks","authors":["Tuantuan Zhang","Zhongmin Liang","Wentao Li","Jun Wang","Yiming Hu","Binquan Li"],"date":"2023-05-22","year":2023,"venue":"Hydrology and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/hess-27-1945-2023","openalex":"W4377238657"},"links":{"paper":"https://doi.org/10.5194/hess-27-1945-2023","pdf":"https://hess.copernicus.org/articles/27/1945/2023/hess-27-1945-2023.pdf"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn","classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"SOM-CNN-LSTM post-processing of 15-day precipitation forecasts in the Huaihe basin improves correlation by up to 32.3% and reduces RMSE by 26.6%.","significance":3,"cited_by":27,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-22-0217.1","title":"The Development of a Consensus Machine Learning Model for Hurricane Rapid Intensification Forecasts with Hurricane Weather Research and Forecasting (HWRF) Data","authors":["Mu-Chieh Ko","Xiaomin Chen","Miroslav Kubát","Sundararaman Gopalakrishnan"],"date":"2023-05-22","year":2023,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-22-0217.1","openalex":"W4377238622"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0217.1"},"orgs":["noaa"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Consensus of classical ML models on HWRF predictors raises rapid-intensification detection to 56% POD, versus 10–30% for operational models.","significance":4,"cited_by":10,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1117-1.jrs.17.024513","title":"Estimating tropical cyclone intensity using dynamic balance convolutional neural network from satellite imagery","authors":["Wei Tian","Linhong Lai","Xianghua Niu","Xinxin Zhou","Yonghong Zhang","Kenny Thiam Choy Lim Kam Sian"],"date":"2023-05-22","year":2023,"venue":"Journal of Applied Remote Sensing","venue_type":"journal","ids":{"doi":"10.1117/1.jrs.17.024513","openalex":"W4377232877"},"links":{"paper":"https://doi.org/10.1117/1.jrs.17.024513"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Dynamic-balance CNN estimates tropical cyclone intensity from satellite imagery with 8.32 kt RMSE, 35% lower than the Dvorak technique.","significance":4,"cited_by":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-02626667.2023.2215931","title":"Climate change effects on sub-daily precipitation in Spain","authors":["Manuel del Jesús","Javier Díez-Sierra"],"date":"2023-05-19","year":2023,"venue":"Hydrological Sciences Journal","venue_type":"journal","ids":{"doi":"10.1080/02626667.2023.2215931","openalex":"W4377096006"},"links":{"paper":"https://doi.org/10.1080/02626667.2023.2215931","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/02626667.2023.2215931?download=true"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Machine-learning downscaling of CORDEX projections to hourly rainfall over Spain projects intensified sub-daily extremes and 100-year events, increasing flash flood risk.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.inpa.2023.05.001","title":"Simulation and forecasting of fishery weather based on statistical machine learning","authors":["Xueqian Fu","Chunyu Zhang","Fuhao Chang","Lingling Han","Xiaolong Zhao","Zhengjie Wang","Qiaoyu Ma"],"date":"2023-05-19","year":2023,"venue":"Information Processing in Agriculture","venue_type":"journal","ids":{"doi":"10.1016/j.inpa.2023.05.001","openalex":"W4377097271"},"links":{"paper":"https://doi.org/10.1016/j.inpa.2023.05.001"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Review of statistical machine learning for fishery weather scenario generation, forecasting and extreme-weather warnings.","significance":1,"cited_by":22,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.8114","title":"Downscaling wind speed based on coupled environmental factors and machine learning","authors":["Yuming Lu","Bingfang Wu","Abdelrazek Elnashar","Nana Yan","Hongwei Zeng","Weiwei Zhu","Bo Pang"],"date":"2023-05-19","year":2023,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.8114","openalex":"W4377096886"},"links":{"paper":"https://doi.org/10.1002/joc.8114"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","satellite","stations"],"status":"research","summary":"Neural-network downscaling of ERA5 daily wind speed to a 1 km China dataset for 2015, with R2 of 0.95 against station observations.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15102640","title":"Towards an Accurate and Reliable Downscaling Scheme for High-Spatial-Resolution Precipitation Data","authors":["Honglin Zhu","Huizeng Liu","Qiming Zhou","Aihong Cui"],"date":"2023-05-18","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15102640","openalex":"W4377139698"},"links":{"paper":"https://doi.org/10.3390/rs15102640","pdf":"https://www.mdpi.com/2072-4292/15/10/2640/pdf?version=1686135278"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Compares ML downscaling of satellite precipitation, finding SRF and XGBoost best and GDA calibration beneficial, while residual Kriging degrades performance.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15102637","title":"Impact of Horizontal Resolution on the Robustness of Radiation Emulators in a Numerical Weather Prediction Model","authors":["Hwan‐Jin Song","Soonyoung Roh"],"date":"2023-05-18","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15102637","openalex":"W4377104706"},"links":{"paper":"https://doi.org/10.3390/rs15102637","pdf":"https://www.mdpi.com/2072-4292/15/10/2637/pdf?version=1684408991"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":["regional-km-scale"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","km-scale-sim"],"status":"pre-operational","summary":"Tests a machine-learning radiation emulator in an NWP model across 0.25–100 km resolutions over Korea, finding larger heating-rate errors at fine scales.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-jog.2023.24","title":"Automated prediction of wet-snow avalanche activity in the Swiss Alps","authors":["Martin Hendrick","Frank Techel","Michele Volpi","Tasko Olevski","Cristina Pérez-Guillén","Alec van Herwijnen","Jürg Schweizer"],"date":"2023-05-18","year":2023,"venue":"Journal of Glaciology","venue_type":"journal","ids":{"doi":"10.1017/jog.2023.24","openalex":"W4377108100"},"links":{"paper":"https://doi.org/10.1017/jog.2023.24","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/166D6321D57FFAC04DC7CEE773C0A45A/S0022143023000242a.pdf/div-class-title-automated-prediction-of-wet-snow-avalanche-activity-in-the-swiss-alps-div.pdf"},"orgs":["sdsc"],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"A random forest driven by weather-station data predicts wet-snow avalanche activity in the Swiss Alps, with F1 near 0.8 in nowcast and NWP-driven 24-hour modes.","significance":3,"cited_by":26,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23104825","title":"Improved the Impact of SST for HY-2A Scatterometer Measurements by Using Neural Network Model","authors":["Jing Wang","Xuetong Xie","Ruru Deng","Jiayi Li","Yuming Tang","Yeheng Liang","Yu Guo"],"date":"2023-05-17","year":2023,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23104825","openalex":"W4377104522"},"links":{"paper":"https://doi.org/10.3390/s23104825","pdf":"https://www.mdpi.com/1424-8220/23/10/4825/pdf?version=1684309118"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"A neural network corrects sea-surface-temperature effects on HY-2A Ku-band scatterometer backscatter, making retrieved surface winds closer to WindSat and ECMWF.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-22-0066.1","title":"Correcting Nonstationary Sea Surface Temperature Bias in NCEP CFSv2 Using Ensemble-Based Neural Networks","authors":["Ziying Yang","Jiping Liu","Chao‐Yuan Yang","Yongyun Hu"],"date":"2023-05-17","year":2023,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-22-0066.1","openalex":"W4376867375"},"links":{"paper":"https://doi.org/10.1175/jtech-d-22-0066.1"},"orgs":["iap-cas"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Ensemble neural networks correct nonstationary sea surface temperature bias in NCEP CFSv2 seasonal forecasts, reducing RMSE by 0.35 °C, with a deeper network giving further gains.","significance":3,"cited_by":2,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijeecs.v31.i1.pp451-458","title":"Precipitation forecasting using machine learning in the region of Beni Mellal-Khenifra","authors":["Hamza Jdi","Noureddine Falih"],"date":"2023-05-17","year":2023,"venue":"Indonesian Journal of Electrical Engineering and Computer Science","venue_type":"journal","ids":{"doi":"10.11591/ijeecs.v31.i1.pp451-458","openalex":"W4376881362"},"links":{"paper":"https://doi.org/10.11591/ijeecs.v31.i1.pp451-458","pdf":"https://ijeecs.iaescore.com/index.php/IJEECS/article/download/31509/17435"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random forest, Lasso, ridge, elastic net and ARIMA forecast daily rainfall in Beni Mellal-Khenifra, Morocco, with random forest giving the lowest error.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.energy.2023.127865","title":"Multi-head attention-based probabilistic CNN-BiLSTM for day-ahead wind speed forecasting","authors":["Yiming Zhang","Hao Wang"],"date":"2023-05-17","year":2023,"venue":"Energy","venue_type":"journal","ids":{"doi":"10.1016/j.energy.2023.127865","openalex":"W4376880182"},"links":{"paper":"https://doi.org/10.1016/j.energy.2023.127865"},"orgs":["university-of-cambridge"],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"A probabilistic CNN-BiLSTM with multi-head attention forecasts day-ahead wind speed for energy use; the abstract was unavailable, so the claim is limited.","significance":2,"cited_by":180,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.11910","title":"Machine Learning and VIIRS Satellite Retrievals for Skillful Fuel Moisture Content Monitoring in Wildfire Management","authors":["John S. Schreck","William Petzke","Pedro A. Jimenez","Thomas Brummet","Jason C. Knievel","Eric James","Branko Kosovic","David John Gagne"],"date":"2023-05-17","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"arxiv":"2305.11910","doi":"10.3390/rs15133372","openalex":"W4382941193"},"links":{"paper":"https://doi.org/10.3390/rs15133372","pdf":"https://arxiv.org/pdf/2305.11910"},"orgs":["ncar","noaa"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"ML models using VIIRS retrievals and HRRR variables estimate dead fuel moisture content over CONUS, outperforming climatology by 24% in hourly RMSE and beating MODIS-based models.","significance":3,"cited_by":15,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.10064","title":"FlashBench: A lightning nowcasting framework based on the hybrid deep learning and physics-based dynamical models","authors":["Manmeet Singh","Vaisakh S. B.","Dipjyoti Mudiar","Deewakar Chakraborty","V. Gopalakrishnan","Bhupendra Bahadur Singh","Shikha Singh","Rakesh Ghosh","Rajib Chattopadhyay","Bipin Kumar","S. D. Pawar","S. A. Rao"],"date":"2023-05-17","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.10064","openalex":"W4377111694"},"links":{"paper":"https://arxiv.org/abs/2305.10064","pdf":"https://arxiv.org/pdf/2305.10064"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"FlashBench combines a LightNet-style deep model with observed field evolution for regional lightning nowcasts over West India, delivered via a cloud forecast system.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-023-35093-9","title":"A novel deep learning approach for typhoon-induced storm surge modeling through efficient emulation of wind and pressure fields","authors":["Iyan E. Mulia","Naonori Ueda","Takemasa Miyoshi","Takumu Iwamoto","Mohammad Heidarzadeh"],"date":"2023-05-16","year":2023,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-023-35093-9","openalex":"W4376643869"},"links":{"paper":"https://doi.org/10.1038/s41598-023-35093-9","pdf":"https://www.nature.com/articles/s41598-023-35093-9.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"A GAN converts parametric typhoon wind and pressure fields into NWP-like forcing, giving storm surge accuracy comparable to NWP and better than parametric models.","significance":4,"cited_by":36,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.pocean.2023.103047","title":"Climate downscaling for regional models with a neural network: A Hawaiian example","authors":["Guangpeng Liu","Brian Powell","Tobias Friedrich"],"date":"2023-05-16","year":2023,"venue":"Progress In Oceanography","venue_type":"journal","ids":{"doi":"10.1016/j.pocean.2023.103047","openalex":"W4376638519"},"links":{"paper":"https://doi.org/10.1016/j.pocean.2023.103047"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":[],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies a neural network to downscale climate for a regional Hawaiian model; the abstract is missing, so the target variables and performance cannot be verified.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.11901","title":"Long-lead forecasts of wintertime air stagnation index in southern China using oceanic memory effects","authors":["Chenhong Zhou","Xiaorui Zhang","Meng Gao","Shanshan Liu","Yike Guo","Jie Chen"],"date":"2023-05-16","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.11901"},"links":{"paper":"https://arxiv.org/abs/2305.11901","pdf":"https://arxiv.org/pdf/2305.11901"},"orgs":[],"topic":"s2s-seasonal","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"LSTM forecasts wintertime air stagnation index in southern China from autumn Niño indices and past ASI, reaching correlation 0.778 at long lead.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.56588-iabcd.v2i1.170","title":"REVIEW OF THE STUDY CLIMATE CHANGE IMPACT ASSESSMENT ON THE GUJARAT COASTLINE: THE ROLE OF ARTIFICIAL INTELLIGENCE, STATISTICAL, MATHEMATICAL AND GEOGRAPHIC INFORMATION SYSTEMS (GIS)","authors":["Krishna Sodha","Priyanka Pati","Dhara Rajput","Hitesh Solanki"],"date":"2023-05-15","year":2023,"venue":"International Association of Biologicals and Computational Digest","venue_type":"journal","ids":{"doi":"10.56588/iabcd.v2i1.170","openalex":"W4376631974"},"links":{"paper":"https://doi.org/10.56588/iabcd.v2i1.170","pdf":"https://iabcd.org.in/index.php/iabcd/article/download/170/116"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["other"],"timescale":["climate"],"spatial":["local"],"data":["other"],"status":"research","summary":"Review of AI, statistical and GIS methods for climate change impact on the Gujarat coastline, with no quantitative results of its own.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022jd038163","title":"Deep Learning for Downscaling Tropical Cyclone Rainfall to Hazard‐Relevant Spatial Scales","authors":["Emily Vosper","Peter A. G. Watson","Lucy Harris","Andrew T. T. McRae","Raúl Santos‐Rodríguez","Laurence Aitchison","Dann Mitchell"],"date":"2023-05-13","year":2023,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2022jd038163","openalex":"W4376504548"},"links":{"paper":"https://doi.org/10.1029/2022jd038163"},"orgs":["university-of-oxford"],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A Wasserstein GAN downscales tropical cyclone rainfall from about 100 km to 10 km, reproducing spatial structure and spectra with mean bias within 5% and extrapolating to extreme storms.","significance":3,"cited_by":29,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.07859","title":"HAiVA: Hybrid AI-assisted Visual Analysis Framework to Study the Effects of Cloud Properties on Climate Patterns","authors":["Subhashis Hazarika","Haruki Hirasawa","Sookyung Kim","Kalai Ramea","Salva R. Cachay","Peetak Mitra","Dipti Hingmire","Hansi Singh","Phil J. Rasch"],"date":"2023-05-13","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.07859"},"links":{"paper":"https://arxiv.org/abs/2305.07859","pdf":"https://arxiv.org/pdf/2305.07859"},"orgs":[],"topic":"climate-emulation","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Hybrid AI emulators of cloud-climate response, with an interactive visual tool, enable what-if testing of marine cloud brightening scenarios without costly Earth system runs.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-nhess-23-1755-2023","title":"Reduced-order digital twin and latent data assimilation for global wildfire prediction","authors":["Caili Zhong","Sibo Lucas Cheng","Matthew R. Kasoar","Rossella Arcucci"],"date":"2023-05-12","year":2023,"venue":"Natural hazards and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/nhess-23-1755-2023","openalex":"W4387437810"},"links":{"paper":"https://doi.org/10.5194/nhess-23-1755-2023","pdf":"https://nhess.copernicus.org/articles/23/1755/2023/nhess-23-1755-2023.pdf","code":"https://github.com/DL-WG/Digital-twin-LA-global-wildfire"},"orgs":[],"topic":"extremes-hazards","topics":["data-assimilation"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Latent-space digital twin of JULES-INFERNO for global wildfire prediction, with latent data assimilation, running 500 times faster than the original model.","significance":3,"cited_by":66,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ins.2023.119106","title":"Forecasting ENSO using convolutional LSTM network with improved attention mechanism and models recombined by genetic algorithm in CMIP5/6","authors":["Yong Wang","Yiming Zhang","Yiming Zhang","Gai‐Ge Wang"],"date":"2023-05-12","year":2023,"venue":"Information Sciences","venue_type":"journal","ids":{"doi":"10.1016/j.ins.2023.119106","openalex":"W4376279928"},"links":{"paper":"https://doi.org/10.1016/j.ins.2023.119106"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","cnn","classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Proposes an attention-enhanced ConvLSTM with genetic-algorithm model recombination to forecast ENSO using CMIP5/6 simulations. No abstract was provided.","significance":4,"cited_by":23,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2508.06122","title":"Learning Representations of Satellite Images with Evaluations on Synoptic Weather Events","authors":["Ting‐Shuo Yo","Shih‐Hao Su","Chien‐Ming Wu","Wei‐Ting Chen","Jung‐Lien Chu","Chiao‐Wei Chang","Hung‐Chi Kuo"],"date":"2023-05-12","year":2023,"venue_type":"other","ids":{"arxiv":"2508.06122","doi":"10.22541/essoar.168394729.95734739/v1","openalex":"W4376504930"},"links":{"paper":"https://doi.org/10.22541/essoar.168394729.95734739/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.168394729.95734739"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["cnn"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Compares PCA, a convolutional autoencoder and a pretrained ResNet as latent representations of satellite images for classifying weather events; the autoencoder gives the highest threat scores.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.08874","title":"Online machine-learning forecast uncertainty estimation for sequential data assimilation","authors":["Maximiliano A. Sacco","Manuel Pulido","Juan J. Ruiz","Pierre Tandeo"],"date":"2023-05-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.08874","openalex":"W4377029507"},"links":{"paper":"https://arxiv.org/abs/2305.08874","pdf":"https://arxiv.org/pdf/2305.08874"},"orgs":[],"topic":"data-assimilation","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A CNN estimates state-dependent forecast error covariance from one model run for hybrid data assimilation, matching ensemble Kalman filter performance on Lorenz96 with small ensembles.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su15107801","title":"Short-Term Climate Prediction over China Mainland: An Attempt Using Machine Learning, Considering Natural and Anthropic Factors","authors":["Ruolin Li","Celestin Sindikubwabo","Qi Feng","Yang Cui"],"date":"2023-05-10","year":2023,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su15107801","openalex":"W4376115556"},"links":{"paper":"https://doi.org/10.3390/su15107801","pdf":"https://www.mdpi.com/2071-1050/15/10/7801/pdf?version=1683702990"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Random forests combining natural and anthropogenic factors hindcast seasonal China temperature and precipitation with R² above 0.95, beating natural-only factors (0.86).","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-2853652-v1","title":"Evaluation of Heat Wave Predictability Skills of Numerical Weather Models","authors":["Ademola Akinbobola","Ibraheem Ayomide Raji"],"date":"2023-05-10","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-2853652/v1","openalex":"W4376104799"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-2853652/v1","pdf":"https://www.researchsquare.com/article/rs-2853652/latest.pdf"},"orgs":["ecmwf","noaa"],"topic":"extremes-hazards","topics":["post-processing"],"type":"evaluation","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"S2S models overestimate heatwave frequency over northern Nigeria at 30-day lead; deep-learning bias correction improves forecast reliability.","significance":2,"cited_by":0,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl102525","title":"Assessing Three Perfect Prognosis Methods for Statistical Downscaling of Climate Change Precipitation Scenarios","authors":["Mikel N. Legasa","Soulivanh Thao","Mathieu Vrac","Rodrigo Manzanas"],"date":"2023-05-10","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl102525","openalex":"W4376601314"},"links":{"paper":"https://doi.org/10.1029/2022gl102525","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL102525"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":["cnn","classical-ml"],"timescale":["climate"],"spatial":["regional","local"],"data":["cmip","era5","stations"],"status":"research","summary":"Compares GLMs, CNNs and a posteriori random forests for perfect-prognosis precipitation downscaling of EC-Earth; APRFs best reproduce the GCM's future climate change signal.","significance":4,"cited_by":22,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.06139","title":"A Neural Emulator for Uncertainty Estimation of Fire Propagation","authors":["Andrew Bolt","Conrad Sanderson","Joel Janek Dabrowski","Carolyn Huston","Petra Kuhnert"],"date":"2023-05-10","year":2023,"venue":"Procedia Computer Science, Vol. 222, pp. 367-376, 2023","venue_type":"journal","ids":{"arxiv":"2305.06139","doi":"10.1016/j.procs.2023.08.175"},"links":{"paper":"https://arxiv.org/abs/2305.06139","pdf":"https://arxiv.org/pdf/2305.06139"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Neural emulator estimates wildfire spread likelihood under perturbed weather forecasts, matching SPARK fire boundaries (Jaccard 67.4%) about ten times faster than ensembles.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1073-pnas.2216158120","title":"Implicit learning of convective organization explains precipitation stochasticity","authors":["Sara Shamekh","Kara D. Lamb","Y. Huang","Pierre Gentine"],"date":"2023-05-08","year":2023,"venue":"Proceedings of the National Academy of Sciences","venue_type":"journal","ids":{"doi":"10.1073/pnas.2216158120","openalex":"W4375955134"},"links":{"paper":"https://doi.org/10.1073/pnas.2216158120"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A neural-network precipitation parameterization fails at extremes unless informed by a novel sub-grid organization metric, which raises variance R² from about 0.4 to 0.95.","significance":5,"cited_by":54,"score":50,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2023.100373","title":"Deep learning in extracting tropical cyclone intensity and wind radius information from satellite infrared images—A review","authors":["Chong Wang","Xiaofeng Li"],"date":"2023-05-08","year":2023,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2023.100373","openalex":"W4382885003"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2023.100373"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Review of deep learning methods for extracting tropical cyclone intensity and wind radius from satellite infrared imagery, with an outlook on future directions.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.04341","title":"Fast parameter estimation of Generalized Extreme Value distribution using Neural Networks","authors":["Sweta Rai","Alexis Hoffman","Soumendra Lahiri","Douglas W. Nychka","Stephan R. Sain","Soutir Bandyopadhyay"],"date":"2023-05-07","year":2023,"venue":"environmeterics, April 2023","venue_type":"journal","ids":{"arxiv":"2305.04341","openalex":"W4375958604"},"links":{"paper":"https://arxiv.org/abs/2305.04341","pdf":"https://arxiv.org/pdf/2305.04341"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A neural network estimates GEV extreme-value parameters for CCSM3 annual maximum temperatures about as accurately as maximum likelihood, with large computational speedups.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.04331","title":"The High-Frequency and Rare Events Barriers to Neural Closures of Atmospheric Dynamics","authors":["Mickaël D. Chekroun","Honghu Liu","Kaushik Srinivasan","James C. McWilliams"],"date":"2023-05-07","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.04331"},"links":{"paper":"https://arxiv.org/abs/2305.04331","pdf":"https://arxiv.org/pdf/2305.04331"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"position","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Argues that neural closures for atmospheric dynamics struggle with rare events and multiscale high-frequency waves, illustrated with the Lorenz 1980 model.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15092454","title":"Dual-Level Contextual Attention Generative Adversarial Network for Reconstructing SAR Wind Speeds in Tropical Cyclones","authors":["Xinhai Han","Xiaohui Li","Jingsong Yang","Jiuke Wang","Gang Zheng","Lin Ren","Peng Chen","He Fang","Qingmei Xiao"],"date":"2023-05-06","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15092454","openalex":"W4381687998"},"links":{"paper":"https://doi.org/10.3390/rs15092454","pdf":"https://www.mdpi.com/2072-4292/15/9/2454/pdf?version=1683380408"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["gan-vae","transformer"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"An attention-based GAN reconstructs low-quality SAR wind speeds in tropical cyclones, halving RMSE versus the existing SAR product in affected regions relative to ECMWF.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-2355-2023","title":"Emulating aerosol optics with randomly generated neural networks","authors":["Andrew Geiss","Po‐Lun Ma","Balwinder Singh","Joseph Clinton Hardin"],"date":"2023-05-05","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-2355-2023","openalex":"W4382812085"},"links":{"paper":"https://doi.org/10.5194/gmd-16-2355-2023","pdf":"https://gmd.copernicus.org/articles/16/2355/2023/gmd-16-2355-2023.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural networks trained on Mie-computed data replace E3SM's aerosol optics parameterization; randomly wired deep networks outperform MLPs and the existing scheme.","significance":4,"cited_by":13,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.51483-ijdsbda.3.1.2023.58-79","title":"Wild Fires and Climate Change-Nowcasting and Forecasting Climate Change Using Advances in Machine Learning Methods","authors":["Christoph Kohlhepp"],"date":"2023-05-05","year":2023,"venue":"International Journal of Data Science and Big Data Analytics","venue_type":"journal","ids":{"doi":"10.51483/ijdsbda.3.1.2023.58-79","openalex":"W4388541933"},"links":{"paper":"https://doi.org/10.51483/ijdsbda.3.1.2023.58-79","pdf":"https://doi.org/10.51483/ijdsbda.3.1.2023.58-79"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":[],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Review-style paper on machine learning for wildfires and climate change; with no abstract, scope and results cannot be verified.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21275-sr23516220618","title":"An Examination of the Applications of Quantum Artificial Intelligence to Addressing Climate Change Effects","authors":["Karan Chawla"],"date":"2023-05-05","year":2023,"venue":"International Journal of Science and Research (IJSR)","venue_type":"journal","ids":{"doi":"10.21275/sr23516220618","openalex":"W4397037870"},"links":{"paper":"https://doi.org/10.21275/sr23516220618","pdf":"http://dx.doi.org/10.21275/sr23516220618"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Reviews quantum artificial intelligence for climate change, including pattern identification and parameterization, but offers no quantitative results and little demonstrated weather-ML content.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-2880376-v1","title":"Federated Learning with GANs-based Synthetic Minority Over-sampling Technique for Improving Weather Prediction from Imbalanced Data","authors":["Elaheh Jafarigol","Theodore B. Trafali̇s"],"date":"2023-05-05","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-2880376/v1","openalex":"W4372347174"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-2880376/v1","pdf":"https://www.researchsquare.com/article/rs-2880376/latest.pdf"},"orgs":["university-of-oklahoma"],"topic":"local-forecasting","topics":[],"type":"model","method":["gan-vae","classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Federated learning with GAN-based oversampling is applied to imbalanced tabular weather data; gains are reported without numbers.","significance":1,"cited_by":3,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jweia.2023.105440","title":"Transformer-based tropical cyclone track and intensity forecasting","authors":["Wenjun Jiang","Dongqin Zhang","Gang Hu","Tiantian Wu","Lingbo Liu","Yiqing Xiao","Zhongdong Duan"],"date":"2023-05-05","year":2023,"venue":"Journal of Wind Engineering and Industrial Aerodynamics","venue_type":"journal","ids":{"doi":"10.1016/j.jweia.2023.105440","openalex":"W4372215895"},"links":{"paper":"https://doi.org/10.1016/j.jweia.2023.105440"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["transformer"],"timescale":["short","medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Transformer model for joint tropical cyclone track and intensity forecasting; the abstract is missing, so results cannot be verified.","significance":3,"cited_by":55,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10618-023-00929-5","title":"A spatiotemporal deep neural network for fine-grained multi-horizon wind prediction","authors":["Fanling Huang","Yangdong Steve Deng"],"date":"2023-05-05","year":2023,"venue":"Data Mining and Knowledge Discovery","venue_type":"journal","ids":{"arxiv":"2309.04733","doi":"10.1007/s10618-023-00929-5","openalex":"W4372259643"},"links":{"paper":"https://doi.org/10.1007/s10618-023-00929-5"},"orgs":["tsinghua-university"],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Spatiotemporal deep network for multi-horizon wind prediction; the abstract is missing, so architecture and results are unverified.","significance":2,"cited_by":3,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.168319865.58439449-v1","title":"Estimating full longwave and shortwave radiative transfer with neural","authors":["Ryan Lagerquist","David D. Turner","Imme Ebert‐Uphoff","Jebb Q. Stewart"],"date":"2023-05-04","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.168319865.58439449/v1","openalex":"W4368372152"},"links":{"paper":"https://doi.org/10.22541/essoar.168319865.58439449/v1","pdf":"https://www.authorea.com/doi/pdf/10.22541/essoar.168319865.58439449"},"orgs":["noaa","colorado-state-university"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Neural networks emulate the full shortwave and longwave RRTM radiation scheme for GFSv16, running 6579x and 96x faster than the original with near-zero bias.","significance":5,"cited_by":1,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2023.04.050","title":"Forecasting day-ahead 1-minute irradiance variability from numerical weather predictions","authors":["Frank Kreuwel","Wouter Knap","Maurice J. Schmeits","Jordi Vilà-Guerau De Arellano","Chiel C. van Heerwaarden"],"date":"2023-05-04","year":2023,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2023.04.050","openalex":"W4368617800"},"links":{"paper":"https://doi.org/10.1016/j.solener.2023.04.050"},"orgs":["knmi"],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","era5","stations"],"status":"research","summary":"Machine-learning post-processing of hourly HARMONIE and ERA5 forecasts predicts 1-minute irradiance variability for Dutch stations, with NWP radiation errors causing about half the inaccuracy.","significance":3,"cited_by":22,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.02397","title":"Widespread Increases in Future Wildfire Risk to Global Forest Carbon Offset Projects Revealed by Explainable AI","authors":["Tristan Ballard","Matthew Cooper","Chris Lowrie","Gopal Erinjippurath"],"date":"2023-05-03","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.02397"},"links":{"paper":"https://arxiv.org/abs/2305.02397","pdf":"https://arxiv.org/pdf/2305.02397"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts","climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["satellite","cmip"],"status":"research","summary":"An explainable ML wildfire model trained on 7 million satellite observations projects a 55% rise in fire exposure for forest carbon projects by 2080 under SSP2-4.5.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11042-023-15450-6","title":"Trs-net tropical revolving storm disasters analysis and classification based on multispectral images using 2-d deep convolutional neural network","authors":["Malathy Jawahar","L. Jani Anbarasi","Graceline Jasmine S","J. L. Febin Daya","Vinayakumar Ravi","Prąsun Chakrabarti"],"date":"2023-05-02","year":2023,"venue":"Multimedia Tools and Applications","venue_type":"journal","ids":{"doi":"10.1007/s11042-023-15450-6","openalex":"W4367678518"},"links":{"paper":"https://doi.org/10.1007/s11042-023-15450-6"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Trs-net applies a 2-D CNN to multispectral satellite images to analyse and classify tropical revolving storms. No abstract was provided.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.01822","title":"Unpaired Downscaling of Fluid Flows with Diffusion Bridges","authors":["Tobias Bischoff","Katherine Deck"],"date":"2023-05-02","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.01822"},"links":{"paper":"https://arxiv.org/abs/2305.01822","pdf":"https://arxiv.org/pdf/2305.01822"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["diffusion"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim","other"],"status":"research","summary":"Unpaired diffusion bridges downscale geophysical fluid simulations without paired data, correcting biases including in extremes and promising use for climate precipitation and temperature.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7220797187","title":"INVESTIGATING THE LIMITED SAMPLE SIZE OF SUBSEASONAL CLIMATE FORECASTING DATASETS IN DEEP LEARNING APPLICATIONS","authors":["Philip Chmielowiec"],"date":"2023-05-01","year":2023,"venue":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","venue_type":"preprint","ids":{"openalex":"W7220797187"},"links":{"paper":"https://hdl.handle.net/2142/124855"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Autoencoder models predict US subseasonal temperature anomalies using CESM2 S2S variables to prepare transfer learning; skill varies by region and season.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.59256-ijire.2023040245","title":"Heat Wave Predication Correlate Data to Predict Drought","authors":["Vidya Mote","Adarsh Patil","Samrudhi Patil","Prof. Jaspreet Kaur"],"date":"2023-05-01","year":2023,"venue":"International Journal of Innovative Research in Engineering","venue_type":"journal","ids":{"doi":"10.59256/ijire.2023040245","openalex":"W4367599296"},"links":{"paper":"https://doi.org/10.59256/ijire.2023040245"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["classical-ml","rnn"],"timescale":["s2s"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"ML models predict India heatwave occurrence a month ahead for each 1° grid cell using six months of maximum temperature data.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32628-cseit2390321","title":"Visibility Analysis and Time Series Forecasting","authors":["Asoke Nath","Swapnil Saha","Himashri Basu","Shalini Torcato"],"date":"2023-05-01","year":2023,"venue":"International Journal of Scientific Research in Computer Science Engineering and Information Technology","venue_type":"journal","ids":{"doi":"10.32628/cseit2390321","openalex":"W4381052206"},"links":{"paper":"https://doi.org/10.32628/cseit2390321","pdf":"https://ijsrcseit.com/paper/CSEIT2390321.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"XGBoost, ARIMA and LSTM models forecast atmospheric visibility from station time series, with outputs reported as close to observed values.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25046-aj080307","title":"Forecasting the Weather behind Pa Sak Jolasid Dam using Quantum Machine Learning","authors":["Chaiyaporn Khemapatapan","Thammanoon Thepsena"],"date":"2023-05-01","year":2023,"venue":"Advances in Science Technology and Engineering Systems Journal","venue_type":"journal","ids":{"doi":"10.25046/aj080307","openalex":"W4377287076"},"links":{"paper":"https://doi.org/10.25046/aj080307","pdf":"https://www.astesj.com/?sdm_process_download=1&download_id=75735"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies quantum classifiers (QSVM, QNN, VQC) to 2016–2022 station weather data from a Thai dam, with QSVM reaching 85.3% accuracy.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003585","title":"Quantifying 3D Gravity Wave Drag in a Library of Tropical Convection‐Permitting Simulations for Data‐Driven Parameterizations","authors":["Y. Qiang Sun","Pedram Hassanzadeh","M. Joan Alexander","Christopher G. Kruse"],"date":"2023-05-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003585","openalex":"W4377137365"},"links":{"paper":"https://doi.org/10.1029/2022ms003585","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003585"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"evaluation","method":["other"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Compares three methods to extract 3D subgrid gravity wave fluxes and drag from 3 km tropical simulations, showing lateral fluxes can matter for data-driven parameterizations.","significance":3,"cited_by":27,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003445","title":"A Physics‐Incorporated Deep Learning Framework for Parameterization of Atmospheric Radiative Transfer","authors":["Yichen Yao","Xiaohui Zhong","Yongjun Zheng","Zhibin Wang"],"date":"2023-05-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003445","openalex":"W4372338097"},"links":{"paper":"https://doi.org/10.1029/2022ms003445","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003445"},"orgs":["nuist","alibaba-damo"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["physics-constrained","rnn","transformer","neural-operator"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Physics-incorporated network enforces flux-heating rate energy conservation in radiative transfer; bidirectional RNNs and transformers beat FC nets and CNNs.","significance":4,"cited_by":31,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.2130","title":"Nowcast for cloud top height from Himawari‐8 data based on deep learning algorithms","authors":["Zhuofu Yu","Zhonghui Tan","Shuo Ma","Wei Yan"],"date":"2023-05-01","year":2023,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.2130","openalex":"W4382071010"},"links":{"paper":"https://doi.org/10.1002/met.2130","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.2130"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"TrajGRU and ConvLSTM nowcast Himawari-8 cloud top height up to 2 h, with TrajGRU beating optical flow and persistence in most seasons.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2309.09002","title":"Earth Virtualization Engines: A Technical Perspective","authors":["Torsten Hoefler","Björn Stevens","Andreas Franz Prein","Johanna Baehr","T. C. Schulthess","Thomas Franziskus Stocker","John Taylor","Daniel Klocke","Pekka Manninen","Piers M. de F. Forster","Tobias Kölling","Nicolas Gruber","Hartwig Anzt","Claudia Frauen","Florian Ziemen","Milan Klöwer","Karthik Kashinath","Christoph Schär","Oliver Fuhrer","Bryan Lawrence"],"date":"2023-05-01","year":2023,"venue":"Computing in Science & Engineering","venue_type":"journal","ids":{"arxiv":"2309.09002","doi":"10.1109/mcse.2023.3311148","openalex":"W4388016776"},"links":{"paper":"https://doi.org/10.1109/mcse.2023.3311148","pdf":"https://arxiv.org/pdf/2309.09002"},"orgs":["cscs","eth-zurich","meteoswiss","mit","mpi-meteorology","ncar","nvidia","university-of-reading"],"topic":"infra-software","topics":["climate-emulation"],"type":"position","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Position paper on Earth Virtualization Engines that pair high-resolution physics-based climate models with machine learning and federated access to exabyte-scale climate data.","significance":3,"cited_by":9,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33394-j-ps.v11i2.7738","title":"Identification of Rainfall events on Climate Phenomena in Medan based on Machine Learning","authors":["Deassy Eirene Diana Doloksaribu","Kerista Tarigan","Richard Mahendra Putra","Yahya Darmawan"],"date":"2023-04-30","year":2023,"venue":"Prisma Sains Jurnal Pengkajian Ilmu dan Pembelajaran Matematika dan IPA IKIP Mataram","venue_type":"journal","ids":{"doi":"10.33394/j-ps.v11i2.7738","openalex":"W4376613936"},"links":{"paper":"https://doi.org/10.33394/j-ps.v11i2.7738","pdf":"https://e-journal.undikma.ac.id/index.php/prismasains/article/download/7738/4403"},"orgs":[],"topic":"local-forecasting","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Uses machine-learning combinations of ENSO, IOD and MJO indices to predict Medan rainfall, finding the SOI plus MJO combination gives the best verification, with MAE of 15.0 mm.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15092328","title":"Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques","authors":["Miguel López-Cuesta","Ricardo Aler","Inés María Galván","Francisco Javier Rodríguez-Benítez","David Pozo‐Vázquez"],"date":"2023-04-28","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15092328","openalex":"W4367315555"},"links":{"paper":"https://doi.org/10.3390/rs15092328","pdf":"https://www.mdpi.com/2072-4292/15/9/2328/pdf?version=1682670709"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"Random-forest blending of sky-imager, satellite and data-driven forecasts improves 90-minute solar irradiance nowcasts by up to 30% for GHI and 40% for DNI.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14050807","title":"Precipitation Nowcasting Based on Deep Learning over Guizhou, China","authors":["Dexuan Kong","Xiefei Zhi","Yan Ji","Chunyan Yang","Yuhong Wang","Yuntao Tian","Gang Li","Xiaotuan Zeng"],"date":"2023-04-28","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14050807","openalex":"W4367314848"},"links":{"paper":"https://doi.org/10.3390/atmos14050807","pdf":"https://www.mdpi.com/2073-4433/14/5/807/pdf?version=1682674642"},"orgs":["nuist","cma"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Deep learning nowcasts 6-minute precipitation up to 2 h over Guizhou from station data; PredRNN beats optical flow at all tested thresholds.","significance":3,"cited_by":14,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.00100","title":"Temporal Subsampling Diminishes Small Spatial Scales in Recurrent Neural Network Emulators of Geophysical Turbulence","authors":["Timothy A. Smith","Stephen G. Penny","Jason A. Platt","Tse-Chun Chen"],"date":"2023-04-28","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.00100"},"links":{"paper":"https://arxiv.org/abs/2305.00100","pdf":"https://arxiv.org/pdf/2305.00100"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"evaluation","method":["rnn"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Shows temporal subsampling of training data adds small-scale bias in reservoir-computing emulators of surface quasi-geostrophic turbulence, with echo state networks more robust than NVAR.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.00048","title":"Verification against in-situ observations for Data-Driven Weather Prediction","authors":["Vivek Ramavajjala","Peetak P. Mitra"],"date":"2023-04-28","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.00048","openalex":"W4367692230"},"links":{"paper":"https://arxiv.org/abs/2305.00048","pdf":"https://arxiv.org/pdf/2305.00048"},"orgs":["excarta"],"topic":"benchmarks-data-eval","topics":["global-medium-range"],"type":"benchmark","method":[],"timescale":["short"],"spatial":["global"],"data":["stations","era5"],"status":"research","summary":"Releases a quality-controlled NOAA MADIS in-situ observation dataset to verify data-driven weather prediction models against real-world operational observations rather than reanalysis.","significance":4,"cited_by":1,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22201-icat.24486736e.2023.21.2.1698","title":"Prediction of weather forecasting using artificial neural networks","authors":["A. Ajina","K. G. Jaya Christiyan","Dheerej N Bhat","Kanishk Saxena"],"date":"2023-04-27","year":2023,"venue":"Journal of Applied Research and Technology","venue_type":"journal","ids":{"doi":"10.22201/icat.24486736e.2023.21.2.1698","openalex":"W4381707588"},"links":{"paper":"https://doi.org/10.22201/icat.24486736e.2023.21.2.1698","pdf":"https://jart.icat.unam.mx/index.php/jart/article/download/1698/992"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies artificial neural networks to predict daily weather for several cities, claiming very low deviations, though without a quantified benchmark in the abstract.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-023-06787-7","title":"Assessment and prediction of regional climate based on a multimodel ensemble machine learning method","authors":["Yinghao Fu","Haoran Zhuang","Xiaojing Shen","Wangcheng Li"],"date":"2023-04-27","year":2023,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-023-06787-7","openalex":"W4367186884"},"links":{"paper":"https://doi.org/10.1007/s00382-023-06787-7"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Multimodel ensemble machine learning for regional climate assessment and prediction; no abstract was supplied, so this classification is tentative.","significance":2,"cited_by":30,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.00975","title":"Deep Ensembles to Improve Uncertainty Quantification of Statistical Downscaling Models under Climate Change Conditions","authors":["Jose González-Abad","Jorge Baño-Medina"],"date":"2023-04-27","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.00975","openalex":"W4367859667"},"links":{"paper":"https://arxiv.org/abs/2305.00975","pdf":"https://arxiv.org/pdf/2305.00975"},"orgs":[],"topic":"downscaling","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Deep ensembles improve uncertainty quantification of statistical downscaling under climate change, tested in a pseudo-reality experiment.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2305.00974","title":"On the use of Deep Generative Models for Perfect Prognosis Climate Downscaling","authors":["Jose González-Abad","Jorge Baño-Medina","Ignacio Heredia Cachá"],"date":"2023-04-27","year":2023,"venue_type":"preprint","ids":{"arxiv":"2305.00974","openalex":"W4367859712"},"links":{"paper":"https://arxiv.org/abs/2305.00974","pdf":"https://arxiv.org/pdf/2305.00974"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"Deep generative models for perfect-prognosis precipitation downscaling improve spatial consistency of high-resolution fields compared with independent per-location estimates.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.14541","title":"Deep Spatiotemporal Clustering: A Temporal Clustering Approach for Multi-dimensional Climate Data","authors":["Omar Faruque","Francis Ndikum Nji","Mostafa Cham","Rohan Mandar Salvi","Xue Zheng","Jianwu Wang"],"date":"2023-04-27","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.14541"},"links":{"paper":"https://arxiv.org/abs/2304.14541","pdf":"https://arxiv.org/pdf/2304.14541"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["cnn","rnn"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Deep spatiotemporal clustering with a CNN-RNN autoencoder groups multivariate climate data, outperforming conventional and deep clustering baselines.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14050792","title":"NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery","authors":["Bin Mu","Xin Jiang","Shijin Yuan","Yuehan Cui","Bo Qin"],"date":"2023-04-26","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14050792","openalex":"W4367182004"},"links":{"paper":"https://doi.org/10.3390/atmos14050792","pdf":"https://www.mdpi.com/2073-4433/14/5/792/pdf?version=1682526992"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"NAO-MCD couples causal discovery with a deep learning air-sea model, outperforming numerical models for 1–6 month NAO seasonal forecasts, especially in winter.","significance":4,"cited_by":10,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30574-gjeta.2023.15.1.0077","title":"Modelling an automated rainfall forecasting system using an optimized intelligent agent","authors":["Umeh Constance Nnenna","James Eke","Eze Ogochukwu Edith"],"date":"2023-04-25","year":2023,"venue":"Global Journal of Engineering and Technology Advances","venue_type":"journal","ids":{"doi":"10.30574/gjeta.2023.15.1.0077","openalex":"W4366994326"},"links":{"paper":"https://doi.org/10.30574/gjeta.2023.15.1.0077","pdf":"https://gjeta.com/sites/default/files/GJETA-2023-0077.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An ANN trained on Nigerian station data reaches over 90% rainfall prediction accuracy, versus 70% for multiple linear regression.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.12952","title":"Causally-informed deep learning to improve climate models and projections","authors":["Fernando Iglesias-Suarez","Pierre Gentine","Breixo Solino-Fernandez","Tom Beucler","Michael Pritchard","Jakob Runge","Veronika Eyring"],"date":"2023-04-25","year":2023,"venue":"Journal of Geophysical Research: Atmospheres, 129, e2023JD039202","venue_type":"journal","ids":{"arxiv":"2304.12952","doi":"10.1029/2023jd039202"},"links":{"paper":"https://arxiv.org/abs/2304.12952","pdf":"https://arxiv.org/pdf/2304.12952"},"orgs":[],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["other","classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Causal discovery selects inputs for neural convection and radiation parameterizations that replace superparameterization, giving stable climate simulations matching the high-resolution model.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.12891","title":"Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification","authors":["Jussi Leinonen","Ulrich Hamann","Daniele Nerini","Urs Germann","Gabriele Franch"],"date":"2023-04-25","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.12891","openalex":"W4367061010"},"links":{"paper":"https://arxiv.org/abs/2304.12891","pdf":"https://arxiv.org/pdf/2304.12891"},"orgs":["meteoswiss"],"topic":"nowcasting","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A latent diffusion model for radar precipitation nowcasting gives more diverse, well-calibrated ensembles than DGMR and PySTEPS, with more accurate predictions.","significance":5,"cited_by":23,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2304.12586","title":"Unsupervised Discovery of Extreme Weather Events Using Universal Representations of Emergent Organization","authors":["Adam Rupe","Karthik Kashinath","Nalini Kumar","James P. Crutchfield"],"date":"2023-04-25","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.12586"},"links":{"paper":"https://arxiv.org/abs/2304.12586","pdf":"https://arxiv.org/pdf/2304.12586"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Unsupervised local causal states detect hurricanes, atmospheric rivers and precipitation extremes in climate data, and track vortices in 2D turbulence.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-22-0109.1","title":"Nowcasting Multiparameter Phased-Array Weather Radar (MP-PAWR) Echoes of Localized Heavy Precipitation Using a 3D Recurrent Neural Network Trained with an Adversarial Technique","authors":["Philippe Baron","Kohei Kawashima","Dongkyun Kim","Hiroshi Hanado","Seiji Kawamura","Takeshi Maesaka","Katsuhiro Nakagawa","Shinsuke Satoh","Tomoo Ushio"],"date":"2023-04-24","year":2023,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-22-0109.1","openalex":"W4366830053"},"links":{"paper":"https://doi.org/10.1175/jtech-d-22-0109.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atot/40/7/JTECH-D-22-0109.1.pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","gan-vae"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"pre-operational","summary":"Adversarially trained 3D LSTM nowcasts sudden localized heavy rain from MP-PAWR radar with 10-min lead, outperforming an advection model and JMA's operational system at onset.","significance":4,"cited_by":10,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.12865","title":"Constraining Chaos: Enforcing dynamical invariants in the training of recurrent neural networks","authors":["Jason A. Platt","Stephen G. Penny","Timothy A. Smith","Tse-Chun Chen","Henry D. I. Abarbanel"],"date":"2023-04-24","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.12865","openalex":"W4367060971"},"links":{"paper":"https://arxiv.org/abs/2304.12865","pdf":"https://arxiv.org/pdf/2304.12865"},"orgs":[],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["rnn","physics-constrained"],"timescale":["medium"],"spatial":[],"data":[],"status":"research","summary":"Trains reservoir-computing RNNs to enforce Lyapunov spectrum and fractal dimension, giving longer stable forecasts on Lorenz 96 and a quasi-geostrophic model.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.12177","title":"Π-ML: A dimensional analysis-based machine learning parameterization of optical turbulence in the atmospheric surface layer","authors":["Maximilian Pierzyna","Rudolf Saathof","Sukanta Basu"],"date":"2023-04-24","year":2023,"venue":"Optics Letters","venue_type":"journal","ids":{"arxiv":"2304.12177","doi":"10.1364/ol.492652","openalex":"W4385427113"},"links":{"paper":"https://doi.org/10.1364/ol.492652","pdf":"https://arxiv.org/pdf/2304.12177"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Dimensional-analysis gradient boosting parameterizes atmospheric surface-layer optical turbulence C_n^2 with R^2 of 0.958 for free-space optical communication.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36948-ijfmr.2023.v05i02.2581","title":"Tropical Cyclone Identification and Alert System using AlexNet and Deep CNN","authors":["Vijay Kumar B -","V. Akhila Sai -","Gondyala Ganesh -","K Hemanth Sagar -"],"date":"2023-04-23","year":2023,"venue":"International Journal For Multidisciplinary Research","venue_type":"journal","ids":{"doi":"10.36948/ijfmr.2023.v05i02.2581","openalex":"W4367189035"},"links":{"paper":"https://doi.org/10.36948/ijfmr.2023.v05i02.2581","pdf":"https://www.ijfmr.com/papers/2023/2/2581.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Uses an AlexNet-based CNN to identify tropical cyclones from aerial imagery for an alert system; a basic classification application.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.11699","title":"DiffESM: Conditional Emulation of Earth System Models with Diffusion Models","authors":["Seth Bassetti","Brian Hutchinson","Claudia Tebaldi","Ben Kravitz"],"date":"2023-04-23","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.11699","openalex":"W4366999846"},"links":{"paper":"https://arxiv.org/abs/2304.11699","pdf":"https://arxiv.org/pdf/2304.11699"},"orgs":[],"topic":"climate-emulation","topics":["extremes-hazards","probabilistic-ensembles"],"type":"model","method":["diffusion"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Diffusion model conditioned on monthly temperature or precipitation generates realistic daily fields matching Earth system model heat waves and dry spells at a fraction of the cost.","significance":5,"cited_by":3,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-2181-2023","title":"Improving trajectory calculations by FLEXPART 10.4+ using single-image super-resolution","authors":["Rüdiger Brecht","Lucie Bakels","Alexander Bihlo","Andreas Stohl"],"date":"2023-04-21","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-2181-2023","openalex":"W4366999412"},"links":{"paper":"https://doi.org/10.5194/gmd-16-2181-2023","pdf":"https://gmd.copernicus.org/articles/16/2181/2023/gmd-16-2181-2023.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"EDSR super-resolution of ERA5 winds halves interpolation RMSE and cuts FLEXPART trajectory errors by at least 49.5% after 48 hours.","significance":4,"cited_by":11,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.106770","title":"Construction of deep-learning based WWBs parameterization for ENSO prediction","authors":["Lirong You","Xiaoxiao Tan","Youmin Tang"],"date":"2023-04-21","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.106770","openalex":"W4366609076"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.106770"},"orgs":[],"topic":"hybrid-parameterization","topics":["s2s-seasonal"],"type":"model","method":[],"timescale":["seasonal"],"spatial":["global"],"data":[],"status":"research","summary":"Builds a deep-learning westerly wind burst parameterization intended to improve ENSO prediction; the abstract is missing, so gains are unknown.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-2167-2023","title":"Forecasting tropical cyclone tracks in the northwestern Pacific based on a deep-learning model","authors":["Liang Wang","Bingcheng Wan","Shaohui Zhou","Haofei Sun","Zhiqiu Gao"],"date":"2023-04-20","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-2167-2023","openalex":"W4366590207"},"links":{"paper":"https://doi.org/10.5194/gmd-16-2167-2023","pdf":"https://gmd.copernicus.org/articles/16/2167/2023/gmd-16-2167-2023.pdf"},"orgs":["nuist","iap-cas"],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"GRU_CNN forecasts northwestern Pacific tropical cyclone tracks for 6 to 72 hours using track history and reanalysis fields, beating RNN, LSTM and GRU.","significance":3,"cited_by":35,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.48185-jaai.v4i1.727","title":"Development of a Lightning Prediction Model Using Machine Learning Algorithm: Survey.","authors":["Babatunde Dauda Raheem","Emeka Ogbuju","Francisca Onaolapo Oladipo"],"date":"2023-04-20","year":2023,"venue":"Journal of Applied Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.48185/jaai.v4i1.727","openalex":"W4366606029"},"links":{"paper":"https://doi.org/10.48185/jaai.v4i1.727","pdf":"https://sabapub.com/index.php/jaai/article/download/727/425"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning lightning prediction model trained on ten years of Lokoja station weather records to give advance lightning warnings.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15082180","title":"Machine Learning-Based Bias Correction of Precipitation Measurements at High Altitude","authors":["Hongyi Li","Yang Zhang","Huajin Lei","Xiaohua Hao"],"date":"2023-04-20","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15082180","openalex":"W4366729194"},"links":{"paper":"https://doi.org/10.3390/rs15082180","pdf":"https://www.mdpi.com/2072-4292/15/8/2180/pdf?version=1681981910"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","satellite"],"status":"research","summary":"XGBoost corrects precipitation gauge undercatch (51.4% at a 4147 m Tibetan site), beating traditional methods and transferring to Norway and the US.","significance":3,"cited_by":43,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0047.1","title":"Correcting Subseasonal Forecast Errors with an Explainable ANN to Understand Misrepresented Sources of Predictability of European Summer Temperatures","authors":["Chiem van Straaten","Kirien Whan","Dim Coumou","Bart van den Hurk","Maurice J. Schmeits"],"date":"2023-04-19","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0047.1","openalex":"W4366413227"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0047.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/aies/2/3/AIES-D-22-0047.1.pdf"},"orgs":["knmi"],"topic":"post-processing","topics":["s2s-seasonal","xai-uq-physics"],"type":"model","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"An explainable ANN corrects ECMWF extended-range European summer temperature exceedance probabilities and traces errors to western Pacific SST teleconnections, improving skill.","significance":4,"cited_by":11,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.09721","title":"Improved Active Fire Detection using Operational U-Nets","authors":["Ozer Can Devecioglu","Mete Ahishali","Fahad Sohrab","Turker Ince","Moncef Gabbouj"],"date":"2023-04-19","year":2023,"venue":"2023 Photonics & Electromagnetics Research Symposium (PIERS), Prague, Czech Republic, 2023, pp. 692-697","venue_type":"journal","ids":{"arxiv":"2304.09721","doi":"10.1109/piers59004.2023.10221241"},"links":{"paper":"https://arxiv.org/abs/2304.09721","pdf":"https://arxiv.org/pdf/2304.09721"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Proposes compact U-Nets with Self-ONN layers for satellite active fire detection, reporting superior detection with reduced computational complexity.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.09536","title":"Decadal Temperature Prediction via Chaotic Behavior Tracking","authors":["Jinfu Ren","Yang Liu","Jiming Liu"],"date":"2023-04-19","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.09536"},"links":{"paper":"https://arxiv.org/abs/2304.09536","pdf":"https://arxiv.org/pdf/2304.09536"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["decadal"],"spatial":["global"],"data":[],"status":"research","summary":"Introduces an information-tracking calibrator that corrects error accumulation in decadal global land-surface temperature prediction, with predictions consistent with known teleconnections.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en16083522","title":"Multi-Horizon Wind Power Forecasting Using Multi-Modal Spatio-Temporal Neural Networks","authors":["Eric Stefan Miele","Nicole Ludwig","Alessandro Corsini"],"date":"2023-04-18","year":2023,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en16083522","openalex":"W4366425360"},"links":{"paper":"https://doi.org/10.3390/en16083522","pdf":"https://www.mdpi.com/1996-1073/16/8/3522/pdf?version=1681825515"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["rnn"],"timescale":["medium"],"spatial":["local"],"data":["nwp-analysis","other"],"status":"research","summary":"Stacked RNN combining SCADA turbine data and NWP maps forecasts wind farm power up to 90 h ahead, with a 25% skill gain over XGBoost.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1186-s40562-023-00272-z","title":"Physics-informed deep learning framework to model intense precipitation events at super resolution","authors":["Bernardo Teufel","Fernanda Custodio Pereira do Carmo","Laxmi Sushama","Lijun Sun","M. Naveed Khaliq","Stéphane Bélair","Asaad Yahia Shamseldin","D. Nagesh Kumar","Jai Vaze"],"date":"2023-04-18","year":2023,"venue":"Geoscience Letters","venue_type":"journal","ids":{"doi":"10.1186/s40562-023-00272-z","openalex":"W4366275709"},"links":{"paper":"https://doi.org/10.1186/s40562-023-00272-z","pdf":"https://geoscienceletters.springeropen.com/counter/pdf/10.1186/s40562-023-00272-z"},"orgs":["eccc"],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["rnn","physics-constrained"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"A physics-informed recurrent deep learning model super-resolves regional climate precipitation from 2.5 km to 250 m, producing realistic intense short-duration events over Montreal.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-15481603.2023.2203363","title":"Precipitation nowcasting using ground radar data and simpler yet better video prediction deep learning","authors":["Daehyeon Han","Minki Choo","Jungho Im","Yeji Shin","Juhyun Lee","Sihun Jung"],"date":"2023-04-18","year":2023,"venue":"GIScience & Remote Sensing","venue_type":"journal","ids":{"doi":"10.1080/15481603.2023.2203363","openalex":"W4366346940"},"links":{"paper":"https://doi.org/10.1080/15481603.2023.2203363"},"orgs":["kma"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"SimVP-based radar nowcasting over South Korea improves 120-min CSI at 1 mm/h to 0.46 and handles typhoons and narrow convection better than prior models.","significance":3,"cited_by":36,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.09070","title":"M-ENIAC: A machine learning recreation of the first successful numerical weather forecasts","authors":["Rüdiger Brecht","Alex Bihlo"],"date":"2023-04-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.09070","openalex":"W4366460024"},"links":{"paper":"https://arxiv.org/abs/2304.09070","pdf":"https://arxiv.org/pdf/2304.09070"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"application","method":["physics-constrained"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Physics-informed neural networks recreate the 1950 ENIAC barotropic vorticity forecasts on the sphere, achieving more accurate solutions than the original numerical solver.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.08754","title":"W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting","authors":["Xin Man","Chenghong Zhang","Jin Feng","Changyu Li","Jie Shao"],"date":"2023-04-18","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.08754","openalex":"W4366457940"},"links":{"paper":"https://arxiv.org/abs/2304.08754","pdf":"https://arxiv.org/pdf/2304.08754"},"orgs":["cma"],"topic":"foundation-models","topics":["global-medium-range"],"type":"model","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"W-MAE pretrains a masked autoencoder on ERA5 and fine-tunes it for forecasting, lifting FourCastNet's anomaly correlation by about 20 percent.","significance":4,"cited_by":9,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-hess-27-1583-2023","title":"Improving regional climate simulations based on a hybrid data assimilation and machine learning method","authors":["Xinlei He","Yanping Li","Shaomin Liu","Tongren Xu","Fei Chen","Zhenhua Li","Zhe Zhang","Rui Liu","Lisheng Song","Ziwei Xu","Zhixing Peng","Chen Zheng"],"date":"2023-04-17","year":2023,"venue":"Hydrology and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/hess-27-1583-2023","openalex":"W4366209655"},"links":{"paper":"https://doi.org/10.5194/hess-27-1583-2023"},"orgs":["ncar"],"topic":"data-assimilation","topics":["regional-km-scale"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Couples data assimilation with ML to optimise WRF land-surface states in the Heihe basin, improving temperature and humidity simulations and ET estimates.","significance":3,"cited_by":33,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.08063","title":"Data-Driven Equation Discovery of a Cloud Cover Parameterization","authors":["Arthur Grundner","Tom Beucler","Pierre Gentine","Veronika Eyring"],"date":"2023-04-17","year":2023,"venue":"Journal of Advances in Modeling Earth Systems (JAMES), 2024","venue_type":"journal","ids":{"arxiv":"2304.08063","doi":"10.1029/2023ms003763","openalex":"W4392352441"},"links":{"paper":"https://arxiv.org/abs/2304.08063","pdf":"https://arxiv.org/pdf/2304.08063"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["global"],"data":["km-scale-sim","era5"],"status":"research","summary":"Symbolic regression yields an 11-parameter interpretable cloud cover equation matching neural network skill (R²=0.94), beating Xu-Randall and transferring better to ERA5.","significance":5,"cited_by":38,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-rs15082085","title":"Estimation of Tropical Cyclone Intensity Using Multi-Platform Remote Sensing and Deep Learning with Environmental Field Information","authors":["Wei Tian","Linhong Lai","Xianghua Niu","Xinxin Zhou","Yonghong Zhang","Kenny Thiam Choy Lim Kam Sian"],"date":"2023-04-15","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15082085","openalex":"W4366091598"},"links":{"paper":"https://doi.org/10.3390/rs15082085","pdf":"https://www.mdpi.com/2072-4292/15/8/2085/pdf?version=1681718895"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["transformer","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Rotation-equivariant convolution combined with a Transformer estimates tropical cyclone intensity from multi-platform satellite and environmental data, with RMSE of 8.19 kt.","significance":3,"cited_by":19,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15081545","title":"A Method for Monthly Extreme Precipitation Forecasting with Physical Explanations","authors":["Binlin Yang","Lu Chen","Vijay Pal Singh","Bin Yi","Zhiyuan Leng","Jie Zheng","Song Qiao"],"date":"2023-04-14","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15081545","openalex":"W4365509517"},"links":{"paper":"https://doi.org/10.3390/w15081545","pdf":"https://www.mdpi.com/2073-4441/15/8/1545/pdf?version=1681468764"},"orgs":[],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Random forest with SST-based predictors forecasts monthly summer extreme precipitation in the Yangtze basin with R2 above 0.81 and physical explanations.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-22-0225.1","title":"Trustworthy Artificial Intelligence for Environmental Sciences: An Innovative Approach for Summer School","authors":["Amy McGovern","David John Gagne","Christopher D. Wirz","Imme Ebert‐Uphoff","Ann Bostrom","Yuhan Douglas Rao","Andrea Schumacher","Montgomery L. Flora","Randy J. Chase","Antonios Mamalakis","Marie C. McGraw","Ryan Lagerquist","Robert Joseph Redmon","Taysia Peterson"],"date":"2023-04-14","year":2023,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-22-0225.1","openalex":"W4365508948"},"links":{"paper":"https://doi.org/10.1175/bams-d-22-0225.1"},"orgs":["noaa","ncar","university-of-washington","colorado-state-university","university-of-oklahoma"],"topic":"xai-uq-physics","topics":["benchmarks-data-eval"],"type":"position","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Describes an AI2ES summer school teaching trustworthy and explainable AI for severe storms, tropical cyclones and space weather to 677 participants.","significance":2,"cited_by":8,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-023-02444-x","title":"Downscaling long lead time daily rainfall ensemble forecasts through deep learning","authors":["Huidong Jin","Weifan Jiang","Minzhe Chen","Ming Li","K. Shuvo Bakar","Quanxi Shao"],"date":"2023-04-14","year":2023,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-023-02444-x","openalex":"W4365514553"},"links":{"paper":"https://doi.org/10.1007/s00477-023-02444-x","pdf":"https://link.springer.com/content/pdf/10.1007/s00477-023-02444-x.pdf"},"orgs":[],"topic":"downscaling","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Deep-learning downscaling of ACCESS-S1 seasonal rainfall ensembles to 12 km, trained on CRPS, beats quantile mapping for lead times up to 217 days.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.07151","title":"End-to-End Learning with Multiple Modalities for System-Optimised Renewables Nowcasting","authors":["Rushil Vohra","Ali Rajaei","Jochen L. Cremer"],"date":"2023-04-14","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.07151"},"links":{"paper":"https://arxiv.org/abs/2304.07151","pdf":"https://arxiv.org/pdf/2304.07151"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"model","method":["cnn","differentiable"],"timescale":["nowcast"],"spatial":["regional"],"data":["other","stations"],"status":"research","summary":"Multimodal sky-image and meteorological end-to-end learning nowcasts renewable power and cuts system cost 30% versus unimodal baselines in a Dutch case study.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.07029","title":"Challenges of learning multi-scale dynamics with AI weather models: Implications for stability and one solution","authors":["Ashesh Chattopadhyay","Y. Qiang Sun","Pedram Hassanzadeh"],"date":"2023-04-14","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.07029","openalex":"W4366198063"},"links":{"paper":"https://arxiv.org/abs/2304.07029","pdf":"https://arxiv.org/pdf/2304.07029"},"orgs":["university-of-chicago"],"topic":"climate-emulation","topics":[],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Attributes instability in AI weather models to spectral bias and proposes a mitigation enabling hundreds of years of physically consistent integration.","significance":4,"cited_by":14,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"openalex-W4365461164","title":"Spatiotemporal Super-Resolution with Generative Machine Learning for Creating Renewable Energy Resource Data Under Climate Change Scenarios","authors":["Grant Buster"],"date":"2023-04-13","year":2023,"venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","venue_type":"preprint","ids":{"openalex":"W4365461164"},"links":{"paper":"https://www.osti.gov/biblio/1968837","pdf":"https://www.osti.gov/biblio/1968837"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Generative ML downscales daily CMIP GCM output to hourly 4 km weather for wind, solar, temperature and humidity, enabling grid studies under climate change.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.65521-intjournalrecadvengtech.v12i1.2201","title":"A Comprehensive Review of Environmental Weather Monitoring and Prediction System Using IoT and Multi-Model Progressive Dense Self-Attention","authors":["Quillon Yaprakli"],"date":"2023-04-13","year":2023,"venue":"International Journal Of Recent Advances in Engineering & Technology","venue_type":"journal","ids":{"doi":"10.65521/intjournalrecadvengtech.v12i1.2201","openalex":"W7162410561"},"links":{"paper":"https://doi.org/10.65521/intjournalrecadvengtech.v12i1.2201","pdf":"https://journals.mriindia.com/index.php/ijraet/article/download/2201/2113"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"review","method":["transformer","rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["stations","satellite"],"status":"research","summary":"Reviews IoT sensor-based weather monitoring and deep learning forecasting, including self-attention and hybrid CNN-LSTM models, with challenges and future directions.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.106754","title":"An innovative approach to predict atmospheric rivers: Exploring convolutional autoencoder","authors":["Shivam H Singh","Manish Kumar Goyal"],"date":"2023-04-13","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.106754","openalex":"W4365458731"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.106754"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"A convolutional autoencoder is proposed to predict atmospheric rivers; the abstract is missing, so accuracy and data cannot be confirmed.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14040708","title":"A Comparison of the Statistical Downscaling and Long-Short-Term-Memory Artificial Neural Network Models for Long-Term Temperature and Precipitations Forecasting","authors":["Noé Carème Fouotsa Manfouo","Linke Potgieter","Andrew Watson","Johanna Helena Nel"],"date":"2023-04-12","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14040708","openalex":"W4365447830"},"links":{"paper":"https://doi.org/10.3390/atmos14040708","pdf":"https://www.mdpi.com/2073-4433/14/4/708/pdf?version=1681374459"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"LSTM outperforms statistical downscaling (SDSM) for monthly temperature and precipitation at five Lake Chad Basin stations using coarse GCM output.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15081495","title":"Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning","authors":["Pranav Dhawan","Daniele Dalla Torre","Ariele Zanfei","Andrea Menapace","Michele Larcher","Maurizio Righetti"],"date":"2023-04-11","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15081495","openalex":"W4365149383"},"links":{"paper":"https://doi.org/10.3390/w15081495"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn"],"timescale":["medium"],"spatial":["local"],"data":["era5","stations"],"status":"research","summary":"An LSTM driven by ERA5-Land inputs forecasts drinking water demand from 7 days to two months; ERA5-Land is usable but needs bias correction.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.05510","title":"chatClimate: Grounding Conversational AI in Climate Science","authors":["Saeid Ashraf Vaghefi","Dominik Stammbach","Veruska Muccione","Julia Bingler","Jingwei Ni","Mathias Kraus","Simon Allen","Chiara Colesanti-Senni","Tobias Wekhof","Tobias Schimanski","Glen Gostlow","Tingyu Yu","Qian Wang","Nicolas Webersinke","Christian Huggel","Markus Leippold"],"date":"2023-04-11","year":2023,"venue":"Communications Earth &amp; Environment","venue_type":"journal","ids":{"arxiv":"2304.05510","doi":"10.1038/s43247-023-01084-x","openalex":"W4389785739"},"links":{"paper":"https://arxiv.org/abs/2304.05510","pdf":"https://arxiv.org/pdf/2304.05510"},"orgs":["eth-zurich","university-of-oxford"],"topic":"llms-agents","topics":["benchmarks-data-eval"],"type":"model","method":["llm"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"GPT-4 grounded with IPCC AR6 content via retrieval; expert-scored answers show the hybrid chatClimate more accurate than GPT-4 alone.","significance":4,"cited_by":135,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2304.05029","title":"Turbulence closure with small, local neural networks: Forced two-dimensional and $β$-plane flows","authors":["Kaushik Srinivasan","Mickael D. Chekroun","James C. McWilliams"],"date":"2023-04-11","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.05029"},"links":{"paper":"https://arxiv.org/abs/2304.05029","pdf":"https://arxiv.org/pdf/2304.05029"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["km-scale-sim"],"status":"research","summary":"Two-layer CNNs with about 1000 parameters learn subgrid stresses for forced 2D beta-plane turbulence, giving stable online LES at 16x downscaling. Idealized geophysical flow.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.7813831","title":"A machine learning approach to model tropical cyclone precipitation","authors":["Joseph W. Lockwood"],"date":"2023-04-10","year":2023,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.7813831","openalex":"W4362737722"},"links":{"paper":"https://doi.org/10.5281/zenodo.7813831"},"orgs":["princeton-university"],"topic":"extremes-hazards","topics":[],"type":"model","method":[],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Supplementary figures only for a machine learning study of tropical cyclone precipitation; the record gives no method or results.","significance":1,"cited_by":0,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15081999","title":"Weather Radar Super-Resolution Reconstruction Based on Residual Attention Back-Projection Network","authors":["Qiu Yu","Ming Qiao Zhu","Qiangyu Zeng","Hao Wang","Qingqing Chen","Xiangyu Fu","Zhipeng Qing"],"date":"2023-04-10","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15081999","openalex":"W4364360105"},"links":{"paper":"https://doi.org/10.3390/rs15081999","pdf":"https://www.mdpi.com/2072-4292/15/8/1999/pdf?version=1681202389"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Residual attention back-projection network super-resolves weather radar base echoes, outperforming compared CNN methods visually and quantitatively in echo detail and edges.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.04728","title":"Visual anemometry: physics-informed inference of wind for renewable energy, urban sustainability, and environmental science","authors":["John O. Dabiri","Michael F. Howland","Matthew K. Fu","Roni H. Goldshmid"],"date":"2023-04-10","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.04728","openalex":"W4364387738"},"links":{"paper":"https://arxiv.org/abs/2304.04728","pdf":"https://arxiv.org/pdf/2304.04728"},"orgs":["mit","caltech"],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"review","method":["physics-constrained","other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Reviews physics-informed and data-driven visual anemometry, inferring local wind from the motion of trees and flags for renewable energy and urban applications.","significance":2,"cited_by":1,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.106750","title":"Extreme and severe convective weather disasters: A dual-polarization radar nowcasting method based on physical constraints and a deep neural network model","authors":["Lei Wang","Yuanchang Dong","Chenghong Zhang","Zhiwei Heng"],"date":"2023-04-09","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.106750","openalex":"W4362719802"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.106750"},"orgs":["cma"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["physics-constrained","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Dual-polarization radar nowcasting of severe convective weather combines physical constraints with a deep neural network; abstract unavailable, so details are limited.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-22-0714.1","title":"A Deep-Learning Reconstruction of Tropical Cyclone Size Metrics 1981–2017: Examining Trends","authors":["Jing‐Yi Zhuo","Zhe‐Min Tan"],"date":"2023-04-07","year":2023,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-22-0714.1","openalex":"W4362698469"},"links":{"paper":"https://doi.org/10.1175/jcli-d-22-0714.1"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards","climate-analysis-attribution"],"type":"benchmark","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Transfer-learned deep networks estimate western North Pacific tropical cyclone size from infrared imagery, producing a 1981–2017 DeepTCSize record with R of 0.76–0.85.","significance":4,"cited_by":19,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s42452-023-05350-7","title":"Early warning of low visibility using the ensembling of machine learning approaches for aviation services at Jay Prakash Narayan International (JPNI) Airport Patna","authors":["Anand Shankar","Bikash Chandra Sahana"],"date":"2023-04-07","year":2023,"venue":"SN Applied Sciences","venue_type":"journal","ids":{"doi":"10.1007/s42452-023-05350-7","openalex":"W4362697160"},"links":{"paper":"https://doi.org/10.1007/s42452-023-05350-7","pdf":"https://link.springer.com/content/pdf/10.1007/s42452-023-05350-7.pdf"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Ensemble ML models forecast fog and dense fog at Patna airport from 6 h to 1 h ahead using historical synoptic station data for aviation early warning.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.03748","title":"Perspectives on AI Architectures and Co-design for Earth System Predictability","authors":["Maruti K. Mudunuru","James A. Ang","Mahantesh Halappanavar","Simon D. Hammond","Maya B. Gokhale","James C. Hoe","Tushar Krishna","Sarat S. Sreepathi","Matthew R. Norman","Ivy B. Peng","Philip W. Jones"],"date":"2023-04-07","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.03748"},"links":{"paper":"https://arxiv.org/abs/2304.03748","pdf":"https://arxiv.org/pdf/2304.03748"},"orgs":[],"topic":"infra-software","topics":[],"type":"position","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A DOE workshop report on AI architectures and HPC co-design for Earth system predictability, covering computing systems, data pipelines and sensor integration.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15071951","title":"A Novel Hybrid Intelligent SOPDEL Model with Comprehensive Data Preprocessing for Long-Time-Series Climate Prediction","authors":["Zeyu Zhou","Tang We","Mingyang Li","Wen Lun Cao","Zhijie Yuan"],"date":"2023-04-06","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15071951","openalex":"W4362665370"},"links":{"paper":"https://doi.org/10.3390/rs15071951","pdf":"https://www.mdpi.com/2072-4292/15/7/1951/pdf?version=1681097940"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["other"],"status":"research","summary":"Hybrid SOPDEL model combining decomposition, DBN-ELM and LSTM improves long-time-series climate prediction; the abstract gives no quantitative result.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.04664","title":"Inductive biases in deep learning models for weather prediction","authors":["Jannik Thuemmel","Matthias Karlbauer","Sebastian Otte","Christiane Zarfl","Georg Martius","Nicole Ludwig","Thomas Scholten","Ulrich Friedrich","Volker Wulfmeyer","Bedartha Goswami","Martin V. Butz"],"date":"2023-04-06","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.04664","openalex":"W4364387432"},"links":{"paper":"https://arxiv.org/abs/2304.04664","pdf":"https://arxiv.org/pdf/2304.04664"},"orgs":["dwd"],"topic":"global-medium-range","topics":["benchmarks-data-eval"],"type":"review","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Reviews and analyses inductive biases (data, objectives, losses, architectures, optimisation) of deep-learning weather prediction models to guide more efficient, probabilistic designs.","significance":4,"cited_by":13,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.02948","title":"FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead","authors":["Kang Chen","Tao Han","Junchao Gong","Lei Bai","Fenghua Ling","Jing-Jia Luo","Xi Chen","Leiming Ma","Tianning Zhang","Rui Su","Yuanzheng Ci","Bin Li","Xiaokang Yang","Wanli Ouyang"],"date":"2023-04-06","year":2023,"venue":"Commun. Earth Environ. 6, 518 (2025)","venue_type":"journal","ids":{"arxiv":"2304.02948","doi":"10.1038/s43247-025-02502-y","openalex":"W4411936988"},"links":{"paper":"https://arxiv.org/abs/2304.02948","pdf":"https://arxiv.org/pdf/2304.02948"},"orgs":["iap-cas","nuist","shanghai-ai-lab"],"topic":"global-medium-range","topics":["data-assimilation"],"type":"model","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"FengWu is a multi-modal transformer forecasting system that extends skillful forecasts to 10.75 days, beating GraphCast on 80% of 880 predictands.","significance":8,"cited_by":136,"score":77,"highlight":true,"highlight_reason":"FengWu beats GraphCast on most variables and extends skillful global forecasts past 10 days, making it a leading data-driven NWP model.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos14040687","title":"Machine Learning and Physics-Based Hybridization Models for Evaluation of the Effects of Climate Change and Urban Expansion on Photosynthetically Active Radiation","authors":["Samuel Chukwujindu Nwokolo","Nikolaos D. Proutsos","Edson L. Meyer","Chinedu Christian Ahia"],"date":"2023-04-05","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14040687","openalex":"W4362669884"},"links":{"paper":"https://doi.org/10.3390/atmos14040687","pdf":"https://www.mdpi.com/2073-4433/14/4/687/pdf?version=1680860666"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Hybrid ML and physics models attribute projected photosynthetically active radiation changes in China and India to climate change versus urban expansion, using CMIP6 models.","significance":2,"cited_by":37,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32628-ijsrset2310288","title":"Marine Weather Forecasting to Enhance Fisherman's Safety Using Machine Learning","authors":["M. Robinson Joel","G. Manikandan","Ms. S. Nivetha"],"date":"2023-04-05","year":2023,"venue":"International Journal of Scientific Research in Science Engineering and Technology","venue_type":"journal","ids":{"doi":"10.32628/ijsrset2310288","openalex":"W4367692519"},"links":{"paper":"https://doi.org/10.32628/ijsrset2310288","pdf":"https://ijsrset.com/paper/8906.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Surveys machine learning methods for weather forecasting, framed around marine forecasts for fisherman safety, without new models or quantitative results.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-x5vq1s","title":"EfficientRainNet: Smaller Neural Networks Based on EfficientNetV2 for Rainfall Nowcasting","authors":["Muhammed Ali Sit","Bong‐Chul Seo","Bekir Zahit Demiray","İbrahim Demir"],"date":"2023-04-05","year":2023,"venue_type":"other","ids":{"doi":"10.31223/x5vq1s","openalex":"W4362632977"},"links":{"paper":"https://doi.org/10.31223/x5vq1s","pdf":"https://eartharxiv.org/repository/object/5232/download/10314/"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"EfficientRainNet, a lightweight EfficientNetV2-based CNN, matches convolutional GRU rainfall nowcasts on Iowa radar data with far fewer parameters.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-wcd-4-287-2023","title":"Improved extended-range prediction of persistent stratospheric perturbations using machine learning","authors":["Raphaël de Fondeville","Zheng Wu","Enikő Székely","Guillaume Obozinski","Daniela I. V. Domeisen"],"date":"2023-04-04","year":2023,"venue":"Weather and Climate Dynamics","venue_type":"journal","ids":{"doi":"10.5194/wcd-4-287-2023","openalex":"W4362554316"},"links":{"paper":"https://doi.org/10.5194/wcd-4-287-2023","pdf":"https://wcd.copernicus.org/articles/4/287/2023/wcd-4-287-2023.pdf"},"orgs":["eth-zurich","sdsc"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["nwp-analysis","era5"],"status":"research","summary":"Data-driven ML models forecast stratospheric sudden warmings better than ECMWF S2S beyond 25 days and boost ensemble skill by up to 20%.","significance":4,"cited_by":8,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-20964471.2023.2196830","title":"Improving risk reduction potential of weather index insurance by spatially downscaling gridded climate data - a machine learning approach","authors":["S. Eltazarov","Ihtiyor Bobojonov","Lena Kuhn","Thomas Glauben"],"date":"2023-04-04","year":2023,"venue":"Big Earth Data","venue_type":"journal","ids":{"doi":"10.1080/20964471.2023.2196830","openalex":"W4362633204"},"links":{"paper":"https://doi.org/10.1080/20964471.2023.2196830","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/20964471.2023.2196830?needAccess=true&role=button"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"ML downscaling of gridded precipitation, temperature and soil moisture improves weather index insurance hedging in 70% of Kazakh and Mongolian county cases.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023gl103405","title":"Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data","authors":["Peiyuan Li","Yu Yin","Daning Huang","Zhi‐Hua Wang","Ashish S. Sharma"],"date":"2023-04-04","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2023gl103405","openalex":"W4362627411"},"links":{"paper":"https://doi.org/10.1029/2023gl103405"},"orgs":["argonne"],"topic":"extremes-hazards","topics":[],"type":"model","method":["gnn"],"timescale":["short"],"spatial":["regional","local"],"data":["stations"],"status":"research","summary":"A graph neural network predicts regional heatwaves from weather station data, enabling real-time warnings at lower computational and data cost.","significance":3,"cited_by":57,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.02117","title":"Statistics of extreme events in coarse-scale climate simulations via machine learning correction operators trained on nudged datasets","authors":["Alexis-Tzianni Charalampopoulos","Shixuan Zhang","Bryce Harrop","Lai-yung Ruby Leung","Themistoklis Sapsis"],"date":"2023-04-04","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.02117","openalex":"W4362702126"},"links":{"paper":"https://arxiv.org/abs/2304.02117","pdf":"https://arxiv.org/pdf/2304.02117"},"orgs":["mit"],"topic":"climate-emulation","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"Machine-learned correction operator, trained on nudged coarse E3SM runs against ERA5, makes free-running climate statistics and extreme-event frequencies resemble observations.","significance":4,"cited_by":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.01879","title":"A neural network-based scale-adaptive cloud-fraction scheme for GCMs","authors":["Guoxing Chen","Wei-Chyung Wang","Shixi Yang","Yixin Wang","Feng Zhang","Kun Wu"],"date":"2023-04-04","year":2023,"venue":"Journal of Advances in Modeling Earth Systems, 2023","venue_type":"journal","ids":{"arxiv":"2304.01879","doi":"10.1029/2022ms003415","openalex":"W4380627071"},"links":{"paper":"https://arxiv.org/abs/2304.01879","pdf":"https://arxiv.org/pdf/2304.01879"},"orgs":["fudan-university","nuist"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["satellite","cmip"],"status":"research","summary":"Neural network sub-grid cloud fraction scheme trained on CloudSat data reaches r > 0.9 and reduces high- and low-level cloud biases in GCM simulations.","significance":4,"cited_by":27,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.00067","title":"Structural Forecasting for Short-Term Tropical Cyclone Intensity Guidance","authors":["Trey McNeely","Pavel Khokhlov","Niccolò Dalmasso","Kimberly M. Wood","Ann B. Lee"],"date":"2023-04-04","year":2023,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"arxiv":"2206.00067","doi":"10.1175/waf-d-22-0111.1","openalex":"W4362554102"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0111.1","pdf":"https://arxiv.org/pdf/2206.00067"},"orgs":["microsoft-research"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["cnn","other"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Probabilistic structural forecasts simulate geostationary IR radial profiles with PixelSNAIL and feed a CNN, giving intensity errors near NHC official forecasts.","significance":3,"cited_by":9,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-01431161.2023.2201383","title":"Retrieving leaf area index from FY-3D MERSI-II data using a sensor-adaptive algorithm","authors":["Yepei Chen","Pengfei Li","Chuan Xu","Zhina Song","Kaimin Sun","Wenzhuo Li","Xiuqing Hu","Qing An"],"date":"2023-04-03","year":2023,"venue":"International Journal of Remote Sensing","venue_type":"journal","ids":{"doi":"10.1080/01431161.2023.2201383","openalex":"W4366692769"},"links":{"paper":"https://doi.org/10.1080/01431161.2023.2201383"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A sensor-adaptive leaf area index retrieval for FY-3D MERSI-II combines radiative transfer with a neural network backup and agrees well with MODIS (R2 0.85).","significance":2,"cited_by":4,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54097-hset.v39i.6613","title":"Precipitation Forecasting Using Transformer: A Comparative Study with Unet","authors":["Sining Ang"],"date":"2023-04-01","year":2023,"venue":"Highlights in Science Engineering and Technology","venue_type":"journal","ids":{"doi":"10.54097/hset.v39i.6613","openalex":"W4362670437"},"links":{"paper":"https://doi.org/10.54097/hset.v39i.6613","pdf":"https://drpress.org/ojs/index.php/HSET/article/download/6613/6405"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","cnn"],"timescale":["nowcast"],"spatial":[],"data":["satellite"],"status":"research","summary":"Compares U-Net and Transformer for precipitation prediction from cloud-layer information; U-Net reaches 96.89% accuracy versus 94.13% for the Transformer.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0078.1","title":"Improving Seasonal Prediction of Summer Precipitation in the Middle–Lower Reaches of the Yangtze River Using a TU-Net Deep Learning Approach","authors":["Shuxian Yang","Fenghua Ling","Yue Li","Jing‐Jia Luo"],"date":"2023-04-01","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0078.1","openalex":"W4379526258"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0078.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0078.1.pdf"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"A two-step U-Net (TU-Net) predicts 4-month-lead summer precipitation over the Yangtze and beats most NMME dynamical models on correlation and RMSE.","significance":4,"cited_by":5,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0061.1","title":"Creating and Evaluating Uncertainty Estimates with Neural Networks for Environmental-Science Applications","authors":["Katherine Haynes","Ryan Lagerquist","Marie McGraw","Kate Musgrave","Imme Ebert-Uphoff"],"date":"2023-04-01","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0061.1","openalex":"W4313893684"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0061.1"},"orgs":["colorado-state-university","noaa"],"topic":"xai-uq-physics","topics":["benchmarks-data-eval"],"type":"review","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Introduces six neural network uncertainty methods and evaluation scores for environmental science, demonstrated on dewpoint profiles and Himawari-8 convection prediction.","significance":5,"cited_by":48,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1088-2515-7620-acca6e","title":"Can we use a machine learning approach to predict the impact of heatwaves on emergency department attendance?","authors":["Le Jian","Dimpalben Patel","Jianguo Xiao","Janis Jansz","Grace Yun","Ting Lin","Andrew Robertson"],"date":"2023-04-01","year":2023,"venue":"Environmental Research Communications","venue_type":"journal","ids":{"doi":"10.1088/2515-7620/acca6e","openalex":"W4362538109"},"links":{"paper":"https://doi.org/10.1088/2515-7620/acca6e","pdf":"https://iopscience.iop.org/article/10.1088/2515-7620/acca6e/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Random forest and geographic random forest models link heatwaves, air pollution and socioeconomic status to emergency department attendances in Perth, with R² of 0.975.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2023ms003606","title":"Neural‐Network Parameterization of Subgrid Momentum Transport in the Atmosphere","authors":["Janni Yuval","Paul Ambrose O'Gorman"],"date":"2023-04-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2023ms003606","openalex":"W4362664248"},"links":{"paper":"https://doi.org/10.1029/2023ms003606","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2023MS003606"},"orgs":["mit"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A neural-network subgrid momentum parameterization trained on high-resolution aquaplanet output conserves momentum and gives stable coarse-model runs with reduced wind biases.","significance":4,"cited_by":27,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003495","title":"Using Deep Learning for an Analysis of Atmospheric Rivers in a High‐Resolution Large Ensemble Climate Data Set","authors":["Timothy B. Higgins","Aneesh C. Subramanian","Andre Graubner","Lukas Kapp‐Schwoerer","Peter A. G. Watson","Sarah Sparrow","Karthik Kashinath","Sol Kim","Luca Delle Monache","Will Chapman"],"date":"2023-04-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003495","openalex":"W4365814766"},"links":{"paper":"https://doi.org/10.1029/2022ms003495","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003495"},"orgs":["nvidia","ncar","eth-zurich","university-of-oxford","uc-berkeley"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["cmip","km-scale-sim"],"status":"research","summary":"A deep learning atmospheric river tracker is applied to a high-resolution large-ensemble climate dataset and checked for consistency against established algorithms over the US West Coast.","significance":3,"cited_by":20,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003135","title":"Improving E3SM Land Model Photosynthesis Parameterization via Satellite SIF, Machine Learning, and Surrogate Modeling","authors":["Anping Chen","Daniel M. Ricciuto","Jiafu Mao","Jiawei Wang","Dan Lu","Fandong Meng"],"date":"2023-04-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003135","openalex":"W4366831741"},"links":{"paper":"https://doi.org/10.1029/2022ms003135","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003135"},"orgs":["ornl","colorado-state-university"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"Boosted trees and random forests map satellite SIF to GPP to calibrate E3SM land photosynthesis parameters, reducing simulated GPP uncertainty after surrogate-based benchmarking.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14040658","title":"Physics-Informed Deep Learning for Reconstruction of Spatial Missing Climate Information in the Antarctic","authors":["Ziqiang Yao","Tao Zhang","Li Wu","Xiaoying Wang","Jianqiang Huang"],"date":"2023-03-31","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14040658","openalex":"W4362472222"},"links":{"paper":"https://doi.org/10.3390/atmos14040658","pdf":"https://www.mdpi.com/2073-4433/14/4/658/pdf?version=1680242120"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","physics-constrained"],"timescale":[],"spatial":["regional"],"data":["stations","cmip"],"status":"research","summary":"A physics-initialized inpainting network (PI-RFR) fills large gaps in Antarctic temperature and wind fields, improving on Kriging and IDW by 63 to 74 percent.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fpls.2023.1143677","title":"A novel pyramid temporal causal network for weather prediction","authors":["Minglei Yuan"],"date":"2023-03-31","year":2023,"venue":"Frontiers in Plant Science","venue_type":"journal","ids":{"doi":"10.3389/fpls.2023.1143677","openalex":"W4362519233"},"links":{"paper":"https://doi.org/10.3389/fpls.2023.1143677","pdf":"https://www.frontiersin.org/articles/10.3389/fpls.2023.1143677/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"PTCN uses multi-scale causal dilated convolutions and a new MVLoss to improve prediction of small-variance weather variables on WFD2018.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.00176","title":"Improving extreme weather events detection with light-weight neural networks","authors":["Romain Lacombe","Hannah Grossman","Lucas Hendren","David Lüdeke"],"date":"2023-03-31","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.00176","openalex":"W4362598044"},"links":{"paper":"https://arxiv.org/abs/2304.00176","pdf":"https://arxiv.org/pdf/2304.00176"},"orgs":["stanford"],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Modified light-weight Context Guided CNN with weighted loss raises recall for tropical cyclone detection in climate simulation data.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.00116","title":"Enhancing Large Language Models with Climate Resources","authors":["Mathias Kraus","Julia Anna Bingler","Markus Leippold","Tobias Schimanski","Chiara Colesanti Senni","Dominik Stammbach","Saeid Ashraf Vaghefi","Nicolas Webersinke"],"date":"2023-03-31","year":2023,"venue_type":"preprint","ids":{"arxiv":"2304.00116"},"links":{"paper":"https://arxiv.org/abs/2304.00116","pdf":"https://arxiv.org/pdf/2304.00116"},"orgs":[],"topic":"llms-agents","topics":[],"type":"model","method":["llm"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"LLM agent retrieves emissions data from ClimateWatch and web search to give more precise answers on climate change topics.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54076-jumpa.v3i1.302","title":"Comparison performance analysis of autoregressive integrated moving average and deep learning long-short term memory forecasting weather data","authors":["Alfiansyah Hasibuan","Medi Hermanto Tinambunan","Purwa Hasan Putra"],"date":"2023-03-30","year":2023,"venue":"Jurnal Matematika Dan Ilmu Pengetahuan Alam LLDikti Wilayah 1 (JUMPA)","venue_type":"journal","ids":{"doi":"10.54076/jumpa.v3i1.302","openalex":"W4365151793"},"links":{"paper":"https://doi.org/10.54076/jumpa.v3i1.302","pdf":"https://lldikti1.kemdikbud.go.id/jurnal/index.php/jumpa/article/download/302/122"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM beats ARIMA on most station weather variables such as temperature, humidity and radiation, and in computation time, though precipitation errors remain highest.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-22-0164.1","title":"Statistical Downscaling in the Tropics and Midlatitudes: A Comparative Assessment over Two Representative Regions","authors":["Alfonso Hernanz","Carlos Correa","Marta Domínguez","Esteban Rodríguez‐Guisado","Ernesto Rodríguez Camino"],"date":"2023-03-30","year":2023,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-22-0164.1","openalex":"W4361272852"},"links":{"paper":"https://doi.org/10.1175/jamc-d-22-0164.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/apme/62/6/JAMC-D-22-0164.1.pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"Compares statistical downscaling methods, including XGBoost, for temperature and precipitation in Spain and Central America, finding model output statistics best for temperature.","significance":4,"cited_by":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-acc8eb","title":"Probabilistic forecasting of tropical cyclones intensity using machine learning model","authors":["Fan Meng","Yichen Yao","Zhibin Wang","Shiqiu Peng","Danya Xu","Tao Song"],"date":"2023-03-30","year":2023,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/acc8eb","openalex":"W4361264505"},"links":{"paper":"https://doi.org/10.1088/1748-9326/acc8eb","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/acc8eb/pdf"},"orgs":["alibaba-damo"],"topic":"extremes-hazards","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning gives probabilistic tropical cyclone intensity forecasts with intervals, and its point forecasts outperform an operational statistical-dynamical model over 2010–2020.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.17195","title":"Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers","authors":["Zied Ben-Bouallegue","Jonathan A Weyn","Mariana C A Clare","Jesper Dramsch","Peter Dueben","Matthew Chantry"],"date":"2023-03-30","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.17195","openalex":"W4361865915"},"links":{"paper":"https://arxiv.org/abs/2303.17195","pdf":"https://arxiv.org/pdf/2303.17195"},"orgs":[],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis","era5"],"status":"research","summary":"PoET, a hierarchical transformer, calibrates ensemble members directly and improves global 2m temperature skill by up to 20% over the raw ensemble.","significance":5,"cited_by":7,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.54302-mausam.v74i2.5997","title":"A Machine Learning Approach for Probabilistic Multi-Model Ensemble Predictions of Indian Summer Monsoon Rainfall","authors":["Nachiketa Acharya","Kyle Joseph Chen Hall"],"date":"2023-03-29","year":2023,"venue":"MAUSAM","venue_type":"journal","ids":{"doi":"10.54302/mausam.v74i2.5997","openalex":"W4361199578"},"links":{"paper":"https://doi.org/10.54302/mausam.v74i2.5997","pdf":"https://mausamjournal.imd.gov.in/index.php/MAUSAM/article/download/5997/5607"},"orgs":["noaa"],"topic":"s2s-seasonal","topics":["post-processing","probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Probabilistic Output Extreme Learning Machine builds multi-model ensembles for Indian summer monsoon rainfall, aiming to avoid overconfidence and Gaussian assumptions. No quantitative skill score given.","significance":3,"cited_by":7,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2023.49852","title":"Prediction Rainfall with Regression Analysis","authors":["Sumit Sarkar","Ayush Kumar Srivastava","Er. Avneet Kaur"],"date":"2023-03-29","year":2023,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2023.49852","openalex":"W4361296888"},"links":{"paper":"https://doi.org/10.22214/ijraset.2023.49852","pdf":"https://doi.org/10.22214/ijraset.2023.49852"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["other"],"status":"research","summary":"Linear regression on atmospheric state variables forecasts monthly precipitation and is claimed to beat established methods; evaluation detail is limited.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.17610","title":"Ensemble weather forecast post-processing with a flexible probabilistic neural network approach","authors":["Peter Mlakar","Janko Merše","Jana Faganeli Pucer"],"date":"2023-03-29","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.17610"},"links":{"paper":"https://arxiv.org/abs/2303.17610","pdf":"https://arxiv.org/pdf/2303.17610"},"orgs":[],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"Normalizing-flow neural post-processing jointly calibrates ensemble temperature forecasts across locations and lead times, reaching state-of-the-art on the EUPPBench station benchmark.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.16684","title":"Super-Resolution of Three-Dimensional Temperature and Velocity for Building-Resolving Urban Micrometeorology Using Physics-Guided Convolutional Neural Networks with Image Inpainting Techniques","authors":["Yuki Yasuda","Ryo Onishi","Keigo Matsuda"],"date":"2023-03-29","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.16684"},"links":{"paper":"https://arxiv.org/abs/2303.16684","pdf":"https://arxiv.org/pdf/2303.16684"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Physics-guided gated-convolution CNN super-resolves 3D urban air temperature and wind from coarse building-resolving simulations, inferring near-surface flow from flow above buildings.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.16363","title":"Data Driven Regional Weather Forecasting: Example using the Shallow Water Equations","authors":["Clark, Randall","Henry D. I. Abarbanel","Luke C. Fairbanks","Ramon E. Sanchez","Pacharadech Wacharanan"],"date":"2023-03-29","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.16363","openalex":"W4361806428"},"links":{"paper":"http://arxiv.org/abs/2303.16363","pdf":"https://arxiv.org/pdf/2303.16363"},"orgs":[],"topic":"regional-km-scale","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Builds data-driven regional forecasting rules from local observations of shallow-water flow, predicting observed variables without governing equations.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15071797","title":"Skillful Seasonal Prediction of Typhoon Track Density Using Deep Learning","authors":["Zhihao Feng","Shuo Lv","Yuan Sun","Panmao Zhai","Yanluan Lin","Yixuan Shen","Wei Zhong"],"date":"2023-03-28","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15071797","openalex":"W4361225860"},"links":{"paper":"https://doi.org/10.3390/rs15071797","pdf":"https://www.mdpi.com/2072-4292/15/7/1797/pdf?version=1679988414"},"orgs":["tsinghua-university","university-of-reading","cma"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"SeaUnet, a fully convolutional network trained on CMIP TC tracks, gives skillful seasonal forecasts of Western North Pacific typhoon track density up to four months ahead.","significance":4,"cited_by":7,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1111-gcb.16696","title":"Unlocking the power of machine learning for Earth system modeling: A game‐changing breakthrough","authors":["Jiquan Chen"],"date":"2023-03-28","year":2023,"venue":"Global Change Biology","venue_type":"journal","ids":{"doi":"10.1111/gcb.16696","openalex":"W4361190476"},"links":{"paper":"https://doi.org/10.1111/gcb.16696"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Reviews machine learning's role in Earth system modelling, covering components beyond the atmosphere such as biogeochemistry and the terrestrial biosphere.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.16301","title":"A Machine Learning Outlook: Post-processing of Global Medium-range Forecasts","authors":["Shreya Agrawal","Rob Carver","Cenk Gazen","Eric Maddy","Vladimir Krasnopolsky","Carla Bromberg","Zack Ontiveros","Tyler Russell","Jason Hickey","Sid Boukabara"],"date":"2023-03-28","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.16301","openalex":"W4361806190"},"links":{"paper":"https://arxiv.org/abs/2303.16301","pdf":"https://arxiv.org/pdf/2303.16301"},"orgs":["google-research","noaa"],"topic":"post-processing","topics":["global-medium-range"],"type":"evaluation","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Neural-network post-processing of global 1 to 7 day forecasts across 30 levels improves RMSE by up to 12% for 850 hPa temperature at day 7, and discusses metric limits.","significance":4,"cited_by":7,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0060.1","title":"Simulation of Atlantic Hurricane Tracks and Features: A Coupled Machine Learning Approach","authors":["Rikhi Bose","Adam L. Pintar","Emil Simiu"],"date":"2023-03-27","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0060.1","openalex":"W4361004506"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0060.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0060.1.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Coupled machine learning trajectory and intensity models generate synthetic Atlantic hurricane tracks and winds consistent with HURDAT2 historical records.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.55041-isjem00134","title":"A Review on Weather Forecasting using Linear Regression","authors":["Pratiksha Tidke","Sakshi Sarode","Prof.Sonali Guhe"],"date":"2023-03-26","year":2023,"venue":"International Scientific Journal of Engineering and Management","venue_type":"journal","ids":{"doi":"10.55041/isjem00134","openalex":"W4360976924"},"links":{"paper":"https://doi.org/10.55041/isjem00134"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Review of linear regression as a machine learning approach to weather forecasting, with little technical depth in the abstract.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-cli11040076","title":"Impact of Accelerated Climate Change on Maximum Temperature Differences between Western and Coastal Sydney","authors":["Varsha Bubathi","Lance M. Leslie","Milton Samuel Speer","Joshua Hartigan","Joanna Wang","Anjali K. Gupta"],"date":"2023-03-26","year":2023,"venue":"Climate","venue_type":"journal","ids":{"doi":"10.3390/cli11040076","openalex":"W4361004796"},"links":{"paper":"https://doi.org/10.3390/cli11040076","pdf":"https://www.mdpi.com/2225-1154/11/4/76/pdf?version=1679878652"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Uses permutation tests and machine learning attribution to show summer heat in western Sydney rose sharply after 1992, with 35% more days above the 95th percentile.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-acp-23-3609-2023","title":"Technical note: Unsupervised classification of ozone profiles in UKESM1","authors":["Fouzia Fahrin","Daniel C. Jones","Yan Wu","James Keeble","Alexander Thomas Archibald"],"date":"2023-03-24","year":2023,"venue":"Atmospheric chemistry and physics","venue_type":"journal","ids":{"doi":"10.5194/acp-23-3609-2023","openalex":"W4360859092"},"links":{"paper":"https://doi.org/10.5194/acp-23-3609-2023"},"orgs":["university-of-cambridge"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Gaussian mixture modelling classifies UKESM1 CMIP6 ozone profiles into six coherent global regimes, with future projections showing ozone hole recovery and lower tropospheric ozone.","significance":2,"cited_by":6,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asoc.2023.110253","title":"Precipitation prediction by integrating Rough Set on Fuzzy Approximation Space with Deep Learning techniques","authors":["Tishya Manna","A. Anitha"],"date":"2023-03-24","year":2023,"venue":"Applied Soft Computing","venue_type":"journal","ids":{"doi":"10.1016/j.asoc.2023.110253","openalex":"W4360839122"},"links":{"paper":"https://doi.org/10.1016/j.asoc.2023.110253"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Rough set feature handling combined with deep learning is proposed for precipitation prediction; the abstract is unavailable, so details and results are unverified.","significance":1,"cited_by":30,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.17496","title":"Data-driven multiscale modeling for correcting dynamical systems","authors":["Karl Otness","Laure Zanna","Joan Bruna"],"date":"2023-03-24","year":2023,"venue":"Machine Learning: Science and Technology. 6 (2025) 045072","venue_type":"journal","ids":{"arxiv":"2303.17496","doi":"10.1088/2632-2153/ae1a36"},"links":{"paper":"https://arxiv.org/abs/2303.17496","pdf":"https://arxiv.org/pdf/2303.17496"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Multiscale networks that pass information fine-to-coarse and coarse-to-fine correct chaotic models, demonstrated on a climate subgrid parameterization task for unresolved fine-scale dynamics.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15071728","title":"A Hybrid ENSO Prediction System Based on the FIO−CPS and XGBoost Algorithm","authors":["Zhiyuan Kuang","Yajuan Song","Jie Wu","Qiuying Fu","Qi Shu","Fangli Qiao","Zhenya Song"],"date":"2023-03-23","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15071728","openalex":"W4360864624"},"links":{"paper":"https://doi.org/10.3390/rs15071728","pdf":"https://www.mdpi.com/2072-4292/15/7/1728/pdf?version=1679563960"},"orgs":["cma"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["nwp-analysis","satellite"],"status":"research","summary":"XGBoost corrects FIO-CPS ENSO forecasts, raising Niño3.4 anomaly correlation at 7 to 13 month leads from 0.40 to 0.63 and cutting RMSE by 25%.","significance":4,"cited_by":5,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15071720","title":"Machine Learning Models for Approximating Downward Short-Wave Radiation Flux over the Ocean from All-Sky Optical Imagery Based on DASIO Dataset","authors":["Mikhail Krinitskiy","Vasilisa Koshkina","Mikhail Borisov","Nikita Anikin","Sergey Gulev","Maria Artemeva"],"date":"2023-03-23","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15071720","openalex":"W4360615677"},"links":{"paper":"https://doi.org/10.3390/rs15071720","pdf":"https://www.mdpi.com/2072-4292/15/7/1720/pdf?version=1679553531"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["local"],"data":["other","stations"],"status":"research","summary":"CNN estimates downward shortwave radiation over the ocean from all-sky RGB images, outperforming empirical parameterizations and MODIS-based methods.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jas-d-22-0113.1","title":"Synchronization of Alternative Models in a Supermodel and the Learning of Critical Behavior","authors":["Gregory S. Duane","Mao‐Lin Shen"],"date":"2023-03-23","year":2023,"venue":"Journal of the Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1175/jas-d-22-0113.1","openalex":"W4360610389"},"links":{"paper":"https://doi.org/10.1175/jas-d-22-0113.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atsc/80/6/JAS-D-22-0113.1.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Supermodels with machine-learned connections synchronize imperfect atmospheric models, reproducing blocking and ITCZ criticality absent from the constituent models.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.12285","title":"Reducing Air Pollution through Machine Learning","authors":["Dimitris Bertsimas","Leonard Boussioux","Cynthia Zeng"],"date":"2023-03-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.12285","openalex":"W4360829334"},"links":{"paper":"https://arxiv.org/abs/2303.12285","pdf":"https://arxiv.org/pdf/2303.12285"},"orgs":["mit"],"topic":"applications-impacts","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"operational","summary":"Gradient-boosted models forecast short-term local wind for a Moroccan chemical plant, cutting errors 38-52% versus official forecasts and enabling pollution-aware production decisions.","significance":3,"cited_by":1,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-16-1461-2023","title":"Correcting 3D cloud effects in X CO 2 retrievals from the Orbiting Carbon Observatory-2 (OCO-2)","authors":["Steffen Mauceri","Steven T. Massie","K. Sebastian Schmidt"],"date":"2023-03-21","year":2023,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-16-1461-2023","openalex":"W4328090534"},"links":{"paper":"https://doi.org/10.5194/amt-16-1461-2023","pdf":"https://amt.copernicus.org/articles/16/1461/2023/amt-16-1461-2023.pdf"},"orgs":["nasa","caltech"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","stations"],"status":"research","summary":"Interpretable non-linear ML bias correction removes 3D cloud artifacts from OCO-2 XCO2, cutting unphysical variability by 31% over land and 55% over ocean.","significance":4,"cited_by":12,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14030600","title":"Improvement of Maximum Air Temperature Forecasts Using a Stacking Ensemble Technique","authors":["Linna Zhao","Shu Xian Lu","Dan Qi"],"date":"2023-03-21","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14030600","openalex":"W4353066294"},"links":{"paper":"https://doi.org/10.3390/atmos14030600","pdf":"https://www.mdpi.com/2073-4433/14/3/600/pdf?version=1679480326"},"orgs":["cma"],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["transformer","rnn","cnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Stacking ensemble of neural networks corrects ECMWF-IFS maximum temperature forecasts at about 2400 stations, cutting RMSE by 52% versus IFS.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ecoinf.2023.102077","title":"Projection of climate variables by general circulation and deep learning model for Lahore, Pakistan","authors":["Duy Thao Nguyen","Saqib Ashraf","Minhhuy Le","Le Quang Trung","Mustajab Ali"],"date":"2023-03-21","year":2023,"venue":"Ecological Informatics","venue_type":"journal","ids":{"doi":"10.1016/j.ecoinf.2023.102077","openalex":"W4328104979"},"links":{"paper":"https://doi.org/10.1016/j.ecoinf.2023.102077"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":[],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Projects future local climate variables for Lahore, Pakistan by combining GCM output with a deep learning model. No abstract available; scope inferred from title.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-2677640-v1","title":"Precipitation Nowcasting using CNN-RNN - Use case: North of Algeria","authors":["Hayat HACHEMI","Leila Hamdad","Oussama DOUBA"],"date":"2023-03-20","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-2677640/v1","openalex":"W4327858858"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-2677640/v1","pdf":"https://www.researchsquare.com/article/rs-2677640/latest.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"application","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"CNN-RNN models predict northeast Algeria precipitation from synoptic station data and NWP outputs, showing gains over NWP-based prediction.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1071-wf22188","title":"Projecting live fuel moisture content via deep learning","authors":["Lynn Miller","Liujun Zhu","Marta Yebra","Christoph Rüdiger","Geoffrey I. Webb"],"date":"2023-03-20","year":2023,"venue":"International Journal of Wildland Fire","venue_type":"journal","ids":{"doi":"10.1071/wf22188","openalex":"W4328030982"},"links":{"paper":"https://doi.org/10.1071/wf22188","pdf":"https://www.publish.csiro.au/wf/pdf/WF22188"},"orgs":["bom-australia"],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Temporal convolutional networks project live fuel moisture content three months ahead across the US, with RMSE 27.5% close to nowcasting accuracy.","significance":3,"cited_by":29,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.11379","title":"Solving High-Dimensional Inverse Problems with Auxiliary Uncertainty via Operator Learning with Limited Data","authors":["Joseph Hart","Mamikon Gulian","Indu Manickam","Laura Swiler"],"date":"2023-03-20","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.11379"},"links":{"paper":"https://arxiv.org/abs/2303.11379","pdf":"https://arxiv.org/pdf/2303.11379"},"orgs":[],"topic":"data-assimilation","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Deep neural network operator surrogates with Bayesian inversion identify sources from sparse observations in an atmospheric dispersion exemplar, with uncertainty quantification under wind uncertainty.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15061639","title":"Mutual Information Boosted Precipitation Nowcasting from Radar Images","authors":["Yuan Cao","Danchen Zhang","Xin Zheng","Hongming Shan","Junping Zhang"],"date":"2023-03-17","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15061639","openalex":"W4327971555"},"links":{"paper":"https://doi.org/10.3390/rs15061639","pdf":"https://www.mdpi.com/2072-4292/15/6/1639/pdf?version=1679125010"},"orgs":["fudan-university"],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":[],"data":["radar"],"status":"research","summary":"Mutual-information reweighting and time-superimposing training improve radar precipitation nowcasts for convective scenarios across several state-of-the-art models.","significance":3,"cited_by":11,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15061635","title":"Forecasting Precipitation from Radar Wind Profiler Mesonet and Reanalysis Using the Random Forest Algorithm","authors":["Yizhi Wu","Jianping Guo","Tianmeng Chen","Aijun Chen"],"date":"2023-03-17","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15061635","openalex":"W4327971350"},"links":{"paper":"https://doi.org/10.3390/rs15061635","pdf":"https://www.mdpi.com/2072-4292/15/6/1635/pdf?version=1679061282"},"orgs":["nuist","cma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite","era5"],"status":"research","summary":"Random forests using wind profiler divergence and vorticity predict rainfall onset 30 minutes ahead, outperforming inputs derived from ERA5 reanalysis.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.167898499.91486328-v1","title":"Improve dynamical climate prediction with machine learning","authors":["Zikang He","Julien Brajard","Yiguo Wang","Xidong Wang","Zheqi Shen"],"date":"2023-03-16","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.167898499.91486328/v1","openalex":"W4327571671"},"links":{"paper":"https://doi.org/10.22541/essoar.167898499.91486328/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.167898499.91486328"},"orgs":["lbnl-nersc"],"topic":"hybrid-parameterization","topics":["s2s-seasonal"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":[],"data":["other"],"status":"research","summary":"Machine learning emulates the systematic error of a reduced-order coupled ocean-atmosphere model, and the resulting hybrid model beats the dynamical model alone in twin experiments, best when correcting both components.","significance":3,"cited_by":2,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.09200","title":"Reduction of rain-induced errors for wind speed estimation on SAR observations using convolutional neural networks","authors":["Aurélien Colin","Pierre Tandeo","Charles Peureux","Romain Husson","Ronan Fablet"],"date":"2023-03-16","year":2023,"venue":"In IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2023), Vol. 16, pp. 8586-8594","venue_type":"journal","ids":{"arxiv":"2303.09200","doi":"10.1109/jstars.2023.3291236"},"links":{"paper":"https://arxiv.org/abs/2303.09200","pdf":"https://arxiv.org/pdf/2303.09200"},"orgs":["inria"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"CNN wind-speed estimator for Sentinel-1 SAR reduces rain-induced errors by 27% and 45% under rain above 1 and 3 mm/h, validated against buoy measurements.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25303-1604da027033","title":"Performance Evaluation of an ANN based Bias Correction algorithm in Monthly and Daily Precipitation Time Series of La Farge Station, USA","authors":["P. Saravanan","A.R. Prethivirajan","A.S. Sivaprasanna","K. Udhayakumar","C. Sivapragasam"],"date":"2023-03-15","year":2023,"venue":"Disaster Advances","venue_type":"journal","ids":{"doi":"10.25303/1604da027033","openalex":"W4327955611"},"links":{"paper":"https://doi.org/10.25303/1604da027033"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","cmip"],"status":"research","summary":"ANN bias correction of monthly and daily precipitation at one US station works well monthly but poorly daily, compared with conventional methods.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.08736","title":"A machine-learning approach to thunderstorm forecasting through post-processing of simulation data","authors":["Kianusch Vahid Yousefnia","Tobias Bölle","Isabella Zöbisch","Thomas Gerz"],"date":"2023-03-15","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.08736","doi":"10.1002/qj.4777"},"links":{"paper":"https://arxiv.org/abs/2303.08736","pdf":"https://arxiv.org/pdf/2303.08736"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"SALAMA, a feedforward network post-processing convection-resolving NWP fields, gives calibrated thunderstorm probabilities with skill beyond NWP reflectivity up to eleven hours lead.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.7734594","title":"An Adaptive Graph Convolutional Recurrent Neural Network for ENSO forecasting","authors":["Jahnavi Jonnalagadda"],"date":"2023-03-14","year":2023,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.7734594","openalex":"W4324260519"},"links":{"paper":"https://doi.org/10.5281/zenodo.7734594"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"benchmark","method":["gnn","rnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Zenodo dataset release accompanying an adaptive graph convolutional recurrent network for ENSO forecasting; the abstract only describes the data.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fmars.2023.1143499","title":"Spatial-temporal transformer network for multi-year ENSO prediction","authors":["Dan Song","Xinqi Su","Wenhui Li","Zhengya Sun","Tongwei Ren","Wen Liu","Anan Liu"],"date":"2023-03-13","year":2023,"venue":"Frontiers in Marine Science","venue_type":"journal","ids":{"doi":"10.3389/fmars.2023.1143499","openalex":"W4324056421"},"links":{"paper":"https://doi.org/10.3389/fmars.2023.1143499","pdf":"https://www.frontiersin.org/articles/10.3389/fmars.2023.1143499/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["transformer"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A spatio-temporal transformer with recurrent multi-step prediction uses SST and heat content anomalies to forecast ENSO 18 months ahead.","significance":4,"cited_by":13,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-2624566-v1","title":"Physics-informed neural networks for prediction and physical interpretability analysis of key regional variables of ENSO","authors":["Biao Chen","Huadong Du","Kang Pu","Shaodong Wang","Zheng Sheng"],"date":"2023-03-13","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-2624566/v1","openalex":"W4324088793"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-2624566/v1","pdf":"https://www.researchsquare.com/article/rs-2624566/latest.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["physics-constrained"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Physics-informed neural networks predict regional ENSO variables and aim to add physical interpretability; the abstract is unavailable, so results cannot be verified.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-023-31394-1","title":"Taking advantage of quasi-periodic signals for S2S operational forecast from a perspective of deep learning","authors":["Yang Zhou","Qifan Zhao"],"date":"2023-03-13","year":2023,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-023-31394-1","openalex":"W4324056308"},"links":{"paper":"https://doi.org/10.1038/s41598-023-31394-1","pdf":"https://www.nature.com/articles/s41598-023-31394-1.pdf"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["rnn"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"LSTM post-processing uses MJO and jet-stream quasi-periodic signals to weight operational S2S ensembles for Asian minimum 2 m temperature.","significance":3,"cited_by":4,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.buildenv.2023.110211","title":"Machine learning-assisted mapping of city-scale air temperature: Using sparse meteorological data for urban climate modeling and adaptation","authors":["Xiaotian Ding","Yongling Zhao","Yifan Fan","Yuguo Li","Jian Ge"],"date":"2023-03-13","year":2023,"venue":"Building and Environment","venue_type":"journal","ids":{"doi":"10.1016/j.buildenv.2023.110211","openalex":"W4324030762"},"links":{"paper":"https://doi.org/10.1016/j.buildenv.2023.110211","pdf":"https://www.researchsquare.com/article/rs-2441080/latest.pdf"},"orgs":["eth-zurich"],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":[],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses machine learning to map city-scale air temperature from sparse meteorological station data for urban climate adaptation. No abstract available; scope inferred from title.","significance":3,"cited_by":53,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2023.100350","title":"Prediction of ENSO using multivariable deep learning","authors":["Yue Chen","Xiaomeng Huang","Jing‐Jia Luo","Yanluan Lin","Jonathon S. Wright","Youyu Lu","Xingrong Chen","Hua Jiang","Pengfei Lin"],"date":"2023-03-13","year":2023,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2023.100350","openalex":"W4324053458"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2023.100350"},"orgs":["tsinghua-university","nuist","iap-cas"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A residual network with automatically selected precursors predicts ENSO up to 8 months ahead, with a 6-month correlation of 0.82 beating the multi-model mean of 0.70.","significance":4,"cited_by":22,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.06663","title":"SAR-UNet: Small Attention Residual UNet for Explainable Nowcasting Tasks","authors":["Mathieu Renault","Siamak Mehrkanoon"],"date":"2023-03-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.06663"},"links":{"paper":"https://arxiv.org/abs/2303.06663","pdf":"https://arxiv.org/pdf/2303.06663"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"SAR-UNet adds residual connections to SmaAt-UNet for precipitation and cloud-cover nowcasting, outperforming baselines from 30 to 180 minutes ahead, with Grad-CAM explanations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.06394","title":"A Novel Method Combines Moving Fronts, Data Decomposition and Deep Learning to Forecast Intricate Time Series","authors":["Debdarsan Niyogi"],"date":"2023-03-11","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.06394"},"links":{"paper":"https://arxiv.org/abs/2303.06394","pdf":"https://arxiv.org/pdf/2303.06394"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","other"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"EWT-MF-LSTM avoids decomposition data leakage and forecasts Indian Summer Monsoon Rainfall with performance parameter 0.86 to 0.95 across phases.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15061529","title":"3D-UNet-LSTM: A Deep Learning-Based Radar Echo Extrapolation Model for Convective Nowcasting","authors":["Shiqing Guo","Nengli Sun","Yanle Pei","Qian Li"],"date":"2023-03-10","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15061529","openalex":"W4324067684"},"links":{"paper":"https://doi.org/10.3390/rs15061529","pdf":"https://www.mdpi.com/2072-4292/15/6/1529/pdf?version=1678443694"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A 3D-UNet-LSTM extractor-forecaster for 0-1 h radar echo extrapolation on MeteoNet outperforms baselines in quantitative and case-study evaluation.","significance":3,"cited_by":40,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1126-sciadv.adf2827","title":"A self-attention–based neural network for three-dimensional multivariate modeling and its skillful ENSO predictions","authors":["Lu Zhou","Rong-Hua Zhang"],"date":"2023-03-10","year":2023,"venue":"Science Advances","venue_type":"journal","ids":{"doi":"10.1126/sciadv.adf2827","openalex":"W4323637041"},"links":{"paper":"https://doi.org/10.1126/sciadv.adf2827"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["transformer"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"3D-Geoformer, a self-attention transformer, predicts Niño3.4 SST anomalies 18 months ahead with high correlation skill for ENSO.","significance":6,"cited_by":174,"score":64,"highlight":true,"highlight_reason":"Transformer-based 3D model gives skillful ENSO forecasts to 18 months; a solid, widely cited step for ML seasonal prediction.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5281-zenodo.7713946","title":"Temperature (maximum) and Rainfall Prediction Using FNN and RNN Models over Kaba Aye Station, Yangon Region, Myanmar","authors":["Khant Hmu Paing","Yu Li","Zin Mie Mie Sein"],"date":"2023-03-09","year":2023,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.7713946","openalex":"W4324002296"},"links":{"paper":"https://doi.org/10.5281/zenodo.7713946"},"orgs":["nuist"],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM outperforms feed-forward networks for predicting monthly maximum temperature at Kaba Aye, Myanmar, with MAE of 1.33 degrees.","significance":1,"cited_by":2,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-math11061330","title":"Physical Attention-Gated Spatial-Temporal Predictive Network for Weather Forecasting","authors":["Xueliang Zhao","Qilong Sun","Xiaoguang Lin"],"date":"2023-03-09","year":2023,"venue":"Mathematics","venue_type":"journal","ids":{"doi":"10.3390/math11061330","openalex":"W4323848639"},"links":{"paper":"https://doi.org/10.3390/math11061330","pdf":"https://www.mdpi.com/2227-7390/11/6/1330/pdf?version=1678359351"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"PastNet uses attention-gated convolutions for spatiotemporal forecasting on synthetic and real datasets, outperforming baselines on weather-style prediction.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2023.100351","title":"A deep learning–based U-Net model for ENSO-related precipitation responses to sea surface temperature anomalies over the tropical Pacific","authors":["Yuchao Zhu","Rong‐Hua Zhang"],"date":"2023-03-09","year":2023,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2023.100351","openalex":"W4323661385"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2023.100351"},"orgs":["nuist"],"topic":"hybrid-parameterization","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A U-Net replaces EOF models for precipitation response to SST anomalies in hybrid ENSO modelling, outperforming EOF over the western-central tropical Pacific.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.7708534","title":"Res: A lightweight Deep Learning model for Quantitative Precipitation Nowcasting Based on New Transformer Customized for Remote Sensing Data","authors":["Li, Dawei"],"date":"2023-03-08","year":2023,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.7708534","openalex":"W4323557166"},"links":{"paper":"https://doi.org/10.5281/zenodo.7708534"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Res is a lightweight transformer for quantitative precipitation nowcasting on remote sensing data; only source code is released while the manuscript is under review.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-1467-2023","title":"Deep learning models for generation of precipitation maps based on numerical weather prediction","authors":["Adrian Rojas-Campos","Michael Langguth","Martin Wittenbrink","Gordon Pipa"],"date":"2023-03-08","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-1467-2023","openalex":"W4323556541"},"links":{"paper":"https://doi.org/10.5194/gmd-16-1467-2023","pdf":"https://gmd.copernicus.org/articles/16/1467/2023/gmd-16-1467-2023.pdf"},"orgs":["dwd","juelich"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["cnn","gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Conditional GAN and U-Net generate high-resolution short-range precipitation maps from full NWP variables, reducing over-forecast bias; CGAN gives the most realistic output.","significance":3,"cited_by":22,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14030520","title":"Multi-Model Ensemble Forecasts of Surface Air Temperatures in Henan Province Based on Machine Learning","authors":["Tian Wang","Yutong Zhang","Xiefei Zhi","Yan Ji"],"date":"2023-03-08","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14030520","openalex":"W4323663638"},"links":{"paper":"https://doi.org/10.3390/atmos14030520","pdf":"https://www.mdpi.com/2073-4433/14/3/520/pdf?version=1678270870"},"orgs":["nuist","cma"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"CNN and FNN multi-model ensembles of ECMWF and CMA forecasts reduce 12-72 h surface air temperature errors in Henan, with the CNN best at short range.","significance":3,"cited_by":13,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-22-0268.1","title":"Deep Learning Forecast Uncertainty for Precipitation over the Western United States","authors":["Weiming Hu","Mohammadvaghef Ghazvinian","William Eric Chapman","Agniv Sengupta","Fred Martin Ralph","Luca Delle Monache"],"date":"2023-03-08","year":2023,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-22-0268.1","openalex":"W4323546156"},"links":{"paper":"https://doi.org/10.1175/mwr-d-22-0268.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/151/6/MWR-D-22-0268.1.pdf"},"orgs":["ncar"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A U-Net postprocesses 4 km West-WRF precipitation reforecasts into censored shifted gamma distributions, beating analog, regression and meta-Gaussian benchmarks at all lead times.","significance":4,"cited_by":36,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11430-022-1050-2","title":"Deep learning-based multi-source precipitation merging for the Tibetan Plateau","authors":["Tianyi Nan","Jie Chen","Zhiwei Ding","Wei Li","Hua Chen"],"date":"2023-03-08","year":2023,"venue":"Science China Earth Sciences","venue_type":"journal","ids":{"doi":"10.1007/s11430-022-1050-2","openalex":"W4323925828"},"links":{"paper":"https://doi.org/10.1007/s11430-022-1050-2"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Deep learning merges multiple precipitation sources over the Tibetan Plateau to produce improved precipitation estimates (abstract unavailable; assessed from title).","significance":3,"cited_by":28,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.04405","title":"Intermediate and Future Frame Prediction of Geostationary Satellite Imagery With Warp and Refine Network","authors":["Minseok Seo","Yeji Choi","Hyungon Ry","Heesun Park","Hyungkun Bae","Hyesook Lee","Wanseok Seo"],"date":"2023-03-08","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.04405","openalex":"W4323710166"},"links":{"paper":"https://arxiv.org/abs/2303.04405","pdf":"https://arxiv.org/pdf/2303.04405"},"orgs":["nvidia","kma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn","other"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"WR-Net combines TV-L1 optical flow warping with a refinement network to interpolate and predict GK2A geostationary imagery from 4- to 2-minute intervals.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-icbats57792.2023.10111347","title":"Retracted: A Systematic Review of Machine Learning and Artificial Intelligence Methods to Tackle Climate Change Impacts","authors":["Abdur Rehman","Sharjeel Tariq","Amina Farrakh","Munir Ahmad","Muhammad Sheraz Javeid"],"date":"2023-03-07","year":2023,"venue":"International Conference on Business Analytics for Technology and Security (ICBATS)","venue_type":"conference","ids":{"doi":"10.1109/icbats57792.2023.10111347","openalex":"W4376605951"},"links":{"paper":"https://doi.org/10.1109/icbats57792.2023.10111347"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Retracted review of machine learning and deep learning methods for weather prediction and IoT-based forecasting, with no specific results reported.","significance":0,"cited_by":5,"score":0,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40808-023-01754-x","title":"A hybrid deep learning model for rainfall in the wetlands of southern Iraq","authors":["Fehaid Alqahtani","Mostafa Salaheldin Abdelsalam Abotaleb","Alhumaima Ali Subhi","El‐Sayed M. El‐kenawy","Abdelaziz A. Abdelhamid","Khder Mohammed Alakkari","Amr Badr","H. K. Al-Mahdawi","Abdelhameed F. Ibrahim","Аммар Мохаммад Яхья Кади"],"date":"2023-03-07","year":2023,"venue":"Modeling Earth Systems and Environment","venue_type":"journal","ids":{"doi":"10.1007/s40808-023-01754-x","openalex":"W4323352867"},"links":{"paper":"https://doi.org/10.1007/s40808-023-01754-x"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A hybrid deep learning model for rainfall in southern Iraq wetlands; the abstract is unavailable, so the details are limited.","significance":1,"cited_by":12,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fams.2023.1133226","title":"Surrogate modeling for the climate sciences dynamics with machine learning and data assimilation","authors":["Marc Bocquet"],"date":"2023-03-06","year":2023,"venue":"Frontiers in Applied Mathematics and Statistics","venue_type":"journal","ids":{"doi":"10.3389/fams.2023.1133226","openalex":"W4323315742"},"links":{"paper":"https://doi.org/10.3389/fams.2023.1133226","pdf":"https://www.frontiersin.org/articles/10.3389/fams.2023.1133226/pdf"},"orgs":[],"topic":"data-assimilation","topics":["hybrid-parameterization","xai-uq-physics"],"type":"position","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Perspective reviewing machine learning combined with data assimilation for climate surrogate models and model error correction, with open challenges for operational use.","significance":3,"cited_by":40,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.dsp.2023.103989","title":"ST-GRF: Spatiotemporal graph neural networks for rainfall forecasting","authors":["Fang-Hao Zhang","Zhi-Gang Shao"],"date":"2023-03-06","year":2023,"venue":"Digital Signal Processing","venue_type":"journal","ids":{"doi":"10.1016/j.dsp.2023.103989","openalex":"W4323319211"},"links":{"paper":"https://doi.org/10.1016/j.dsp.2023.103989"},"orgs":[],"topic":"local-forecasting","topics":["nowcasting"],"type":"model","method":["gnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Spatiotemporal graph neural network for rainfall forecasting; no abstract was provided, so the assessment rests on the title.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.06049","title":"Affordable Artificial Intelligence -- Augmenting Farmer Knowledge with AI","authors":["Peeyush Kumar","Andrew Nelson","Zerina Kapetanovic","Ranveer Chandra"],"date":"2023-03-04","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.06049","doi":"10.4060/cb7142en"},"links":{"paper":"https://arxiv.org/abs/2303.06049","pdf":"https://arxiv.org/pdf/2303.06049"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"application","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Describes a Microsoft AI system that predicts on-farm micro-climate conditions from farm sensor data to support precision agriculture decisions.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.renene.2023.02.130","title":"Evaluating neural network models in site-specific solar PV forecasting using numerical weather prediction data and weather observations","authors":["Christina Brester","Viivi Kallio‐Myers","Anders Vilhelm Lindfors","Mikko Kolehmainen","Harri Niska"],"date":"2023-03-03","year":2023,"venue":"Renewable Energy","venue_type":"journal","ids":{"doi":"10.1016/j.renene.2023.02.130","openalex":"W4323030717"},"links":{"paper":"https://doi.org/10.1016/j.renene.2023.02.130"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"ANN trained on station weather observations matches NWP-trained PV forecasts closely and beats a physical model at three Finnish sites.","significance":2,"cited_by":119,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.8056","title":"Bias correction of CMIP6 simulations of precipitation over Indian monsoon core region using deep learning algorithms","authors":["T. Kesavavarthini","A. Naga Rajesh","Challa Venkata Srinivas","T. V. Lakshmi Kumar"],"date":"2023-03-02","year":2023,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.8056","openalex":"W4322721694"},"links":{"paper":"https://doi.org/10.1002/joc.8056","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.8056"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Compares CNN1D and LSTM encoder-decoder deep learning for bias correcting CMIP6 monsoon precipitation over India, with LSTM-ED performing best against IMD observations.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.01220","title":"Evaluation of drain, a deep-learning approach to rain retrieval from gpm passive microwave radiometer","authors":["Nicolas Viltard","Vibolroth Sambath","Pierre Lepetit","Audrey Martini","Laurent Barthès","Cécile Mallet"],"date":"2023-03-02","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing, In press","venue_type":"journal","ids":{"arxiv":"2303.01220"},"links":{"paper":"https://arxiv.org/abs/2303.01220","pdf":"https://arxiv.org/pdf/2303.01220"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite","radar"],"status":"research","summary":"DRAIN, a U-Net on GPM passive microwave brightness temperatures, retrieves rain rates with performance similar to or slightly better than the official GPROF algorithm.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.58564-ijser.1.2.2023.74","title":"Machine Learning Prediction Models applied to Weather Forecasting: A survey","authors":["Israa Jasim Mohmmed","Bashar Talib Al-Nuaimi","Asst . Prof. Dr. Dher Intisar Social Bakr"],"date":"2023-03-01","year":2023,"venue":"Al-Iraqia Journal of Scientific Engineering Research","venue_type":"journal","ids":{"doi":"10.58564/ijser.1.2.2023.74","openalex":"W4361199694"},"links":{"paper":"https://doi.org/10.58564/ijser.1.2.2023.74","pdf":"https://ijser.aliraqia.edu.iq/index.php/ijser/article/download/63/47"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":["stations"],"status":"research","summary":"Survey of classical machine learning methods, from SVMs to neural networks, applied to weather prediction, to help researchers choose approaches.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.51903-jtikp.v14i1.531","title":"WEATHER FORECAST FROM TIME SERIES DATA USING LSTM ALGORITHM","authors":["Yoga Estu Nugraha Nugraha","Ishak Ariawan","Willdan Aprizal Arifin"],"date":"2023-03-01","year":2023,"venue":"JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI","venue_type":"journal","ids":{"doi":"10.51903/jtikp.v14i1.531","openalex":"W4323045976"},"links":{"paper":"https://doi.org/10.51903/jtikp.v14i1.531","pdf":"https://ejurnal.provisi.ac.id/index.php/JTIKP/article/download/531/472"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An LSTM forecasts temperature, humidity, rainfall and wind speed from Serang maritime station data, with best RMSE of 0.37 for temperature.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21608-sis.2023.206017.1080","title":"Using Deep learning to Improve the Classification of Weather Phenomena from Images","authors":["abdelmonaim fakhry mohamad"],"date":"2023-03-01","year":2023,"venue":"Afāq Asyawiyyaẗ","venue_type":"journal","ids":{"doi":"10.21608/sis.2023.206017.1080","openalex":"W4376055230"},"links":{"paper":"https://doi.org/10.21608/sis.2023.206017.1080","pdf":"https://sis.journals.ekb.eg/article_297314_3203d5e281df79ab1da4c7cddd68537d.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"benchmark","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Introduces the 6,691-image WEAPD dataset of 11 weather phenomena and benchmarks five AI classifiers for image-based weather recognition.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ef003291","title":"Using Machine Learning to Cut the Cost of Dynamical Downscaling","authors":["Sanaa Hobeichi","Nidhi Nishant","Yawen Shao","Gab Abramowitz","A. J. Pitman","Steven C. Sherwood","Craig H. Bishop","Samuel Green"],"date":"2023-03-01","year":2023,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2022ef003291","openalex":"W4323307475"},"links":{"paper":"https://doi.org/10.1029/2022ef003291","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EF003291"},"orgs":[],"topic":"downscaling","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Machine learning emulators (MLP and error-corrected regression with random forest) downscale GCM evapotranspiration from 12.5 km to 1.5 km, reaching KGE of 0.86 and beating statistical downscaling.","significance":5,"cited_by":58,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13143-023-00319-3","title":"Development of Deep Convolutional Neural Network Ensemble Models for 36-Month ENSO Forecasts","authors":["Yannic Lops","Yunsoo Choi","Seyedali Mousavinezhad","Ahmed Khan Salman","Delaney L. Nelson","Deveshwar Singh"],"date":"2023-03-01","year":2023,"venue":"Asia-Pacific Journal of Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s13143-023-00319-3","openalex":"W4322734209"},"links":{"paper":"https://doi.org/10.1007/s13143-023-00319-3"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Ensembles of deep convolutional networks extend ENSO forecasts to 36 months ahead; the abstract is unavailable, so the claim rests on the title.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.00836","title":"Ensemble flow reconstruction in the atmospheric boundary layer from spatially limited measurements through latent diffusion models","authors":["Alex Rybchuk","Malik Hassanaly","Nicholas Hamilton","Paula Doubrawa","Mitchell J. Fulton","Luis A. Martínez-Tossas"],"date":"2023-03-01","year":2023,"venue":"Physics of Fluids, 35, 12 (2023) 126604","venue_type":"journal","ids":{"arxiv":"2303.00836","doi":"10.1063/5.0172559"},"links":{"paper":"https://arxiv.org/abs/2303.00836","pdf":"https://arxiv.org/pdf/2303.00836"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["diffusion"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Latent diffusion model inpaints 3D atmospheric boundary-layer LES flow from observations covering under 1% of the volume, producing diverse physically plausible turbulent samples usable as LES initial conditions.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","authors":["Philine Bommer","Marlene Kretschmer","Anna Hedström","Dilyara Bareeva","Marina M. -C. Höhne"],"date":"2023-03-01","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.00652"},"links":{"paper":"https://arxiv.org/abs/2303.00652","pdf":"https://arxiv.org/pdf/2303.00652"},"orgs":[],"topic":"xai-uq-physics","topics":["benchmarks-data-eval"],"type":"evaluation","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Proposes a framework to evaluate XAI methods for climate-science networks on robustness, faithfulness, randomization, complexity and localization, ranking methods on a temperature-map task.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ea002693","title":"Tropical Cyclone Wind Speed Estimation: A Large Scale Training Data Set and Community Benchmarking","authors":["Iksha Gurung","Muthukumaran Ramasubramanian","Brian M. Freitag","Aaron S. Kaulfus","Manil Maskey","Rahul Ramachandran","Hamed Alemohammad"],"date":"2023-02-28","year":2023,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2022ea002693","openalex":"W4322623334"},"links":{"paper":"https://doi.org/10.1029/2022ea002693","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EA002693"},"orgs":["nasa"],"topic":"benchmarks-data-eval","topics":["extremes-hazards","observations-remote-sensing"],"type":"benchmark","method":[],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"Curates an hourly-interpolated satellite image and wind-speed dataset for tropical cyclones, plus a community competition whose winners improved on the benchmark by about 50%.","significance":4,"cited_by":4,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.34312-jjom.v5i1.17496","title":"Peramalan Data Cuaca Ekstrim Indonesia Menggunakan Model ARIMA dan Recurrent Neural Network","authors":["Hikmah Hikmah","Asrirawan Asrirawan","Apriyanto Apriyanto","Nilawati Nilawati"],"date":"2023-02-27","year":2023,"venue":"Jambura Journal of Mathematics","venue_type":"journal","ids":{"doi":"10.34312/jjom.v5i1.17496","openalex":"W4322721518"},"links":{"paper":"https://doi.org/10.34312/jjom.v5i1.17496","pdf":"https://ejurnal.ung.ac.id/index.php/jjom/article/download/17496/6178"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["rnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Hybrid ARIMA-RNN models forecast monthly extreme weather in West Sulawesi, Indonesia, with the ARIMA-RNN-Adam model giving the lowest RMSE.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23052609","title":"Pred-SF: A Precipitation Prediction Model Based on Deep Neural Networks","authors":["Rongnian Tang","Pu Zhang","Jingjin Wu","Youlong Chen","Lingyu Dong","Song Tang","Chuang Li"],"date":"2023-02-27","year":2023,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23052609","openalex":"W4322501642"},"links":{"paper":"https://doi.org/10.3390/s23052609","pdf":"https://www.mdpi.com/1424-8220/23/5/2609/pdf?version=1677487599"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","transformer"],"timescale":["nowcast"],"spatial":["local"],"data":["era5","satellite"],"status":"research","summary":"Pred-SF combines PredRNN-V2 with a stepwise refinement network to predict 4-hour precipitation for a target area from ERA5 multivariate fields and GPM data.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003334","title":"Machine Learning of Key Variables Impacting Extreme Precipitation in Various Regions of the Contiguous United States","authors":["Xinming Lin","Jiwen Fan","Zhangshuan Hou","Jingyu Wang"],"date":"2023-02-27","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003334","openalex":"W4322494676"},"links":{"paper":"https://doi.org/10.1029/2022ms003334","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003334"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Random forest, XGBoost and ANN with Shapley analysis identify latent heat flux, humidity and soil moisture as key drivers of US extreme precipitation, plus return-period emulators.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003094","title":"Large Ensemble Particle Filter for Spatial Climate Reconstructions Using a Linear Inverse Model","authors":["Beyrem Jebri","Myriam Khodri"],"date":"2023-02-27","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003094","openalex":"W4321177884"},"links":{"paper":"https://doi.org/10.1029/2022ms003094","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003094"},"orgs":[],"topic":"data-assimilation","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["decadal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Particle filter with linear inverse model emulators of CMIP-class GCMs produces ensemble millennial temperature reconstructions and skillful one-year-ahead forecasts in a perfect-model test.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15051279","title":"Spatiotemporal Prediction of Radar Echoes Based on ConvLSTM and Multisource Data","authors":["Mingyue Lu","Yuchen Li","Manzhu Yu","Qian Zhang","Yadong Zhang","Bin Liu","Menglong Wang"],"date":"2023-02-25","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15051279","openalex":"W4322503148"},"links":{"paper":"https://doi.org/10.3390/rs15051279","pdf":"https://www.mdpi.com/2072-4292/15/5/1279/pdf?version=1677633944"},"orgs":["nuist"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Proposes MS-ConvLSTM, adding echo top, VIL and radar-retrieved winds to reflectivity inputs to improve precipitation nowcasts over conventional deep learning baselines.","significance":3,"cited_by":13,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-1277-2023","title":"A new precipitation emulator (PREMU v1.0) for lower-complexity models","authors":["Gang Liu","Shushi Peng","Chris Huntingford","Yi Xi"],"date":"2023-02-22","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-1277-2023","openalex":"W4321497055"},"links":{"paper":"https://doi.org/10.5194/gmd-16-1277-2023"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Data-calibrated PREMU emulator predicts ESM precipitation from gridded temperature modes, reproducing global land precipitation interannual variability (R 0.82-0.93) across nine models.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23052426","title":"An Intelligent Anomaly Detection Approach for Accurate and Reliable Weather Forecasting at IoT Edges: A Case Study","authors":["Şükrü Mustafa Kaya","Buket İşler","Adnan Mohammed I Abu-Mahfouz","Jawad Rasheed","Abdulaziz Alshammari"],"date":"2023-02-22","year":2023,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23052426","openalex":"W4321599780"},"links":{"paper":"https://doi.org/10.3390/s23052426","pdf":"https://www.mdpi.com/1424-8220/23/5/2426/pdf?version=1677065337"},"orgs":[],"topic":"observations-remote-sensing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares five ML anomaly detectors for cleaning noisy IoT sensor data to improve local weather forecast reliability; the abstract gives no headline numbers.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-agronomy13030625","title":"BMAE-Net: A Data-Driven Weather Prediction Network for Smart Agriculture","authors":["Jianlei Kong","Xiaomeng Fan","Xuebo Jin","Tingli Su","Yuting Bai","Huijun Ma","Min Zuo"],"date":"2023-02-22","year":2023,"venue":"Agronomy","venue_type":"journal","ids":{"doi":"10.3390/agronomy13030625","openalex":"W4321496041"},"links":{"paper":"https://doi.org/10.3390/agronomy13030625","pdf":"https://www.mdpi.com/2073-4395/13/3/625/pdf?version=1677060244"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn","other"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Bayesian-GRU encoder-decoder with multi-head attention forecasts station temperature and humidity for agriculture, reporting R of 0.80–0.90 at three sites.","significance":2,"cited_by":58,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0031.1","title":"Bias Correcting Climate Model Simulations Using Unpaired Image-to-Image Translation Networks","authors":["D. James Fulton","Ben J. Clarke","Gabriele Clarissa Hegerl"],"date":"2023-02-22","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0031.1","openalex":"W4321490771"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0031.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0031.1.pdf"},"orgs":["university-of-oxford"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["gan-vae","cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Applies unpaired UNIT image-to-image translation, combined with quantile mapping, to bias-correct HadGEM3 monsoon simulations toward ERA5, preserving cross-variable correlations and spatial structure.","significance":4,"cited_by":17,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2303.07122","title":"Quantifying Causes of Arctic Amplification via Deep Learning based Time-series Causal Inference","authors":["Sahara Ali","Omar Faruque","Yiyi Huang","Md. Osman Gani","Aneesh Subramanian","Nicole-Jienne Shchlegel","Jianwu Wang"],"date":"2023-02-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2303.07122"},"links":{"paper":"https://arxiv.org/abs/2303.07122","pdf":"https://arxiv.org/pdf/2303.07122"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"TCINet, a recurrent causal inference model with probabilistic balancing, quantifies atmospheric drivers of Arctic sea-ice melt under continuous treatment.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.11357","title":"On the Relative Role of East and West Pacific Sea Surface Temperature (SST) Gradients in the Prediction Skill of Central Pacific NINO3.4 SST","authors":["Lekshmi S","Rajib Chattopadhyay","D. S. Pai","M. Rajeevan","Vinu Valsala","K. S. Hosalikar","M. Mohapatra"],"date":"2023-02-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.11357","doi":"10.1007/s10236-023-01581-9"},"links":{"paper":"https://arxiv.org/abs/2302.11357","pdf":"https://arxiv.org/pdf/2302.11357"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"evaluation","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"CNN ENSO forecasts from 5000 random-initialized members show western Pacific SST gives better Nino3.4 skill than eastern Pacific SST.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15040826","title":"Rainfall Prediction Rate in Saudi Arabia Using Improved Machine Learning Techniques","authors":["Mohammed Abubakor Baljon","Sunil Kumar Sharma"],"date":"2023-02-20","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15040826","openalex":"W4321458286"},"links":{"paper":"https://doi.org/10.3390/w15040826","pdf":"https://www.mdpi.com/2073-4441/15/4/826/pdf?version=1676895721"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares several machine learning classifiers and regressors for rainfall prediction in southern Saudi Arabia using station meteorological records, with crop-yield motivation.","significance":2,"cited_by":24,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.23960-jtaf.v11i1.3164","title":"Penerapan Jaringan Saraf Tiruan / JST (Backpropagation) untuk Prakiraan Cuaca di Bandar Udara Radin Inten II Lampung","authors":["Adi Saputra","Sri Ratna Sulistiyanti","Roniyus Marjunus","Yanti Yuliant","Junaidi Junaidi","Arif Surtono"],"date":"2023-02-20","year":2023,"venue":"Jurnal Teori dan Aplikasi Fisika","venue_type":"journal","ids":{"doi":"10.23960/jtaf.v11i1.3164","openalex":"W4323569911"},"links":{"paper":"https://doi.org/10.23960/jtaf.v11i1.3164","pdf":"https://jurnal.fmipa.unila.ac.id/jtaf/article/download/3164/2165"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Backpropagation neural network forecasts daily weather at Radin Inten II airport, Lampung, from three years of station data, reaching 74.36% best test accuracy.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.09990","title":"Deep Vision in Analysis and Recognition of Radar Data: Achievements, Advancements and Challenges","authors":["Qi Liu","Zhiyun Yang","Ru Ji","Yonghong Zhang","Muhammad Bilal","Xiaodong Liu","S Vimal","Xiaolong Xu"],"date":"2023-02-20","year":2023,"venue":"in IEEE Systems, Man, and Cybernetics Magazine, vol. 9, no. 4, pp. 4-12, Oct. 2023","venue_type":"journal","ids":{"arxiv":"2302.09990","doi":"10.1109/msmc.2022.3216943","openalex":"W4387606420"},"links":{"paper":"https://arxiv.org/abs/2302.09990","pdf":"https://arxiv.org/pdf/2302.09990"},"orgs":["nuist"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"review","method":[],"timescale":["nowcast"],"spatial":[],"data":["radar"],"status":"research","summary":"Review of deep learning for weather radar analysis covering beam blockage correction, echo extrapolation and precipitation nowcasting, with open challenges.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app13042646","title":"Comparison of Artificial Neural Network and Regression Models for Filling Temporal Gaps of Meteorological Variables Time Series","authors":["Egor Dyukarev"],"date":"2023-02-18","year":2023,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app13042646","openalex":"W4321374616"},"links":{"paper":"https://doi.org/10.3390/app13042646","pdf":"https://www.mdpi.com/2076-3417/13/4/2646/pdf?version=1676712351"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["era5","stations"],"status":"research","summary":"Neural network and Gaussian process models fill gaps and bias-correct ERA5-Land meteorological series against station data, reducing NRMSE to 2–11%.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-022-2119-x","title":"Predictor Selection for CNN-based Statistical Downscaling of Monthly Precipitation","authors":["Dangfu Yang","Shengjun Liu","Yamin Hu","Xinru Liu","Jiehong Xie","Liang Zhao"],"date":"2023-02-18","year":2023,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-022-2119-x","openalex":"W4321352841"},"links":{"paper":"https://doi.org/10.1007/s00376-022-2119-x"},"orgs":["iap-cas","cma"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Studies predictor selection for CNN-based statistical downscaling of monthly precipitation, aiming to improve regional precipitation fields from large-scale predictors.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7217862654","title":"Spiking Neural Network based Water management in Drought Area of Maharashtra India: A Case Study of Osmanabad District","authors":["Devdatta K. Mokashi","Vidula Sohoni"],"date":"2023-02-17","year":2023,"venue":"International Journal of Intelligent Systems and Applications in Engineering","venue_type":"journal","ids":{"openalex":"W7217862654"},"links":{"paper":"https://ijisae.org/index.php/IJISAE/article/view/2982","pdf":"https://ijisae.org/index.php/IJISAE/article/download/2982/1560"},"orgs":[],"topic":"extremes-hazards","topics":["downscaling"],"type":"model","method":["other"],"timescale":[],"spatial":["regional","local"],"data":["other"],"status":"research","summary":"A spiking neural network downscales coarse precipitation to map meteorological drought (SPI) in Osmanabad, India; reported efficiency is claimed without rigorous benchmarking.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7217700526","title":"BBCNN: Bounding Box Convolution Neural Network for Cyclone Prediction and Monitoring","authors":["Mamatha N. P.","Mohmad Umair Bagali","N Thangadurai"],"date":"2023-02-17","year":2023,"venue":"International Journal of Intelligent Systems and Applications in Engineering","venue_type":"journal","ids":{"openalex":"W7217700526"},"links":{"paper":"https://ijisae.org/index.php/IJISAE/article/view/2596","pdf":"https://ijisae.org/index.php/IJISAE/article/download/2596/1178"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Neural network applied to MOSDAC satellite imagery for cyclone identification and monitoring, reported only qualitatively without a quantitative benchmark.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7217394415","title":"Tuned Fusion Deep Learning Approach for Unsupervised Cyclone Passive Microwave Rainfall Imagery Prediction","authors":["Mamatha N. P.","Mohmad Umair Bagali","N Thangadurai"],"date":"2023-02-17","year":2023,"venue":"International Journal of Intelligent Systems and Applications in Engineering","venue_type":"journal","ids":{"openalex":"W7217394415"},"links":{"paper":"https://ijisae.org/index.php/IJISAE/article/view/2793","pdf":"https://ijisae.org/index.php/IJISAE/article/download/2793/1371"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing","extremes-hazards"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Tuned fusion deep learning model forecasts tropical cyclone passive microwave rainfall images from satellite data, with no quantitative results reported in the abstract.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.08720","title":"Algorithmic Hallucinations of Near-Surface Winds: Statistical Downscaling with Generative Adversarial Networks to Convection-Permitting Scales","authors":["Nicolaas J. Annau","Alex J. Cannon","Adam H. Monahan"],"date":"2023-02-17","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2302.08720","doi":"10.1175/aies-d-23-0015.1","openalex":"W4386925640"},"links":{"paper":"https://doi.org/10.1175/aies-d-23-0015.1","pdf":"https://arxiv.org/pdf/2302.08720"},"orgs":["eccc"],"topic":"downscaling","topics":[],"type":"evaluation","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"GANs statistically downscale near-surface winds to convection-permitting WRF scales, with spectral analysis exposing spatial-structure biases and a partial frequency-separation loss.","significance":4,"cited_by":20,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.13659","title":"Data assimilation in operator algebras","authors":["David Freeman","Dimitrios Giannakis","Brian Mintz","A. Ourmazd","Joanna Sławińska"],"date":"2023-02-17","year":2023,"venue":"Proceedings of the National Academy of Sciences","venue_type":"journal","ids":{"arxiv":"2206.13659","doi":"10.1073/pnas.2211115120","openalex":"W4321165559"},"links":{"paper":"https://doi.org/10.1073/pnas.2211115120"},"orgs":[],"topic":"data-assimilation","topics":["foundation-models"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Introduces an operator-algebra framework for sequential data assimilation with kernel-based data-driven schemes, tested on Lorenz 96 and ENSO in a climate model.","significance":3,"cited_by":4,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-math11041018","title":"Polynomial Chaos Expansion-Based Enhanced Gaussian Process Regression for Wind Velocity Field Estimation from Aircraft-Derived Data","authors":["Marius Marinescu","Alberto Olivares","Ernesto Staffetti","Junzi Sun"],"date":"2023-02-16","year":2023,"venue":"Mathematics","venue_type":"journal","ids":{"doi":"10.3390/math11041018","openalex":"W4321248272"},"links":{"paper":"https://doi.org/10.3390/math11041018","pdf":"https://www.mdpi.com/2227-7390/11/4/1018/pdf?version=1676544029"},"orgs":[],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Combines polynomial chaos expansion and Gaussian process regression to estimate and forecast wind fields from ADS-B aircraft-derived data, with confidence intervals.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0053.1","title":"Application of Machine Learning Techniques to Improve Multi-Radar Multi-Sensor (MRMS) Precipitation Estimates in the Western United States","authors":["Andrew P. Osborne","Jian Zhang","Micheal J. Simpson","Kenneth W. Howard","Stephen B. Cocks"],"date":"2023-02-16","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0053.1","openalex":"W4321071162"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0053.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0053.1.pdf"},"orgs":["noaa","university-of-oklahoma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar","stations"],"status":"pre-operational","summary":"CNN corrects MRMS radar precipitation estimates over complex western US terrain, beating radar QPE on several atmospheric river events in a year-long evaluation.","significance":4,"cited_by":11,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2023.100339","title":"Short-term wind speed forecasting bias correction in the Hangzhou area of China based on a machine learning model","authors":["Yi Fang","Yunfei Wu","Fengmin Wu","Yan Yan","Qi Liu","Nian Liu","Jiangjiang Xia"],"date":"2023-02-16","year":2023,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2023.100339","openalex":"W4321019954"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2023.100339"},"orgs":["iap-cas"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"XGBoost corrects short-term wind speed forecasts from a local NWP system at Hangzhou stations, cutting RMSE 26.1% versus NWP and outperforming MOS.","significance":3,"cited_by":20,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.10274","title":"A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN)","authors":["Jennifer Sleeman","David Chung","Anand Gnanadesikan","Jay Brett","Yannis Kevrekidis","Marisa Hughes","Thomas Haine","Marie-Aude Pradal","Renske Gelderloos","Chace Ashcraft","Caroline Tang","Anshu Saksena","Larry White"],"date":"2023-02-16","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.10274"},"links":{"paper":"https://arxiv.org/abs/2302.10274","pdf":"https://arxiv.org/pdf/2302.10274"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Adversarial generators find Earth system model configurations that trigger AMOC collapse, with a discriminator predicting collapse accurately without the oracle.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-wes-8-173-2023","title":"Introducing a data-driven approach to predict site-specific leading-edge erosion from mesoscale weather simulations","authors":["Jens Visbech","Tuhfe Göçmen","Charlotte Bay Hasager","Hristo Shkalov","Morten Handberg","Kristian Pagh Nielsen"],"date":"2023-02-15","year":2023,"venue":"Wind energy science","venue_type":"journal","ids":{"doi":"10.5194/wes-8-173-2023","openalex":"W4320916079"},"links":{"paper":"https://doi.org/10.5194/wes-8-173-2023"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Feed-forward neural networks with ensemble learning predict wind turbine leading-edge erosion from mesoscale NWP weather data and blade inspections in Northern Europe.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12145-023-00945-5","title":"A sequence-to-sequence based multi-scale deep learning model for satellite cloud image prediction","authors":["Jie Lian","Ruirong Chen"],"date":"2023-02-15","year":2023,"venue":"Earth Science Informatics","venue_type":"journal","ids":{"doi":"10.1007/s12145-023-00945-5","openalex":"W4321242399"},"links":{"paper":"https://doi.org/10.1007/s12145-023-00945-5"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":[],"data":["satellite"],"status":"research","summary":"Multi-scale sequence-to-sequence deep network predicts future satellite cloud images; the abstract is unavailable, so quantitative results are unknown.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.65521-ijeecs.v12i1.2621","title":"Recent Advances in Environmental Weather Monitoring and Prediction System Using IoT and Multi-Model Progressive Dense Self-Attention: A Systematic Review","authors":["Edvinas Mulyadi"],"date":"2023-02-14","year":2023,"venue":"International Journal of Electrical Electronics and Computer Systems","venue_type":"journal","ids":{"doi":"10.65521/ijeecs.v12i1.2621","openalex":"W7162462921"},"links":{"paper":"https://doi.org/10.65521/ijeecs.v12i1.2621","pdf":"https://journals.mriindia.com/index.php/ijeecs/article/download/2621/2510"},"orgs":[],"topic":"local-forecasting","topics":["llms-agents"],"type":"review","method":["transformer","cnn","rnn","gnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Systematic review of IoT and deep learning weather monitoring and prediction, covering CNN, LSTM, transformer and hybrid models; no new results are reported.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.renene.2023.01.111","title":"Photovoltaic power electricity generation nowcasting combining sky camera images and learning supervised algorithms in the Southern Spain","authors":["Mauricio Trigo-González","Marcelo Cortés-Carmona","Aitor Marzo","Joaquín Alonso-Montesinos","M. Martínez-Durbán","Gabriel López","Carlos Portillo","Francisco Javier Batlles"],"date":"2023-02-14","year":2023,"venue":"Renewable Energy","venue_type":"journal","ids":{"doi":"10.1016/j.renene.2023.01.111","openalex":"W4320730508"},"links":{"paper":"https://doi.org/10.1016/j.renene.2023.01.111"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Sky-camera images feed ANN and SVM models that nowcast photovoltaic output 3 hours ahead, with errors close to the uncertainty of the solar resource itself.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.06852","title":"Using Artificial Intelligence to aid Scientific Discovery of Climate Tipping Points","authors":["Jennifer Sleeman","David Chung","Chace Ashcraft","Jay Brett","Anand Gnanadesikan","Yannis Kevrekidis","Marisa Hughes","Thomas Haine","Marie-Aude Pradal","Renske Gelderloos","Caroline Tang","Anshu Saksena","Larry White"],"date":"2023-02-14","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.06852","openalex":"W4321012258"},"links":{"paper":"https://arxiv.org/abs/2302.06852","pdf":"https://arxiv.org/pdf/2302.06852"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Hybrid neural and neuro-symbolic approach uses a surrogate ocean model to predict Atlantic Meridional Overturning Circulation collapse with high accuracy, adding explainability.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.62643-ijerst.v19n1.3073","title":"Rainfall Forecasting System Using Intelligent Algorithms","authors":["Dr. Ch.Srinivasa Rao","T.Srinaina","T. Pavani","P. Keerthana","A. Rachana","G. Tejaswini"],"date":"2023-02-13","year":2023,"venue":"International Journal of Engineering Research and Science & Technology","venue_type":"journal","ids":{"doi":"10.62643/ijerst.v19n1.3073","openalex":"W7160594039"},"links":{"paper":"https://doi.org/10.62643/ijerst.v19n1.3073","pdf":"https://ijerst.org/index.php/ijerst/article/download/3073/2789"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares decision trees, random forest, SVM and ANN on historical meteorological variables to estimate rainfall; reports improved accuracy but no specific numbers in the abstract.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-2528100-v1","title":"Basin Dependence of the Tropical Cyclone Genesis Environment and the Future Changes Revealed by Machine Learning Methods","authors":["Xiaojing Jia","Qifeng Qian"],"date":"2023-02-13","year":2023,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-2528100/v1","openalex":"W4320482011"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-2528100/v1","pdf":"https://www.researchsquare.com/article/rs-2528100/latest.pdf"},"orgs":["cma"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning examines basin-dependent tropical cyclone genesis environments and their projected future changes; the abstract is unavailable, so this is judged from the title.","significance":2,"cited_by":1,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-20964471.2023.2172820","title":"A deep learning approach for spatial error correction of numerical seasonal weather prediction simulation data","authors":["Stelios Karozis","Iraklis Klampanos","Athanasios Sfetsos","Diamando Vlachogiannis"],"date":"2023-02-13","year":2023,"venue":"Big Earth Data","venue_type":"journal","ids":{"doi":"10.1080/20964471.2023.2172820","openalex":"W4320733184"},"links":{"paper":"https://doi.org/10.1080/20964471.2023.2172820","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/20964471.2023.2172820?needAccess=true&role=button"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Convolutional autoencoder corrects 3–6 month seasonal forecast errors for Greece using NCEP FNL analysis, improving 6-month-ahead accuracy.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asoc.2023.110118","title":"Accurate long-term air temperature prediction with Machine Learning models and data reduction techniques","authors":["Dušan Fister","Jorge Pérez‐Aracil","César Peláez-Rodríguez","Javier Del Ser","Sancho Salcedo‐Sanz"],"date":"2023-02-13","year":2023,"venue":"Applied Soft Computing","venue_type":"journal","ids":{"doi":"10.1016/j.asoc.2023.110118","openalex":"W4320498740"},"links":{"paper":"https://doi.org/10.1016/j.asoc.2023.110118"},"orgs":[],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["cnn","classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN and ML models predict August fortnight air temperature in Paris and Córdoba months ahead, targeting heatwave-related signals; skill is reported as very good.","significance":3,"cited_by":74,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.apenergy.2023.120818","title":"Omnivision forecasting: Combining satellite and sky images for improved deterministic and probabilistic intra-hour solar energy predictions","authors":["Quentin Paletta","Guillaume Arbod","Joan Lasenby"],"date":"2023-02-13","year":2023,"venue":"Applied Energy","venue_type":"journal","ids":{"doi":"10.1016/j.apenergy.2023.120818","openalex":"W4320519443"},"links":{"paper":"https://doi.org/10.1016/j.apenergy.2023.120818"},"orgs":["university-of-cambridge"],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":[],"timescale":["nowcast"],"spatial":["local"],"data":["satellite","other"],"status":"pre-operational","summary":"Combines sky images and satellite observations in one ML framework for deterministic and probabilistic intra-hour solar irradiance nowcasts up to 60 minutes ahead.","significance":3,"cited_by":76,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.apenergy.2023.120801","title":"Probabilistic modeling of future electricity systems with high renewable energy penetration using machine learning","authors":["Martin János Mayer","Bence Bíró","Botond Szücs","Attila Aszódi"],"date":"2023-02-13","year":2023,"venue":"Applied Energy","venue_type":"journal","ids":{"doi":"10.1016/j.apenergy.2023.120801","openalex":"W4320713523"},"links":{"paper":"https://doi.org/10.1016/j.apenergy.2023.120801","pdf":"https://ars.els-cdn.com/content/image/1-s2.0-S0306261923001654-ga1_lrg.jpg"},"orgs":[],"topic":"applications-impacts","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Neural networks map reanalysis weather to PV, wind and load, generating 42-year synthetic ensembles for Hungary; Dunkelflaute events and a variance-correction step are analysed.","significance":4,"cited_by":63,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.05886","title":"An unsupervised learning approach for predicting wind farm power and downstream wakes using weather patterns","authors":["Mariana C A Clare","Simon C Warder","Robert Neal","B Bhaskaran","Matthew D Piggott"],"date":"2023-02-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.05886"},"links":{"paper":"https://arxiv.org/abs/2302.05886","pdf":"https://arxiv.org/pdf/2302.05886"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Unsupervised clustering of ERA5 wind patterns drives a few WRF runs, reproducing a year of wind farm power and wake predictions at under 2% of the compute.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.55041-ijsrem17712","title":"CLASSIFICATION FOR BIG DATA DRIVEN MARINE WEATHER FORECASTING USING MACHINE LEARNING TECHNIQUES","authors":["Deepa Anbarasi J","V. Radha"],"date":"2023-02-11","year":2023,"venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","venue_type":"journal","ids":{"doi":"10.55041/ijsrem17712","openalex":"W4320037346"},"links":{"paper":"https://doi.org/10.55041/ijsrem17712","pdf":"https://ijsrem.com/download/classification-for-big-data-driven-marine-weather-forecasting-using-machine-learning-techniques/?wpdmdl=14029&refresh=657ea827d50dd1702799399"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Proposes a perceptron feature selection with Kriging gradient-boost classifier for marine weather forecasting; the abstract gives no quantitative results.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0044.1","title":"Reducing Southern Ocean Shortwave Radiation Errors in the ERA5 Reanalysis with Machine Learning and 25 Years of Surface Observations","authors":["Marc D. Mallet","Simon Peter Alexander","Alain Protat","Sonya Louise Fiddes"],"date":"2023-02-10","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0044.1","openalex":"W4319963651"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0044.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0044.1.pdf"},"orgs":["bom-australia"],"topic":"post-processing","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"XGBoost and random forest models trained on 25 years of Southern Ocean surface observations cut ERA5 shortwave mean bias to near zero and reduce RMSE by about 25%.","significance":4,"cited_by":14,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asr.2023.02.006","title":"Evaluation of near-surface air temperature reanalysis datasets and downscaling with machine learning based Random Forest method for complex terrain of Turkey","authors":["Çağrı Hasan Karaman","Zuhal Akyürek"],"date":"2023-02-10","year":2023,"venue":"Advances in Space Research","venue_type":"journal","ids":{"doi":"10.1016/j.asr.2023.02.006","openalex":"W4319926139"},"links":{"paper":"https://doi.org/10.1016/j.asr.2023.02.006"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Evaluates near-surface air temperature reanalyses over Turkey and downscales them with a random forest for complex terrain; no abstract available.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.agrformet.2023.109362","title":"A simplified multi-model statistical approach for predicting the effects of forest management on land surface temperature in Fennoscandia","authors":["Bo Huang","Yan Li","Yi Liu","Xiangping Hu","Wenwu Zhao","Francesco Cherubini"],"date":"2023-02-09","year":2023,"venue":"Agricultural and Forest Meteorology","venue_type":"journal","ids":{"doi":"10.1016/j.agrformet.2023.109362","openalex":"W4319762941"},"links":{"paper":"https://doi.org/10.1016/j.agrformet.2023.109362"},"orgs":[],"topic":"climate-analysis-attribution","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Multi-model machine learning estimates that fully developed Fennoscandian forests warm annual mean land surface temperature by 0.26 °C relative to present forest states.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12040-022-02042-5","title":"Tropical Cyclone intensity prediction based on hybrid learning techniques","authors":["P. Varalakshmi","N. Vasumathi","R. Venkatesan"],"date":"2023-02-09","year":2023,"venue":"Journal of Earth System Science","venue_type":"journal","ids":{"doi":"10.1007/s12040-022-02042-5","openalex":"W4319662786"},"links":{"paper":"https://doi.org/10.1007/s12040-022-02042-5"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Hybrid learning techniques predict tropical cyclone intensity; the abstract is unavailable, so this is judged from the title.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenvs.2023.1116672","title":"Improving the heavy rainfall forecasting using a weighted deep learning model","authors":["Yutong Chen","Gang Huang","Ya Wang","Weichen Tao","Qun Tian","Kai Ge Yang","Jiangshan Zheng","Hubin He"],"date":"2023-02-08","year":2023,"venue":"Frontiers in Environmental Science","venue_type":"journal","ids":{"doi":"10.3389/fenvs.2023.1116672","openalex":"W4319597769"},"links":{"paper":"https://doi.org/10.3389/fenvs.2023.1116672","pdf":"https://www.frontiersin.org/articles/10.3389/fenvs.2023.1116672/pdf"},"orgs":["iap-cas","cma"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Weighted U-Net corrects ECMWF-IFS precipitation over China, improving heavy-rainfall forecast skill over the ordinary U-Net, with gains growing at longer lead times.","significance":4,"cited_by":32,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-22-0002.1","title":"Improving Precipitation Forecasts with Convolutional Neural Networks","authors":["Anirudhan Badrinath","Luca Delle Monache","Negin Hayatbini","Will Chapman","Forest Cannon","Marty Ralph"],"date":"2023-02-08","year":2023,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-22-0002.1","openalex":"W4319591303"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0002.1"},"orgs":["uc-berkeley"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"U-Net CNN post-processes West-WRF precipitation over the US West Coast, cutting RMSE 12.9–15.9% versus raw model at 1–4 day leads.","significance":4,"cited_by":26,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.04102","title":"WF-UNet: Weather Fusion UNet for Precipitation Nowcasting","authors":["Christos Kaparakis","Siamak Mehrkanoon"],"date":"2023-02-08","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.04102"},"links":{"paper":"https://arxiv.org/abs/2302.04102","pdf":"https://arxiv.org/pdf/2302.04102"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","era5"],"status":"research","summary":"WF-UNet fuses precipitation radar with wind fields to nowcast western European precipitation 1 to 3 hours ahead, giving 6 to 22% lower MSE than radar-only UNets.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.03845","title":"Two-step hyperparameter optimization method: Accelerating hyperparameter search by using a fraction of a training dataset","authors":["Sungduk Yu","Mike Pritchard","Po-Lun Ma","Balwinder Singh","Sam Silva"],"date":"2023-02-08","year":2023,"venue":"Artificial Intelligence for the Earth Systems, 3(1), 2024, e230013","venue_type":"journal","ids":{"arxiv":"2302.03845","doi":"10.1175/aies-d-23-0013.1"},"links":{"paper":"https://arxiv.org/abs/2302.03845","pdf":"https://arxiv.org/pdf/2302.03845"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"A two-step hyperparameter search tuned on a tiny data fraction gives up to 135x speedup, demonstrated on neural emulators of aerosol activation in climate models.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-isprs-archives-xlviii-4-w6-2022-327-2023","title":"SPATIAL DOWNSCALING OF GPM IMERG V06 GRIDDED PRECIPITATION USING MACHINE LEARNING ALGORITHMS","authors":["Manikandan Sathianarayanan","P.-H. Hsu"],"date":"2023-02-07","year":2023,"venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","venue_type":"journal","ids":{"doi":"10.5194/isprs-archives-xlviii-4-w6-2022-327-2023","openalex":"W4319599466"},"links":{"paper":"https://doi.org/10.5194/isprs-archives-xlviii-4-w6-2022-327-2023","pdf":"https://isprs-archives.copernicus.org/articles/XLVIII-4-W6-2022/327/2023/isprs-archives-XLVIII-4-W6-2022-327-2023.pdf"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Downscales GPM IMERG precipitation from 10 km to 1 km over Taiwan using decision trees, SVR and random forests with NDVI and terrain predictors, validated against gauges.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.03258","title":"Climate Intervention Analysis using AI Model Guided by Statistical Physics Principles","authors":["Soo Kyung Kim","Kalai Ramea","Salva Rühling Cachay","Haruki Hirasawa","Subhashis Hazarika","Dipti Hingmire","Peetak Mitra","Philip J. Rasch","Hansi A. Singh"],"date":"2023-02-07","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.03258","openalex":"W4319653547"},"links":{"paper":"https://arxiv.org/abs/2302.03258","pdf":"https://arxiv.org/pdf/2302.03258","code":"https://github.com/kramea/kdd_aibedo"},"orgs":["university-of-washington","excarta"],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"AiBEDO uses the Fluctuation-Dissipation Theorem and 8250 years of Earth system model output to emulate regional climate responses to marine cloud brightening forcing.","significance":4,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.03173","title":"Learning bias corrections for climate models using deep neural operators","authors":["Aniruddha Bora","Khemraj Shukla","Shixuan Zhang","Bryce Harrop","Ruby Leung","George Em Karniadakis"],"date":"2023-02-07","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.03173","openalex":"W4319653593"},"links":{"paper":"https://arxiv.org/abs/2302.03173","pdf":"https://arxiv.org/pdf/2302.03173"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["neural-operator","cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"A DeepONet with autoencoder replaces the nudging bias-correction module in the E3SMv2 climate model, matching nudging tendencies with a learned surrogate for online use.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en16041603","title":"Renewable Energy Potential Estimation Using Climatic-Weather-Forecasting Machine Learning Algorithms","authors":["Chika  Calistus Maduabuchi","Chinedu Candidus Nsude","Chibuoke Eneh","Emmanuel T. Eke","Kingsley Okoli","Emmanuel Okpara","Christian Idogho","Bryan Waya","Catur Harsito"],"date":"2023-02-05","year":2023,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en16041603","openalex":"W4319319751"},"links":{"paper":"https://doi.org/10.3390/en16041603","pdf":"https://www.mdpi.com/1996-1073/16/4/1603/pdf?version=1676870632"},"orgs":["mit","university-of-oklahoma"],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Neural networks forecast Nigerian weather parameters from 19 years of NASA data to assess solar PV siting, reaching 96% training correlation.","significance":2,"cited_by":33,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-869-2023","title":"AttentionFire_v1.0: interpretable machine learning fire model for burned-area predictions over tropics","authors":["Fa Li","Qing Zhu","W. J. Riley","Lei Zhao","Li Xu","Kunxiaojia Yuan","Min Chen","Huayi Wu","Zhipeng Gui","Jianya Gong","James T. Randerson"],"date":"2023-02-03","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-869-2023","openalex":"W4319081738"},"links":{"paper":"https://doi.org/10.5194/gmd-16-869-2023"},"orgs":["lbnl-nersc"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["transformer"],"timescale":["seasonal","climate"],"spatial":["regional"],"data":["other","cmip"],"status":"research","summary":"Interpretable attention-based fire model for African and South American burned area reveals lagged climate-wetness controls and projects South American burned-area recovery under high emissions.","significance":4,"cited_by":45,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0207.1","title":"Postprocessing of NWP Precipitation Forecasts Using Deep Learning","authors":["Adrian Rojas-Campos","Martin Wittenbrink","Pascal Nieters","Erik Jan Schaffernicht","Jan D. Keller","Gordon Pipa"],"date":"2023-02-03","year":2023,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0207.1","openalex":"W4319079426"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0207.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/wefo/38/3/WAF-D-21-0207.1.pdf"},"orgs":["dwd"],"topic":"post-processing","topics":[],"type":"evaluation","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Probabilistic neural networks post-process ensemble precipitation at four stations, outperforming logistic regression and GLM for hourly precipitation and rain probability.","significance":3,"cited_by":28,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.01957","title":"Accelerating exploration of Marine Cloud Brightening impacts on tipping points Using an AI Implementation of Fluctuation-Dissipation Theorem","authors":["Haruki Hirasawa","Sookyung Kim","Peetak Mitra","Subhashis Hazarika","Salva Ruhling-Cachay","Dipti Hingmire","Kalai Ramea","Hansi Singh","Philip J. Rasch"],"date":"2023-02-03","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.01957"},"links":{"paper":"https://arxiv.org/abs/2302.01957","pdf":"https://arxiv.org/pdf/2302.01957"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"AiBEDO, an MLP built on the Fluctuation-Dissipation Theorem, emulates climate responses to marine cloud brightening forcing and matches Earth system model simulations at far lower cost.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.01771","title":"Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches","authors":["Jose González-Abad","Jorge Baño-Medina","José Manuel Gutiérrez"],"date":"2023-02-03","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.01771"},"links":{"paper":"https://arxiv.org/abs/2302.01771","pdf":"https://arxiv.org/pdf/2302.01771"},"orgs":[],"topic":"downscaling","topics":["xai-uq-physics"],"type":"evaluation","method":[],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Intercompares deep learning perfect-prognosis temperature downscaling models for CORDEX North America and uses XAI to expose extrapolation behaviour beyond standard validation.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.03606","title":"Merging satellite and gauge-measured precipitation using LightGBM with an emphasis on extreme quantiles","authors":["Hristos Tyralis","Georgia Papacharalampous","Nikolaos Doulamis","Anastasios Doulamis"],"date":"2023-02-02","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 16 (2023) 6969-6979","venue_type":"journal","ids":{"arxiv":"2302.03606","doi":"10.1109/jstars.2023.3297013"},"links":{"paper":"https://arxiv.org/abs/2302.03606","pdf":"https://arxiv.org/pdf/2302.03606"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Applies LightGBM to probabilistically merge contiguous-US gauge data with PERSIANN and IMERG satellite precipitation, outperforming quantile regression forests at extreme quantiles.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.01236","title":"A Machine Learning Approach to Measuring Climate Adaptation","authors":["Max Vilgalys"],"date":"2023-02-02","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.01236"},"links":{"paper":"https://arxiv.org/abs/2302.01236","pdf":"https://arxiv.org/pdf/2302.01236"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Debiased machine learning estimates adaptation to damaging heat in US corn and soy, finding short-run heat losses are largely offset in the long run.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w15030575","title":"A Novel Merging Method for Generating High-Quality Spatial Precipitation Information over Mainland China","authors":["Na Zhao"],"date":"2023-02-01","year":2023,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w15030575","openalex":"W4318776541"},"links":{"paper":"https://doi.org/10.3390/w15030575","pdf":"https://www.mdpi.com/2073-4441/15/3/575/pdf?version=1675244965"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"An energy-function merging method fuses downscaled GPM IMERG with gauge data to produce 1 km monthly precipitation over China, outperforming IMERG in cross-validation.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fmars.2022.1046964","title":"USFP: An unbalanced severe typhoon formation prediction framework based on transfer learning","authors":["Xiaotian Pan","Xiang Wang","Chengwu Zhao","Jianping Wu","Huizan Wang","Senzhang Wang","Sihao Chen"],"date":"2023-02-01","year":2023,"venue":"Frontiers in Marine Science","venue_type":"journal","ids":{"doi":"10.3389/fmars.2022.1046964","openalex":"W4318814832"},"links":{"paper":"https://doi.org/10.3389/fmars.2022.1046964","pdf":"https://www.frontiersin.org/articles/10.3389/fmars.2022.1046964/pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Transfer-learning framework predicts unbalanced severe typhoon formation from atmosphere and ocean variables, outperforming ECMWF IFS and prior ML methods across three regions.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2022.12.054","title":"Probabilistic solar forecasting: Benchmarks, post-processing, verification","authors":["Tilmann Gneiting","Sebastian Lerch","Benedikt Schulz"],"date":"2023-02-01","year":2023,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2022.12.054","openalex":"W4320168704"},"links":{"paper":"https://doi.org/10.1016/j.solener.2022.12.054"},"orgs":["kit"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Proposes a probabilistic clear-sky benchmark and neural post-processing methods for NWP-based solar irradiance forecasts, with proper scoring and calibration checks.","significance":3,"cited_by":62,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.00170","title":"Diffusion Models for High-Resolution Solar Forecasts","authors":["Yusuke Hatanaka","Yannik Glaser","Geoff Galgon","Giuseppe Torri","Peter Sadowski"],"date":"2023-02-01","year":2023,"venue_type":"preprint","ids":{"arxiv":"2302.00170","openalex":"W4320513550"},"links":{"paper":"https://arxiv.org/abs/2302.00170","pdf":"https://arxiv.org/pdf/2302.00170"},"orgs":[],"topic":"probabilistic-ensembles","topics":["downscaling","applications-impacts"],"type":"model","method":["diffusion"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","satellite"],"status":"research","summary":"Score-based diffusion models super-resolve coarse NWP to satellite-resolution day-ahead solar irradiance, giving probabilistic forecasts with many samples.","significance":5,"cited_by":13,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15030816","title":"Retrieving Vertical Cloud Radar Reflectivity from MODIS Cloud Products with CGAN: An Evaluation for Different Cloud Types and Latitudes","authors":["Fengxian Wang","Yubao Liu","Yongbo Zhou","Rongfu Sun","Jing Duan","Yang Li","Qiuji Ding","Haoliang Wang"],"date":"2023-01-31","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15030816","openalex":"W4318818790"},"links":{"paper":"https://doi.org/10.3390/rs15030816","pdf":"https://www.mdpi.com/2072-4292/15/3/816/pdf?version=1675831014"},"orgs":["nuist","cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A conditional GAN retrieves CloudSat 94 GHz radar reflectivity from MODIS cloud products over global oceans, performing best for deep convective clouds.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14020280","title":"Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification","authors":["Emmanuel Kwabena Gyasi","Swarnalatha Purushotham"],"date":"2023-01-31","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14020280","openalex":"W4318706773"},"links":{"paper":"https://doi.org/10.3390/atmos14020280","pdf":"https://www.mdpi.com/2073-4433/14/2/280/pdf?version=1675147617"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Cloud-MobiNet, a lightweight MobileNet-based CNN, classifies ground-based cloud images from the CCSN dataset with 97.45% accuracy for smartphone use.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fmars.2022.1077901","title":"Tropical cyclone size estimation based on deep learning using infrared and microwave satellite data","authors":["Jianbo Xu","Xiang Wang","Haiqi Wang","Haiqi Wang","Chengwu Zhao","Huizan Wang","Huizan Wang","Junxing Zhu"],"date":"2023-01-31","year":2023,"venue":"Frontiers in Marine Science","venue_type":"journal","ids":{"doi":"10.3389/fmars.2022.1077901","openalex":"W4318828913"},"links":{"paper":"https://doi.org/10.3389/fmars.2022.1077901","pdf":"https://www.frontiersin.org/articles/10.3389/fmars.2022.1077901/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"TC-Resnet estimates tropical cyclone 34-kt wind radii from infrared and microwave satellite data with MAE of 11.3 nmi and r of 0.907.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10115-023-01829-2","title":"Climate modeling with neural advection–diffusion equation","authors":["Hwangyong Choi","Jeongwhan Choi","Jeehyun Hwang","Kookjin Lee","Dong Eun Lee","Noseong Park"],"date":"2023-01-31","year":2023,"venue":"Knowledge and Information Systems","venue_type":"journal","ids":{"doi":"10.1007/s10115-023-01829-2","openalex":"W4318596161"},"links":{"paper":"https://doi.org/10.1007/s10115-023-01829-2"},"orgs":["ucla"],"topic":"climate-emulation","topics":[],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Neural advection-diffusion equation approach to climate modeling; the abstract is missing, so the scope and results cannot be verified.","significance":2,"cited_by":20,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1073-pnas.2207183120","title":"Data-driven predictions of the time remaining until critical global warming thresholds are reached","authors":["Noah S. Diffenbaugh","Elizabeth A. Barnes"],"date":"2023-01-30","year":2023,"venue":"Proceedings of the National Academy of Sciences","venue_type":"journal","ids":{"doi":"10.1073/pnas.2207183120","openalex":"W4318577731"},"links":{"paper":"https://doi.org/10.1073/pnas.2207183120"},"orgs":["colorado-state-university","stanford"],"topic":"climate-analysis-attribution","topics":["climate-emulation"],"type":"model","method":["other"],"timescale":["decadal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"ANNs trained on climate model output estimate observed timing of 1.5°C and 2°C warming, with a 2033–2035 central estimate for 1.5°C.","significance":4,"cited_by":170,"score":56,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.26421-qic23.3-4-1","title":"The effect of superposition and entanglement on hybrid quantum machine learning for weather forecasting","authors":["Besir Ogur","İhsan Yılmaz"],"date":"2023-01-29","year":2023,"venue":"Quantum Information and Computation","venue_type":"journal","ids":{"doi":"10.26421/qic23.3-4-1","openalex":"W4319449194"},"links":{"paper":"https://doi.org/10.26421/qic23.3-4-1"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Shows that entanglement and superposition layers improve variational quantum circuits for weather forecasting on small datasets, reducing the number of variational layers needed.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.12471","title":"Maximising Weather Forecasting Accuracy through the Utilisation of Graph Neural Networks and Dynamic GNNs","authors":["Gaganpreet Singh","Surya Durbha","Shreelakshmi C R"],"date":"2023-01-29","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.12471","openalex":"W4318752007"},"links":{"paper":"https://arxiv.org/abs/2301.12471","pdf":"https://arxiv.org/pdf/2301.12471"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"evaluation","method":["gnn","classical-ml"],"timescale":["medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Compares graph neural networks with traditional ML for multivariate weather forecasting from heterogeneous sensors; the abstract reports no quantitative results.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12040-022-02028-3","title":"Nomadic people optimisation based Bi-LSTM for detection and tracking of tropical cyclone","authors":["S. Akila Rajini","G. Tamilpavai"],"date":"2023-01-27","year":2023,"venue":"Journal of Earth System Science","venue_type":"journal","ids":{"doi":"10.1007/s12040-022-02028-3","openalex":"W4318215338"},"links":{"paper":"https://doi.org/10.1007/s12040-022-02028-3"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["rnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Bi-LSTM tuned by nomadic people optimisation detects and tracks tropical cyclones; the abstract is missing, so performance cannot be confirmed.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00521-023-08288-4","title":"Weather forecasting based on hybrid decomposition methods and adaptive deep learning strategy","authors":["Khouloud Zouaidia","Mohamed Saber Rais","Salim Ghanemi"],"date":"2023-01-27","year":2023,"venue":"Neural Computing and Applications","venue_type":"journal","ids":{"doi":"10.1007/s00521-023-08288-4","openalex":"W4318220466"},"links":{"paper":"https://doi.org/10.1007/s00521-023-08288-4"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Combines hybrid decomposition with adaptive deep learning for weather forecasting; the abstract is unavailable so the classification relies on the title.","significance":1,"cited_by":9,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.11707","title":"Improving deep learning precipitation nowcasting by using prior knowledge","authors":["Matej Choma","Petr Šimánek","Jakub Bartel"],"date":"2023-01-27","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.11707","openalex":"W4318621006"},"links":{"paper":"https://arxiv.org/abs/2301.11707","pdf":"https://arxiv.org/pdf/2301.11707"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["physics-constrained","rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Adds a hand-engineered advection-diffusion PhyCell to PhyDNet for radar nowcasting, but the physics prior does not improve prediction skill.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-cit2.12184","title":"Multi‐task framework of precipitation nowcasting","authors":["Zheng Zhang","Chuyao Luo","Baoquan Zhang","Hao Jiang","Bowen Zhang"],"date":"2023-01-26","year":2023,"venue":"CAAI Transactions on Intelligence Technology","venue_type":"journal","ids":{"doi":"10.1049/cit2.12184","openalex":"W4318192412"},"links":{"paper":"https://doi.org/10.1049/cit2.12184"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"GCMT-ConvRNN adds motion-field and sub-regression auxiliary tasks with a gradient-correlation loss to improve radar-based precipitation nowcasting.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-535-2023","title":"Customized deep learning for precipitation bias correction and downscaling","authors":["Fang Wang","Di Tian","Mark Carroll"],"date":"2023-01-25","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-535-2023","openalex":"W4317936154"},"links":{"paper":"https://doi.org/10.5194/gmd-16-535-2023","pdf":"https://gmd.copernicus.org/articles/16/535/2023/gmd-16-535-2023.pdf"},"orgs":["nasa"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","radar"],"status":"research","summary":"Customized deep learning with weighted losses, multitask learning and covariates improves hourly precipitation bias correction and downscaling, better capturing extremes than quantile mapping.","significance":4,"cited_by":70,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2023.106635","title":"The reconstruction for the monthly surface air temperature over the Tibetan Plateau during 1901–2020 by deep learning","authors":["Yang Ye","Qinglong You","Zheng Zhong Jin","Zhiyan Zuo","Yuqing Zhang","Shichang Kang"],"date":"2023-01-25","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2023.106635","openalex":"W4317934176"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.106635"},"orgs":["fudan-university"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Deep learning reconstructs monthly surface air temperature over the Tibetan Plateau for 1901–2020, filling gaps in the historical station record.","significance":3,"cited_by":10,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.167458059.91056213-v1","title":"Prediction of rainfall response to the 21st-century climate change in Ghana using machine learning empirical statistical downscaling","authors":["Frank Arthur","Daniel Boateng","Michael Baidu","Jeffrey N. A. Aryee"],"date":"2023-01-24","year":2023,"venue_type":"other","ids":{"doi":"10.22541/essoar.167458059.91056213/v1","openalex":"W4317894222"},"links":{"paper":"https://doi.org/10.22541/essoar.167458059.91056213/v1","pdf":"https://www.authorea.com/doi/pdf/10.22541/essoar.167458059.91056213"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Machine learning empirical statistical downscaling projects 21st-century rainfall change in Ghana under emission scenarios; the abstract is minimal.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2023.100330","title":"A spatiotemporal 3D convolutional neural network model for ENSO predictions: A test case for the 2020/21 La Niña conditions","authors":["Lu Zhou","Chuan Gao","Rong‐Hua Zhang"],"date":"2023-01-24","year":2023,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2023.100330","openalex":"W4317906506"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2023.100330"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A divided 3D CNN (TS-3DCNN) predicts the 2020–22 multi-year La Niña, comparable to a dynamical intermediate coupled model.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.10343","title":"ClimaX: A foundation model for weather and climate","authors":["Tung Nguyen","Johannes Brandstetter","Ashish Kapoor","Jayesh K. Gupta","Aditya Grover"],"date":"2023-01-24","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.10343","openalex":"W4318225439"},"links":{"paper":"https://arxiv.org/abs/2301.10343","pdf":"https://arxiv.org/pdf/2301.10343","code":"https://github.com/microsoft/ClimaX"},"orgs":["microsoft-research","ucla"],"topic":"foundation-models","topics":["global-medium-range","climate-emulation"],"type":"model","method":["transformer"],"timescale":["short","medium","climate"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"ClimaX is a transformer foundation model pretrained on CMIP6 that fine-tunes to many weather and climate tasks, outperforming data-driven baselines.","significance":7,"cited_by":174,"score":83,"highlight":true,"highlight_reason":"ClimaX is a widely cited foundation-model approach for weather and climate, pre-trained on CMIP6 and fine-tuned across tasks, though its forecast skill trails the leading models.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2022ms003164","title":"Application of Recurrent Neural Networks to Model Bias Correction: Idealized Experiments With the Lorenz‐96 Model","authors":["Arata Amemiya","M. Shlok","Takemasa Miyoshi"],"date":"2023-01-23","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003164","openalex":"W4317717825"},"links":{"paper":"https://doi.org/10.1029/2022ms003164"},"orgs":[],"topic":"data-assimilation","topics":["post-processing"],"type":"model","method":["rnn"],"timescale":["medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Recurrent neural networks learn model bias from analysis increments in an idealized Lorenz-96 setup, outperforming linear regression and reducing extended-range forecast error growth.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.09318","title":"Toward Foundation Models for Earth Monitoring: Generalizable Deep Learning Models for Natural Hazard Segmentation","authors":["Johannes Jakubik","Michal Muszynski","Michael Vössing","Niklas Kühl","Thomas Brunschwiler"],"date":"2023-01-23","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.09318"},"links":{"paper":"https://arxiv.org/abs/2301.09318","pdf":"https://arxiv.org/pdf/2301.09318"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Pre-training on a suitable pretask improves U-Net generalization for segmenting unseen natural hazards from satellite imagery across regions without target labels.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2023.48718","title":"Machine Learning Methods to Weather Forecasting to Predict Apparent Temperature: A Review","authors":["Saurabh Nayak","Priyanka Dubey"],"date":"2023-01-22","year":2023,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2023.48718","openalex":"W4317698039"},"links":{"paper":"https://doi.org/10.22214/ijraset.2023.48718","pdf":"http://dx.doi.org/10.22214/ijraset.2023.48718"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":[],"timescale":["medium"],"spatial":["global"],"data":[],"status":"research","summary":"Reviews machine learning methods as alternatives to physical models for weather forecasting, with a focus on predicting apparent temperature.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.09152","title":"Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data","authors":["Shengchao Chen","Guodong Long","Tao Shen","Jing Jiang"],"date":"2023-01-22","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.09152"},"links":{"paper":"https://arxiv.org/abs/2301.09152","pdf":"https://arxiv.org/pdf/2301.09152"},"orgs":[],"topic":"foundation-models","topics":[],"type":"model","method":["transformer"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Federated prompt learning trains a spatio-temporal Transformer foundation model across regions with heterogeneous meteorological sensors while protecting data exposure.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15030630","title":"A Novel Framework for Correcting Satellite-Based Precipitation Products for Watersheds with Discontinuous Observed Data, Case Study in Mekong River Basin","authors":["Giha Lee","Duc Hai Nguyen","Xuan-Hien Le"],"date":"2023-01-20","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15030630","openalex":"W4317739112"},"links":{"paper":"https://doi.org/10.3390/rs15030630","pdf":"https://www.mdpi.com/2072-4292/15/3/630/pdf?version=1675073638"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Convolutional autoencoder bias correction of TRMM and PERSIANN-CDR satellite rainfall over the Mekong basin, using APHRODITE gauge data as benchmark.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-au.167425256.66042780-v1","title":"MODEL INTERPRETABILITY VIA INTERACTION FEATURE DETECTION USING ROUGHSET IN A GENERALIZED LINEAR MODEL FOR WEATHER PREDICTION IN KENYA.","authors":["Isaac Kega","Lawrence Nderu","Ronald Waweru Mwangi","Dennis Njagi"],"date":"2023-01-20","year":2023,"venue_type":"other","ids":{"doi":"10.22541/au.167425256.66042780/v1","openalex":"W4317602522"},"links":{"paper":"https://doi.org/10.22541/au.167425256.66042780/v1"},"orgs":[],"topic":"local-forecasting","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A rough-set feature-interaction method feeds a generalized linear model for interpretable station weather prediction at one Kenyan farm station.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14020215","title":"Tropical Cyclone Detection from the Thermal Infrared Sensor IASI Data Using the Deep Learning Model YOLOv3","authors":["Lisa Lam","Maya George","Sébastien Gardoll","Sarah A. Safieddine","Simon Whitburn","Cathy Clerbaux"],"date":"2023-01-19","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14020215","openalex":"W4317623132"},"links":{"paper":"https://doi.org/10.3390/atmos14020215","pdf":"https://www.mdpi.com/2073-4433/14/2/215/pdf?version=1675239007"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"YOLOv3 detects tropical cyclones in IASI infrared sounder radiances over the North Atlantic, a proof of concept with AP 78.3% at IoU 0.1.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14020214","title":"Projected Rainfall Triggered Landslide Susceptibility Changes in the Hengduan Mountain Region, Southwest China under 1.5–4.0 °C Warming Scenarios Based on CMIP6 Models","authors":["Huaxiang Yin","Jiahui Zhang","Sanjit Kumar Mondal","Bingwei Wang","Lingfeng Zhou","Leibin Wang","Qigen Lin"],"date":"2023-01-19","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14020214","openalex":"W4317623158"},"links":{"paper":"https://doi.org/10.3390/atmos14020214","pdf":"https://www.mdpi.com/2073-4433/14/2/214/pdf?version=1674138788"},"orgs":["nuist"],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Random Forest, GAM and LightGBM map landslide susceptibility under CMIP6 warming, finding high-susceptibility zones grow by up to 4.0% at 4 °C warming.","significance":2,"cited_by":13,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0025.1","title":"Convective-Scale Assimilation of Cloud Cover from Photographs Using a Machine Learning Forward Operator","authors":["Maria Reinhardt","Sybille Y. Schoger","Frederik Kurzrock","Roland Potthast"],"date":"2023-01-19","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0025.1","openalex":"W4317437841"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0025.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0025.1.pdf"},"orgs":["dwd"],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["other","nwp-analysis"],"status":"research","summary":"A CNN detects clouds in camera photos to build a forward operator, enabling convective-scale assimilation of cloud cover into the ICON-D2 model; proof of concept over 6 days.","significance":4,"cited_by":0,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-022-2082-6","title":"Convective Storm VIL and Lightning Nowcasting Using Satellite and Weather Radar Measurements Based on Multi-Task Learning Models","authors":["Yang Li","Yubao Liu","Rongfu Sun","Fengxia Guo","Xiaofeng Xu","Haixiang Xu"],"date":"2023-01-19","year":2023,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-022-2082-6","openalex":"W4317438763"},"links":{"paper":"https://doi.org/10.1007/s00376-022-2082-6"},"orgs":["nuist","cma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Multi-task learning models nowcast convective storm vertically integrated liquid and lightning using satellite and weather radar observations; abstract not provided.","significance":3,"cited_by":23,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14020195","title":"Investigating Tropical Cyclone Rapid Intensification with an Advanced Artificial Intelligence System and Gridded Reanalysis Data","authors":["Yijun Wei","Ruixin Yang","Donglian Sun"],"date":"2023-01-17","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14020195","openalex":"W4317107245"},"links":{"paper":"https://doi.org/10.3390/atmos14020195","pdf":"https://www.mdpi.com/2073-4433/14/2/195/pdf?version=1673954802"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["era5"],"status":"research","summary":"CNN-derived ERA-Interim features (humidity, vorticity, ozone) added to SHIPS predictors improve tropical cyclone rapid intensification prediction by 23–43%.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31219-osf.io-gqrjt","title":"AiBEDO: A hybrid AI model to capture the effects of cloud properties on global circulation and regional climate patterns","authors":["Kalai Ramea","Sookyung Kim","Peetak Mitra","Subhashis Hazarika","Haruki Hirasawa","Dipti Hingmire","Philip John Rasch","Hansi Singh"],"date":"2023-01-17","year":2023,"venue_type":"other","ids":{"doi":"10.31219/osf.io/gqrjt","openalex":"W4317036914"},"links":{"paper":"https://doi.org/10.31219/osf.io/gqrjt","pdf":"https://osf.io/gqrjt/download"},"orgs":[],"topic":"climate-emulation","topics":["hybrid-parameterization"],"type":"model","method":["other"],"timescale":["decadal","climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Hybrid AI surrogate links cloud radiative effects to large-scale circulation and regional climate, enabling low-cost scenario runs for cloud-based climate intervention.","significance":4,"cited_by":0,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-acb3e3","title":"Improving remote sensing of extreme events with machine learning: land surface temperature retrievals from IASI observations","authors":["Eulalie Boucher","Filipe Aires"],"date":"2023-01-17","year":2023,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/acb3e3","openalex":"W4316926683"},"links":{"paper":"https://doi.org/10.1088/1748-9326/acb3e3","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/acb3e3/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Localized statistical retrievals from IASI sounder data reduce dampening and inflating errors in extreme land surface temperature retrievals, from 1.9 K to 1.6 K.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl101042","title":"The Role of Mesoscale Cloud Morphology in the Shortwave Cloud Feedback","authors":["Isabel L. McCoy","Daniel Thompson McCoy","Robert Wood","Paquita Zuidema","Frida A.‐M. Bender"],"date":"2023-01-17","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl101042","openalex":"W4317397798"},"links":{"paper":"https://doi.org/10.1029/2022gl101042","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL101042"},"orgs":["noaa","ncar","university-of-washington"],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"application","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["satellite","cmip"],"status":"research","summary":"A neural network classifies satellite cloud morphology, showing that closed-cell cloud changes contribute about 0.06 W/m²/K to global shortwave cloud feedback under CO2 quadrupling.","significance":4,"cited_by":42,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl100727","title":"Spring Regional Sea Surface Temperatures as a Precursor of European Summer Heatwaves","authors":["Goratz Beobide‐Arsuaga","André Düsterhus","Wolfgang A. Müller","Elizabeth A. Barnes","Johanna Baehr"],"date":"2023-01-17","year":2023,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl100727","openalex":"W4317397246"},"links":{"paper":"https://doi.org/10.1029/2022gl100727","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL100727"},"orgs":["mpi-meteorology","colorado-state-university"],"topic":"climate-analysis-attribution","topics":["extremes-hazards","xai-uq-physics"],"type":"application","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Explainable neural network on 100 MPI Grand Ensemble members identifies spring tripolar North Atlantic SST patterns as precursors of European summer heatwaves.","significance":3,"cited_by":19,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-isprs-annals-x-4-w1-2022-405-2023","title":"NEAR SURFACE AIR TEMPERATURE ESTIMATION THROUGH PARAMETRIZATION OF MODIS PRODUCTS","authors":["Elahe Khesali","Mohammad Reza Mobasheri"],"date":"2023-01-13","year":2023,"venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","venue_type":"journal","ids":{"doi":"10.5194/isprs-annals-x-4-w1-2022-405-2023","openalex":"W4316116053"},"links":{"paper":"https://doi.org/10.5194/isprs-annals-x-4-w1-2022-405-2023","pdf":"https://isprs-annals.copernicus.org/articles/X-4-W1-2022/405/2023/isprs-annals-X-4-W1-2022-405-2023.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Support vector regression and hybrid neural networks estimate 2 m air temperature from MODIS land surface temperature and vapour pressure, reaching about 2.25 °C accuracy.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15020498","title":"Retrieval of Atmospheric Water Vapor Content in the Environment from AHI/H8 Using Both Physical and Random Forest Methods—A Case Study for Typhoon Maria (201808)","authors":["Linyan Zhu","Ronglian Zhou","Di Di","Wenguang Bai","Zijing Liu"],"date":"2023-01-13","year":2023,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15020498","openalex":"W4316664557"},"links":{"paper":"https://doi.org/10.3390/rs15020498","pdf":"https://www.mdpi.com/2072-4292/15/2/498/pdf?version=1673945588"},"orgs":["nuist","cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Random forest retrieves Himawari-8 AHI water vapor 35–45% more accurately than 1DVAR at much lower cost, demonstrated for Typhoon Maria.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.8005","title":"A machine learning approach for prediction of seasonal lightning density in different lightning regions of India","authors":["Chandrani Chatterjee","Joyjit Mandal","Saurabh Das"],"date":"2023-01-13","year":2023,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.8005","openalex":"W4316041049"},"links":{"paper":"https://doi.org/10.1002/joc.8005","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.8005"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Random forest regionalizes India into seven lightning climatologies and predicts seasonal lightning density from CAPE and humidity, with R² of 0.81 in monsoon.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.05427","title":"Building a Fuel Moisture Model for the Coupled Fire-Atmosphere Model WRF-SFIRE from Data: From Kalman Filters to Recurrent Neural Networks","authors":["J. Mandel","J. Hirschi","A. K. Kochanski","A. Farguell","J. Haley","D. V. Mallia","B. Shaddy","A. A. Oberai","K. A. Hilburn"],"date":"2023-01-13","year":2023,"venue":"https://www.ugn.cas.cz/event/2023/sna pp. 52-55","venue_type":"journal","ids":{"arxiv":"2301.05427","openalex":"W4316829949"},"links":{"paper":"https://arxiv.org/abs/2301.05427","pdf":"https://arxiv.org/pdf/2301.05427"},"orgs":["colorado-state-university"],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["rnn","physics-constrained"],"timescale":["short"],"spatial":["regional","local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Builds a recurrent neural network fuel moisture model for WRF-SFIRE, initialized as a numerical ODE solver and trained on RAWS sensor and RTMA weather data to improve fire-weather inputs.","significance":2,"cited_by":1,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-frai.2022.963781","title":"Frost prediction using machine learning and deep neural network models","authors":["Carl James Talsma","Kurt C. Solander","Maruti Kumar Mudunuru","Brandon Crawford","Michelle Powell"],"date":"2023-01-12","year":2023,"venue":"Frontiers in Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.3389/frai.2022.963781","openalex":"W4315796201"},"links":{"paper":"https://doi.org/10.3389/frai.2022.963781","pdf":"https://www.frontiersin.org/articles/10.3389/frai.2022.963781/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Point-scale machine learning models predict frost events 6-48 h ahead in New Mexico, with 6-h RMSE of 1.53-1.72 °C, outperforming HRRR.","significance":3,"cited_by":37,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.1031186","title":"NWPP-EDH: Numerical weather prediction products evaporation duct regional prediction model","authors":["Xingyu Chai","Jincai Li","Jun Zhao","Yifan Hu","Xiaofeng Zhao"],"date":"2023-01-12","year":2023,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.1031186","openalex":"W4315796730"},"links":{"paper":"https://doi.org/10.3389/feart.2022.1031186","pdf":"https://public-pages-files-2025.frontiersin.org/journals/earth-science/articles/10.3389/feart.2022.1031186/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"NWPP-EDH maps regional evaporation duct height from NWP products, reducing RMSE 61–87% versus classical theoretical duct models.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-22-0107.1","title":"Statistical Modeling of 2-m Temperature and 10-m Wind Speed Forecast Errors","authors":["Zied Ben Bouallègue","Fenwick Cooper","Matthew Chantry","Peter D. Düben","Peter Bechtold","Irina Sandu"],"date":"2023-01-12","year":2023,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-22-0107.1","openalex":"W4315706382"},"links":{"paper":"https://doi.org/10.1175/mwr-d-22-0107.1"},"orgs":["ecmwf","university-of-oxford"],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis","stations"],"status":"research","summary":"Linear regression, random forests and neural networks correct ECMWF IFS 2 m temperature and 10 m wind errors, improving RMSE by 10–15% with uncertainty estimates.","significance":4,"cited_by":25,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10546-022-00779-6","title":"Machine Learning Weather Analogs for Near-Surface Variables","authors":["Weiming Hu","Guido Cervone","George S. Young","Luca Delle Monache"],"date":"2023-01-12","year":2023,"venue":"Boundary-Layer Meteorology","venue_type":"journal","ids":{"doi":"10.1007/s10546-022-00779-6","openalex":"W4315651797"},"links":{"paper":"https://doi.org/10.1007/s10546-022-00779-6","pdf":"https://link.springer.com/content/pdf/10.1007/s10546-022-00779-6.pdf"},"orgs":[],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Deep-learning latent space replaces hand-tuned similarity weights in analog ensembles for near-surface wind and solar forecasts, improving RMSE in Pennsylvania.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.05070","title":"Wildfire Smoke Detection with Computer Vision","authors":["Eldan R. Daniel"],"date":"2023-01-12","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.05070"},"links":{"paper":"https://arxiv.org/abs/2301.05070","pdf":"https://arxiv.org/pdf/2301.05070"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"YOLOv7 detects smoke columns in camera imagery for early wildfire warning, reaching F1 of 0.74 at confidence 0.298.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fmars.2022.956813","title":"Typhoon cloud image prediction based on enhanced multi-scale deep neural network","authors":["Xin Wang","Mengjiao Qin","Zhe Zhang","Yuanyuan Wang","Zhenhong Du","Nan Wang"],"date":"2023-01-11","year":2023,"venue":"Frontiers in Marine Science","venue_type":"journal","ids":{"doi":"10.3389/fmars.2022.956813","openalex":"W4315650665"},"links":{"paper":"https://doi.org/10.3389/fmars.2022.956813","pdf":"https://www.frontiersin.org/articles/10.3389/fmars.2022.956813/pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Enhanced multi-scale ConvLSTM network predicts typhoon cloud images three hours ahead from satellite sequences with sharper detail than prior methods.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-asl.1151","title":"A deep learning ensemble approach for predicting tropical cyclone rapid intensification","authors":["Buo‐Fu Chen","Yu‐Te Kuo","Treng-Shi Huang"],"date":"2023-01-11","year":2023,"venue":"Atmospheric Science Letters","venue_type":"journal","ids":{"doi":"10.1002/asl.1151","openalex":"W4315651321"},"links":{"paper":"https://doi.org/10.1002/asl.1151","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asl.1151"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Ensemble of 20 deep learning models combining satellite images and environmental predictors yields higher rapid-intensification detection than operational forecasts for western Pacific tropical cyclones.","significance":3,"cited_by":53,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2306.03110","title":"SwinRDM: Integrate SwinRNN with Diffusion Model Towards High-Resolution and High-Quality Weather Forecasting","authors":["Association for Artificial Intelligence 2023","Lei Chen","Du, Fei","Hu, Yuan","Fan Wang","Zhibin Wang"],"date":"2023-01-11","year":2023,"venue_type":"preprint","ids":{"arxiv":"2306.03110","doi":"10.48448/zn7f-fc64","openalex":"W4379919090"},"links":{"paper":"https://doi.org/10.48448/zn7f-fc64","pdf":"https://arxiv.org/pdf/2306.03110"},"orgs":["alibaba-damo"],"topic":"global-medium-range","topics":["downscaling"],"type":"model","method":["transformer","diffusion"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"SwinRDM couples a SwinRNN forecaster with a diffusion super-resolution step to reach 0.25° forecasts that beat IFS up to 5 days on Z500, T850, T2M and precipitation.","significance":4,"cited_by":9,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14010157","title":"A Neural-Network Based MPAS—Shallow Water Model and Its 4D-Var Data Assimilation System","authors":["Xiaoxu Tian","Luke Conibear","Jeffrey Steward"],"date":"2023-01-10","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14010157","openalex":"W4317547549"},"links":{"paper":"https://doi.org/10.3390/atmos14010157","pdf":"https://www.mdpi.com/2073-4433/14/1/157/pdf?version=1673355833"},"orgs":["tomorrow-io"],"topic":"data-assimilation","topics":["hybrid-parameterization"],"type":"model","method":["differentiable","classical-ml"],"timescale":["short"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A neural-network shallow-water emulator of MPAS with tangent-linear and adjoint code enables a continuous 4D-Var assimilation system demonstrated on twin experiments.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0037.1","title":"Detail Enhancement of AIRS/AMSU Temperature and Moisture Profiles Using a 3D Deep Neural Network","authors":["Adam B. Milstein","Joseph A. Santanello","William J. Blackwell"],"date":"2023-01-10","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0037.1","openalex":"W4315478794"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0037.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0037.1.pdf"},"orgs":["nasa","mit"],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"A 3D deep neural network sharpens AIRS/AMSU temperature and humidity retrievals, better capturing planetary boundary layer top inversions and improving PBL height estimates.","significance":4,"cited_by":5,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-acc81a","title":"Identifying the regional emergence of climate patterns in the ARISE-SAI-1.5 simulations","authors":["Labe. Zachary Michael","Barnes. Elizabeth A","Hurrell. James W."],"date":"2023-01-10","year":2023,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/acc81a","openalex":"W7212401625"},"links":{"paper":"https://doi.org/10.1088/1748-9326/acc81a"},"orgs":["colorado-state-university","princeton-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"application","method":["classical-ml","cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Logistic regression and neural networks show stratospheric aerosol injection signals in regional temperature emerge within a decade, while precipitation signals are harder to detect.","significance":4,"cited_by":15,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.7476791","title":"Material for \"A Comparison between Perfect-Prognosis and Super-Resolution Deep Learning for Statistical Downscaling of Climate Change Simulations\"","authors":["Jorge Baño‐Medina"],"date":"2023-01-09","year":2023,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.7476791","openalex":"W4313838235"},"links":{"paper":"https://doi.org/10.5281/zenodo.7476791"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":[],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Repository with code and material comparing perfect-prognosis and super-resolution deep learning for statistical downscaling of climate change simulations.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14010145","title":"Grid-to-Point Deep-Learning Error Correction for the Surface Weather Forecasts of a Fine-Scale Numerical Weather Prediction System","authors":["Yu Qin","Yubao Liu","Xinyu Jiang","Yang Li","Haixiang Xu","Yueqin Shi","Zhaoyang Huo"],"date":"2023-01-09","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14010145","openalex":"W4313889921"},"links":{"paper":"https://doi.org/10.3390/atmos14010145","pdf":"https://www.mdpi.com/2073-4433/14/1/145/pdf?version=1673258852"},"orgs":["nuist","cma"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Grid-to-point deep learning corrects 3 km PRUFS forecasts at 311 stations, cutting RMSE 19% for temperature, 24% for humidity and 42% for wind.","significance":4,"cited_by":14,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos14010142","title":"Estimating Site-Specific Wind Speeds Using Gridded Data: A Comparison of Multiple Machine Learning Models","authors":["Jintao Zhou","Jin Feng","Xin Zhou","Yang Li","Fuxin Zhu"],"date":"2023-01-09","year":2023,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14010142","openalex":"W4313824248"},"links":{"paper":"https://doi.org/10.3390/atmos14010142","pdf":"https://www.mdpi.com/2073-4433/14/1/142/pdf?version=1673231258"},"orgs":["cma"],"topic":"downscaling","topics":["post-processing"],"type":"application","method":["cnn"],"timescale":[],"spatial":["local"],"data":["era5","stations"],"status":"research","summary":"A deep CNN estimates site-specific surface wind speed from gridded ECMWF ERA5 across eastern China, reducing RMSE 23–26% versus linear interpolation.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2022.1022624","title":"A modified deep learning weather prediction using cubed sphere for global precipitation","authors":["Manmeet Singh","Nachiketa Acharya","Pratiman Patel","Sajad Jamshidi","Zong‐Liang Yang","Bipin Kumar","Suryachandra A. Rao","Sukhpal Singh Gill","Rajib Chattopadhyay","Ravi Shankar Nanjundiah","Dev Niyogi"],"date":"2023-01-09","year":2023,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2022.1022624","openalex":"W4313824201"},"links":{"paper":"https://doi.org/10.3389/fclim.2022.1022624","pdf":"https://www.frontiersin.org/articles/10.3389/fclim.2022.1022624/pdf"},"orgs":["noaa"],"topic":"global-medium-range","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Modified cubed-sphere deep learning weather model predicts global daily precipitation from surface temperature, matching GFS skill at a 1-day lag.","significance":3,"cited_by":7,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0038.1","title":"Subseasonal Prediction of Central European Summer Heatwaves with Linear and Random Forest Machine Learning Models","authors":["Elizabeth Weirich-Benet","Maria Pyrina","Bernat Jiménez‐Esteve","Ernest Fraenkel","Judah L. Cohen","Daniela I. V. Domeisen"],"date":"2023-01-09","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0038.1","openalex":"W4313888525"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0038.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/2/AIES-D-22-0038.1.pdf"},"orgs":["eth-zurich","mit"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Linear and random forest models forecast central European summer heatwaves 1–6 weeks ahead, matching ECMWF hindcast ensemble mean beyond two weeks lead.","significance":3,"cited_by":32,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.03360","title":"Upward lightning at wind turbines: Risk assessment from larger-scale meteorology","authors":["Isabell Stucke","Deborah Morgenstern","Thorsten Simon","Georg J. Mayr","Achim Zeileis","Gerhard Diendorfer","Wolfgang Schulz","Hannes Pichler"],"date":"2023-01-09","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.03360"},"links":{"paper":"https://arxiv.org/abs/2301.03360","pdf":"https://arxiv.org/pdf/2301.03360"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations","other"],"status":"research","summary":"Random forests linking direct upward lightning tower measurements to reanalysis meteorology identify drivers of lightning risk at wind turbines, with skill on independent data across Germany.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-16-199-2023","title":"WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer","authors":["Xiaohui Zhong","Zhijian Ma","Yichen Yao","Lifei Xu","Wu Yuan","Zhibin Wang"],"date":"2023-01-06","year":2023,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-16-199-2023","openalex":"W4313641022"},"links":{"paper":"https://doi.org/10.5194/gmd-16-199-2023","pdf":"https://gmd.copernicus.org/articles/16/199/2023/gmd-16-199-2023.pdf"},"orgs":["alibaba-damo"],"topic":"hybrid-parameterization","topics":["infra-software"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim","other"],"status":"pre-operational","summary":"WRF-ML coupler lets Python deep learning parameterizations run inside the Fortran WRF model, demonstrated with trained DL radiation emulators coupled to WRF.","significance":4,"cited_by":34,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-22-0132.1","title":"Skillful Extended-Range Forecast of Rainfall and Extreme Events in East China Based on Deep Learning","authors":["Jiehong Xie","Pang‐Chi Hsu","Yamin Hu","Mengxi Ye","Jinhua Yu"],"date":"2023-01-06","year":2023,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-22-0132.1","openalex":"W4313597868"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0132.1"},"orgs":["nuist","cma"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"CNN and GRU models forecast East China rainfall anomalies at 10–30 day leads, beating CMA and ECMWF dynamical models in skill and extreme-event scores.","significance":4,"cited_by":27,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijpeds.v14.i1.pp496-505","title":"Global solar radiation forecast using an ensemble learning approach","authors":["Debani Prasad Mishra","Subhrajit Jena","Rudranarayan Senapati","Atman Panigrahi","Surender Reddy Salkuti"],"date":"2023-01-06","year":2023,"venue":"International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering","venue_type":"journal","ids":{"doi":"10.11591/ijpeds.v14.i1.pp496-505","openalex":"W4313654558"},"links":{"paper":"https://doi.org/10.11591/ijpeds.v14.i1.pp496-505","pdf":"https://ijpeds.iaescore.com/index.php/IJPEDS/article/download/22308/14107"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Random forest and XGBoost ensembles predict site-specific solar radiation from station weather forecast reports, then convert it to PV power output.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.02361","title":"A Bayesian Neural Network Approach for Tropospheric Temperature Retrievals from a Lidar Instrument","authors":["Ghazal Farhani","Giovanni Martucci","Tyler Roberts","Alexander Haefele","Robert J. Sica"],"date":"2023-01-06","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.02361","doi":"10.1080/01431161.2023.2187723"},"links":{"paper":"https://arxiv.org/abs/2301.02361","pdf":"https://arxiv.org/pdf/2301.02361"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["other","stations"],"status":"research","summary":"Bayesian neural network retrieves 0.7–6 km tropospheric temperature profiles from Raman lidar with per-profile uncertainty, agreeing with the standard algorithm to within 0.05 K below 4.5 km.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.1012165","title":"A hybrid data assimilation system based on machine learning","authors":["Renze Dong","Hongze Leng","Chengwu Zhao","Junqiang Song","Juan Zhao","Xiaoqun Cao"],"date":"2023-01-05","year":2023,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.1012165","openalex":"W4313559365"},"links":{"paper":"https://doi.org/10.3389/feart.2022.1012165","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.1012165/pdf"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Hybrid DA system uses a bilinear network as tangent-linear/adjoint and a CNN to adaptively blend 4DVar and EnKF analyses, tested on Lorenz-96 with lower cost.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2022.1058677","title":"Deep learning for skillful long-lead ENSO forecasts","authors":["Kalpesh Ravindra Patil","Takeshi Doi","Venkata Ratnam Jayanthi","Swadhin Kumar Behera"],"date":"2023-01-04","year":2023,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2022.1058677","openalex":"W4313585738"},"links":{"paper":"https://doi.org/10.3389/fclim.2022.1058677","pdf":"https://www.frontiersin.org/articles/10.3389/fclim.2022.1058677/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"Seasonal CNN ENSO predictor with a modified loss function forecasts ENSO 18–24 months ahead, overcoming the spring barrier better than SINTEX-F2.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33395-sinkron.v8i1.12048","title":"Weather Forecast In Medan City With Hopfield Artificial Neural Network Algorithm","authors":["Badrul Anwar","Nizwardi Jalinus","Rijal Abdullah"],"date":"2023-01-04","year":2023,"venue":"SinkrOn","venue_type":"journal","ids":{"doi":"10.33395/sinkron.v8i1.12048","openalex":"W4317034882"},"links":{"paper":"https://doi.org/10.33395/sinkron.v8i1.12048","pdf":"https://jurnal.polgan.ac.id/index.php/sinkron/article/download/12048/1310"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Builds a website weather forecast application for Medan City using a Hopfield neural network and BMKG data to disseminate forecasts.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2023.48291","title":"Machine Learning Methods to Weather Forecasting to Predict Apparent Temperature","authors":["Saurabh Nayak","Kamal Shrivastav"],"date":"2023-01-04","year":2023,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2023.48291","openalex":"W4313588785"},"links":{"paper":"https://doi.org/10.22214/ijraset.2023.48291","pdf":"http://dx.doi.org/10.22214/ijraset.2023.48291"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Random forests, decision trees and regression forecast apparent temperature from Dark Sky API data, offering a generic comparison with limited novelty.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13143-022-00313-1","title":"Improved Tropical Cyclone Track Simulation over the Western North Pacific using the WRF Model and a Machine Learning Method","authors":["Kyoung-Min Kim","Donghyuck Yoon","Dong‐Hyun Cha","Jungho Im"],"date":"2023-01-04","year":2023,"venue":"Asia-Pacific Journal of Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s13143-022-00313-1","openalex":"W4313595131"},"links":{"paper":"https://doi.org/10.1007/s13143-022-00313-1"},"orgs":[],"topic":"extremes-hazards","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Machine learning combined with WRF improves western North Pacific tropical cyclone track simulation; the abstract is unavailable, so the gain is unquantified.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40808-022-01678-y","title":"An evaluation of satellite precipitation downscaling models using machine learning algorithms in Hashtgerd Plain, Iran","authors":["Mohammad Nakhaei","Amin Mohebbi Tafreshi","Tofigh Saadi"],"date":"2023-01-03","year":2023,"venue":"Modeling Earth Systems and Environment","venue_type":"journal","ids":{"doi":"10.1007/s40808-022-01678-y","openalex":"W4313532263"},"links":{"paper":"https://doi.org/10.1007/s40808-022-01678-y"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Evaluates machine learning models for downscaling satellite precipitation over Hashtgerd Plain, Iran, checked against local observations.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-022-02378-w","title":"LSTM-CM: a hybrid approach for natural drought prediction based on deep learning and climate models","authors":["Tuong Quang Vo","Seon‐Ho Kim","Duc Hai Nguyen","Deg‐Hyo Bae"],"date":"2023-01-03","year":2023,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-022-02378-w","openalex":"W4313531911"},"links":{"paper":"https://doi.org/10.1007/s00477-022-02378-w"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":[],"data":["cmip"],"status":"research","summary":"Hybrid LSTM driven by climate model outputs to predict natural drought; the abstract is missing, so details are limited.","significance":2,"cited_by":43,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.00819","title":"A Concurrent CNN-RNN Approach for Multi-Step Wind Power Forecasting","authors":["Syed Kazmi","Berk Gorgulu","Mucahit Cevik","Mustafa Gokce Baydogan"],"date":"2023-01-02","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.00819","openalex":"W4313529674"},"links":{"paper":"https://arxiv.org/abs/2301.00819","pdf":"https://arxiv.org/pdf/2301.00819"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["cnn","rnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"A CNN-RNN model combining multi-NWP grid inputs with farm histories improves day-ahead wind power forecasts over LightGBM when trained globally across farms.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.00496","title":"Using Neural Networks to Learn the Jet Stream Forced Response from Natural Variability","authors":["Charlotte Connolly","Elizabeth A. Barnes","Pedram Hassanzadeh","Mike Pritchard"],"date":"2023-01-02","year":2023,"venue_type":"preprint","ids":{"arxiv":"2301.00496"},"links":{"paper":"https://arxiv.org/abs/2301.00496","pdf":"https://arxiv.org/pdf/2301.00496"},"orgs":[],"topic":"climate-analysis-attribution","topics":["climate-emulation"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["other","cmip"],"status":"research","summary":"Trains a CNN on internal variability of a long dry-core control run to predict the nonlinear jet stream response to tropospheric forcing, extending fluctuation-dissipation ideas beyond linear response.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7137707613","title":"CERN openlab Summer Student Lightning Talks (1/2)","authors":["David Hidary"],"date":"2023-01-01","year":2023,"venue":"CERN Document Server (European Organization for Nuclear Research)","venue_type":"preprint","ids":{"openalex":"W7137707613"},"links":{"paper":"http://cds.cern.ch/record/2867767"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"evaluation","method":["transformer"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Applies self-attention map analysis to the AtmoRep weather foundation model to interpret how meteorological variables drive its predictions; a short talk without quantitative results.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.62991-mmt1996365745","title":"CLOUD TYPE CLASSIFICATION IN GROUND-BASED SKY IMAGES WITH DEEP LEARNING","authors":["Ardan Hüseyin Eşlik","Emre Akarslan","Fatih Onur Hocaoğlu"],"date":"2023-01-01","year":2023,"venue":"Journal of International Scientific Publications : Materials, Methods & Technologies.","venue_type":"journal","ids":{"doi":"10.62991/mmt1996365745","openalex":"W4395472371"},"links":{"paper":"https://doi.org/10.62991/mmt1996365745","pdf":"https://www.scientific-publications.net/en/article/1002695/1000063-1701362279960241.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A CNN classifies six cloud types in ground-based sky images from the SWIMCAT-EXT dataset for use in solar radiation forecasting.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.58496-mjbd-2023-017","title":"Climate Changes through Data Science: Understanding and Mitigating Environmental Crisis","authors":["Ahmed Hussein Ali","Rahul Thakkar"],"date":"2023-01-01","year":2023,"venue":"Mesopotamian Journal of Big Data","venue_type":"journal","ids":{"doi":"10.58496/mjbd/2023/017","openalex":"W4389286478"},"links":{"paper":"https://doi.org/10.58496/mjbd/2023/017","pdf":"https://mesopotamian.press/journals/index.php/bigdata/article/download/177/171"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Broad review of data science and machine learning for climate detection, attribution, impacts and mitigation, with limited technical novelty.","significance":2,"cited_by":39,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4236-ajcc.2023.124027","title":"Segmentation and Classification of Individual Clouds in Images Captured with Horizon-Aimed Cameras for Nowcasting of Solar Irradiance Absorption","authors":["Bruno Juncklaus Martins","Juliana Marian Arrais","Allan Cerentini","Aldo von Wangenheim","Gilberto Perello Ricci Neto","Sylvio Luiz Mantelli Neto"],"date":"2023-01-01","year":2023,"venue":"American Journal of Climate Change","venue_type":"journal","ids":{"doi":"10.4236/ajcc.2023.124027","openalex":"W4389318333"},"links":{"paper":"https://doi.org/10.4236/ajcc.2023.124027","pdf":"http://www.scirp.org/journal/PaperDownload.aspx?paperID=129625"},"orgs":[],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"application","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"U-Net with ResNet18 segments clouds in horizon-camera images for solar irradiance nowcasting, reaching mean IoU 0.6 with class imbalance limiting performance.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4236-acs.2023.134033","title":"A Wavelet-Based Deep Learning Framework for Predicting Peak Intensity of Hurricanes in the Atlantic Ocean","authors":["Jiahe Liu","Xiaodi Wang"],"date":"2023-01-01","year":2023,"venue":"Atmospheric and Climate Sciences","venue_type":"journal","ids":{"doi":"10.4236/acs.2023.134033","openalex":"W4387984324"},"links":{"paper":"https://doi.org/10.4236/acs.2023.134033","pdf":"http://www.scirp.org/journal/PaperDownload.aspx?paperID=128650"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Multi-input CNN with wavelet-decomposed satellite imagery estimates Atlantic hurricane maximum wind speed with 15-knot RMSE.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4236-acs.2023.134029","title":"Application of Machine-Learning-Based Objective Correction Method in the Intelligent Grid Maximum and Minimum Temperature Predictions","authors":["Jing Liu","Chuan Ren","Ningle Yuan","Shuai Zhang","Yue Wang"],"date":"2023-01-01","year":2023,"venue":"Atmospheric and Climate Sciences","venue_type":"journal","ids":{"doi":"10.4236/acs.2023.134029","openalex":"W4387585654"},"links":{"paper":"https://doi.org/10.4236/acs.2023.134029","pdf":"https://www.scirp.org/pdf/acs_2023101213443745.pdf"},"orgs":["cma"],"topic":"post-processing","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine-learning correction of ECMWF and grid forecasts for Shenyang station maximum and minimum temperature improves accuracy by up to 186% in some seasons.","significance":2,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35679-1991-9476-2023-18-5-686-695","title":"PREDICTION OF EVAPORATION FROM THE WATER SURFACE USING MACHINE LEARNING","authors":["Alessandro Brunovich Cavalli","Alexander Ivanovich Belolyubtsev","Anna Vladislavovna Belkova","Vitaly Vitalievich Ilyinich"],"date":"2023-01-01","year":2023,"venue":"SCIENTIFIC LIFE","venue_type":"journal","ids":{"doi":"10.35679/1991-9476-2023-18-5-686-695","openalex":"W4403184327"},"links":{"paper":"https://doi.org/10.35679/1991-9476-2023-18-5-686-695"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A neural ML method predicts pentad water-surface evaporation for rice fields from forecast temperature, wind and precipitation, aimed at medium-term agricultural planning.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35444-ijana.2023.15211","title":"Deep Neural Networks for Weather Forecasting","authors":["Naglaa Saeed Shehata"],"date":"2023-01-01","year":2023,"venue":"International Journal of Advanced Networking and Applications","venue_type":"journal","ids":{"doi":"10.35444/ijana.2023.15211","openalex":"W4386690329"},"links":{"paper":"https://doi.org/10.35444/ijana.2023.15211","pdf":"http://dx.doi.org/10.35444/ijana.2023.15211"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Deep networks map reanalysis fields at one time to a future time, a basic data-driven forecast setup with little methodological detail.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35266-1999-7604-2023-3-76-81","title":"AN INTELLIGENT SYSTEM FOR TEMPERATURE FORECASTING BASED ON A MODIFIED FUZZY NEURAL NETWORK","authors":["Екатерина Александровна Энгель","Никита Евгеньевич Энгель"],"date":"2023-01-01","year":2023,"venue":"Vestnik kibernetiki","venue_type":"journal","ids":{"doi":"10.35266/1999-7604-2023-3-76-81","openalex":"W4389142592"},"links":{"paper":"https://doi.org/10.35266/1999-7604-2023-3-76-81"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"A modified fuzzy neural network with attention forecasts location-specific temperature from website data, reporting RMSE about three times lower than recurrent networks.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.34133-olar.0031","title":"Enhanced Offshore Wind Speed Forecasts along the US East Coast: A Deep Learning Framework Leveraging NDBC Buoy Data","authors":["Xinhai Han","Xiaohui Li","Jingsong Yang","Jiuke Wang","Jun Ding","Hui Shen","Jun Yan","He Fang","Qingmei Xiao"],"date":"2023-01-01","year":2023,"venue":"Ocean-Land-Atmosphere Research","venue_type":"journal","ids":{"doi":"10.34133/olar.0031","openalex":"W4389189039"},"links":{"paper":"https://doi.org/10.34133/olar.0031"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"An LSTM with a site-embedding layer forecasts hourly wind speeds at multiple US East Coast buoys, with 2.09 m/s average RMSE, and works during hurricanes.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.34133-olar.0012","title":"An Interpretable Deep Learning ENSO Forecasting Model","authors":["Haoyu Wang","Shineng Hu","Xiaofeng Li"],"date":"2023-01-01","year":2023,"venue":"Ocean-Land-Atmosphere Research","venue_type":"journal","ids":{"doi":"10.34133/olar.0012","openalex":"W4376874322"},"links":{"paper":"https://doi.org/10.34133/olar.0012"},"orgs":[],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["cnn","transformer"],"timescale":["seasonal"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Interpretable deep learning ENSO model uses global ocean heat signatures to reach 22-month effective forecast length, with skill maintained using SST alone.","significance":3,"cited_by":39,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32604-csse.2023.033991","title":"Improvements in Weather Forecasting Technique Using Cognitive Internet of Things","authors":["Kaushlendra Yadav","Anuj Kumar Singh","Arvind Kumar Tiwari"],"date":"2023-01-01","year":2023,"venue":"Computer Systems Science and Engineering","venue_type":"journal","ids":{"doi":"10.32604/csse.2023.033991","openalex":"W4362514455"},"links":{"paper":"https://doi.org/10.32604/csse.2023.033991"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Stacked ensemble of ML models on IoT sensor data reports 99.25% accuracy for local weather parameters, and 85% on Australian rainfall. Limited generality.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30919-es1047","title":"Combining Long-Short Term Memory and Genetic Programming for Monthly Rainfall Downscaling in Southern Thailand's Thale Sap Songkhla River Basin","authors":["Sirimon Pinthong","Pakorn Ditthakit","Nureehan Salaeh","Warit Wipulanusat","Uruya Weesakul","Ismail Elkhrachy","Krishna Kumar Yadav","Nand Lal Kushwaha"],"date":"2023-01-01","year":2023,"venue":"Engineered Science","venue_type":"journal","ids":{"doi":"10.30919/es1047","openalex":"W4389484457"},"links":{"paper":"https://doi.org/10.30919/es1047","pdf":"https://www.espublisher.com/uploads/article_pdf/es1047_JustAccepted.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Combines LSTM and genetic programming to downscale CMIP5 and CMIP6 monthly rainfall at three Thai stations, projecting 2030s to 2080s trends.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.28974-idojaras.2023.3.4","title":"Impacts of large scale climate drivers on precipitation in Sindh, Pakistan using machine learning techniques","authors":["Sapna Tajbar","Ali Mohammad Khorshiddoust","Saeed Jahanbakhsh Asl"],"date":"2023-01-01","year":2023,"venue":"Időjárás","venue_type":"journal","ids":{"doi":"10.28974/idojaras.2023.3.4","openalex":"W4386611147"},"links":{"paper":"https://doi.org/10.28974/idojaras.2023.3.4","pdf":"https://www.met.hu/downloads.php?fn=/metadmin/newspaper/2023/09/9013f976f28b825b7b07ab64f150c9f6-127-3-4-tajbar.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"ANN and BRNN models with 12-month lagged climate drivers forecast monthly precipitation in Sindh, Pakistan, reaching correlations of 0.57 to 0.83.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.26464-epp2023049","title":"Deep learning-based subseasonal to seasonal precipitation prediction in southwest China: Algorithm comparison and sensitivity to input features","authors":["Guolu Gao","Ya’an Meteorological Observatory, Sichuan Meteorological Bureau, Ya’an Sichuan 625000, China","Yang Li","XueYun Zhou","XiaoMing Xiang","Jiaqi Li","ShuCheng Yin","Leshan Meteorological Observatory, Sichuan Meteorological Bureau, Leshan Sichuan 614000, China","Quanzhou Meteorological Observatory, Fujian Meteorological Bureau, Quanzhou Fujian 362000, China"],"date":"2023-01-01","year":2023,"venue":"Earth and Planetary Physics","venue_type":"journal","ids":{"doi":"10.26464/epp2023049","openalex":"W4382361007"},"links":{"paper":"https://doi.org/10.26464/epp2023049","pdf":"https://www.eppcgs.org/article/pdf/preview/10.26464/epp2023049.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn"],"timescale":["s2s"],"spatial":["regional"],"data":["other"],"status":"research","summary":"RNN outperforms LSTM and GRU for S2S wet-season precipitation in Sichuan, reaching 88.95% trend sign accuracy and highlighting Niño index sensitivity.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25984-1970814","title":"Super-Resolution for Renewable Energy Resource Data with Climate Change Impacts (Sup3rCC)","authors":["Grant Buster","Brandon Benton","Andrew Glaws","Ryan King"],"date":"2023-01-01","year":2023,"venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","venue_type":"preprint","ids":{"doi":"10.25984/1970814","openalex":"W4389525130"},"links":{"paper":"https://doi.org/10.25984/1970814"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"benchmark","method":["gan-vae"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Releases 4 km hourly wind, solar and meteorological fields for the contiguous US under climate scenarios, generatively downscaled from GCMs for energy studies.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2298-csis220717018c","title":"Machine learning-based intelligent weather modification forecast in smart city potential area","authors":["Zengyuan Chao"],"date":"2023-01-01","year":2023,"venue":"Computer Science and Information Systems","venue_type":"journal","ids":{"doi":"10.2298/csis220717018c","openalex":"W4323781422"},"links":{"paper":"https://doi.org/10.2298/csis220717018c","pdf":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142300018C"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Decision-tree and ML systems are proposed for smart-city weather modification forecasting, claiming 35% accuracy gains over traditional models on Shaanxi data with limited methodological detail.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4671922","title":"Machine Learning-Based Downscaling of Urban Air Temperature Using Lidar Data","authors":["Fatemeh Chajaei","Hossein Bagheri"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4671922","openalex":"W4390075564"},"links":{"paper":"https://doi.org/10.2139/ssrn.4671922"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Machine learning downscaling of urban air temperature using lidar data; the abstract is missing, so the method and results are limited.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4661666","title":"Using Machine Learning to Analyze the Changes in Extreme Precipitation in Southern China","authors":["Bojun Wang","Wei Wei","Zejiang Yin","Lianlian Xu"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4661666","openalex":"W4389631603"},"links":{"paper":"https://doi.org/10.2139/ssrn.4661666"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Machine learning analysis of changes in extreme precipitation over southern China; abstract unavailable, so judgement is based on title only.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4573420","title":"Srndiff: Short-Term Rainfall Nowcasting with Condition Diffusion Model","authors":["Xudong Ling","Chaorong Li","Fengqing Qin","Peng Yang","Yuanyuan Huang"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4573420","openalex":"W4386761825"},"links":{"paper":"https://doi.org/10.2139/ssrn.4573420"},"orgs":[],"topic":"nowcasting","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion"],"timescale":["nowcast"],"spatial":[],"data":["radar"],"status":"research","summary":"Conditional diffusion model for short-term rainfall nowcasting; the abstract is unavailable so the classification relies on the title.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4537479","title":"Efficientrainnet: Memory Resilient Neural Networks Based on Efficientnetv2 for Rainfall Nowcasting","authors":["Muhammed Ali Sit","Bong‐Chul Seo","Bekir Zahit Demiray","İbrahim Demir"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4537479","openalex":"W4385732208"},"links":{"paper":"https://doi.org/10.2139/ssrn.4537479"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":[],"data":[],"status":"research","summary":"EfficientNetV2-based memory-resilient network for rainfall nowcasting; the abstract is unavailable so the classification relies on the title.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4481893","title":"Optimal Rain-Gauge Network Design for Spatial Average Estimation with Missing Data: A Nested Optimization Framework with Genetic Algorithm and Machine Learning","authors":["Sumanth Kumar Boya","Deepak Subramani"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4481893","openalex":"W4380906390"},"links":{"paper":"https://doi.org/10.2139/ssrn.4481893"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Nested genetic-algorithm and machine learning framework optimizes rain-gauge network design for spatial average rainfall estimation under missing data; the abstract is unavailable.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4457264","title":"Seasonal Forecast of Winter Precipitation Over China Using Machine Learning Models","authors":["Xiaojing Jia","Qifeng Qian"],"date":"2023-01-01","year":2023,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.2139/ssrn.4457264","openalex":"W4377723613"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2023.106961"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Applies machine learning models to seasonal forecasting of winter precipitation over China; the abstract is missing, so skill results cannot be confirmed.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4437064","title":"Towards Replacing Precipitation Ensemble Predictions Systems Using Machine Learning","authors":["Rüdiger Brecht","Alexander Bihlo"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"arxiv":"2304.10251","doi":"10.2139/ssrn.4437064","openalex":"W4371783470"},"links":{"paper":"https://doi.org/10.2139/ssrn.4437064"},"orgs":[],"topic":"probabilistic-ensembles","topics":["post-processing"],"type":"position","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Explores replacing precipitation ensemble prediction systems with machine learning; no abstract is available, so the approach and results are unclear.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4423582","title":"Artificial Neural Network-Empowered Projected Future Rainfall Intensity-Duration-Frequency Curves Under Changing Climate","authors":["Bijoychandra S. Takhellambam","Puneet Srivastava","Jasmeet Lamba","Wenpeng Zhao","Hemendra Kumar","Di Tian","Roberto Molinari"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4423582","openalex":"W4366407353"},"links":{"paper":"https://doi.org/10.2139/ssrn.4423582"},"orgs":[],"topic":"extremes-hazards","topics":["downscaling"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Artificial neural networks project future rainfall intensity-duration-frequency curves under climate change; the abstract is missing, so results are limited.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4415957","title":"Offshore Wind Field Super-Resolution Using Deep Learning Methods","authors":["Sarah Maebius","Niamh French","Philippa Jane Mason"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4415957","openalex":"W4365788144"},"links":{"paper":"https://doi.org/10.2139/ssrn.4415957"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":[],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies deep learning to super-resolve offshore wind fields; the abstract is unavailable, so the method and gains cannot be verified.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4381923","title":"Detection of Tropical Cyclone Using Deep Learning Network","authors":["D. Kavitha","T Nikhil","R Praveen","Mohammed Nhj"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4381923","openalex":"W4323908295"},"links":{"paper":"https://doi.org/10.2139/ssrn.4381923"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Deep learning network detects tropical cyclones; no abstract is available.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4331675","title":"Prediction of Lightning Occurrence in South Africa Using Neural Network and Meteorological Data","authors":["Sizwe Mzila","H. J. HUNT","Ritesh Ajoodha"],"date":"2023-01-01","year":2023,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4331675","openalex":"W4319996998"},"links":{"paper":"https://doi.org/10.2139/ssrn.4331675"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Neural network predicts lightning occurrence in South Africa from meteorological station data; no abstract is available.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21046-2070-7401-2023-20-6-35-48","title":"Neural network approaches to precipitation nowcasting: A review and test of existing methods","authors":["Кучма Михаил Олегович","Sergey I. Malkovsky","A.I. Andreev","Vladislav D. Bloshchinskiy"],"date":"2023-01-01","year":2023,"venue":"Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa","venue_type":"journal","ids":{"doi":"10.21046/2070-7401-2023-20-6-35-48","openalex":"W4390422323"},"links":{"paper":"https://doi.org/10.21046/2070-7401-2023-20-6-35-48","pdf":"https://doi.org/10.21046/2070-7401-2023-20-6-35-48"},"orgs":[],"topic":"nowcasting","topics":[],"type":"review","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Reviews neural network approaches to precipitation nowcasting and tests existing methods, providing a comparative evaluation for radar-based forecasting.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.17762-ijisae.v11i3s.7686","title":"Neural Network Surrogates for Weather Prediction Using Numerical Solutions of the Shallow Water Equations","authors":["Suresh Kumar Sahani"],"date":"2023-01-01","year":2023,"venue":"International Journal of Intelligent Systems and Applications in Engineering","venue_type":"journal","ids":{"doi":"10.17762/ijisae.v11i3s.7686","openalex":"W4412043893"},"links":{"paper":"https://doi.org/10.17762/ijisae.v11i3s.7686","pdf":"https://ijisae.org/index.php/IJISAE/article/download/7686/6704"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":[],"data":["era5","other"],"status":"research","summary":"Physics-informed neural network surrogate for shallow water equations cuts solver compute time by over 80% while keeping RMSE near 0.07 on normalized variables.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijgw.2023.133219","title":"Prediction of weather using high-performance gradient boosting","authors":["V. Bibin Christopher","R. Isaac Sajan","T. S. Akhila","M. Joselin Kavitha"],"date":"2023-01-01","year":2023,"venue":"International Journal of Global Warming","venue_type":"journal","ids":{"doi":"10.1504/ijgw.2023.133219","openalex":"W4386394509"},"links":{"paper":"https://doi.org/10.1504/ijgw.2023.133219"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LightGBM gradient boosting forecasts daily Seattle precipitation and temperatures from 1948–2017 station records, claimed to outperform other boosting methods.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijgw.2023.130984","title":"Efficient data pruning using optimal KNN for weather forecasting in cloud computing","authors":["T. Benil","P. Krishna Kumar","R. Bharathi"],"date":"2023-01-01","year":2023,"venue":"International Journal of Global Warming","venue_type":"journal","ids":{"doi":"10.1504/ijgw.2023.130984","openalex":"W4377081950"},"links":{"paper":"https://doi.org/10.1504/ijgw.2023.130984"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Proposes an optimal KNN with data pruning for missing values to classify Seattle rainfall; reports better accuracy and lower runtime. Weakly described and narrow.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14569-ijacsa.2023.0140567","title":"Integrating Regression Models and Climatological Data for Improved Precipitation Forecast in Southern India","authors":["J. Subha","S. Saudia"],"date":"2023-01-01","year":2023,"venue":"International Journal of Advanced Computer Science and Applications","venue_type":"journal","ids":{"doi":"10.14569/ijacsa.2023.0140567","openalex":"W4379385774"},"links":{"paper":"https://doi.org/10.14569/ijacsa.2023.0140567","pdf":"https://thesai.org/Downloads/Volume14No5/Paper_67-Integrating_Regression_Models_and_Climatological_Data.pdf"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Compares regression models and ensembles on NASA POWER climate data for precipitation forecasts in southern India, with ensemble E-MLR-RFR performing best.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-21-0012.1","title":"Strictly Enforcing Invertibility and Conservation in CNN-Based Super Resolution for Scientific Datasets","authors":["Andrew Geiss","Joseph Clinton Hardin"],"date":"2023-01-01","year":2023,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-21-0012.1","openalex":"W4321612349"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0012.1"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["satellite","other"],"status":"research","summary":"Differentiable operator enforces exact conservation of low-resolution values in CNN super-resolution, tested on radar, satellite and climate model data.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2023-3569538","title":"Tropical Cyclone Intensity Probabilistic Forecasting System Based on Deep Learning","authors":["Fan Meng","Kun‐Lin Yang","Yichen Yao","Zhibin Wang","Tao Song"],"date":"2023-01-01","year":2023,"venue":"International Journal of Intelligent Systems","venue_type":"journal","ids":{"doi":"10.1155/2023/3569538","openalex":"W4327811049"},"links":{"paper":"https://doi.org/10.1155/2023/3569538","pdf":"https://downloads.hindawi.com/journals/ijis/2023/3569538.pdf"},"orgs":["alibaba-damo"],"topic":"extremes-hazards","topics":["probabilistic-ensembles"],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"PTCIF gives probabilistic 6-24 h tropical cyclone intensity forecasts from multimodal data, with prediction intervals comparable to forecast centres on deterministic scores.","significance":3,"cited_by":22,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3329649","title":"Toward Physics-Informed Neural Networks for 3-D Multilayer Cloud Mask Reconstruction","authors":["Yiding Wang","Jie Gong","Dong L. Wu","Lei Ding"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3329649","openalex":"W4388240334"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3329649"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":["xai-uq-physics"],"type":"model","method":["physics-constrained","cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A physics-informed CloudMask loss improves deep networks that reconstruct 3D multilayer cloud masks from 2D satellite imagery over binary cross-entropy.","significance":3,"cited_by":8,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3328945","title":"LPT-QPN: A Lightweight Physics-Informed Transformer for Quantitative Precipitation Nowcasting","authors":["Dawei Li","Kefeng Deng","Di Zhang","Yudi Liu","Hongze Leng","Fukang Yin","Kaijun Ren","Junqiang Song"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3328945","openalex":"W4388087636"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3328945"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","physics-constrained"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Lightweight physics-informed transformer nowcasts quantitative precipitation from VIL radar products with convection-diffusion constraints and beats state-of-the-art models.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3323679","title":"MF-ANN: A Novel Artificial Neural Network-Based Method for Ocean Wind Speed Retrieval on Spaceborne GNSS-R Signal","authors":["Heng Xie","Xing Cheng","Shanbao He","Yujie Li","Jingjing Pang","Shuaishuai Li"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3323679","openalex":"W4387546353"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3323679"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"MF-ANN retrieves ocean surface wind speed from CYGNSS GNSS-R data with feature selection and outlier filtering, cutting RMSE by 29% over a single ANN.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3322676","title":"Improvement in District Scale Heavy Rainfall Prediction Over Complex Terrain of North East India Using Deep Learning","authors":["Omveer Sharma","Dhananjay Trivedi","Sandeep Pattnaik","Vivekananda Hazra","Niladri Bihari Puhan"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3322676","openalex":"W4387449032"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3322676"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"U-Net trained on WRF rainfall outputs cuts district-scale heavy rainfall MAE by 64.78% over Assam and lifts categorical accuracy to 77.9%.","significance":3,"cited_by":31,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3303268","title":"A Feedforward Neural Network Approach for the Detection of Optically Thin Cirrus From IASI-NG","authors":["Elisabetta Ricciardelli","Francesco Di Paola","Domenico Cimini","Salvatore Larosa","Pietro Mastro","Guido Masiello","Carmine Serio","Tim Hultberg","Thomas August","Filomena Romano"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3303268","openalex":"W4385626792"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3303268","pdf":"https://ieeexplore.ieee.org/ielx7/36/4358825/10210600.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Feedforward neural network detects optically thin cirrus in IASI-NG simulations, improving detection probability by 3% over IASI with false alarm ratio falling to 0.01.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3300880","title":"Long-Term Calibration of Satellite-Based All-Weather Precipitable Water Vapor Product From FengYun-3A MERSI Near-Infrared Bands From 2010 to 2017 in China","authors":["Jiafei Xu","Zhizhao Liu"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3300880","openalex":"W4385626815"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3300880"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Four machine learning methods recalibrate FY-3A MERSI near-infrared precipitable water vapor against GPS stations, cutting RMSE by 58–72% over China.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3295211","title":"Skillful Radar-Based Heavy Rainfall Nowcasting Using Task-Segmented Generative Adversarial Network","authors":["Rui Wang","Lin Su","Wai Kin Wong","Alexis K.H. Lau","Jimmy Chi Hung Fung"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3295211","openalex":"W4384162039"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3295211"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional","local"],"data":["radar"],"status":"research","summary":"TS-RainGAN splits heavy-rainfall nowcasting into coverage and intensity GAN modules, reducing blurriness and giving skillful district-level forecasts up to 2 hours ahead.","significance":5,"cited_by":16,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3294266","title":"A XGBoost-Based Downscaling-Calibration Scheme for Extreme Precipitation Events","authors":["Honglin Zhu","Huizeng Liu","Qiming Zhou","Aihong Cui"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3294266","openalex":"W4383960224"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3294266"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"XGBoost used for both downscaling and calibration of satellite precipitation during typhoons, better reproducing extreme rainfall spatial variability than single-step alternatives.","significance":3,"cited_by":65,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3280799","title":"Polarimetric Radar Quantitative Precipitation Estimation Using Deep Convolutional Neural Networks","authors":["Wenyuan Li","Haonan Chen","Lei Han"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3280799","openalex":"W4378697256"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3280799"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Deep CNNs with dense blocks estimate hourly rainfall from polarimetric WSR-88D radar, reaching MAE 1.58 mm and beating traditional Z-R relations.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3276173","title":"Global Ocean Wind Speed Retrieval From GNSS Reflectometry Using CNN-LSTM Network","authors":["Cuixian Lu","Zhuo Wang","Zhilu Wu","Yuxin Zheng","Yuxuan Liu"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3276173","openalex":"W4376607832"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3276173"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","rnn"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"A CNN-LSTM retrieves global ocean surface wind speed from CYGNSS GNSS-R data, reaching 1.34 m/s RMSE against ERA5 and beating CNN by 6.3%.","significance":3,"cited_by":44,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3269622","title":"Multiinformation Fusion Network for Mapping Gapless All-Sky Land Surface Temperature Using Thermal Infrared and Reanalysis Data","authors":["Yong Zhang","Yingbao Yang","Xin Pan","Yuan Ding","Jia Hu","Yang Dai"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3269622","openalex":"W4366967739"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3269622"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","other"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"A CNN attention fusion network combines MODIS and ERA5 data to produce gapless all-sky land surface temperature maps, outperforming four state-of-the-art methods.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3268187","title":"STUNNER: Radar Echo Extrapolation Model Based on Spatiotemporal Fusion Neural Network","authors":["Wei Fang","Lin Pang","Victor S. Sheng","Qiguang Wang"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3268187","openalex":"W4366310767"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3268187"},"orgs":["nuist","cma"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"STUNNER uses a two-stream spatiotemporal fusion network with temporal differencing for radar echo extrapolation, achieving best results on two public datasets.","significance":3,"cited_by":19,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3267976","title":"Pixel-CRN: A New Machine Learning Approach for Convective Storm Nowcasting","authors":["Wei Zhang","Haonan Chen","Lei Han","Rui Zhang","Yurong Ge"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3267976","openalex":"W4366147359"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3267976"},"orgs":["colorado-state-university"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","era5"],"status":"research","summary":"Pixel-CRN nowcasts convective storms 30 and 60 min ahead from 3-D radar and reanalysis, and works with only a small training dataset.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3267840","title":"Hypothetical Ground Radar-Like Rain Rate Generation of Geostationary Weather Satellite Using Data-to-Data Translation","authors":["Yeonjun Kim","Sungwook Hong"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3267840","openalex":"W4366150263"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3267840"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Adversarial data-to-data translation converts geostationary satellite albedo and brightness temperature into radar-like rainfall over Korea, outperforming GK2A, PERSIANN-CCS and IMERG products.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3264545","title":"MM-RNN: A Multimodal RNN for Precipitation Nowcasting","authors":["Zhifeng Ma","Hao Zhang","Jie Liu"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3264545","openalex":"W4362653028"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3264545"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","other"],"status":"research","summary":"MM-RNN adds meteorological element guidance to RNN nowcasters, raising CSI at R≥10 by 23.4% over MS-MotionRNN on MeteoNet.","significance":3,"cited_by":88,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2023.3246019","title":"A Bagged-Tree Machine Learning Model for High and Low Wind Speed Ocean Wind Retrieval From CYGNSS Measurements","authors":["Pin‐Hsuan Cheng","Chien‐Hung Lin","Y. Jade Morton","Shu‐Chih Yang","Jann‐Yenq Liu"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2023.3246019","openalex":"W4321021527"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3246019"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Bagged-tree ensembles retrieve ocean wind speed from CYGNSS GNSS-R, reducing RMSE by about 29% and 65% versus the Level 2 product, including typhoon cases.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2023.3307717","title":"A Deep Learning Method Integrating Multisource Data for ECMWF Forecasting Products Correction","authors":["Jingming Xia","Qiao Liu","Ling Tan"],"date":"2023-01-01","year":2023,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2023.3307717","openalex":"W4386088303"},"links":{"paper":"https://doi.org/10.1109/lgrs.2023.3307717"},"orgs":["nuist"],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","satellite","era5"],"status":"research","summary":"NFC-Net fuses FY-4A satellite, DEM and ERA5 data with a UNet to correct ECMWF forecasts, cutting 2m temperature and 10m wind speed RMSE by about 50%.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3325783","title":"LSDSSIMR: Large-Scale Dust Storm Database Based on Satellite Images and Meteorological Reanalysis Data","authors":["Cong Bai","Zhipeng Cai","Xiaomei Yin","Jinglin Zhang"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3325783","openalex":"W4387757459"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3325783","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10287393.pdf"},"orgs":[],"topic":"benchmarks-data-eval","topics":["extremes-hazards"],"type":"benchmark","method":[],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Releases LSDSSIMR, a 2020–2022 dataset of FY-4A satellite dust images at 15-minute, 4 km resolution, paired with reanalysis for dust storm prediction.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3310361","title":"A Heterogeneous Spatiotemporal Attention Fusion Prediction Network for Precipitation Nowcasting","authors":["Dan Niu","Hongshu Che","Chunlei Shi","Zengliang Zang","Hongbin Wang","Xunlai Chen","Qunbo Huang"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3310361","openalex":"W4386275821"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3310361","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10234590.pdf"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"HST-AFP fuses radar echoes with NWP data via attention-based multi-encoder and fusion decoder, outperforming RNN and U-Net nowcasting baselines in South China.","significance":3,"cited_by":17,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3299459","title":"Downscaling the Midsummer Temperature-Humidity Index Based on Multiple Machine Learning Methods","authors":["D. L. Wu","Zhenhai Yao","Linlin Wu","Xichang Luo","Shuai Sun","Binfang He","Yali Zhang"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3299459","openalex":"W4385325569"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3299459","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9973430/10195986.pdf"},"orgs":["cma"],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other","stations"],"status":"research","summary":"Random Forest downscales the summer temperature-humidity index from 6 km to 1 km over Anhui, achieving correlations above 0.97 with site observations.","significance":2,"cited_by":3,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3278381","title":"A Combined Model to Predict GNSS Precipitable Water Vapor Based on Deep Learning","authors":["Ming Shangguan","Meng Dang","Yingchun Yue","Rong Zou"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3278381","openalex":"W4377232612"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3278381","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9973430/10130370.pdf"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"Wavelet-LSTM-ARIMA hybrid predicts GNSS precipitable water vapour, cutting RMSE by about 55% versus other models over 3 h horizons.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3277842","title":"TCCL-DenseFuse: Infrared and Water Vapor Satellite Image Fusion Model Using Deep Learning","authors":["Changjiang Zhang","Jia-Xu Guo","Leiming Ma","Xiaoqin Lu","Wen-Cai Liu"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3277842","openalex":"W4379180595"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3277842","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9973430/10129798.pdf"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"DenseNet-based fusion of infrared and water vapor satellite images, with a tropical-cyclone-specific loss, improves TC center location accuracy.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3273232","title":"DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images","authors":["Wenjun Jiang","Gang Hu","Tiantian Wu","Lingbo Liu","Bubryur Kim","Yiqing Xiao","Zhongdong Duan"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3273232","openalex":"W4381795066"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3273232","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9973430/10121612.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn","other"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Attention network with Kalman filter estimates tropical cyclone intensity from multispectral infrared images, cutting RMSE from 9.79 to 7.82 knots.","significance":3,"cited_by":31,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3262557","title":"Toward a Deep-Learning-Network-Based Convective Weather Initiation Algorithm From the Joint Observations of Fengyun-4A Geostationary Satellite and Radar for 0–1h Nowcasting","authors":["Fenglin Sun","Bo Li","Min Min","Danyu Qin"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3262557","openalex":"W4361766701"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3262557","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10083166.pdf"},"orgs":["cma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"CWNNet, a ConvRNN fusing Fengyun-4A satellite and radar inputs, predicts 0-1 h reflectivity and convective initiation, outperforming single-source models (POD 0.87 at 1 h).","significance":3,"cited_by":20,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3239109","title":"Statistical Downscaling of Temperature Distributions in Southwest China by Using Terrain-Guided Attention Network","authors":["Guangyu Liu","Rui Zhang","Renlong Hang","Lingling Ge","Chunxiang Shi","Qingshan Liu"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3239109","openalex":"W4317795290"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3239109","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9973430/10024787.pdf"},"orgs":["nuist","cma"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Terrain-guided attention CNN downscales 2 m air temperature from 0.0625° to 0.01° over Southwest China, reaching 1.12 °C RMSE using DEM attention blocks.","significance":3,"cited_by":23,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2023.3238016","title":"Advection-Free Convolutional Neural Network for Convective Rainfall Nowcasting","authors":["Jenna Ritvanen","Bent Harnist","Miguel Aldana","Terhi Mäkinen","Seppo Pulkkinen"],"date":"2023-01-01","year":2023,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2023.3238016","openalex":"W4317437760"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3238016","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9973430/10021317.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Lagrangian CNN models rainfall growth and decay from advected radar differences, improving heavy-rain nowcast POD over RainNet and LINDA on Finnish radar.","significance":3,"cited_by":41,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2023.3337998","title":"Sub-Seasonal Precipitation Bias-Correction in Thailand Using Attention U-Net With Seasonal and Meteorological Effects","authors":["Tanatorn Faijaroenmongkol","Kanoksri Sarinnapakorn","Peerapon Vateekul"],"date":"2023-01-01","year":2023,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2023.3337998","openalex":"W4389164251"},"links":{"paper":"https://doi.org/10.1109/access.2023.3337998","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10335653.pdf"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Attention U-Net with multi-scale residual blocks bias-corrects CFSv2 sub-seasonal rainfall over Thailand, improving RMSE by 8.65% over linear downscaling.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2023.3309054","title":"Machine Learning Approaches to Improve North American Precipitation Forecasts","authors":["Cenker Sengoz","Sheela Ramanna","Scott D. Kehler","Rushil Goomer","Paul Pries"],"date":"2023-01-01","year":2023,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2023.3309054","openalex":"W4386233852"},"links":{"paper":"https://doi.org/10.1109/access.2023.3309054","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10231339.pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Neural networks ensembling eight North American NWP precipitation models cut MAE 17% and false alarm ratio 41% versus the mean baseline.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2023.3297200","title":"Optimizing Numerical Weather Prediction Model Performance Using Machine Learning Techniques","authors":["S. Choi","Eun-Sung Jung"],"date":"2023-01-01","year":2023,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2023.3297200","openalex":"W4385062322"},"links":{"paper":"https://doi.org/10.1109/access.2023.3297200","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10188815.pdf"},"orgs":[],"topic":"infra-software","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning tunes hardware and software parameters to reduce the I/O and runtime cost of the Low GloSea6 weather model.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2023.3280932","title":"A Forecast-Refinement Neural Network Based on DyConvGRU and U-Net for Radar Echo Extrapolation","authors":["Jinliang Yao","Feifan Xu","Zheng Ming Qian","Zhipeng Cai"],"date":"2023-01-01","year":2023,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2023.3280932","openalex":"W4378714713"},"links":{"paper":"https://doi.org/10.1109/access.2023.3280932","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10138400.pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","cnn","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A DyConvGRU and U-Net forecast-refinement network with WGAN training improves high-reflectivity radar echo extrapolation over Shanghai, raising POD and CSI.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2023.3243252","title":"Solar Radiation Forecasting Based on the Hybrid CNN-CatBoost Model","authors":["Hyojeoung Kim","Sujin Park","Hee-Jun Park","Heung-Gu Son","Sahm Kim"],"date":"2023-01-01","year":2023,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2023.3243252","openalex":"W4319459177"},"links":{"paper":"https://doi.org/10.1109/access.2023.3243252","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10040681.pdf"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid CNN-CatBoost predicts solar radiation at 18 Korean locations from weather variables, and adding wind and precipitation improves results at 15 of them.","significance":3,"cited_by":68,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-5.0123759","title":"Short-term wind power prediction based on the combination of numerical weather forecast and time series","authors":["Liang Zeng","Xin Lan","Shanshan Wang"],"date":"2023-01-01","year":2023,"venue":"Journal of Renewable and Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1063/5.0123759","openalex":"W4313682926"},"links":{"paper":"https://doi.org/10.1063/5.0123759"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["rnn","classical-ml","reinforcement-learning"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Hybrid GWO-WNN, VMD-LSTM and Q-learning model combines NWP forecasts with wind power series to improve short-term wind power prediction accuracy.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022wr032789","title":"Effects of Automatic Hyperparameter Tuning on the Performance of Multi‐Variate Deep Learning‐Based Rainfall Nowcasting","authors":["Amirmasoud Amini","Mehri Dolatshahi","Reza Kerachian"],"date":"2023-01-01","year":2023,"venue":"Water Resources Research","venue_type":"journal","ids":{"doi":"10.1029/2022wr032789","openalex":"W4315490959"},"links":{"paper":"https://doi.org/10.1029/2022wr032789","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022WR032789"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn","classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Ensembles of CNN and LSTM networks with automatic hyperparameter tuning improve multi-step rainfall nowcasting by 10-25% over univariate models in Tehran.","significance":2,"cited_by":30,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003034","title":"Deep Learning Parameterization of the Tropical Cyclone Boundary Layer","authors":["Le‐Yi Wang","Zhe‐Min Tan"],"date":"2023-01-01","year":2023,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003034","openalex":"W4313537378"},"links":{"paper":"https://doi.org/10.1029/2022ms003034","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003034"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"DeepBL, a small 1D convolutional tropical cyclone boundary-layer parameterization trained on LES, outperforms the WRF YSU scheme in predicting turbulent fluxes.","significance":4,"cited_by":25,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2023.7","title":"Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts","authors":["Elizabeth A. Barnes","Randal J. Barnes","Mark DeMaria"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2023.7","openalex":"W4380987700"},"links":{"paper":"https://doi.org/10.1017/eds.2023.7","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/88BFA8863A396DBBF36AF64F24C31A64/S2634460223000079a.pdf/div-class-title-sinh-arcsinh-normal-distributions-to-add-uncertainty-to-neural-network-regression-tasks-applications-to-tropical-cyclone-intensity-forecasts-div.pdf"},"orgs":["colorado-state-university"],"topic":"probabilistic-ensembles","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Sinh-arcsinh-normal output distributions give neural networks asymmetric, heteroscedastic uncertainty, demonstrated on tropical cyclone intensity forecast errors.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2023.5","title":"A climate index collection based on model data","authors":["Marco Landt-Hayen","Willi Rath","Sebastian Wahl","Nils Niebaum","Martin Claus","Peer Kröger"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2023.5","openalex":"W4367723937"},"links":{"paper":"https://doi.org/10.1017/eds.2023.5","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/4282613A3EAE5DE9D4D7D67D6C0C81EC/S2634460223000055a.pdf/div-class-title-a-climate-index-collection-based-on-model-data-div.pdf"},"orgs":[],"topic":"benchmarks-data-eval","topics":["climate-analysis-attribution"],"type":"benchmark","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Open dataset of climate indices from 1000-year Earth system model control runs, with ML benchmarks predicting Sahel rainfall and ENSO.","significance":4,"cited_by":2,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2023.36","title":"Machine learning and feature selection: Applications in economics and climate change","authors":["Berkay Akyapı"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2023.36","openalex":"W4389819320"},"links":{"paper":"https://doi.org/10.1017/eds.2023.36","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/4B729313EA2D42759A9C8E8A5C099D30/S2634460223000365a.pdf/div-class-title-machine-learning-and-feature-selection-applications-in-economics-and-climate-change-div.pdf"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Reviews feature selection methods such as LASSO and causal selection for climate-economy studies, and applies them to find an optimal heatwave definition for economic outcomes.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2023.23","title":"Identifying climate models based on their daily output using machine learning","authors":["Lukas Brunner","Sebastian Sippel"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2023.23","openalex":"W4382996746"},"links":{"paper":"https://doi.org/10.1017/eds.2023.23","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/0D2453720761810E4382709E0BEC62CE/S2634460223000237a.pdf/div-class-title-identifying-climate-models-based-on-their-daily-output-using-machine-learning-div.pdf"},"orgs":["eth-zurich"],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"evaluation","method":["other"],"timescale":[],"spatial":["global"],"data":["cmip","km-scale-sim","other"],"status":"research","summary":"Machine learning classifiers identify individual days of CMIP6 and ICON-Sapphire output versus observations, showing model differences appear at daily timescales.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2023.18","title":"A precipitation downscaling method using a super-resolution deconvolution neural network with step orography","authors":["P. Jyoteeshkumar Reddy","Richard J. Matear","John Taylor","Marcus Thatcher","Michael Grose"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2023.18","openalex":"W4382771631"},"links":{"paper":"https://doi.org/10.1017/eds.2023.18","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/8C067A59AC3775C661BFAC75D1C2A47B/S2634460223000183a.pdf/div-class-title-a-precipitation-downscaling-method-using-a-super-resolution-deconvolution-neural-network-with-step-orography-div.pdf"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Super-resolution deconvolution network with orography downscales hourly precipitation from 100 to 12.5 km over Australia, improving fine-scale extremes over DeepSD.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2023.16","title":"Short-term forecasting of typhoon rainfall with a deep-learning-based disaster monitoring model","authors":["Doyi Kim","Yeji Choi","Minseok Seo","Seungheon Shin","Hyun-Jin Jeong"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2023.16","openalex":"W4385061583"},"links":{"paper":"https://doi.org/10.1017/eds.2023.16","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/C3D6DEF55802A01CCA8E713CBC26A29E/S263446022300016Xa.pdf/div-class-title-short-term-forecasting-of-typhoon-rainfall-with-a-deep-learning-based-disaster-monitoring-model-div.pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Two-stage deep learning predicts typhoon satellite images and converts them to rainfall maps, reaching correlation 0.81 at 3 hours ahead.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2023.15","title":"Neural style transfer between observed and simulated cloud images to improve the detection performance of tropical cyclone precursors","authors":["Daisuke Matsuoka","Steve Easterbrook"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2023.15","openalex":"W4383040563"},"links":{"paper":"https://doi.org/10.1017/eds.2023.15","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/4B8325E936D96BDF514DE7B38CC6A9BA/S2634460223000158a.pdf/div-class-title-neural-style-transfer-between-observed-and-simulated-cloud-images-to-improve-the-detection-performance-of-tropical-cyclone-precursors-div.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","km-scale-sim"],"status":"research","summary":"Neural style transfer makes simulated cloud images resemble satellite data, raising tropical cyclone precursor classification performance by 40–90% at 3–7 days lead.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4422","title":"Machine learning and dynamics based error‐index method for the detection of monsoon onset vortex over the Arabian Sea: Climatology and composite structures","authors":["Talukdar Sasanka","Krishna Kishore Osuri","Dev Niyogi"],"date":"2023-01-01","year":2023,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4422","openalex":"W4313480355"},"links":{"paper":"https://doi.org/10.1002/qj.4422"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Hybrid error-index and machine-learning method detects Arabian Sea monsoon onset vortices in ERA5, recovering all 27 observed vortices with 5 false positives.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2307.10422","title":"PreDiff: Precipitation Nowcasting with Latent Diffusion Models","authors":["Zhihan Gao","Xingjian Shi","Boran Han","Hao Wang","Xiaoyong Jin","Danielle Maddix","Yi Zhu","Mu Li","Yuyang Wang"],"date":"2023-01-01","year":2023,"venue":"Advances in Neural Information Processing Systems 36","venue_type":"preprint","ids":{"arxiv":"2307.10422","doi":"10.52202/075280-3439"},"links":{"paper":"https://arxiv.org/abs/2307.10422","pdf":"https://arxiv.org/pdf/2307.10422"},"orgs":[],"topic":"nowcasting","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion","physics-constrained"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"PreDiff is a latent diffusion precipitation nowcasting model with a physics-based knowledge alignment step that enforces domain constraints on SEVIR radar forecasts.","significance":4,"cited_by":55,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2307.01909","title":"ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling","authors":["Tung Nguyen","Jason Jewik","Hritik Bansal","Prakhar Sharma","Aditya Grover"],"date":"2023-01-01","year":2023,"venue":"Advances in Neural Information Processing Systems 36","venue_type":"preprint","ids":{"arxiv":"2307.01909","doi":"10.52202/075280-3279","openalex":"W7133237462"},"links":{"paper":"https://arxiv.org/abs/2307.01909","pdf":"https://arxiv.org/pdf/2307.01909","code":"https://github.com/aditya-grover/climate-learn"},"orgs":[],"topic":"benchmarks-data-eval","topics":[],"type":"benchmark","method":["transformer","cnn"],"timescale":["medium","climate"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"Open-source PyTorch library standardizing ERA5 and CMIP6 pipelines, deep models and evaluation for ML weather forecasting and climate downscaling.","significance":5,"cited_by":16,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2306.10574","title":"Score-based Data Assimilation","authors":["François Rozet","Gilles Louppe"],"date":"2023-01-01","year":2023,"venue":"Advances in Neural Information Processing Systems 36","venue_type":"preprint","ids":{"arxiv":"2306.10574","doi":"10.52202/075280-1763","openalex":"W7133203373"},"links":{"paper":"https://arxiv.org/abs/2306.10574","pdf":"https://arxiv.org/pdf/2306.10574"},"orgs":[],"topic":"data-assimilation","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Score-based data assimilation learns a generative prior over state trajectories and applies observations only at inference, enabling zero-shot observation scenarios for long dynamical-system trajectories.","significance":5,"cited_by":28,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2306.08754","title":"ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation","authors":["Sungduk Yu","Walter Hannah","Liran Peng","Jerry Lin","Mohamed Aziz Bhouri","Ritwik Gupta","Björn Lütjens","Justus C. Will","Gunnar Behrens","Julius Busecke","Nora Loose","Charles Stern","Tom Beucler","Bryce Harrop","Benjamin Hillman","Andrea Jenney","Savannah L. Ferretti","Nana Liu","Animashree Anandkumar","Noah Brenowitz","Veronika Eyring","Nicholas Geneva","Pierre Gentine","Stephan Mandt","Jaideep Pathak","Akshay Subramaniam","Carl Vondrick","Rose Yu","Laure Zanna","Tian Zheng","Ryan Abernathey","Fiaz Ahmed","David Bader","Pierre Baldi","Elizabeth Barnes","Christopher Bretherton","Peter Caldwell","Wayne Chuang","Yilun Han","Yu Huang","Fernando Iglesias-Suarez","Sanket Jantre","Karthik Kashinath","Marat Khairoutdinov","Thorsten Kurth","Nicholas Lutsko","Po-Lun Ma","Griffin Mooers","J. David Neelin","David Randall"],"date":"2023-01-01","year":2023,"venue":"Advances in Neural Information Processing Systems 36","venue_type":"preprint","ids":{"arxiv":"2306.08754","doi":"10.52202/075280-0968","openalex":"W7133212227"},"links":{"paper":"https://arxiv.org/abs/2306.08754","pdf":"https://arxiv.org/pdf/2306.08754","code":"https://github.com/leap-stc/climsim-online"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"benchmark","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"ClimSim-Online releases a 5.7-billion-sample multiscale dataset plus a containerized workflow for integrating ML emulators into a host climate model for hybrid ML-physics testing.","significance":6,"cited_by":20,"score":34,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2305.15618","title":"Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models","authors":["Zhong Yi Wan","Ricardo Baptista","Yi-fan Chen","John Anderson","Anudhyan Boral","Fei Sha","Leonardo Zepeda-Núñez"],"date":"2023-01-01","year":2023,"venue":"Advances in Neural Information Processing Systems 36","venue_type":"preprint","ids":{"arxiv":"2305.15618","doi":"10.52202/075280-2069","openalex":"W7133220996"},"links":{"paper":"https://arxiv.org/abs/2305.15618","pdf":"https://arxiv.org/pdf/2305.15618","code":"https://github.com/google-research/swirl-dynamics"},"orgs":[],"topic":"downscaling","topics":["probabilistic-ensembles"],"type":"model","method":["diffusion","other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A two-stage statistical downscaling method combines optimal-transport debiasing with diffusion upsampling, enabling unpaired 8x and 16x super-resolution on fluid flows relevant to weather and climate.","significance":4,"cited_by":13,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2305.02090","title":"Understanding cirrus clouds using explainable machine learning","authors":["Kai Jeggle","David Neubauer","Gustau Camps‐Valls","Ulrike Lohmann"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2305.02090","doi":"10.1017/eds.2023.14","openalex":"W4383040977"},"links":{"paper":"https://doi.org/10.1017/eds.2023.14","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A2466D7AC4C80DEE3406879B2FA73249/S2634460223000146a.pdf/div-class-title-understanding-cirrus-clouds-using-explainable-machine-learning-div.pdf"},"orgs":["eth-zurich"],"topic":"xai-uq-physics","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml","rnn"],"timescale":[],"spatial":[],"data":["satellite","era5"],"status":"research","summary":"Gradient boosting and attention-LSTM models predict cirrus ice water content and crystal number (R² = 0.49), with SHAP attributions linking dust aerosols to ice crystal changes.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.14131","title":"TempEE: Temporal–Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Autoregression","authors":["Shengchao Chen","Ting Shu","Huan Qi Zhao","Guo Zhong","Xunlai Chen"],"date":"2023-01-01","year":2023,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2304.14131","doi":"10.1109/tgrs.2023.3311510","openalex":"W4386432115"},"links":{"paper":"https://doi.org/10.1109/tgrs.2023.3311510","pdf":"https://arxiv.org/pdf/2304.14131"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"TempEE uses a parallel spatio-temporal transformer with one-step forecasting instead of autoregression to avoid error accumulation in radar echo extrapolation.","significance":4,"cited_by":30,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.05294","title":"Selecting robust features for machine-learning applications using multidata causal discovery","authors":["S. Saranya Ganesh","Tom Beucler","Frederick Iat‐Hin Tam","Milton S. Gomez","Jakob Runge","Andreas Gerhardus"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2304.05294","doi":"10.1017/eds.2023.21","openalex":"W4383567618"},"links":{"paper":"https://doi.org/10.1017/eds.2023.21","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/29C08A0FF7BFD2347768F315E041A143/S2634460223000213a.pdf/div-class-title-selecting-robust-features-for-machine-learning-applications-using-multidata-causal-discovery-div.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"PCMCI-based multidata causal discovery selects drivers for Western Pacific tropical cyclone intensity prediction, outperforming noncausal and correlation-based feature selection.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2304.03127","title":"Statistical constraints on climate model parameters using a scalable cloud-based inference framework","authors":["James Carzon","Bruno Ricardi de Abreu","Leighton A. Regayre","K. S. Carslaw","Lucia Timea Deaconu","Philip Stier","Hamish Gordon","Mikael Kuusela"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2304.03127","doi":"10.1017/eds.2023.12","openalex":"W4383268176"},"links":{"paper":"https://doi.org/10.1017/eds.2023.12","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/4E406C69C234B7C5B0E40FC699F29F39/S2634460223000122a.pdf/div-class-title-statistical-constraints-on-climate-model-parameters-using-a-scalable-cloud-based-inference-framework-div.pdf"},"orgs":["met-office","university-of-oxford"],"topic":"climate-analysis-attribution","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["cmip","satellite"],"status":"research","summary":"Surrogate-based statistical framework constrains UKESM1 aerosol parameters against MODIS observations on a cloud platform, using 3-hourly outputs for tighter constraints.","significance":3,"cited_by":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2302.10480","title":"Climate model-driven seasonal forecasting approach with deep learning","authors":["Alper Ünal","Busra Asan","İsmail Sezen","Bugra Yesilkaynak","Yusuf Alizade Govarchin Ghale","Mehmet Ilıcak A","Gözde Ünal"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2302.10480","doi":"10.1017/eds.2023.24","openalex":"W4385278976"},"links":{"paper":"https://doi.org/10.1017/eds.2023.24","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/3046D1C9903ABF0AB49DCEA473DB5E32/S2634460223000249a.pdf/div-class-title-climate-model-driven-seasonal-forecasting-approach-with-deep-learning-div.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"CNN segmentation models (UNet++, ResNet, PSPNet, DeepLabv3) trained on CMIP6 and fine-tuned on ERA5 forecast global temperature a month ahead, with MAE of 0.7.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.13462","title":"Towards Learned Emulation of Interannual Water Isotopologue Variations in General Circulation Models","authors":["Jonathan Wider","Jakob Kruse","Nils Weitzel","Janica C. Bühler","Ullrich Köthe","Kira Rehfeld"],"date":"2023-01-01","year":2023,"venue":"Environmental Data Science, Volume 2 (2023), e35","venue_type":"journal","ids":{"arxiv":"2301.13462","doi":"10.1017/eds.2023.29","openalex":"W4387349254"},"links":{"paper":"https://arxiv.org/abs/2301.13462","pdf":"https://arxiv.org/pdf/2301.13462"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"UNet-based CNNs emulate interannual oxygen isotope composition of precipitation from temperature and precipitation fields, explaining about 40% of temporal variance in a last-millennium run.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15010241","title":"Whitecap Fraction Parameterization and Understanding with Deep Neural Network","authors":["Shuyi Zhou","Fanghua Xu","Ruizi Shi"],"date":"2022-12-31","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15010241","openalex":"W4313471290"},"links":{"paper":"https://doi.org/10.3390/rs15010241","pdf":"https://www.mdpi.com/2072-4292/15/1/241/pdf?version=1672904571"},"orgs":["tsinghua-university"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep neural network whitecap-fraction parameterization for Earth system models reduces error by about 15% versus a recent scheme and ranks drivers by permutation importance.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.167252578.88217202-v1","title":"Quantifying Feedback Sensitivities of Permafrost Degradation and Carbon Release with Earth Observation Data and Feedback Neural Networks","authors":["Bradley A. Gay","Amanda Armstrong","Neal J. Pastick","Hélène Genet","Jennifer D. Watts"],"date":"2022-12-31","year":2022,"venue_type":"other","ids":{"doi":"10.22541/essoar.167252578.88217202/v1","openalex":"W4313393504"},"links":{"paper":"https://doi.org/10.22541/essoar.167252578.88217202/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.167252578.88217202"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["rnn","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"GeoCryoAI, a hybrid CNN-LSTM ensemble, models permafrost degradation and soil carbon feedbacks in Alaska, aiming to fill a gap in Earth system models.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-17538947.2022.2152886","title":"An improvement of snow/cloud discrimination from machine learning using geostationary satellite data","authors":["Donghyun Jin","Kyeong-Sang Lee","Sungwon Choi","Noh-Hun Seong","Daeseong Jung","Suyoung Sim","Jongho Woo","Uujin Jeon","Yugyeong Byeon","Kyung‐Soo Han"],"date":"2022-12-31","year":2022,"venue":"International Journal of Digital Earth","venue_type":"journal","ids":{"doi":"10.1080/17538947.2022.2152886","openalex":"W4313455977"},"links":{"paper":"https://doi.org/10.1080/17538947.2022.2152886","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/17538947.2022.2152886?needAccess=true&role=button"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml","transformer"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random forest and deep neural network reclassify snow versus cloud in GK-2A geostationary imagery, raising F1-score from 73% to about 77-78% against ground truth.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.01214","title":"Comparison of tree-based ensemble algorithms for merging satellite and earth-observed precipitation data at the daily time scale","authors":["Georgia Papacharalampous","Hristos Tyralis","Anastasios Doulamis","Nikolaos Doulamis"],"date":"2022-12-31","year":2022,"venue":"Hydrology 10 (2023) 50","venue_type":"journal","ids":{"arxiv":"2301.01214","doi":"10.3390/hydrology10020050"},"links":{"paper":"https://arxiv.org/abs/2301.01214","pdf":"https://arxiv.org/pdf/2301.01214"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Compares random forests, gradient boosting and XGBoost for merging PERSIANN/IMERG satellite rainfall with gauge data over the contiguous US; XGBoost performs best.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-22-0006.1","title":"Postprocessing of Ensemble Weather Forecast Using Decision Tree–Based Probabilistic Forecasting Methods","authors":["Patrik Benáček","Aleš Farda","Petr Štěpánek"],"date":"2022-12-29","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-22-0006.1","openalex":"W4313263148"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0006.1"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares tree-based probabilistic post-processing (NGB, QRF, DRF) with EMOS for 1-10 day ensemble 2 m temperature over the Czech Republic; QRF and NGB lead at short lead times.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.01254","title":"Machine learning prediction of the MJO extends beyond one month","authors":["Tamaki Suematsu","Kengo Nakai","Tsuyoshi Yoneda","Daisuke Takasuka","Takuya Jinno","Yoshitaka Saiki","Hiroaki Miura"],"date":"2022-12-29","year":2022,"venue_type":"preprint","ids":{"arxiv":"2301.01254","openalex":"W4313533607"},"links":{"paper":"https://arxiv.org/abs/2301.01254","pdf":"https://arxiv.org/pdf/2301.01254"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn"],"timescale":["s2s"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"A reservoir computing model forecasts the MJO real-time index for over a month, with the best cases reaching two months, beyond the expected predictability limit.","significance":4,"cited_by":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.14143","title":"Multimodal Wildland Fire Smoke Detection","authors":["Siddhant Baldota","Shreyas Anantha Ramaprasad","Jaspreet Kaur Bhamra","Shane Luna","Ravi Ramachandra","Eugene Zen","Harrison Kim","Daniel Crawl","Ismael Perez","Ilkay Altintas","Garrison W. Cottrell","Mai H. Nguyen"],"date":"2022-12-29","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.14143"},"links":{"paper":"https://arxiv.org/abs/2212.14143","pdf":"https://arxiv.org/pdf/2212.14143"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"SmokeyNet fuses wildland camera imagery with weather sensor data to detect smoke, with a few-minute time-to-detection for early wildfire alerts.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15010142","title":"TSRC: A Deep Learning Model for Precipitation Short-Term Forecasting over China Using Radar Echo Data","authors":["Qiqiao Huang","Sheng Chen","Jinkai Tan"],"date":"2022-12-27","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15010142","openalex":"W4313244318"},"links":{"paper":"https://doi.org/10.3390/rs15010142","pdf":"https://www.mdpi.com/2072-4292/15/1/142/pdf?version=1672129172"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"TSRC, a residual convolutional network using previous-frame cues, improves 3-hour radar-based precipitation nowcasts over China versus optical flow and UNet, including typhoon cases.","significance":3,"cited_by":35,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.167214210.02213149-v1","title":"Deep Learning Regional Climate Model Emulators: a comparison of two downscaling training frameworks","authors":["Marijn van der Meer","Sophie de Roda Husman","Stef Lhermitte"],"date":"2022-12-27","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.22541/essoar.167214210.02213149/v1","openalex":"W4312202294"},"links":{"paper":"https://doi.org/10.1029/2022ms003593","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.167214210.02213149"},"orgs":["eth-zurich"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Deep learning emulator downscales a global climate model to regional Antarctic surface mass balance; the imperfect-model training framework outperforms the perfect-model one.","significance":3,"cited_by":50,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0034.1","title":"Emulating the Adaptation of Wind Fields to Complex Terrain with Deep Learning","authors":["Louis Le Toumelin","Isabelle Gouttevin","Nora Helbig","Clovis Galiez","Mathis Roux","Fatima Karbou"],"date":"2022-12-27","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0034.1","openalex":"W4312213174"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0034.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/1/AIES-D-22-0034.1.pdf"},"orgs":["meteo-france"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","km-scale-sim","stations"],"status":"research","summary":"DEVINE, a CNN trained on ARPS simulations, downscales AROME winds to 30 m over the Alps and cuts the mean wind-speed bias by 27% at 61 stations.","significance":3,"cited_by":31,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15010137","title":"MSSTNet: A Multi-Scale Spatiotemporal Prediction Neural Network for Precipitation Nowcasting","authors":["Yuankang Ye","Feng Gao","Wei Xin Cheng","Chang Liu","Shaoqing Zhang"],"date":"2022-12-26","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15010137","openalex":"W4313259290"},"links":{"paper":"https://doi.org/10.3390/rs15010137","pdf":"https://www.mdpi.com/2072-4292/15/1/137/pdf?version=1672831711"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"MSSTNet uses multi-scale 3D convolutions to predict precipitation nowcasts from radar echoes, achieving state-of-the-art on MovingMNIST and improved real radar accuracy.","significance":3,"cited_by":16,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs15010119","title":"Advanced Machine Learning Methods for Major Hurricane Forecasting","authors":["Javier Martínez-Amaya","Cristina Radin","Verònica Nieves"],"date":"2022-12-26","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs15010119","openalex":"W4313244265"},"links":{"paper":"https://doi.org/10.3390/rs15010119","pdf":"https://www.mdpi.com/2072-4292/15/1/119/pdf?version=1672046541"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Decision-tree framework using GOES cloud-structure parameters predicts major hurricane intensification with 73% accuracy 6 to 54 hours ahead.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s23010210","title":"Early Stage Forest Fire Detection from Himawari-8 AHI Images Using a Modified MOD14 Algorithm Combined with Machine Learning","authors":["Naoto Maeda","Hideyuki Tonooka"],"date":"2022-12-25","year":2022,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s23010210","openalex":"W4313244202"},"links":{"paper":"https://doi.org/10.3390/s23010210","pdf":"https://www.mdpi.com/1424-8220/23/1/210/pdf?version=1671958815"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A random forest on a modified MOD14 scheme with Himawari-8 AHI data detects early-stage forest fires in Australia at about 90% precision and recall.","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.22775530","title":"Machine Learning Downscaling of Regional Precipitation Patterns in Mountainous Terrain","authors":["Eszter Jonsdottir","Andrew Charles Meltzer","Joao Bakker"],"date":"2022-12-24","year":2022,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.22775530","openalex":"W7213343672"},"links":{"paper":"https://doi.org/10.5281/zenodo.22775530"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional","local"],"data":["cmip","stations","radar"],"status":"research","summary":"CNN downscales 25 km regional climate precipitation to 1 km in mountain terrain, cutting RMSE 34% versus raw output and 12% versus quantile mapping.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.12794","title":"GraphCast: Learning skillful medium-range global weather forecasting","authors":["Remi Lam","Alvaro Sanchez-Gonzalez","Matthew Willson","Peter Wirnsberger","Meire Fortunato","Ferran Alet","Suman Ravuri","Timo Ewalds","Zach Eaton-Rosen","Weihua Hu","Alexander Merose","Stephan Hoyer","George Holland","Oriol Vinyals","Jacklynn Stott","Alexander Pritzel","Shakir Mohamed","Peter Battaglia"],"date":"2022-12-24","year":2022,"venue":"Science","venue_type":"journal","ids":{"arxiv":"2212.12794","doi":"10.1126/science.adi2336","openalex":"W4388654737"},"links":{"paper":"https://arxiv.org/abs/2212.12794","pdf":"https://arxiv.org/pdf/2212.12794","code":"https://github.com/deepmind/graphcast"},"orgs":["google-deepmind","google-research"],"topic":"global-medium-range","topics":[],"type":"model","method":["gnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"GraphCast, a graph neural network trained on ERA5, makes 10-day global forecasts at 0.25 degrees in under a minute, beating operational systems on 90% of targets.","significance":10,"cited_by":1472,"score":100,"highlight":true,"highlight_reason":"GraphCast in Science: landmark ML model beating IFS HRES on 90% of targets, setting a new state of the art and driving operational adoption.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos14010025","title":"CSIP-Net: Convolutional Satellite Image Prediction Network for Meteorological Satellite Infrared Observation Imaging","authors":["Yuhang Jiang","Wei Xin Cheng","Feng Gao","Shaoqing Zhang","Chang Liu","Jingzhe Sun"],"date":"2022-12-23","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos14010025","openalex":"W4313246010"},"links":{"paper":"https://doi.org/10.3390/atmos14010025","pdf":"https://www.mdpi.com/2073-4433/14/1/25/pdf?version=1673255399"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"CSIP-Net, a convolutional network that predicts FY-4A infrared satellite images, reaching 4.77 K mean error at 2 h and 0.855 accuracy for precipitation-area detection.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3233-jifs-223183","title":"Application of deep learning to multivariate aviation weather forecasting by long short-term memory","authors":["Chuen-Jyh Chen","Chieh-Ni Huang","S. M. Yang"],"date":"2022-12-23","year":2022,"venue":"Journal of Intelligent & Fuzzy Systems","venue_type":"journal","ids":{"doi":"10.3233/jifs-223183","openalex":"W4312181817"},"links":{"paper":"https://doi.org/10.3233/jifs-223183"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An LSTM with regression-based feature selection forecasts daily temperature from station variables for aviation safety, cutting RMSE from 4.03 to 2.22.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.12573","title":"Combining Stochastic Parameterized Reduced-Order Models with Machine Learning for Data Assimilation and Uncertainty Quantification with Partial Observations","authors":["Changhong Mou","Leslie M. Smith","Nan Chen"],"date":"2022-12-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.12573"},"links":{"paper":"https://arxiv.org/abs/2212.12573","pdf":"https://arxiv.org/pdf/2212.12573"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Hybrid data assimilation pairs a stochastic reduced-order model with a learned nonlinear map to recover unobserved states in a precipitating quasi-geostrophic model. Idealized atmosphere testbed.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wst.2022.425","title":"Monthly precipitation prediction in Luoyang city based on EEMD-LSTM-ARIMA model","authors":["Jiwei Zhao","Guangzheng Nie","Yihao Wen"],"date":"2022-12-22","year":2022,"venue":"Water Science & Technology","venue_type":"journal","ids":{"doi":"10.2166/wst.2022.425","openalex":"W4312189194"},"links":{"paper":"https://doi.org/10.2166/wst.2022.425","pdf":"https://iwaponline.com/wst/article-pdf/87/1/318/1161334/wst087010318.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"EEMD-LSTM-ARIMA coupled model forecasts monthly precipitation in Luoyang by modelling high- and low-frequency components separately, outperforming single and combined baselines.","significance":2,"cited_by":38,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2022.100324","title":"3D DBSCAN detection and parameter sensitivity of the 2022 Yangtze river summertime heatwave and drought","authors":["Zhenchen Liu","Wen Zhou","Yuan Yuan"],"date":"2022-12-22","year":2022,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2022.100324","openalex":"W4312160353"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2022.100324"},"orgs":["fudan-university","cma"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A 3D DBSCAN clustering workflow detects the 2022 Yangtze heatwave and drought from ERA5 and tests how clustering parameters change event tracking.","significance":3,"cited_by":37,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.14160","title":"A Deep Learning Method for Real-time Bias Correction of Wind Field Forecasts in the Western North Pacific","authors":["Wei Zhang","Yueyue Jiang","Junyu Dong","Xiaojiang Song","Renbo Pang","Boyu Guoan","Hui Yu"],"date":"2022-12-22","year":2022,"venue":"Atmospheric Research, Volume 284, 15 March, 2023","venue_type":"journal","ids":{"arxiv":"2212.14160","doi":"10.1016/j.atmosres.2022.106586","openalex":"W4313399947"},"links":{"paper":"https://arxiv.org/abs/2212.14160","pdf":"https://arxiv.org/pdf/2212.14160"},"orgs":[],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["rnn"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"pre-operational","summary":"A multi-task double-encoder TrajGRU corrects ECMWF 10-day wind forecasts over the western North Pacific in real time, cutting speed and direction biases by 8-11% and 9-14%.","significance":3,"cited_by":44,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-hydro.2022.099","title":"Low complexity single-layer neural network for enhanced rainfall estimation using microwave links","authors":["Ali Daher","Hassan Al-Sakka","Khaled Chaaban"],"date":"2022-12-21","year":2022,"venue":"Journal of Hydroinformatics","venue_type":"journal","ids":{"doi":"10.2166/hydro.2022.099","openalex":"W4313468545"},"links":{"paper":"https://doi.org/10.2166/hydro.2022.099"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"A single-layer perceptron on commercial microwave-link attenuation cuts rainfall-rate test MSE from 0.2 to 0.1 mm² h⁻¹, beating the ITU R-k method.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.10735","title":"NADBenchmarks -- a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasters","authors":["Adiba Mahbub Proma","Md Saiful Islam","Stela Ciko","Raiyan Abdul Baten","Ehsan Hoque"],"date":"2022-12-21","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.10735"},"links":{"paper":"https://arxiv.org/abs/2212.10735","pdf":"https://arxiv.org/pdf/2212.10735"},"orgs":[],"topic":"benchmarks-data-eval","topics":["extremes-hazards"],"type":"benchmark","method":[],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Compiles and proposes a searchable web platform of ML benchmark datasets for natural disasters, organized by disaster management cycle. Mostly a catalogue, low novelty.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-cp-18-2643-2022","title":"Evaluation of statistical climate reconstruction methods based on pseudoproxy experiments using linear and machine-learning methods","authors":["Zeguo Zhang","Sebastian Wagner","Marlene Klockmann","Eduardo Zorita"],"date":"2022-12-20","year":2022,"venue":"Climate of the past","venue_type":"journal","ids":{"doi":"10.5194/cp-18-2643-2022","openalex":"W4313447233"},"links":{"paper":"https://doi.org/10.5194/cp-18-2643-2022","pdf":"https://cp.copernicus.org/articles/18/2643/2022/cp-18-2643-2022.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"evaluation","method":["rnn"],"timescale":[],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Pseudoproxy tests compare Bi-LSTM with linear PCR and CCA for millennial NH and NAE summer temperature reconstruction; Bi-LSTM is less skilful but captures extreme cooling.","significance":4,"cited_by":22,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2022.3231125","title":"Relative Importance of Radar Variables for Nowcasting Heavy Rainfall: A Machine Learning Approach","authors":["Yi Victor Wang","Seung Hee Kim","Geunsu Lyu","Choeng-Lyong Lee","GyuWon Lee","Ki‐Hong Min","Menas C. Kafatos"],"date":"2022-12-20","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2022.3231125","openalex":"W4313590825"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3231125","pdf":"https://ieeexplore.ieee.org/ielx7/36/10006360/09994767.pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Ranks dual-polarimetric radar variables for predicting heavy rainfall from mesoscale convective systems over Korea and uses them in ML early-warning models.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14246398","title":"Drought Monitoring and Performance Evaluation Based on Machine Learning Fusion of Multi-Source Remote Sensing Drought Factors","authors":["Yangyang Zhao","Jiahua Zhang","Yun Bai","Sha Zhang","Shanshan Yang","Malak Henchiri","Ayalkibet Mekonnen Seka","Lkhagvadorj Nanzad"],"date":"2022-12-19","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14246398","openalex":"W4313408434"},"links":{"paper":"https://doi.org/10.3390/rs14246398","pdf":"https://www.mdpi.com/2072-4292/14/24/6398/pdf?version=1671526048"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Random forest fusing MODIS, GPM and GLDAS factors reproduces the SPEI drought index for Shandong, China, from 2002-2020, outperforming XGBoost and SVM.","significance":2,"cited_by":70,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2022.100322","title":"U-Net: A deep-learning method for improving summer precipitation forecasts in China","authors":["Qimin Deng","Peirong Lu","Shuyun Zhao","Naiming Yuan"],"date":"2022-12-18","year":2022,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2022.100322","openalex":"W4311969322"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2022.100322","pdf":"https://www.sciencedirect.com/science/article/pii/S1674283422002100/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A U-Net corrects CFSv2 one-month-lead summer precipitation forecasts over China, cutting RMSE by about 43-50% on test data while leaving correlation skill largely unchanged.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00024-022-03206-6","title":"A Machine Learning (ML)-Based Approach to Improve Tropical Cyclone Intensity Prediction of NCMRWF Ensemble Prediction System","authors":["Sushant Kumar","Anumeha Dube","Raghavendra Ashrit","Ashis Kumar Mitra"],"date":"2022-12-17","year":2022,"venue":"Pure and Applied Geophysics","venue_type":"journal","ids":{"doi":"10.1007/s00024-022-03206-6","openalex":"W4313352115"},"links":{"paper":"https://doi.org/10.1007/s00024-022-03206-6"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Applies machine learning to improve tropical cyclone intensity forecasts from the NCMRWF ensemble prediction system; abstract not provided, so results are unknown.","significance":2,"cited_by":14,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.01252","title":"Comparison of machine learning algorithms for merging gridded satellite and earth-observed precipitation data","authors":["Georgia Papacharalampous","Hristos Tyralis","Anastasios Doulamis","Nikolaos Doulamis"],"date":"2022-12-17","year":2022,"venue":"Water 15 (2023) 634","venue_type":"journal","ids":{"arxiv":"2301.01252","doi":"10.3390/w15040634"},"links":{"paper":"https://arxiv.org/abs/2301.01252","pdf":"https://arxiv.org/pdf/2301.01252"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Comparison of eight machine learning algorithms correcting PERSIANN satellite precipitation against GHCN gauges over CONUS finds XGBoost and random forests most accurate.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14246367","title":"A Method for Retrieving Cloud-Top Height Based on a Machine Learning Model Using the Himawari-8 Combined with Near Infrared Data","authors":["Yan Dong","Xuejin Sun","Qinghui Li"],"date":"2022-12-16","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14246367","openalex":"W4311885914"},"links":{"paper":"https://doi.org/10.3390/rs14246367","pdf":"https://www.mdpi.com/2072-4292/14/24/6367/pdf?version=1671183243"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"XGBoost retrieves cloud-top height from Himawari-8 imagery with RMSE 1.74 km versus CALIPSO and corrects JMA's large biases for ice and multilayer clouds.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-essoar.167117448.86075329-v1","title":"Using Machine Learning with Partial Dependence Analysis to Investigate Land-Atmosphere Coupling","authors":["Jared T. Trok","Frances V. Davenport","Elizabeth A. Barnes","Noah S. Diffenbaugh"],"date":"2022-12-16","year":2022,"venue_type":"other","ids":{"doi":"10.22541/essoar.167117448.86075329/v1","openalex":"W4311726315"},"links":{"paper":"https://doi.org/10.22541/essoar.167117448.86075329/v1","pdf":"https://essopenarchive.org/doi/pdf/10.22541/essoar.167117448.86075329"},"orgs":["stanford","colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"CNNs predict daily maximum temperature from soil moisture and geopotential, and partial dependence reveals nonlinear soil moisture-temperature coupling across mid-latitude regions.","significance":4,"cited_by":0,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.01253","title":"Deep learning for bias-correcting CMIP6-class Earth system models","authors":["Philipp Hess","Stefan Lange","Christof Schötz","Niklas Boers"],"date":"2022-12-16","year":2022,"venue":"Earth s Future","venue_type":"journal","ids":{"arxiv":"2301.01253","doi":"10.1029/2023ef004002","openalex":"W4387610444"},"links":{"paper":"https://doi.org/10.1029/2023ef004002","pdf":"https://arxiv.org/pdf/2301.01253"},"orgs":["pik","tum"],"topic":"post-processing","topics":["climate-emulation"],"type":"model","method":["gan-vae","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Physically constrained cGANs correct CMIP6-class Earth system model precipitation biases in both local distributions and spatial patterns, outperforming existing methods on extremes' spatial intermittency.","significance":5,"cited_by":42,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.08376","title":"Easy Uncertainty Quantification (EasyUQ): Generating Predictive Distributions from Single-valued Model Output","authors":["Eva‐Maria Walz","Alexander Henzi","Johanna F. Ziegel","Tilmann Gneiting"],"date":"2022-12-16","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.08376","openalex":"W4311993027"},"links":{"paper":"http://arxiv.org/abs/2212.08376","pdf":"https://arxiv.org/pdf/2212.08376"},"orgs":["eth-zurich","kit"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"EasyUQ converts single-valued model output into calibrated predictive distributions via isotonic regression, with a smooth variant and weather forecast examples; the method is general across models.","significance":3,"cited_by":2,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.08208","title":"Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting","authors":["Mohamad Hakam Shams Eddin","Ribana Roscher","Juergen Gall"],"date":"2022-12-16","year":2022,"venue":"in IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-18, 2023, Art no. 4703018","venue_type":"journal","ids":{"arxiv":"2212.08208","doi":"10.1109/tgrs.2023.3285401"},"links":{"paper":"https://arxiv.org/abs/2212.08208","pdf":"https://arxiv.org/pdf/2212.08208","code":"https://github.com/HakamShams/LOAN"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"A 2D/3D CNN with location-aware adaptive normalization improves wildfire danger forecasting on the FireCube dataset over baselines, with the performance gain reported but not quantified in the abstract.","significance":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2022.128949","title":"Short-term rainfall forecasting using cumulative precipitation fields from station data: a probabilistic machine learning approach","authors":["Dina Pirone","Luigi Cimorelli","Giuseppe Del Giudice","Domenico Pianese"],"date":"2022-12-15","year":2022,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2022.128949","openalex":"W4311750299"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2022.128949"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Probabilistic machine learning forecasts short-term rainfall from cumulative precipitation fields built from station observations; the abstract is missing, so this rests on the title.","significance":3,"cited_by":110,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11069-022-05754-5","title":"Study on typhoon disaster assessment by mining data from social media based on artificial neural network","authors":["Shaopan Li","Yan Wang","Hong Huang","Lida Huang","Yang Chen"],"date":"2022-12-15","year":2022,"venue":"Natural Hazards","venue_type":"journal","ids":{"doi":"10.1007/s11069-022-05754-5","openalex":"W4311773696"},"links":{"paper":"https://doi.org/10.1007/s11069-022-05754-5","pdf":"https://www.researchsquare.com/article/rs-1849410/latest.pdf"},"orgs":["tsinghua-university"],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies neural networks to social-media data to assess typhoon disaster impacts; the abstract is missing, so details are inferred from the title.","significance":1,"cited_by":24,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.08102","title":"A Multi-Modal Machine Learning Approach to Detect Extreme Rainfall Events in Sicily","authors":["Eleonora Vitanza","Giovanna Maria Dimitri","Chiara Mocenni"],"date":"2022-12-14","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.08102"},"links":{"paper":"https://arxiv.org/abs/2212.08102","pdf":"https://arxiv.org/pdf/2212.08102"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Affinity Propagation clustering on a 2009-2021 Sicilian rainfall dataset identifies extreme rain events, including anomalous recent events near Catania.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-8931-2022","title":"Temperature forecasting by deep learning methods","authors":["Bing Gong","Michael Langguth","Yan Ji","Amirpasha Mozaffari","Scarlet Stadtler","Karim Mache","Martin G. Schultz"],"date":"2022-12-13","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-8931-2022","openalex":"W4312200505"},"links":{"paper":"https://doi.org/10.5194/gmd-15-8931-2022","pdf":"https://gmd.copernicus.org/articles/15/8931/2022/gmd-15-8931-2022.pdf"},"orgs":["juelich"],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","rnn","cnn"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Compares ConvLSTM and adversarial SAVP models for hourly 12-hour 2 m temperature forecasts over Europe; SAVP reaches MSE about 2.3 K² versus 3.6 K² for ConvLSTM.","significance":3,"cited_by":71,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en15249433","title":"Very Short-Term Forecast: Different Classification Methods of the Whole Sky Camera Images for Sudden PV Power Variations Detection","authors":["Alessandro Niccolai","Emanuèle Ogliari","Alfredo Nespoli","Riccardo Enrico Zich","Valentina Vanetti"],"date":"2022-12-13","year":2022,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en15249433","openalex":"W4311377263"},"links":{"paper":"https://doi.org/10.3390/en15249433","pdf":"https://www.mdpi.com/1996-1073/15/24/9433/pdf?version=1671599225"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite","stations"],"status":"pre-operational","summary":"Neural network and random forest classify sky-camera images to nowcast clear-sky index drops 1–5 minutes ahead for PV cloud-induced variations.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12652-022-04491-8","title":"LSTM-UKF framework for an effective global land-ocean index temperature prediction","authors":["Souvik Bera","Gauri Shanker Gupta","Deepak Kumar","Sarode Shiva Kumar","Karunesh Kumar Gupta"],"date":"2022-12-13","year":2022,"venue":"Journal of Ambient Intelligence and Humanized Computing","venue_type":"journal","ids":{"doi":"10.1007/s12652-022-04491-8","openalex":"W4311314340"},"links":{"paper":"https://doi.org/10.1007/s12652-022-04491-8"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["rnn","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"LSTM combined with an unscented Kalman filter to predict the global land-ocean temperature index; the abstract is missing, so the scope is inferred from the title.","significance":1,"cited_by":7,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-info13120577","title":"SWAR: A Deep Multi-Model Ensemble Forecast Method with Spatial Grid and 2-D Time Structure Adaptability for Sea Level Pressure","authors":["Jingyun Zhang","Lingyu Xu","Baogang Jin"],"date":"2022-12-12","year":2022,"venue":"Information","venue_type":"journal","ids":{"doi":"10.3390/info13120577","openalex":"W4311372923"},"links":{"paper":"https://doi.org/10.3390/info13120577","pdf":"https://www.mdpi.com/2078-2489/13/12/577/pdf?version=1670844699"},"orgs":[],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["transformer","rnn"],"timescale":["short","medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Deep multi-model ensemble method combining NWP outputs with window attention and a rolling recurrent network for the two-dimensional initial-lead time structure, applied to sea level pressure.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2022.48026","title":"Prediction and Classification of Weather Using Machine Learning","authors":["Yash Mali","Aarya Kurlekar","Shambhavi Lalsinge"],"date":"2022-12-12","year":2022,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2022.48026","openalex":"W4311408927"},"links":{"paper":"https://doi.org/10.22214/ijraset.2022.48026","pdf":"https://doi.org/10.22214/ijraset.2022.48026"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Presents a generic machine learning classifier for weather prediction with a farmer-oriented regional guidance angle; no quantitative results reported.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41467-022-35412-0","title":"Multi-task machine learning improves multi-seasonal prediction of the Indian Ocean Dipole","authors":["Fenghua Ling","Jing-Jia Luo","Yue Li","Tao Tang","Lei Bai","Wanli Ouyang","Toshio Yamagata"],"date":"2022-12-12","year":2022,"venue":"Nature Communications","venue_type":"journal","ids":{"doi":"10.1038/s41467-022-35412-0","openalex":"W4311219469"},"links":{"paper":"https://doi.org/10.1038/s41467-022-35412-0"},"orgs":["nuist","shanghai-ai-lab"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["transformer"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"MTL-NET multi-task deep learning predicts the Indian Ocean Dipole up to 7 months ahead, outperforming most dynamical models in hindcasts.","significance":4,"cited_by":90,"score":71,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1016-j.engappai.2022.105673","title":"TFG-Net:Tropical Cyclone Intensity Estimation from a Fine-grained perspective with the Graph convolution neural network","authors":["Guangning Xu","Yan Li","Chi Ma","Xutao Li","Yunming Ye","Qingquan Lin","Zhichao Huang","Shidong Chen"],"date":"2022-12-10","year":2022,"venue":"Engineering Applications of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1016/j.engappai.2022.105673","openalex":"W4311775278"},"links":{"paper":"https://doi.org/10.1016/j.engappai.2022.105673"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["gnn","cnn"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Graph convolutional network estimates tropical cyclone intensity from satellite imagery; the abstract is missing, so details are inferred from the title.","significance":2,"cited_by":24,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.06149","title":"Forecasting formation of a Tropical Cyclone Using Reanalysis Data","authors":["Sandeep Kumar","Koushik Biswas","Ashish Kumar Pandey"],"date":"2022-12-10","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.06149","doi":"10.54364/aaiml.2024.43158"},"links":{"paper":"https://arxiv.org/abs/2212.06149","pdf":"https://arxiv.org/pdf/2212.06149"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"A deep learning model forecasts tropical cyclone formation up to 60 hours ahead from ERA5 and IBTrACS, reaching 86.9% to 92.9% accuracy across six ocean basins.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.04905","title":"Robust detection and attribution of climate change under interventions","authors":["Enikő Székely","Sebastian Sippel","Nicolai Meinshausen","Guillaume Obozinski","Reto Knutti"],"date":"2022-12-09","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.04905"},"links":{"paper":"https://arxiv.org/abs/2212.04905","pdf":"https://arxiv.org/pdf/2212.04905"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Introduces a distributionally robust supervised fingerprint method using anchor regression for climate change detection and attribution that stays robust under interventions on other drivers.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-frwa.2022.1053020","title":"Seasonal prediction of Horn of Africa long rains using machine learning: The pitfalls of preselecting correlated predictors","authors":["Victoria M. H. Deman","Akash Koppa","Willem Waegeman","David A. MacLeod","Michael Bliss Singer","Diego G. Miralles"],"date":"2022-12-08","year":2022,"venue":"Frontiers in Water","venue_type":"journal","ids":{"doi":"10.3389/frwa.2022.1053020","openalex":"W4311870594"},"links":{"paper":"https://doi.org/10.3389/frwa.2022.1053020","pdf":"https://www.frontiersin.org/articles/10.3389/frwa.2022.1053020/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Ridge, lasso, random forest and neural models forecast Horn of Africa long-rains precipitation; preselecting predictors on full data inflates skill, and honest tests fall below dynamical hindcasts.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenvs.2022.1035540","title":"Encoding diel hysteresis and the Birch effect in dryland soil respiration models through knowledge-guided deep learning","authors":["Peishi Jiang","Xingyuan Chen","Justine Missik","Zhongming Gao","Heping Liu","Brittany A. Verbeke"],"date":"2022-12-08","year":2022,"venue":"Frontiers in Environmental Science","venue_type":"journal","ids":{"doi":"10.3389/fenvs.2022.1035540","openalex":"W4311939141"},"links":{"paper":"https://doi.org/10.3389/fenvs.2022.1035540","pdf":"https://www.frontiersin.org/articles/10.3389/fenvs.2022.1035540/pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-analysis-attribution"],"type":"model","method":["rnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"A knowledge-guided LSTM encoding diel hysteresis and Birch effect outperforms Q10 models and CLM in dryland soil respiration (correlation 0.7 vs under 0.4).","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-aca9e3","title":"European heatwave tracks: using causal discovery to detect recurring pathways in a single-regional climate model large ensemble","authors":["Andrea Böhnisch","Elizaveta Felsche","Ralf Ludwig"],"date":"2022-12-08","year":2022,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/aca9e3","openalex":"W4311910651"},"links":{"paper":"https://doi.org/10.1088/1748-9326/aca9e3","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/aca9e3/pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Causal discovery identifies recurrent European heatwave tracks and their seasonality in a single-model large ensemble, enabling a new model evaluation approach for extremes.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-aca9e2","title":"Tropical cyclone intensity prediction by inter- and intra-pattern fusion based on multi-source data","authors":["Dongfang Ma","Lingjie Wang","Sunke Fang","Jianmin Lin"],"date":"2022-12-08","year":2022,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/aca9e2","openalex":"W4311910646"},"links":{"paper":"https://doi.org/10.1088/1748-9326/aca9e2","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/aca9e2/pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Pre_3D fuses tropical cyclone intensity series with environmental factors via separate sub-networks, beating official agency 24-hour intensity forecasts by over 15%.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13143-022-00310-4","title":"Evaluation of Deep-Learning-Based Very Short-Term Rainfall Forecasts in South Korea","authors":["Seok‐Geun Oh","Chanil Park","Seok‐Woo Son","Jihoon Ko","Kijung Shin","Sun‐Young Kim","Junsang Park"],"date":"2022-12-08","year":2022,"venue":"Asia-Pacific Journal of Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s13143-022-00310-4","openalex":"W4311881576"},"links":{"paper":"https://doi.org/10.1007/s13143-022-00310-4"},"orgs":["kma"],"topic":"nowcasting","topics":["benchmarks-data-eval"],"type":"evaluation","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Evaluates deep-learning very-short-term rainfall forecasts over South Korea; abstract not provided, so specific skill numbers are unknown.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.04487","title":"Physics-constrained deep learning postprocessing of temperature and humidity","authors":["Francesco Zanetta","Daniele Nerini","Tom Beucler","Mark A. Liniger"],"date":"2022-12-07","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2212.04487","doi":"10.1175/aies-d-22-0089.1","openalex":"W4387905198"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0089.1","pdf":"https://arxiv.org/pdf/2212.04487"},"orgs":["eth-zurich","meteoswiss"],"topic":"post-processing","topics":["xai-uq-physics"],"type":"model","method":["physics-constrained"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural network post-processing of Swiss surface forecasts enforces thermodynamic equations, yielding physically consistent temperature and humidity without losing accuracy, especially with scarce data.","significance":3,"cited_by":11,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.04005","title":"RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts","authors":["Jinyoung Park","Minseok Son","Seungju Cho","Inyoung Lee","Changick Kim"],"date":"2022-12-07","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.04005"},"links":{"paper":"https://arxiv.org/abs/2212.04005","pdf":"https://arxiv.org/pdf/2212.04005","code":"https://github.com/jinyxp/Weather4cast-2022"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"RainUNet with decoupled large-kernel 3D convolutions forecasts high-resolution radar rainfall movies from low-resolution satellite data in the Weather4cast 2022 challenge.","significance":2,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.04001","title":"TweetDrought: A Deep-Learning Drought Impacts Recognizer based on Twitter Data","authors":["Beichen Zhang","Frank Schilder","Kelly Helm Smith","Michael J. Hayes","Sherri Harms","Tsegaye Tadesse"],"date":"2022-12-07","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.04001"},"links":{"paper":"https://arxiv.org/abs/2212.04001","pdf":"https://arxiv.org/pdf/2212.04001"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["llm","transformer"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Fine-tuned BERT recognizes seven drought impact types in tweets, reaching 0.89 macro-F1 on the Drought Impact Report test set.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.03369","title":"Exploring Randomly Wired Neural Networks for Climate Model Emulation","authors":["William Yik","Sam J. Silva","Andrew Geiss","Duncan Watson-Parris"],"date":"2022-12-06","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2212.03369","doi":"10.1175/aies-d-22-0088.1","openalex":"W4383817485"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0088.1","pdf":"https://arxiv.org/pdf/2212.03369"},"orgs":["university-of-oxford"],"topic":"climate-emulation","topics":[],"type":"evaluation","method":["cnn","rnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Randomly wired dense layers in ClimateBench emulators improve performance in 14 of 24 cases, up to 30.4% for MLPs, with no slower prediction.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.02968","title":"Domain Generalization Strategy to Train Classifiers Robust to Spatial-Temporal Shift","authors":["Minseok Seo","Doyi Kim","Seungheon Shin","Eunbin Kim","Sewoong Ahn","Yeji Choi"],"date":"2022-12-06","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.02968","openalex":"W4310884225"},"links":{"paper":"https://arxiv.org/abs/2212.02968","pdf":"https://arxiv.org/pdf/2212.02968"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Hyperparameter, augmentation and test-time augmentation recipe makes satellite-to-rainfall models robust to spatial-temporal shifts, ranking first on the W4C22 Transfer dataset.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.02952","title":"Simple Baseline for Weather Forecasting Using Spatiotemporal Context Aggregation Network","authors":["Minseok Seo","Doyi Kim","Seungheon Shin","Eunbin Kim","Sewoong Ahn","Yeji Choi"],"date":"2022-12-06","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.02952","openalex":"W4310884541"},"links":{"paper":"https://arxiv.org/abs/2212.02952","pdf":"https://arxiv.org/pdf/2212.02952"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Simple CNN baseline (SIANet) using only satellite images reaches state-of-the-art on four of five W4C22 rainfall benchmark tasks without ensembling or fine-tuning.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2022.3225154","title":"A Lightweight Multitask Learning Model With Adaptive Loss Balance for Tropical Cyclone Intensity and Size Estimation","authors":["Wei Tian","Xinxin Zhou","Xianhua Niu","Linhong Lai","Yonghong Zhang","Kenny Thiam Choy Lim Kam Sian"],"date":"2022-12-05","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2022.3225154","openalex":"W4312857493"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3225154","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9973430/09970399.pdf"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Lightweight multitask CNN estimates tropical cyclone intensity and size from satellite data, with intensity RMSE of 8.40 kt, 33.5% below the ADT baseline.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.04478","title":"An Interpretable Model of Climate Change Using Correlative Learning","authors":["Charles Anderson","Jason Stock"],"date":"2022-12-05","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.04478"},"links":{"paper":"https://arxiv.org/abs/2212.04478","pdf":"https://arxiv.org/pdf/2212.04478"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A neural network trained on CMIP6 global temperature and precipitation means predicts the year, and Alopex-derived patterns reveal how climate change signals evolve.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.02456","title":"Solving the Weather4cast Challenge via Visual Transformers for 3D Images","authors":["Yury Belousov","Sergey Polezhaev","Brian Pulfer"],"date":"2022-12-05","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.02456"},"links":{"paper":"https://arxiv.org/abs/2212.02456","pdf":"https://arxiv.org/pdf/2212.02456"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Transformer ensembles predict eight hours of rainfall from one hour of satellite imagery, ranking third in the NeurIPS 2022 Weather4cast challenge.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.01998","title":"An operational framework to automatically evaluate the quality of weather observations from third-party stations","authors":["Quanxi Shao","Ming Li","Joel Janek Dabrowski","Shuvo Bakar","Ashfaqur Rahman","Andrea Powell","Brent Henderson"],"date":"2022-12-05","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.01998"},"links":{"paper":"https://arxiv.org/abs/2212.01998","pdf":"https://arxiv.org/pdf/2212.01998"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Near real-time framework fuses per-source statistical and ML models to quality-assess crowdsourced third-party weather station observations, tested on synthetic and real network data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-cli10120193","title":"Influence of Meteo-Climatic Variables and Fertilizer Use on Crop Yields in the Sahel: A Nonlinear Neural-Network Analysis","authors":["Antonello Pasini","Giuseppina De Felice Proia","Francesco Nicola Tubiello"],"date":"2022-12-04","year":2022,"venue":"Climate","venue_type":"journal","ids":{"doi":"10.3390/cli10120193","openalex":"W4310681743"},"links":{"paper":"https://doi.org/10.3390/cli10120193","pdf":"https://www.mdpi.com/2225-1154/10/12/193/pdf?version=1670134740"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Feed-forward neural networks show heat stress and fertilizer drive maize and millet yields in the Sahel, explaining 59-79% of yield variance.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10512988.1","title":"Multi-site and multi-year precipitation isotope δ18O forecasting using CNN, Bi-LSTM, CNN-Bi-LSTM, and spatiotemporal clustering","authors":["Yang Li","Siyuan Huo","Bin Ma","Bingbing Pei","Qiankun Tan","Deng Wang"],"date":"2022-12-04","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10512988.1","openalex":"W4311529524"},"links":{"paper":"https://doi.org/10.1002/essoar.10512988.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10512988.1"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"CNN-Bi-LSTM with spatiotemporal clustering forecasts precipitation delta-18O at 10 German stations, performing best for multi-site multi-year forecasts.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.01796","title":"Insights into the drivers and spatio-temporal trends of extreme Mediterranean wildfires with statistical deep-learning","authors":["Jordan Richards","Raphaël Huser","Emanuele Bevacqua","Jakob Zscheischler"],"date":"2022-12-04","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.01796"},"links":{"paper":"https://arxiv.org/abs/2212.01796","pdf":"https://arxiv.org/pdf/2212.01796"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"A hybrid statistical deep learning model links VPD and temperature to Mediterranean burnt area, projecting a 17.1% rise in expected August wildfire frequency under observed warming.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2022.106548","title":"Nowcasting extreme rain and extreme wind speed with machine learning techniques applied to different input datasets","authors":["Sandy Chkeir","Aikaterini Anesiadou","Alessandra Mascitelli","Riccardo Biondi"],"date":"2022-12-02","year":2022,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2022.106548","openalex":"W4311765019"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2022.106548"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","radar"],"status":"research","summary":"An LSTM encoder-decoder nowcasts extreme rain and wind over Malpensa airport for one hour, reaching over 90% wind detection probability with station and GNSS inputs.","significance":3,"cited_by":67,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11600-022-00978-2","title":"Analyzing trend and forecast of rainfall and temperature in Valmiki Tiger Reserve, India, using non-parametric test and random forest machine learning algorithm","authors":["Roshani","Haroon Sajjad","Tamal Kanti Saha","Md Hibjur Rahaman","Md Masroor","Yatendra Sharma","Swades Pal"],"date":"2022-12-02","year":2022,"venue":"Acta Geophysica","venue_type":"journal","ids":{"doi":"10.1007/s11600-022-00978-2","openalex":"W4311098408"},"links":{"paper":"https://doi.org/10.1007/s11600-022-00978-2"},"orgs":[],"topic":"local-forecasting","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random forest forecasts and non-parametric trend tests for rainfall and temperature at one Indian tiger reserve; no abstract provided, so scope is limited to local station climate.","significance":1,"cited_by":47,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.02236","title":"A Deep Learning Architecture for Passive Microwave Precipitation Retrievals using CloudSat and GPM Data","authors":["Reyhaneh Rahimi","Sajad Vahedizadeh","Ardeshir Ebtehaj"],"date":"2022-12-02","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.02236"},"links":{"paper":"https://arxiv.org/abs/2212.02236","pdf":"https://arxiv.org/pdf/2212.02236"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5","radar"],"status":"research","summary":"Dense neural networks retrain passive microwave rainfall and snowfall retrievals from GPM and CloudSat, detecting precipitation with over 0.95 probability and showing large global snowfall uncertainty.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.01446","title":"Downscaling Extreme Rainfall Using Physical-Statistical Generative Adversarial Learning","authors":["Anamitra Saha","Sai Ravela"],"date":"2022-12-02","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.01446","openalex":"W4310820096"},"links":{"paper":"https://arxiv.org/abs/2212.01446","pdf":"https://arxiv.org/pdf/2212.01446"},"orgs":["mit"],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["gan-vae","physics-constrained"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"A physics-statistical GAN downscales 0.25° climate model rainfall to 0.01° fields, quantifying uncertainty and matching observed extreme rainfall distributions.","significance":4,"cited_by":7,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2212.00970","title":"Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfires","authors":["Joel Janek Dabrowski","Daniel Edward Pagendam","James Hilton","Conrad Sanderson","Daniel MacKinlay","Carolyn Huston","Andrew Bolt","Petra Kuhnert"],"date":"2022-12-02","year":2022,"venue_type":"preprint","ids":{"arxiv":"2212.00970","doi":"10.1016/j.spasta.2023.100746"},"links":{"paper":"https://arxiv.org/abs/2212.00970","pdf":"https://arxiv.org/pdf/2212.00970"},"orgs":[],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"model","method":["physics-constrained"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Bayesian physics-informed neural networks model wildfire fronts under changing wind, adding data assimilation and uncertainty quantification to level-set fire spread.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7220134854","title":"A Machine Learning Perspective for Data Analytics in Solar Powered Weather Station using IoT","authors":["Praveen S Chakkravarthy","P. Bharath Chandra","D. Anwar Basha","G. Sai Kiran"],"date":"2022-12-01","year":2022,"venue":"CVR Journal of Science & Technology","venue_type":"journal","ids":{"openalex":"W7220134854"},"links":{"paper":"https://cvr.ac.in/ojs/index.php/cvracin/article/view/811","pdf":"https://cvr.ac.in/ojs/index.php/cvracin/article/download/811/653"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Describes a solar-powered IoT weather station with a machine learning model to predict local weather conditions in Mangalpalli; results are not quantified.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46632-daai-2-4-16","title":"Accurate Stipulation of Weather Condition Using Deep Learning","authors":[],"date":"2022-12-01","year":2022,"venue_type":"other","ids":{"doi":"10.46632/daai/2/4/16","openalex":"W4312098451"},"links":{"paper":"https://doi.org/10.46632/daai/2/4/16","pdf":"https://doi.org/10.46632/daai/2/4/16"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Reviews deep learning weather forecasting and classifies weather conditions such as rainy, sunny and foggy from images; the abstract offers no quantitative results.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-ws.2022.412","title":"Research on precipitation prediction based on a complete ensemble empirical mode decomposition with adaptive noise–long short-term memory coupled model","authors":["Shaolei Guo","Yihao Wen","Xianqi Zhang","Guoyu Zhu","Jiafeng Huang"],"date":"2022-12-01","year":2022,"venue":"Water Science & Technology Water Supply","venue_type":"journal","ids":{"doi":"10.2166/ws.2022.412","openalex":"W4311628009"},"links":{"paper":"https://doi.org/10.2166/ws.2022.412"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"CEEMDAN-LSTM hybrid predicts annual precipitation in Zhengzhou city, reaching 2.69% MAPE and R² of 0.9863, outperforming five baseline models.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-22-0046.1","title":"Outcomes of the WMO Prize Challenge to Improve Subseasonal to Seasonal Predictions Using Artificial Intelligence","authors":["F. Vitart","A. W. Robertson","A. Spring","F. Pinault","R. Roškar","W. Cao","S. Bech","A. Bienkowski","N. Caltabiano","E. De Coning","B. Denis","A. Dirkson","J. Dramsch","P. Dueben","J. Gierschendorf","H. S. Kim","K. Nowak","D. Landry","L. Lledó","L. Palma","S. Rasp","S. Zhou"],"date":"2022-12-01","year":2022,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-22-0046.1","openalex":"W4298138444"},"links":{"paper":"https://doi.org/10.1175/bams-d-22-0046.1"},"orgs":["columbia-leap","eccc","ecmwf","mpi-meteorology","sdsc"],"topic":"s2s-seasonal","topics":["post-processing","benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"WMO prize challenge winners used AI to post-process ECMWF S2S forecasts, beating bias-corrected references for weeks 3-6 precipitation and temperature.","significance":5,"cited_by":41,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2022ms003132","title":"ENSO‐GTC: ENSO Deep Learning Forecast Model With a Global Spatial‐Temporal Teleconnection Coupler","authors":["Bin Mu","Bo Qin","Shijin Yuan"],"date":"2022-12-01","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003132","openalex":"W4311747516"},"links":{"paper":"https://doi.org/10.1029/2022ms003132","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003132"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["gnn"],"timescale":["s2s","seasonal"],"spatial":["global"],"data":[],"status":"research","summary":"ENSO-GTC graph-based model with a teleconnection coupler reaches Niño3.4 correlation 0.51 at 18-month lead and above 0.6 out to 20 months with direct strategy.","significance":4,"cited_by":34,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aiig.2022.11.001","title":"ResGraphNet: GraphSAGE with embedded residual module for prediction of global monthly mean temperature","authors":["Ziwei Chen","Zhiguo Wang","Yang Yang","Jinghuai Gao"],"date":"2022-12-01","year":2022,"venue":"Artificial Intelligence in Geosciences","venue_type":"journal","ids":{"doi":"10.1016/j.aiig.2022.11.001","openalex":"W4311144837"},"links":{"paper":"https://doi.org/10.1016/j.aiig.2022.11.001","pdf":"https://www.sciencedirect.com/science/article/pii/S2666544122000314/pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["gnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"ResGraphNet, a GraphSAGE model with residual links, predicts HadCRUT5 global monthly mean temperature more accurately than 11 baselines across seven datasets.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13351-022-1214-3","title":"A New Hybrid Machine Learning Model for Short-Term Climate Prediction by Performing Classification Prediction and Regression Prediction Simultaneously","authors":["Deqian Li","Shujuan Hu","Jinyuan Guo","Kai Wang","Chenbin Gao","Siyi Wang","Wenping He"],"date":"2022-12-01","year":2022,"venue":"气象学报：英文版","venue_type":"journal","ids":{"doi":"10.1007/s13351-022-1214-3","openalex":"W4320030914"},"links":{"paper":"https://doi.org/10.1007/s13351-022-1214-3"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":[],"status":"research","summary":"Hybrid machine learning model that jointly performs classification and regression for short-term climate prediction; the abstract is missing, so details are inferred from the title.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.29220-csam.2022.29.6.709","title":"Solar radiation forecasting using boosting decision tree and recurrent neural networks","authors":["Hyojeoung Kim","Sujin Park","Sahm Kim"],"date":"2022-11-30","year":2022,"venue":"Communications for Statistical Applications and Methods","venue_type":"journal","ids":{"doi":"10.29220/csam.2022.29.6.709","openalex":"W4311077346"},"links":{"paper":"https://doi.org/10.29220/csam.2022.29.6.709","pdf":"http://www.csam.or.kr/journal/download_pdf.php?doi=10.29220/CSAM.2022.29.6.709"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"evaluation","method":["classical-ml","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"CatBoost best predicts solar radiation in Korea from temperature, humidity, cloudiness and extraterrestrial radiation, outperforming LSTM and GRU variants.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0050.1","title":"Can a Machine Learning–Enabled Numerical Model Help Extend Effective Forecast Range through Consistently Trained Subgrid-Scale Models?","authors":["Yongquan Qu","Xiaoming Shi"],"date":"2022-11-30","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0050.1","openalex":"W4310442368"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0050.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/2/1/AIES-D-22-0050.1.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["differentiable","physics-constrained"],"timescale":["medium"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A differentiable solver trains an ML subgrid turbulence model inside a barotropic vorticity model, extending effective forecast lead time by up to 50%, or 73% with transfer learning.","significance":4,"cited_by":10,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2301.11921","title":"Using uncertainty-aware machine learning models to study aerosol-cloud interactions","authors":["Maëlys Solal","Andrew Jesson","Yarin Gal","Alyson Douglas"],"date":"2022-11-30","year":2022,"venue_type":"preprint","ids":{"arxiv":"2301.11921","openalex":"W4318719651"},"links":{"paper":"https://arxiv.org/abs/2301.11921","pdf":"https://arxiv.org/pdf/2301.11921"},"orgs":["university-of-oxford"],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","cmip"],"status":"research","summary":"Causal machine learning on satellite observations estimates aerosol-cloud interaction with uncertainty bounds, finding only one of three climate models reproduces the cooling trend.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.16824","title":"WeatherFusionNet: Predicting Precipitation from Satellite Data","authors":["Jiří Pihrt","Rudolf Raevskiy","Petr Šimánek","Matej Choma"],"date":"2022-11-30","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.16824"},"links":{"paper":"https://arxiv.org/abs/2211.16824","pdf":"https://arxiv.org/pdf/2211.16824","code":"https://github.com/Datalab-FIT-CTU/weather4cast-2022"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"U-Net fusing satellite frame prediction and rain extraction won the NeurIPS 2022 Weather4Cast challenge, forecasting severe rain up to eight hours ahead.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.16708","title":"Statistical treatment of convolutional neural network super-resolution of inland surface wind for subgrid-scale variability quantification","authors":["Daniel Getter","Julie Bessac","Johann Rudi","Yan Feng"],"date":"2022-11-30","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.16708"},"links":{"paper":"https://arxiv.org/abs/2211.16708","pdf":"https://arxiv.org/pdf/2211.16708"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["km-scale-sim","other"],"status":"research","summary":"CNNs super-resolve surface wind from 25-100 km to 3 km, with coarse wind plus fine topography giving the best out-of-sample extreme-wind skill.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en15239045","title":"Optimal Design of Hybrid Renewable Energy Systems Considering Weather Forecasting Using Recurrent Neural Networks","authors":["Alfonso Angel Medina-Santana","Leopoldo Eduardo Cárdenas‐Barrón"],"date":"2022-11-29","year":2022,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en15239045","openalex":"W4310387075"},"links":{"paper":"https://doi.org/10.3390/en15239045","pdf":"https://www.mdpi.com/1996-1073/15/23/9045/pdf?version=1670243810"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn","classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["other"],"status":"research","summary":"LSTM weather prediction feeds a clustering and nonlinear sizing model for off-grid hybrid renewable systems, giving a 0.1% loss-of-load gain over seasonal naive.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-aca68a","title":"Two deep learning-based bias-correction pathways improve summer precipitation prediction over China","authors":["Fenghua Ling","Yue Li","Jing‐Jia Luo","Xiaohui Zhong","Zhibin Wang"],"date":"2022-11-29","year":2022,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/aca68a","openalex":"W4310125456"},"links":{"paper":"https://doi.org/10.1088/1748-9326/aca68a","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/aca68a/pdf"},"orgs":["nuist","alibaba-damo"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Two deep-learning bias-correction pathways improve 4-month-lead summer precipitation forecasts from a Chinese GCM, with the deterministic pathway better for extremes.","significance":3,"cited_by":29,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-aca689","title":"Regional differences in the response of California’s rangeland production to climate and future projection","authors":["Liu Han","Yufang Jin A","Leslie M. Roche","Anthony T O’Geen","Randy Alan Dahlgren"],"date":"2022-11-29","year":2022,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/aca689","openalex":"W4310124562"},"links":{"paper":"https://doi.org/10.1088/1748-9326/aca689","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/aca689/pdf"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["satellite","cmip"],"status":"research","summary":"Gradient boosted trees link California rangeland productivity to climate variables and project regional changes in gross primary production under downscaled future climate.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.16116","title":"Machine learning emulation of a local-scale UK climate model","authors":["Henry Addison","Elizabeth Kendon","Suman Ravuri","Laurence Aitchison","Peter AG Watson"],"date":"2022-11-29","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.16116","openalex":"W4310512276"},"links":{"paper":"https://arxiv.org/abs/2211.16116","pdf":"https://arxiv.org/pdf/2211.16116"},"orgs":["met-office"],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["diffusion"],"timescale":["climate"],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Diffusion models generate realistic high-resolution UK rainfall samples conditioned on low-resolution simulations, matching the high-resolution model's quantiles and time-mean.","significance":4,"cited_by":4,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.15856","title":"Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting","authors":["Elena Orlova","Haokun Liu","Raphael Rossellini","Benjamin A. Cash","Rebecca Willett"],"date":"2022-11-29","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.15856","doi":"10.1175/aies-d-23-0103.1"},"links":{"paper":"https://arxiv.org/abs/2211.15856","pdf":"https://arxiv.org/pdf/2211.15856"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml","cnn"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"ML post-processing of lagged ensemble forecasts improves two-week-ahead monthly precipitation and temperature forecasts over the continental US, beating climatology and ensemble means.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25743-ict.2022.27.5.005","title":"Using a case-based approach to predict the risk of forest fires","authors":["Nikita O. Dorodnykh","Olga Anatolievna Nikolaychuk","Julia Pestova","Юрин Александр Юрьевич"],"date":"2022-11-28","year":2022,"venue":"Вычислительные технологии","venue_type":"journal","ids":{"doi":"10.25743/ict.2022.27.5.005","openalex":"W4310075514"},"links":{"paper":"https://doi.org/10.25743/ict.2022.27.5.005"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Case-based expert system predicts forest fire risk in the Irkutsk region from 2017–2020 fire records, weather and remote sensing data, with a web-service prototype.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.15046","title":"PCT-CycleGAN: Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting","authors":["Jaeho Choi","Yura Kim","Kwang-Ho Kim","Sung-Hwa Jung","Ikhyun Cho"],"date":"2022-11-28","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.15046"},"links":{"paper":"https://arxiv.org/abs/2211.15046","pdf":"https://arxiv.org/pdf/2211.15046"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"CycleGAN-style model with forward and backward temporal cycles generates radar precipitation 10 minutes ahead and rolls out 2-hour nowcasts with a heavy-rain loss.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14235960","title":"Estimating All-Weather Surface Longwave Radiation from Satellite Passive Microwave Data","authors":["Zhonghu Jiao"],"date":"2022-11-25","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14235960","openalex":"W4310042499"},"links":{"paper":"https://doi.org/10.3390/rs14235960","pdf":"https://www.mdpi.com/2072-4292/14/23/5960/pdf?version=1669345003"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Neural network retrievals from AMSR2 microwave data estimate all-weather surface longwave radiation globally, with R² of 0.82–0.89 against ERA5 over land.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenvs.2022.1039764","title":"Spatiotemporal model based on transformer for bias correction and temporal downscaling of forecasts","authors":["Xiang Li","Jiping Guan","Jie Xiang","Lifeng Zhang","Fuhan Zhang"],"date":"2022-11-25","year":2022,"venue":"Frontiers in Environmental Science","venue_type":"journal","ids":{"doi":"10.3389/fenvs.2022.1039764","openalex":"W4310039988"},"links":{"paper":"https://doi.org/10.3389/fenvs.2022.1039764","pdf":"https://www.frontiersin.org/articles/10.3389/fenvs.2022.1039764/pdf"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["transformer","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Swin-transformer U-Net corrects NWP 2 m temperature and 10 m wind biases and produces hourly temporal downscaling, cutting RMSE by 0.78 versus the original forecasts.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ef003048","title":"Achieving Brazil's Deforestation Target Will Reduce Fire and Deliver Air Quality and Public Health Benefits","authors":["Edward Butt","Luke Conibear","Callum Smith","Jessica C. A. Baker","Richard Rigby","Christoph Knote","Dominick Vincent Spracklen"],"date":"2022-11-25","year":2022,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2022ef003048","openalex":"W4310059367"},"links":{"paper":"https://doi.org/10.1029/2022ef003048","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EF003048"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning on climate and deforestation data attributes Amazon fire counts to deforestation, estimating a 42% rise in 2020 and 32% fewer fires under the Brazilian target.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.neucom.2022.11.078","title":"ENSO analysis and prediction using deep learning: A review","authors":["Gai‐Ge Wang","Honglei Cheng","Yiming Zhang","Hui Ling Yu"],"date":"2022-11-25","year":2022,"venue":"Neurocomputing","venue_type":"journal","ids":{"doi":"10.1016/j.neucom.2022.11.078","openalex":"W4309945030"},"links":{"paper":"https://doi.org/10.1016/j.neucom.2022.11.078"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"review","method":[],"timescale":["seasonal"],"spatial":["global"],"data":[],"status":"research","summary":"Review of deep learning methods for ENSO analysis and prediction, covering evaluation metrics, the spring predictability barrier and prediction uncertainty.","significance":4,"cited_by":50,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14235950","title":"Rainfall Forecast Using Machine Learning with High Spatiotemporal Satellite Imagery Every 10 Minutes","authors":["Febryanto Simanjuntak","Ilham Jamaluddin","Tang-Huang Lin","Hary Aprianto Wijaya Siahaan","Ying-Nong Chen"],"date":"2022-11-24","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14235950","openalex":"W4310039782"},"links":{"paper":"https://doi.org/10.3390/rs14235950","pdf":"https://www.mdpi.com/2072-4292/14/23/5950/pdf?version=1669358887"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"LSTM forecasts Himawari-8 brightness temperatures and random forest converts them into 10-minute rainfall estimates over Indonesia, with RMSE of 1.54 mm per 3 h.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14235948","title":"Two-Stage UA-GAN for Precipitation Nowcasting","authors":["Liujia Xu","Dan Niu","Tianbao Zhang","Pengju Chen","Xunlai Chen","Yinghao Li"],"date":"2022-11-24","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14235948","openalex":"W4310038336"},"links":{"paper":"https://doi.org/10.3390/rs14235948","pdf":"https://www.mdpi.com/2072-4292/14/23/5948/pdf?version=1669299284"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Two-stage TrajGRU and attention-enhanced U-Net GAN refines radar echo extrapolations, outperforming ROVER and RNN baselines on detail and precipitation accuracy metrics.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13121963","title":"Short-Term Rainfall Prediction Based on Radar Echo Using an Improved Self-Attention PredRNN Deep Learning Model","authors":["Dali Wu","Li Jie Wu","Tao Zhang","Wenxuan Zhang","Jianqiang Huang","Xiaoying Wang"],"date":"2022-11-24","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13121963","openalex":"W4309971527"},"links":{"paper":"https://doi.org/10.3390/atmos13121963","pdf":"https://www.mdpi.com/2073-4433/13/12/1963/pdf?version=1669356929"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"ISA-PredRNN adds self-attention and a weighted loss to PredRNN-V2 for radar echo nowcasting, reaching CSI 0.70 at the 10 dBZ threshold.","significance":3,"cited_by":25,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.26599-bdma.2021.9020017","title":"Deep Convolutional Network Based Machine Intelligence Model for Satellite Cloud Image Classification","authors":["Kalyan Kumar Jena","Sourav Kumar Bhoi","Soumya Ranjan Nayak","Ranjit Panigrahi","Akash Kumar Bhoi"],"date":"2022-11-24","year":2022,"venue":"Big Data Mining and Analytics","venue_type":"journal","ids":{"doi":"10.26599/bdma.2021.9020017","openalex":"W4310295432"},"links":{"paper":"https://doi.org/10.26599/bdma.2021.9020017","pdf":"https://ieeexplore.ieee.org/ielx7/8254253/9962810/09962954.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A deep convolutional network classifies satellite cloud images from MOSDAC over India with 94% accuracy, aimed at tropical cyclone prediction.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-21-0009.1","title":"Skillful U.S. Soy Yield Forecasts at Presowing Lead Times","authors":["Sem Vijverberg","Raed Hamed","Dim Coumou"],"date":"2022-11-24","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-21-0009.1","openalex":"W4309878702"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0009.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/aies/2/3/AIES-D-21-0009.1.pdf"},"orgs":["knmi"],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Statistical ML seasonal forecasts of poor US soybean harvests from Pacific SST and soil moisture precursors reach 67% correct at three months before sowing.","significance":3,"cited_by":5,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tpwrs.2022.3224006","title":"A Bi-Party Engaged Modeling Framework for Renewable Power Predictions With Privacy-Preserving","authors":["Hong Liu","Zijun Zhang"],"date":"2022-11-24","year":2022,"venue":"IEEE Transactions on Power Systems","venue_type":"journal","ids":{"doi":"10.1109/tpwrs.2022.3224006","openalex":"W4312400898"},"links":{"paper":"https://doi.org/10.1109/tpwrs.2022.3224006"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Privacy-preserving bi-party framework learns local and global latent features from multi-site NWP inputs for renewable power forecasts, with at least 3% average gains over baselines.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.13491","title":"Spatial Mixture-of-Experts","authors":["Nikoli Dryden","Torsten Hoefler"],"date":"2022-11-24","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.13491"},"links":{"paper":"https://arxiv.org/abs/2211.13491","pdf":"https://arxiv.org/pdf/2211.13491"},"orgs":[],"topic":"global-medium-range","topics":["post-processing"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Spatial Mixture-of-Experts layer routes experts by location and sets new state of the art for medium-range weather prediction and ensemble post-processing.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.14434","title":"Multi-Step Short-Term Wind Speed Prediction with Rank Pooling and Fast Fourier Transformation","authors":["Hailong Shu"],"date":"2022-11-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.14434"},"links":{"paper":"https://arxiv.org/abs/2211.14434","pdf":"https://arxiv.org/pdf/2211.14434"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A hybrid rank-pooling and FFT model with MLP or LSTM heads improves multi-step station wind speed forecasts over single and hybrid baselines using 2010-2020 data.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.13354","title":"Improving the predictions of ML-corrected climate models with novelty detection","authors":["Clayton Sanford","Anna Kwa","Oliver Watt-Meyer","Spencer Clark","Noah Brenowitz","Jeremy McGibbon","Christopher Bretherton"],"date":"2022-11-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.13354","openalex":"W4310269389"},"links":{"paper":"https://arxiv.org/abs/2211.13354","pdf":"https://arxiv.org/pdf/2211.13354"},"orgs":["nvidia","ai2","columbia-leap"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"A one-class SVM novelty detector disables ML corrections on out-of-sample inputs, stabilizing coarse climate runs and improving temperature and precipitation over standard ML corrections.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.13181","title":"A Deep Learning-based Velocity Dealiasing Algorithm Derived from the WSR-88D Open Radar Product Generator","authors":["Mark S. Veillette","James M. Kurdzo","Phillip M. Stepanian","Joseph McDonald","Siddharth Samsi","John Y. N. Cho"],"date":"2022-11-23","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2211.13181","doi":"10.1175/aies-d-22-0084.1","openalex":"W4327716819"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0084.1","pdf":"https://arxiv.org/pdf/2211.13181"},"orgs":["mit"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A U-Net emulates the WSR-88D operational velocity dealiasing algorithm, giving accurate, fast radar dealiasing that ports to other radar systems.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13121943","title":"Forecasting and Optimization of Wind Speed over the Gobi Grassland Wind Farm in Western Inner Mongolia","authors":["Jinyuan Xin","Daen Bao","Yining Ma","Yining Ma","Chongshui Gong","Shuai Qiao","Yunyan Jiang","Xinbing Ren","Tao Pang","Pengcheng Yan"],"date":"2022-11-22","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13121943","openalex":"W4309722169"},"links":{"paper":"https://doi.org/10.3390/atmos13121943","pdf":"https://www.mdpi.com/2073-4433/13/12/1943/pdf?version=1669187509"},"orgs":["iap-cas","cma"],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"CatBoost bias-corrects WRF wind-speed forecasts at a Gobi wind farm, reducing a four-day mean deviation from 3.21 to about 2.50 m/s.","significance":2,"cited_by":6,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenvs.2022.1034536","title":"A comprehensive wind speed forecast correction strategy with an artificial intelligence algorithm","authors":["Xueliang Zhao","Qilong Sun","Wanru Tang","Shuang Yu","Boyu Wang"],"date":"2022-11-22","year":2022,"venue":"Frontiers in Environmental Science","venue_type":"journal","ids":{"doi":"10.3389/fenvs.2022.1034536","openalex":"W4327782432"},"links":{"paper":"https://doi.org/10.3389/fenvs.2022.1034536","pdf":"https://www.frontiersin.org/articles/10.3389/fenvs.2022.1034536/pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Deep-learning error correction of day-ahead NWP wind speed forecasts improves accuracy without per-site modelling, compared with ARIMA and smoothing baselines.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13143-022-00303-3","title":"Analysis of the Interdecadal and Interannual Variability of Autumn Extreme Rainfall in Taiwan Using a Deep-Learning-Based Weather Typing Approach","authors":["Li‐Huan Hsu","Yi‐chao Wu","Chou-Chun Chiang","Jung‐Lien Chu","Yi‐Chiang Yu","An-Hsiang Wang","Ben Jong‐Dao Jou"],"date":"2022-11-22","year":2022,"venue":"Asia-Pacific Journal of Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s13143-022-00303-3","openalex":"W4309879857"},"links":{"paper":"https://doi.org/10.1007/s13143-022-00303-3"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":[],"timescale":["decadal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Deep-learning weather typing analyses interdecadal and interannual variability of autumn extreme rainfall in Taiwan; abstract unavailable, scope inferred from title.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.13052","title":"Pyrocast: a Machine Learning Pipeline to Forecast Pyrocumulonimbus (PyroCb) Clouds","authors":["Kenza Tazi","Emiliano Díaz Salas-Porras","Ashwin Braude","Daniel Okoh","Kara D. Lamb","Duncan Watson-Parris","Paula Harder","Nis Meinert"],"date":"2022-11-22","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.13052"},"links":{"paper":"https://arxiv.org/abs/2211.13052","pdf":"https://arxiv.org/pdf/2211.13052"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml","cnn","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Pyrocast pipeline with a 148-event pyroCb database and CNN or random-forest models predicts pyroCb six hours ahead with AUC 0.90.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.7340401","title":"Improving Heat Index Results Derived From IOT Data through the Application of Detailed Neural Networks","authors":["A. Karthik","Dr.G Sunil Kumar"],"date":"2022-11-21","year":2022,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.7340401","openalex":"W4309500002"},"links":{"paper":"https://doi.org/10.5281/zenodo.7340401","pdf":"https://zenodo.org/record/7340402"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An LSTM-style deep network forecasts heat index from IoT temperature sensor series and is compared with generalized linear regression; the methods are thinly described.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-egusphere-2022-1222","title":"Data Driven Regional Weather Forecasting","authors":["Randall Clark","Luke C. Fairbanks","Ramon A. Sanchez","Pacharadech Wacharanan","Henry D. I. Abarbanel"],"date":"2022-11-21","year":2022,"venue_type":"other","ids":{"doi":"10.5194/egusphere-2022-1222","openalex":"W4309451017"},"links":{"paper":"https://doi.org/10.5194/egusphere-2022-1222"},"orgs":[],"topic":"regional-km-scale","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Data-driven forecasting rules built from regional observations predict shallow-water flow on a beta plane without explicit physical equations.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-15-6653-2022","title":"A CO 2 -independent cloud mask from Infrared Atmospheric Sounding Interferometer (IASI) radiances for climate applications","authors":["Simon Whitburn","Lieven Clarisse","Marc Crapeau","Thomas August","Tim Hultberg","Pierre Coheur","Cathy Clerbaux"],"date":"2022-11-21","year":2022,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-15-6653-2022","openalex":"W4309782964"},"links":{"paper":"https://doi.org/10.5194/amt-15-6653-2022","pdf":"https://amt.copernicus.org/articles/15/6653/2022/amt-15-6653-2022.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"CO2-independent neural-network cloud mask for IASI radiances agrees about 87% pixel-by-pixel with the operational IASI L2 cloud product, suited to climate records.","significance":4,"cited_by":16,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w14223782","title":"Smooth Spatial Modeling of Extreme Mediterranean Precipitation","authors":["Hela Hammami","Julie Carreau","Luc Neppel","Sadok El Asmi","Haifa Feki"],"date":"2022-11-21","year":2022,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w14223782","openalex":"W4309710933"},"links":{"paper":"https://doi.org/10.3390/w14223782","pdf":"https://www.mdpi.com/2073-4441/14/22/3782/pdf?version=1669024426"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Compares GEV models with GLM or neural network spatial interpolation of extreme Mediterranean precipitation parameters, with the ANN hidden-unit complexity key to performance.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.11820","title":"Machine-learned climate model corrections from a global storm-resolving model","authors":["Anna Kwa","Spencer K. Clark","Brian Henn","Noah D. Brenowitz","Jeremy McGibbon","W. Andre Perkins","Oliver Watt-Meyer","Lucas Harris","Christopher S. Bretherton"],"date":"2022-11-21","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.11820","openalex":"W4309867720"},"links":{"paper":"https://arxiv.org/abs/2211.11820","pdf":"https://arxiv.org/pdf/2211.11820"},"orgs":["ai2","noaa"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Neural network corrections trained on a 3 km storm-resolving model reduce a 200 km climate model's land temperature and precipitation pattern errors by 6-25%.","significance":5,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-022-04242-x","title":"Forecasting seasonal to sub-seasonal rainfall in Great Britain using convolutional-neural networks","authors":["Andrew Paul Barnes","Nick McCullen","Thomas Kjeldsen"],"date":"2022-11-19","year":2022,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-022-04242-x","openalex":"W4309582575"},"links":{"paper":"https://doi.org/10.1007/s00704-022-04242-x","pdf":"https://link.springer.com/content/pdf/10.1007/s00704-022-04242-x.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"CNN using ECMWF SEAS5 pressure and temperature forecasts beats the raw ECMWF output for monthly regional rainfall in Great Britain at 1 to 6 month leads.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.10774","title":"Emulating Fast Processes in Climate Models","authors":["Noah D. Brenowitz","W. Andre Perkins","Jacqueline M. Nugent","Oliver Watt-Meyer","Spencer K. Clark","Anna Kwa","Brian Henn","Jeremy McGibbon","Christopher S. Bretherton"],"date":"2022-11-19","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.10774","openalex":"W4309798989"},"links":{"paper":"https://arxiv.org/abs/2211.10774","pdf":"https://arxiv.org/pdf/2211.10774"},"orgs":["ai2"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"First neural emulator of a full cloud microphysics parameterization, including fast phase changes, performs well offline and online but shows Antarctic biases.","significance":4,"cited_by":12,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1142-s0219649222500939","title":"A Wide Scale Survey on Weather Prediction Using Machine Learning Techniques","authors":["Shabnam Kumari","P. Muthulakshmi"],"date":"2022-11-18","year":2022,"venue":"Journal of Information & Knowledge Management","venue_type":"journal","ids":{"doi":"10.1142/s0219649222500939","openalex":"W4309386169"},"links":{"paper":"https://doi.org/10.1142/s0219649222500939"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Survey of machine learning methods for rainfall and weather prediction, arguing that reported accuracy often fails when applied at large scale.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1073-pnas.2209431119","title":"Internal variability and forcing influence model–satellite differences in the rate of tropical tropospheric warming","authors":["Stephen Po–Chedley","John Fasullo","Nicholas Siler","Zachary Michael Labe","Elizabeth A. Barnes","C. Bonfils","Benjamin David Santer"],"date":"2022-11-18","year":2022,"venue":"Proceedings of the National Academy of Sciences","venue_type":"journal","ids":{"doi":"10.1073/pnas.2209431119","openalex":"W4309662170"},"links":{"paper":"https://doi.org/10.1073/pnas.2209431119"},"orgs":["ncar","ucla","colorado-state-university"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip","satellite"],"status":"research","summary":"A machine learning framework trained on climate models attributes tropical tropospheric warming: forcing adds 0.25 K/decade, internal variability offsets 0.07, and an aerosol bias adds 0.04.","significance":4,"cited_by":34,"score":71,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.eswa.2022.119270","title":"DWFH: An improved data-driven deep weather forecasting hybrid model using Transductive Long Short Term Memory (T-LSTM)","authors":["K. Venkatachalam","Pavel Trojovský","Dragan Stevan Pamucar","Nebojša Bačanin","Vladimir Šimić"],"date":"2022-11-18","year":2022,"venue":"Expert Systems with Applications","venue_type":"journal","ids":{"doi":"10.1016/j.eswa.2022.119270","openalex":"W4309694784"},"links":{"paper":"https://doi.org/10.1016/j.eswa.2022.119270"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"DWFH hybrid uses transductive LSTM for deep weather forecasting; abstract missing, so classification relies on the title alone.","significance":2,"cited_by":80,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.10381","title":"Environmental Sensor Placement with Convolutional Gaussian Neural Processes","authors":["Tom R. Andersson","Wessel P. Bruinsma","Stratis Markou","James Requeima","Alejandro Coca-Castro","Anna Vaughan","Anna-Louise Ellis","Matthew A. Lazzara","Dani Jones","J. Scott Hosking","Richard E. Turner"],"date":"2022-11-18","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.10381"},"links":{"paper":"https://arxiv.org/abs/2211.10381","pdf":"https://arxiv.org/pdf/2211.10381"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Convolutional Gaussian neural processes outperform non-stationary GPs for Antarctic air-temperature sensor placement, giving more informative station siting in a simulated experiment.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.10378","title":"Comparing Explanation Methods for Traditional Machine Learning Models Part 2: Quantifying Model Explainability Faithfulness and Improvements with Dimensionality Reduction","authors":["Montgomery Flora","Corey Potvin","Amy McGovern","Shawn Handler"],"date":"2022-11-18","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.10378"},"links":{"paper":"https://arxiv.org/abs/2211.10378","pdf":"https://arxiv.org/pdf/2211.10378"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Tests explanation faithfulness on weather ML models, showing that reducing correlated features shrinks ranking uncertainty 2-10x and favors permutation importance.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.47760-cognizance.2022.v02i11.002","title":"Bayesian Network for Predicting Dustfall in Iraq","authors":["Ali Fahem Neamah","Mohammed Ibrahim Mahdi"],"date":"2022-11-17","year":2022,"venue":"Cognizance Journal of Multidisciplinary Studies","venue_type":"journal","ids":{"doi":"10.47760/cognizance.2022.v02i11.002","openalex":"W4309237903"},"links":{"paper":"https://doi.org/10.47760/cognizance.2022.v02i11.002","pdf":"https://doi.org/10.47760/cognizance.2022.v02i11.002"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Bayesian network predicts monthly maximum and minimum dustfall in Iraq from station weather data, reporting 75% and 89% precision.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su142215260","title":"Solar Irradiance Probabilistic Forecasting Using Machine Learning, Metaheuristic Models and Numerical Weather Predictions","authors":["Vateanui Sansine","Pascal Ortéga","Daniel Hissel","Marania Hopuare"],"date":"2022-11-17","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su142215260","openalex":"W4309460910"},"links":{"paper":"https://doi.org/10.3390/su142215260","pdf":"https://www.mdpi.com/2071-1050/14/22/15260/pdf?version=1668678835"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml","rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"PSO-tuned LSTM hybrids using AROME NWP inputs give the best day-ahead probabilistic solar irradiance forecasts for a Tahiti microgrid.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.09741","title":"Learning 4DVAR inversion directly from observations","authors":["Arthur Filoche","Julien Brajard","Anastase Charantonis","Dominique Béréziat"],"date":"2022-11-17","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.09741"},"links":{"paper":"https://arxiv.org/abs/2211.09741","pdf":"https://arxiv.org/pdf/2211.09741"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["physics-constrained","differentiable"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Hybrid network learns 4DVAR-style inversion directly from partial, noisy observations, using the variational mechanistic constraint for regularization and reduced computation.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su142215191","title":"Development of the Indian Future Weather File Generator Based on Representative Concentration Pathways","authors":["Naga Venkata Sai Kumar Manapragada","Anoop Kumar Shukla","Gloria Pignatta","Komali Yenneti","Deepika Shetty","Bibhu Kalyan Nayak","Venkataramana Boorla"],"date":"2022-11-16","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su142215191","openalex":"W4309604208"},"links":{"paper":"https://doi.org/10.3390/su142215191","pdf":"https://www.mdpi.com/2071-1050/14/22/15191/pdf?version=1669259260"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Generates future weather files for India from CanESM2 using spatial and temporal downscaling plus ML bias correction across three RCP scenarios and five future years.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14225775","title":"Reconstruction of Near-Surface Air Temperature over the Greenland Ice Sheet Based on MODIS Data and Machine Learning Approaches","authors":["Jiahang Che","Minghu Ding","Qinglin Zhang","Yetang Wang","Weijun Sun","Yuzhe Wang","Lei Wang","Baojuan Huai"],"date":"2022-11-16","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14225775","openalex":"W4309310009"},"links":{"paper":"https://doi.org/10.3390/rs14225775","pdf":"https://www.mdpi.com/2072-4292/14/22/5775/pdf?version=1668655686"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Neural networks reconstruct daily and monthly 780 m Greenland Ice Sheet air temperature from MODIS land surface temperature, reaching R of 0.96 against automatic weather stations.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-jpeodx.pveng-1192","title":"An Ensemble Deep Learning Model for Short-Term Road Surface Temperature Prediction","authors":["Bingyou Dai","Wenchen Yang","Xiaofeng Ji","Feng Zhu","Rui Fang","Linyi Zhou"],"date":"2022-11-16","year":2022,"venue":"Journal of Transportation Engineering Part B Pavements","venue_type":"journal","ids":{"doi":"10.1061/jpeodx.pveng-1192","openalex":"W4309336610"},"links":{"paper":"https://doi.org/10.1061/jpeodx.pveng-1192"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Ensemble GRU-LSTM model predicts road surface temperature 1 to 6 hours ahead from station data, lowering MAE versus CNN-LSTM and SVR baselines.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10512862.1","title":"Climate Adaptation in 2021: How Machine Learning and Earth Observation are Key to Extreme Event Resilience","authors":["Thomas Y. Chen","Luca Marini"],"date":"2022-11-16","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10512862.1","openalex":"W7140300192"},"links":{"paper":"https://doi.org/10.1002/essoar.10512862.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10512862.1"},"orgs":["columbia-leap"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Reviews 2021 extreme events and barriers to deploying ML models on Earth observation imagery for disaster damage detection, highlighting InSAR as a tool.","significance":2,"cited_by":0,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.08943","title":"Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement","authors":["Montgomery Flora","Corey Potvin","Amy McGovern","Shawn Handler"],"date":"2022-11-16","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.08943","openalex":"W4320813917"},"links":{"paper":"https://arxiv.org/abs/2211.08943","pdf":"https://arxiv.org/pdf/2211.08943"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Compares explanation methods on severe-weather and road-surface-temperature models, finding top-10 feature sets agree on about six features, and releases scikit-explain.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.29244-jpsl.12.4.587-598","title":"An Application of Deep Learning Technique to Improve Subseasonal to Seasonal Rainfall Forecast over Java Island, Indonesia","authors":["Adyaksa Budi Raharja","Akhmad Faqih","Amsari Mudzakir Setiawan"],"date":"2022-11-15","year":2022,"venue":"Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management)","venue_type":"journal","ids":{"doi":"10.29244/jpsl.12.4.587-598","openalex":"W4310290443"},"links":{"paper":"https://doi.org/10.29244/jpsl.12.4.587-598"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Convolutional autoencoder bias-corrects seven SubX S2S rainfall forecasts over Java, raising weekly correlations (e.g. 0.76 to 0.81) and CRPSS by 20–30%.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.08160","title":"Spatiotemporal modeling of European paleoclimate using doubly sparse Gaussian processes","authors":["Seth D. Axen","Alexandra Gessner","Christian Sommer","Nils Weitzel","Álvaro Tejero-Cantero"],"date":"2022-11-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.08160"},"links":{"paper":"https://arxiv.org/abs/2211.08160","pdf":"https://arxiv.org/pdf/2211.08160"},"orgs":[],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Doubly sparse spatiotemporal Gaussian process builds a probabilistic European climate-field reconstruction from the Last Glacial Maximum to mid-Holocene, combining simulations with pollen proxies.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s22228790","title":"Design of a Forest Fire Early Alert System through a Deep 3D-CNN Structure and a WRF-CNN Bias Correction","authors":["Alejandro Casallas","Camila Jiménez-Saenz","Victor Torres","Miguel Quirama-Aguilar","Augusto Lizcano","Ellie Anne López-Barrera","Camilo Ferro","Nathalia Celis","Ricardo Arenas"],"date":"2022-11-14","year":2022,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s22228790","openalex":"W4309212885"},"links":{"paper":"https://doi.org/10.3390/s22228790","pdf":"https://www.mdpi.com/1424-8220/22/22/8790/pdf?version=1669094374"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["regional","local"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Early wildfire alert system combining a 3D CNN on satellite data and a CNN bias correction of WRF, feeding a Fire Weather Index for Colombian regions.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2022.10.062","title":"An archived dataset from the ECMWF Ensemble Prediction System for probabilistic solar power forecasting","authors":["Wenting Wang","Dazhi Yang","Tao Hong","Jan P. Kleissl"],"date":"2022-11-14","year":2022,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2022.10.062","openalex":"W4309030289"},"links":{"paper":"https://doi.org/10.1016/j.solener.2022.10.062"},"orgs":[],"topic":"benchmarks-data-eval","topics":["post-processing"],"type":"benchmark","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Archived ECMWF ensemble dataset for 2017 to 2020 over Europe and North America supports probabilistic solar forecasting, with calibration and ML-versus-physics case studies.","significance":3,"cited_by":70,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-20964471.2022.2140868","title":"Generating high-resolution climatological precipitation data using SinGAN","authors":["Yang Wang","Hassan A. Karimi"],"date":"2022-11-13","year":2022,"venue":"Big Earth Data","venue_type":"journal","ids":{"doi":"10.1080/20964471.2022.2140868","openalex":"W4309012457"},"links":{"paper":"https://doi.org/10.1080/20964471.2022.2140868"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A single-image GAN with a weighted patchGAN discriminator generates high-resolution precipitation from one low-resolution sample, improving detail in extreme-value regions.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.cageo.2022.105268","title":"Cross-track infrared sounder cloud fraction retrieval using a deep neural network","authors":["Qian Liu","Hui Xu","Paul R. Houser","Donglian Sun","Matthew T. Rice","Likun Wang","Daniel Q. Duffy","Chaowei Phil Yang"],"date":"2022-11-12","year":2022,"venue":"Computers & Geosciences","venue_type":"journal","ids":{"doi":"10.1016/j.cageo.2022.105268","openalex":"W4309342246"},"links":{"paper":"https://doi.org/10.1016/j.cageo.2022.105268"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Deep neural network retrieves cloud fraction from CrIS infrared sounder observations; abstract unavailable, so scope is inferred from the title.","significance":2,"cited_by":3,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-15-6489-2022","title":"Retrieval of ice water path from the Microwave Humidity Sounder (MWHS) aboard FengYun-3B (FY-3B) satellite polarimetric measurements based on a deep neural network","authors":["Wenyu Wang","Zhenzhan Wang","Qiurui He","Lanjie Zhang"],"date":"2022-11-11","year":2022,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-15-6489-2022","openalex":"W4309181214"},"links":{"paper":"https://doi.org/10.5194/amt-15-6489-2022","pdf":"https://amt.copernicus.org/articles/15/6489/2022/amt-15-6489-2022.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Deep neural networks retrieve global ice water path from FY-3B MWHS microwave sounder, with a cloud filter; accuracy is good above 100 g/m2 and tested on tropical cyclones.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-15435075.2022.2143272","title":"An integrated framework of robust local mean decomposition and bidirectional long short-term memory to forecast solar irradiance","authors":["Pardeep Singla","Manoj Duhan","Sumit Saroha"],"date":"2022-11-11","year":2022,"venue":"International Journal of Green Energy","venue_type":"journal","ids":{"doi":"10.1080/15435075.2022.2143272","openalex":"W4308919474"},"links":{"paper":"https://doi.org/10.1080/15435075.2022.2143272"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn","other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"RLMD-BiLSTM hybrid forecasts solar irradiance at two Indian sites, cutting RMSE by 59–89% against benchmark models; the study is station-based and regional.","significance":2,"cited_by":40,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-022-04274-3","title":"Machine learning-based downscaling: application of multi-gene genetic programming for downscaling daily temperature at Dogonbadan, Iran, under CMIP6 scenarios","authors":["Majid Niazkar","Mohammad Reza Goodarzi","Atiyeh Fatehifar","Mohammad Javad Abedi"],"date":"2022-11-11","year":2022,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-022-04274-3","openalex":"W4308846880"},"links":{"paper":"https://doi.org/10.1007/s00704-022-04274-3"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Multi-gene genetic programming downscales daily temperature at Dogonbadan, Iran, under CMIP6 scenarios, producing local projections from global climate models.","significance":2,"cited_by":48,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.06233","title":"Comparison of Uncertainty Quantification with Deep Learning in Time Series Regression","authors":["Levente Foldesi","Matias Valdenegro-Toro"],"date":"2022-11-11","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.06233"},"links":{"paper":"https://arxiv.org/abs/2211.06233","pdf":"https://arxiv.org/pdf/2211.06233"},"orgs":[],"topic":"xai-uq-physics","topics":["local-forecasting"],"type":"evaluation","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares uncertainty estimation methods for deep learning forecasts of meteorological time series, testing whether predicted uncertainty behaves as expected across horizons.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.07555","title":"Contrastive Learning for Climate Model Bias Correction and Super-Resolution","authors":["Tristan Ballard","Gopal Erinjippurath"],"date":"2022-11-10","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.07555"},"links":{"paper":"https://arxiv.org/abs/2211.07555","pdf":"https://arxiv.org/pdf/2211.07555"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Contrastive-learning GAN performs super-resolution and bias correction of CMIP6 daily precipitation and temperature, reaching double NEX-GDDP resolution with comparable or better bias reduction.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2022.128706","title":"Dynamic-LSTM hybrid models to improve seasonal drought predictions over China","authors":["Zhiyong Wu","Hao Yin","Hai He","Yuan Li"],"date":"2022-11-09","year":2022,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2022.128706","openalex":"W4308601244"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2022.128706"},"orgs":[],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Hybrid dynamic model and LSTM aim to improve seasonal drought prediction over China; the abstract is missing, so scope is inferred from the title.","significance":3,"cited_by":65,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-022-04201-6","title":"Transformer for sub-seasonal extreme high temperature probabilistic forecasting over eastern China","authors":["Wei Jin","Wei Zhang","Jie Hu","Jiazhen Chen","Bin Weng","Jianyun Gao","Tianqiang Huang"],"date":"2022-11-09","year":2022,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-022-04201-6","openalex":"W4308752201"},"links":{"paper":"https://doi.org/10.1007/s00704-022-04201-6","pdf":"https://www.researchsquare.com/article/rs-1230879/latest.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["transformer"],"timescale":["s2s"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Transformer produces probabilistic sub-seasonal forecasts of extreme high temperatures over eastern China; abstract unavailable, so scope is inferred from the title.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.wace.2022.100525","title":"High-resolution downscaling with interpretable deep learning: Rainfall extremes over New Zealand","authors":["Neelesh Rampal","Peter B. Gibson","Abha Sood","Stephen J. Stuart","Nicolas Fauchereau","Chris Brandolino","Ben Noll","Tristan Meyers"],"date":"2022-11-08","year":2022,"venue":"Weather and Climate Extremes","venue_type":"journal","ids":{"doi":"10.1016/j.wace.2022.100525","openalex":"W4308540792"},"links":{"paper":"https://doi.org/10.1016/j.wace.2022.100525","pdf":"https://www.sciencedirect.com/science/article/pii/S2212094722001049/pdf"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"A simple CNN with tailored loss functions outperforms regression for downscaling New Zealand rainfall, raising wet-day explained variance from 0.35 to 0.52.","significance":4,"cited_by":114,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.04392","title":"Reduced Order Probabilistic Emulation for Physics-Based Thermosphere Models","authors":["Richard J. Licata","Piyush M. Mehta"],"date":"2022-11-08","year":2022,"venue":"Space Weather","venue_type":"journal","ids":{"arxiv":"2211.04392","doi":"10.1029/2022sw003345","openalex":"W4378212485"},"links":{"paper":"https://doi.org/10.1029/2022sw003345","pdf":"https://arxiv.org/pdf/2211.04392"},"orgs":[],"topic":"climate-emulation","topics":["extremes-hazards"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Builds a PCA plus LSTM probabilistic surrogate for the TIE-GCM thermosphere model, giving density distributions with under 5 km satellite position bias in the 2003 storm.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.03925","title":"AutoML-based Almond Yield Prediction and Projection in California","authors":["Shiheng Duan","Shuaiqi Wu","Erwan Monier","Paul Ullrich"],"date":"2022-11-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.03925","openalex":"W4308669613"},"links":{"paper":"https://arxiv.org/abs/2211.03925","pdf":"https://arxiv.org/pdf/2211.03925"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"AutoML models link climate to California almond yields and project yield changes using 17 downscaled climate models under two climate scenarios.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12559-022-10070-y","title":"Hybrid Convolutional Neural Network-Multilayer Perceptron Model for Solar Radiation Prediction","authors":["Sujan Ghimire","Thong Nguyen‐Huy","Ramendra Prasad","Ravinesh Chand Deo","David Casillas-Pérez","Sancho Salcedo‐Sanz","Binayak Bhandari"],"date":"2022-11-07","year":2022,"venue":"Cognitive Computation","venue_type":"journal","ids":{"doi":"10.1007/s12559-022-10070-y","openalex":"W4309323351"},"links":{"paper":"https://doi.org/10.1007/s12559-022-10070-y"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid CNN-MLP model predicts solar radiation for solar energy; the abstract is missing, so the contribution is inferred from the title only.","significance":2,"cited_by":81,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su142114577","title":"Comparison of CLDAS and Machine Learning Models for Reference Evapotranspiration Estimation under Limited Meteorological Data","authors":["Long Qian","Lifeng Wu","Xiaogang Liu","Yaokui Cui","Yongwen Wang"],"date":"2022-11-06","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su142114577","openalex":"W4308392015"},"links":{"paper":"https://doi.org/10.3390/su142114577","pdf":"https://www.mdpi.com/2071-1050/14/21/14577/pdf?version=1667875784"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Simplified machine learning and CLDAS-based estimates of reference evapotranspiration across China perform well when station meteorological inputs are missing.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7909","title":"Identification of tropical cyclone centre based on satellite images via deep learning techniques","authors":["Teng Long","Jiyang Fu","Biao Tong","Pak Wai Chan","Yuncheng He"],"date":"2022-11-04","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7909","openalex":"W4308338323"},"links":{"paper":"https://doi.org/10.1002/joc.7909"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"YOLOv4 locates tropical cyclone centres in satellite cloud images with over 99% confidence, the best of six deep learning models tested.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.02768","title":"Quantitative Assessment of Drought Impacts Using XGBoost based on the Drought Impact Reporter","authors":["Beichen Zhang","Fatima K. Abu Salem","Michael J. Hayes","Tsegaye Tadesse"],"date":"2022-11-04","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.02768"},"links":{"paper":"https://arxiv.org/abs/2211.02768","pdf":"https://arxiv.org/pdf/2211.02768"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"XGBoost with SHAP links SPI drought indices to text-based drought impacts in Texas across agriculture, fire, and public health categories.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-hess-2022-348","title":"Machine Learning and Committee Models for Improving ECMWF Subseasonal to Seasonal (S2S) Precipitation Forecast","authors":["Mohamed Elneel Elshaikh Eltayeb Elbasheer","Gerald Corzo","DIMITRI P. SOLOMATINE","Emmanouil Α. Varouchakis"],"date":"2022-11-03","year":2022,"venue_type":"other","ids":{"doi":"10.5194/hess-2022-348","openalex":"W4307995081"},"links":{"paper":"https://doi.org/10.5194/hess-2022-348"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml","rnn"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Machine learning classifiers and committee models correct ECMWF S2S precipitation category forecasts over three regions, improving on the raw ECMWF baseline.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.02556","title":"Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast","authors":["Kaifeng Bi","Lingxi Xie","Hengheng Zhang","Xin Chen","Xiaotao Gu","Qi Tian"],"date":"2022-11-03","year":2022,"venue":"Nature","venue_type":"journal","ids":{"arxiv":"2211.02556","doi":"10.1038/s41586-023-06185-3","openalex":"W4383218913"},"links":{"paper":"https://arxiv.org/abs/2211.02556","pdf":"https://arxiv.org/pdf/2211.02556"},"orgs":["huawei"],"topic":"global-medium-range","topics":["probabilistic-ensembles"],"type":"model","method":["transformer"],"timescale":["short","medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"3D Earth-Specific Transformer trained on ERA5 is the first AI model to beat IFS across variables and lead times from 1 hour to one week.","significance":9,"cited_by":1651,"score":100,"highlight":true,"highlight_reason":"Pangu-Weather in Nature: the first AI model reported to beat IFS HRES deterministically across variables and lead times, a landmark for the field.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2211.02108","title":"Sky-image-based solar forecasting using deep learning with multi-location data: training models locally, globally or via transfer learning?","authors":["Yuhao Nie","Quentin Paletta","Andea Scott","Luis Martin Pomares","Guillaume Arbod","Sgouris Sgouridis","Joan Lasenby","Adam Brandt"],"date":"2022-11-03","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.02108"},"links":{"paper":"https://arxiv.org/abs/2211.02108","pdf":"https://arxiv.org/pdf/2211.02108"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Compares local, global and transfer-learning strategies for deep learning solar forecasting from sky images across three heterogeneous datasets; transfer needs 80% less data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.01629","title":"Image-based Early Detection System for Wildfires","authors":["Omkar Ranadive","Jisu Kim","Serin Lee","Youngseo Cha","Heechan Park","Minkook Cho","Young K. Hwang"],"date":"2022-11-03","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.01629"},"links":{"paper":"https://arxiv.org/abs/2211.01629","pdf":"https://arxiv.org/pdf/2211.01629"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"operational","summary":"Deployed camera-based system detects wildfire smoke with a high true-detection rate and alerts faster than human observers.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.01613","title":"Understanding Extreme Precipitation Changes through Unsupervised Machine Learning","authors":["Griffin Mooers","Tom Beucler","Mike Pritchard","Stephan Mandt"],"date":"2022-11-03","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.01613","openalex":"W4308243422"},"links":{"paper":"https://arxiv.org/abs/2211.01613","pdf":"https://arxiv.org/pdf/2211.01613"},"orgs":["nvidia"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","km-scale-sim"],"status":"research","summary":"Unsupervised clustering of storm-scale climate model output shows extreme precipitation changes driven mainly by shifts in storm regimes rather than precipitation efficiency.","significance":4,"cited_by":1,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.energy.2022.125893","title":"Intelligent estimation of wind farm performance with direct and indirect ‘point’ forecasting approaches integrating several NWP models","authors":["Ghali Yakoub","Sathyajith Mathew","J. B. Leal"],"date":"2022-11-02","year":2022,"venue":"Energy","venue_type":"journal","ids":{"doi":"10.1016/j.energy.2022.125893","openalex":"W4307923426"},"links":{"paper":"https://doi.org/10.1016/j.energy.2022.125893"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Genetic-programming AutoML wind power forecasts combining three NWP sources cut errors by 8–22% at a Norwegian wind farm using direct and indirect turbine-level schemes.","significance":3,"cited_by":58,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2022.106500","title":"A study on loss function against data imbalance in deep learning correction of precipitation forecasts","authors":["Xiaoxiong You","Zhaoming Liang","Ya-qiang Wang","Hui Zhang"],"date":"2022-11-02","year":2022,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2022.106500","openalex":"W4308112140"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2022.106500"},"orgs":["cma"],"topic":"post-processing","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Study of loss functions to counter class imbalance when deep learning corrects precipitation forecasts; abstract unavailable, so based on title only.","significance":2,"cited_by":40,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10291-022-01357-6","title":"Precipitable water vapor fusion of MODIS and ERA5 based on convolutional neural network","authors":["Cuixian Lu","Yushan Zhang","Yuxin Zheng","Zhilu Wu","Qiuyi Wang"],"date":"2022-11-02","year":2022,"venue":"GPS Solutions","venue_type":"journal","ids":{"doi":"10.1007/s10291-022-01357-6","openalex":"W4308112396"},"links":{"paper":"https://doi.org/10.1007/s10291-022-01357-6"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"CNN fuses MODIS and ERA5 to estimate precipitable water vapour; abstract unavailable, so scope is inferred from the title.","significance":2,"cited_by":50,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.01001","title":"Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model","authors":["Jussi Leinonen","Ulrich Hamann","Ioannis V. Sideris","Urs Germann"],"date":"2022-11-02","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"arxiv":"2211.01001","doi":"10.1029/2022gl101626","openalex":"W4327734664"},"links":{"paper":"https://doi.org/10.1029/2022gl101626","pdf":"https://arxiv.org/pdf/2211.01001"},"orgs":["meteoswiss"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite","nwp-analysis","other"],"status":"research","summary":"Deep learning fuses radar, lightning, satellite, NWP and terrain data to probabilistically nowcast lightning, hail and heavy rain at 1 km and 5 min up to 60 min.","significance":4,"cited_by":53,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.00860","title":"Insight into cloud processes from unsupervised classification with a rotationally invariant autoencoder","authors":["Takuya Kurihana","James Franke","Ian Foster","Ziwei Wang","Elisabeth Moyer"],"date":"2022-11-02","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.00860"},"links":{"paper":"https://arxiv.org/abs/2211.00860","pdf":"https://arxiv.org/pdf/2211.00860"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Rotation-invariant autoencoder clusters 22 years of MODIS imagery into 42 AI-generated cloud classes (AICCA), revealing cloud-type trends linked to stratocumulus decline.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-egusphere-2022-1024","title":"TIMBER v0.1: a conceptual framework for emulating temperature responses to tree cover change","authors":["Shruti Nath","Lukas Gudmundsson","Jonas Schwaab","Grégory Duveiller","Steven Johan De Hertog","Suqi Guo","Felix Havermann","Fei Luo","Iris Manola","Julia Pongratz","Sonia Isabelle Seneviratne","Carl‐Friedrich Schleussner","Wim Thiery","Quentin Lejeune"],"date":"2022-11-01","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/egusphere-2022-1024","openalex":"W4307854381"},"links":{"paper":"https://doi.org/10.5194/gmd-16-4283-2023"},"orgs":["eth-zurich","knmi","mpi-biogeochemistry","mpi-meteorology"],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global","local"],"data":["cmip"],"status":"research","summary":"A statistical GAM emulator predicts local surface temperature responses to tree cover change from ESM output, offering a cheap complement to greenhouse-gas emulators.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jphotov.2022.3215890","title":"Cloud Segmentation and Motion Tracking in Sky Images","authors":["Benjamin G. Pierce","Joshua S. Stein","Jennifer L. Braid","Daniel Riley"],"date":"2022-11-01","year":2022,"venue":"IEEE Journal of Photovoltaics","venue_type":"journal","ids":{"doi":"10.1109/jphotov.2022.3215890","openalex":"W4310789942"},"links":{"paper":"https://doi.org/10.1109/jphotov.2022.3215890"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"A convolutional autoencoder segments clouds in sky images above 90% pixel accuracy, and particle tracking predicts cloud motion for short-term PV power.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022rs007483","title":"Prediction of Atmospheric Noise Temperature at the Deep Space Network With Machine Learning","authors":["Longtao Wu","David D. Morabito","Joaquim Teixeira","Lei Huang","Hai Nguyen","Hui Su","Melissa A. Soriano","Lei Pan","Daniel S. Kahan","Rohini Lakshman Bhawar"],"date":"2022-11-01","year":2022,"venue":"Radio Science","venue_type":"journal","ids":{"doi":"10.1029/2022rs007483","openalex":"W4307836689"},"links":{"paper":"https://doi.org/10.1029/2022rs007483","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022RS007483"},"orgs":["nasa","caltech","ucla"],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Random forest trained on GFS forecasts and radiometer data predicts zenith atmospheric noise temperature at NASA Deep Space Network sites, enabling up to 2.43 dB downlink gain.","significance":2,"cited_by":1,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10512277.2","title":"Bias correction of modelled urban temperatures with crowd-sourced weather data","authors":["Oscar Brousse","Charles H. Simpson","Owain A. Kenway","Alberto Martilli","E. Scott Krayenhoff","Andrea Zonato","Clare Heaviside"],"date":"2022-11-01","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10512277.2","openalex":"W4307852306"},"links":{"paper":"https://doi.org/10.1002/essoar.10512277.2","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10512277.2"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Crowd-sourced personal weather station data reveal a spatially varying WRF cool bias over London; a machine-learning per-cell bias correction improves daily min, mean and max temperatures.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.00534","title":"Deep Learning for Global Wildfire Forecasting","authors":["Ioannis Prapas","Akanksha Ahuja","Spyros Kondylatos","Ilektra Karasante","Eleanna Panagiotou","Lazaro Alonso","Charalampos Davalas","Dimitrios Michail","Nuno Carvalhais","Ioannis Papoutsis"],"date":"2022-11-01","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.00534","openalex":"W4308023001"},"links":{"paper":"https://arxiv.org/abs/2211.00534","pdf":"https://arxiv.org/pdf/2211.00534"},"orgs":["mpi-biogeochemistry"],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"Global open datacube and segmentation deep learning model predicting burned areas 8 to 64 days ahead using climate and fire-driver variables.","significance":4,"cited_by":8,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2151-jmsj.2023-005","title":"A Machine Learning Approach to the Observation Operator for Satellite Radiance Data Assimilation","authors":["Jianyu Liang","Koji Terasaki","Takemasa Miyoshi"],"date":"2022-10-31","year":2022,"venue":"Journal of the Meteorological Society of Japan Ser II","venue_type":"journal","ids":{"doi":"10.2151/jmsj.2023-005","openalex":"W4307877913"},"links":{"paper":"https://doi.org/10.2151/jmsj.2023-005","pdf":"https://www.jstage.jst.go.jp/article/jmsj/101/1/101_2023-005/_pdf"},"orgs":[],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Machine learning replaces the radiative transfer observation operator for AMSU-A radiance assimilation in NICAM-LETKF, performing near RTTOV but slightly worse with simpler bias handling.","significance":4,"cited_by":23,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.16746","title":"Deep learning for quality control of surface physiographic fields using satellite Earth observations","authors":["Tom Kimpson","Margarita Choulga","Matthew Chantry","Gianpaolo Balsamo","Souhail Boussetta","Peter Dueben","Tim Palmer"],"date":"2022-10-30","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.16746","doi":"10.5194/egusphere-2022-1177"},"links":{"paper":"https://arxiv.org/abs/2210.16746","pdf":"https://arxiv.org/pdf/2210.16746"},"orgs":[],"topic":"benchmarks-data-eval","topics":["observations-remote-sensing"],"type":"evaluation","method":["other"],"timescale":[],"spatial":["global"],"data":["era5","satellite"],"status":"research","summary":"A neural network trained on ERA5 and MODIS skin temperature quality-checks IFS physiographic upgrades, improving land-surface temperature prediction by 0.37 K for updated lakes.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.9798-kosham.2022.22.5.33","title":"Projection of Flight Cancellations and Economic Losses Caused by Future Climate Change","authors":["Hoyong Lee","Kyunghun Kim","Jong Gu Hwang-Bo","Soojun Kim"],"date":"2022-10-28","year":2022,"venue":"Korean Society of Hazard Mitigation","venue_type":"journal","ids":{"doi":"10.9798/kosham.2022.22.5.33","openalex":"W4307435162"},"links":{"paper":"https://doi.org/10.9798/kosham.2022.22.5.33","pdf":"http://www.j-kosham.or.kr/upload/pdf/KOSHAM-2022-22-5-33.pdf"},"orgs":[],"topic":"applications-impacts","topics":["downscaling"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Applies machine learning and nearest-neighbour with genetic algorithms to downscale SSP projections, estimating flight cancellations and losses rising up to 8.29 times by 2100.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.7261530","title":"Software for \"Using Neural Networks to Predict Hurricane Storm Surge and to Assess the Sensitivity of Surge to Storm Characteristics\"","authors":["Joseph W. Lockwood"],"date":"2022-10-28","year":2022,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.5281/zenodo.7261530","openalex":"W4307484986"},"links":{"paper":"https://doi.org/10.1029/2022jd037617"},"orgs":["princeton-university"],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Software accompanying a study that uses neural networks to predict hurricane storm surge and assess its sensitivity to storm characteristics.","significance":2,"cited_by":38,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-forecast4040046","title":"Coupling a Neural Network with a Spatial Downscaling Procedure to Improve Probabilistic Nowcast for Urban Rain Radars","authors":["Marino Marrocu","Luca Massidda"],"date":"2022-10-28","year":2022,"venue":"Forecasting","venue_type":"journal","ids":{"doi":"10.3390/forecast4040046","openalex":"W4307939221"},"links":{"paper":"https://doi.org/10.3390/forecast4040046","pdf":"https://www.mdpi.com/2571-9394/4/4/46/pdf?version=1667213960"},"orgs":[],"topic":"nowcasting","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"Adds a stochastic noise generation step to a deep network for ensemble urban radar rainfall nowcasts, matching optical flow skill over a full year at 5-minute resolution.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-22-0166.1","title":"A Deep Learning Model for Estimating Tropical Cyclone Wind Radius from Geostationary Satellite Infrared Imagery","authors":["Chong Wang","Xiaofeng Li"],"date":"2022-10-28","year":2022,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-22-0166.1","openalex":"W4307714586"},"links":{"paper":"https://doi.org/10.1175/mwr-d-22-0166.1"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Deep learning estimates 34, 50 and 64-kt tropical cyclone wind radii in four quadrants from geostationary IR images, cutting errors 12-36% over prior methods.","significance":4,"cited_by":23,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.16382","title":"The Hurricane Track Fit Consensus Model for Improving Hurricane Forecasting","authors":["Nathan Ginis","Timothy Marchok"],"date":"2022-10-28","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.16382"},"links":{"paper":"https://arxiv.org/abs/2210.16382","pdf":"https://arxiv.org/pdf/2210.16382"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"pre-operational","summary":"HFIT statistically fits NWP track forecasts per lead hour, cutting 2014–2021 Atlantic hurricane track errors 8% at 24 h versus the NHC official forecast.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tia.2022.3217099","title":"Deterministic and Probabilistic Wind Power Forecasts by Considering Various Atmospheric Models and Feature Engineering Approaches","authors":["Yuan‐Kang Wu","Cheng‐Liang Huang","Shenghong Wu","Jing‐Shan Hong","Hui-Ling Chang"],"date":"2022-10-27","year":2022,"venue":"IEEE Transactions on Industry Applications","venue_type":"journal","ids":{"doi":"10.1109/tia.2022.3217099","openalex":"W4312470194"},"links":{"paper":"https://doi.org/10.1109/tia.2022.3217099"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["rnn","classical-ml"],"timescale":["short","medium"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Combines CWB WRF-based NWP wind speeds with PCA/EMD preprocessing and XGBoost for wind power forecasts, reaching 5.43% NRMSE at one hour ahead.","significance":3,"cited_by":51,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003245","title":"Calibration and Uncertainty Quantification of a Gravity Wave Parameterization: A Case Study of the Quasi‐Biennial Oscillation in an Intermediate Complexity Climate Model","authors":["Laura Mansfield","Aditi Sheshadri"],"date":"2022-10-27","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003245","openalex":"W4307645834"},"links":{"paper":"https://doi.org/10.1029/2022ms003245","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003245"},"orgs":["stanford"],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Calibrate-emulate-sample with a Gaussian process emulator quantifies gravity wave parameterization uncertainty, showing QBO parametric uncertainty comparable to internal variability under 2xCO2.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10618-022-00877-6","title":"ConvMOS: climate model output statistics with deep learning","authors":["Michael Steininger","Daniel Abel","Katrin Ziegler","Anna Krause","Heiko Paeth","Andreas Hotho A"],"date":"2022-10-27","year":2022,"venue":"Data Mining and Knowledge Discovery","venue_type":"journal","ids":{"doi":"10.1007/s10618-022-00877-6","openalex":"W4307412617"},"links":{"paper":"https://doi.org/10.1007/s10618-022-00877-6","pdf":"https://link.springer.com/content/pdf/10.1007/s10618-022-00877-6.pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"ConvMOS, a convolutional bias-correction model for REMO precipitation with per-location and global parameters, reduces errors and better captures extreme precipitation.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14215355","title":"Integration of Satellite-Derived and Ground-Based Soil Moisture Observations for a Precipitation Product over the Upper Heihe River Basin, China","authors":["Ying Zhang","Jinliang Hou","Chunlin Huang"],"date":"2022-10-26","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14215355","openalex":"W4308173656"},"links":{"paper":"https://doi.org/10.3390/rs14215355","pdf":"https://www.mdpi.com/2072-4292/14/21/5355/pdf?version=1667874943"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["rnn","cnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"ML merges satellite and ground soil moisture, then SM2RAIN derives a rainfall product outperforming GPM, CHIRPS, ERA5-Land and MSWEP over the Heihe basin.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.14488","title":"History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz '96","authors":["Mohamed Aziz Bhouri","Pierre Gentine"],"date":"2022-10-26","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.14488","openalex":"W4307474573"},"links":{"paper":"https://arxiv.org/abs/2210.14488","pdf":"https://arxiv.org/pdf/2210.14488"},"orgs":[],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"A Bayesian neural-network closure with memory, sampled by Hamiltonian Monte Carlo, gives skillful Lorenz-96 forecasts with calibrated uncertainty from noisy, sparse data.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30865-mib.v6i4.4556","title":"Prediction of Rainfall Classification of Java Island with ANN-Feature Expansion and Ordinary Kriging","authors":["Irfani Adri Maulana","Sri Suryani Prasetiyowati","Yuliant Sibaroni"],"date":"2022-10-25","year":2022,"venue":"JURNAL MEDIA INFORMATIKA BUDIDARMA","venue_type":"journal","ids":{"doi":"10.30865/mib.v6i4.4556","openalex":"W4320062409"},"links":{"paper":"https://doi.org/10.30865/mib.v6i4.4556","pdf":"https://ejurnal.stmik-budidarma.ac.id/index.php/mib/article/download/4556/2981"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"ANN classifies monthly and daily rainfall in Java with up to 89% accuracy, then Ordinary Kriging maps six-month rainfall estimates.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.13817","title":"Online model error correction with neural networks in the incremental 4D-Var framework","authors":["Alban Farchi","Marcin Chrust","Marc Bocquet","Patrick Laloyaux","Massimo Bonavita"],"date":"2022-10-25","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2210.13817","doi":"10.1029/2022ms003474","openalex":"W4386256297"},"links":{"paper":"https://doi.org/10.1029/2022ms003474","pdf":"https://arxiv.org/pdf/2210.13817"},"orgs":["ecmwf"],"topic":"data-assimilation","topics":["hybrid-parameterization"],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Online neural-network model error correction is added to incremental 4D-Var in ECMWF's OOPS, showing online learning beats offline learning on a quasi-geostrophic model.","significance":4,"cited_by":42,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1098-rsta.2021.0288","title":"Status and prospects for drought forecasting: opportunities in artificial intelligence and hybrid physical–statistical forecasting","authors":["Amir AghaKouchak","Baoxiang Pan","Omid Mazdiyasni","Mojtaba Sadegh","Shakil Jiwa","Wenkai Zhang","Charlotte A. Love","Shahrbanou Madadgar","Simon Michael Papalexiou","Steven J. Davis","Kuolin Hsu","Soroosh Sorooshian"],"date":"2022-10-23","year":2022,"venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","venue_type":"journal","ids":{"doi":"10.1098/rsta.2021.0288","openalex":"W4307111613"},"links":{"paper":"https://doi.org/10.1098/rsta.2021.0288","pdf":"https://repository.library.noaa.gov/view/noaa/60315/noaa_60315_DS1.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"review","method":["classical-ml","other"],"timescale":["s2s","seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Review argues for bottom-up AI and hybrid physical-statistical drought forecasting, prioritising robustness and uncertainty stability over event-based verification.","significance":3,"cited_by":67,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1098-rsta.2021.0287","title":"Using machine learning to identify novel hydroclimate states","authors":["Kate Marvel","Benjamin I. Cook"],"date":"2022-10-23","year":2022,"venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","venue_type":"journal","ids":{"doi":"10.1098/rsta.2021.0287","openalex":"W4307329875"},"links":{"paper":"https://doi.org/10.1098/rsta.2021.0287"},"orgs":["nasa","columbia-leap"],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Unsupervised ML on tree-ring PDSI drought atlases finds outlier drought patterns in 80% of 21st-century years, showing unusual hydroclimate states.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.17013","title":"Climate Change Policy Exploration using Reinforcement Learning","authors":["Theodore Wolf"],"date":"2022-10-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2211.17013"},"links":{"paper":"https://arxiv.org/abs/2211.17013","pdf":"https://arxiv.org/pdf/2211.17013"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["reinforcement-learning"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep reinforcement learning agents probe a simplified World-Earth climate-economy model to find renewable-energy transition policies within planetary boundaries.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.13410","title":"Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation","authors":["Suraj A. Pawar","Omer San"],"date":"2022-10-23","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2205.13410","doi":"10.1029/2022ms003170","openalex":"W4281967986"},"links":{"paper":"https://doi.org/10.1029/2022ms003170","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003170"},"orgs":[],"topic":"data-assimilation","topics":["xai-uq-physics"],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"Couples POD-LSTM reduced-order models with an ensemble Kalman filter for geophysical flows, improving SST forecast error by about an order of magnitude.","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14215292","title":"Regional Typhoon Track Prediction Using Ensemble k-Nearest Neighbor Machine Learning in the GIS Environment","authors":["Mamad Tamamadin","Changkye Lee","Seong‐Hoon Kee","Jurng‐Jae Yee"],"date":"2022-10-22","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14215292","openalex":"W4308048041"},"links":{"paper":"https://doi.org/10.3390/rs14215292","pdf":"https://www.mdpi.com/2072-4292/14/21/5292/pdf?version=1666948947"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Ensemble k-nearest-neighbour method in a GIS environment predicts regional typhoon tracks with fast simulation and high accuracy.","significance":2,"cited_by":28,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.12538","title":"Compressing multidimensional weather and climate data into neural networks","authors":["Langwen Huang","Torsten Hoefler"],"date":"2022-10-22","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.12538","openalex":"W4307311484"},"links":{"paper":"https://arxiv.org/abs/2210.12538","pdf":"https://arxiv.org/pdf/2210.12538"},"orgs":["eth-zurich"],"topic":"infra-software","topics":["benchmarks-data-eval"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Coordinate-based neural networks compress weather and climate grids by 300x to 3000x, beating SZ3 on error, and a 790x compressed WeatherBench loader raises RMSE by under 2%.","significance":4,"cited_by":11,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2210.12504","title":"Generative Modeling of High-resolution Global Precipitation Forecasts","authors":["James Duncan","Shashank Subramanian","Peter Harrington"],"date":"2022-10-22","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.12504","openalex":"W4307311105"},"links":{"paper":"https://arxiv.org/abs/2210.12504","pdf":"https://arxiv.org/pdf/2210.12504"},"orgs":["uc-berkeley","lbnl-nersc"],"topic":"global-medium-range","topics":["extremes-hazards"],"type":"model","method":["gan-vae"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A GAN-enhanced FourCastNet better captures fine-scale structure and extreme global precipitation percentiles, matching NWP skill at 1-2 day leads.","significance":4,"cited_by":6,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.12310","title":"Tools for Extracting Spatio-Temporal Patterns in Meteorological Image Sequences: From Feature Engineering to Attention-Based Neural Networks","authors":["Akansha Singh Bansal","Yoonjin Lee","Kyle Hilburn","Imme Ebert-Uphoff"],"date":"2022-10-22","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.12310"},"links":{"paper":"https://arxiv.org/abs/2210.12310","pdf":"https://arxiv.org/pdf/2210.12310"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"review","method":["cnn","rnn","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Survey of feature engineering, convolutional, LSTM and attention methods for spatio-temporal patterns in meteorological image sequences, illustrated with solar forecasting and convection detection.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.12293","title":"DL-Corrector-Remapper: A grid-free bias-correction deep learning methodology for data-driven high-resolution global weather forecasting","authors":["Tao Ge","Jaideep Pathak","Akshay Subramaniam","Karthik Kashinath"],"date":"2022-10-21","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.12293","openalex":"W4307308716"},"links":{"paper":"https://arxiv.org/abs/2210.12293","pdf":"https://arxiv.org/pdf/2210.12293"},"orgs":[],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["neural-operator"],"timescale":["medium"],"spatial":["global"],"data":["era5","stations"],"status":"research","summary":"DLCR corrects and remaps FourCastNet gridded forecasts onto sparse, non-uniform observation locations, bias-correcting them against ground truth without gridded targets.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.12185","title":"Attention-Based Scattering Network for Satellite Imagery","authors":["Jason Stock","Chuck Anderson"],"date":"2022-10-21","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.12185","openalex":"W4307307821"},"links":{"paper":"https://arxiv.org/abs/2210.12185","pdf":"https://arxiv.org/pdf/2210.12185"},"orgs":["colorado-state-university"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["transformer","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Scattering-transform features with channel attention from multi-band satellite imagery estimate tropical cyclone intensity and predict lightning occurrence.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.12137","title":"A Multi-Scale Deep Learning Framework for Projecting Weather Extremes","authors":["Antoine Blanchard","Nishant Parashar","Boyko Dodov","Christian Lessig","Themistoklis Sapsis"],"date":"2022-10-21","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.12137","openalex":"W4307207318"},"links":{"paper":"https://arxiv.org/abs/2210.12137","pdf":"https://arxiv.org/pdf/2210.12137"},"orgs":["mit"],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Multi-resolution deep learning debiases GCM tail statistics against reanalysis and reconstructs finer scales, producing realistic Western European weather-extreme realizations for risk assessment.","significance":4,"cited_by":10,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022jd037038","title":"Machine Learning‐Based Detection of Weather Fronts and Associated Extreme Precipitation in Historical and Future Climates","authors":["Katherine Dagon","John Truesdale","James C Biard","Kenneth E. Kunkel","Gerald A. Meehl","María J. Molina"],"date":"2022-10-20","year":2022,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2022jd037038","openalex":"W4306919374"},"links":{"paper":"https://doi.org/10.1029/2022jd037038","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022JD037038"},"orgs":["ncar"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5","km-scale-sim"],"status":"research","summary":"Deep learning detects weather fronts in high-resolution CESM simulations over CONUS, showing frontal extreme precipitation becomes less likely under climate change despite overall increases.","significance":4,"cited_by":27,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.12853","title":"Deep-Learning-Based Precipitation Nowcasting with Ground Weather Station Data and Radar Data","authors":["Jihoon Ko","Kyuhan Lee","Hyunjin Hwang","Kijung Shin"],"date":"2022-10-20","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.12853"},"links":{"paper":"https://arxiv.org/abs/2210.12853","pdf":"https://arxiv.org/pdf/2210.12853"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"ASOC attention fuses sparse ground-station observations with radar images, raising CSI for 1-6 h heavy and light rainfall nowcasts by 5.7% over image-only models.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.11529","title":"Identifying Lightning Processes in ERA5 Soundings with Deep Learning","authors":["Gregor Ehrensperger","Thorsten Simon","Georg J. Mayr","Tobias Hell"],"date":"2022-10-20","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.11529"},"links":{"paper":"https://arxiv.org/abs/2210.11529","pdf":"https://arxiv.org/pdf/2210.11529"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A deep network on ERA5 vertical profiles identifies lightning-favourable atmosphere better than expert features, with SHAP pointing to cloud ice and snow content.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.11269","title":"Inference from Real-World Sparse Measurements","authors":["Arnaud Pannatier","Kyle Matoba","François Fleuret"],"date":"2022-10-20","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.11269","openalex":"W4307078073"},"links":{"paper":"https://arxiv.org/abs/2210.11269","pdf":"https://arxiv.org/pdf/2210.11269"},"orgs":[],"topic":"global-medium-range","topics":["nowcasting"],"type":"model","method":["transformer"],"timescale":["nowcast","short"],"spatial":["global"],"data":["other"],"status":"research","summary":"A ViT-style transformer handles irregular sensor data directly, cutting wind nowcasting RMSE from 9.24 to 7.98 and beating GNN baselines across several domains.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.11236","title":"Optical turbulence forecast over short timescales using machine learning techniques","authors":["A. Turchi","E. Masciadri","L. Fini"],"date":"2022-10-20","year":2022,"venue":"Proc. SPIE Volume 12185, SPIE Astronomical Telescopes + Instrumentation, 2022, Montreal, Quebec, Canada","venue_type":"journal","ids":{"arxiv":"2210.11236","doi":"10.1117/12.2629501"},"links":{"paper":"https://arxiv.org/abs/2210.11236","pdf":"https://arxiv.org/pdf/2210.11236"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Purely machine-learning forecasts of optical turbulence and astroclimate parameters 1-2 hours ahead above the Paranal VLT, benchmarked against autoregressive approaches.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.5638435","title":"Neural Network Radiation Scheme","authors":["Hwan‐Jin Song"],"date":"2022-10-19","year":2022,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.5638435","openalex":"W4226160182"},"links":{"paper":"https://doi.org/10.5281/zenodo.5638435"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Releases code and training data for a neural network radiation scheme in the WRF model, developed with stochastic weight averaging for numerical weather prediction.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2022.47098","title":"Climate Change Forecasting using Machine Learning Algorithms","authors":["Tanmya Vishvakarma"],"date":"2022-10-19","year":2022,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2022.47098","openalex":"W4306783272"},"links":{"paper":"https://doi.org/10.22214/ijraset.2022.47098","pdf":"https://doi.org/10.22214/ijraset.2022.47098"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["stations","other"],"status":"research","summary":"Applies standard ML models to historical global land temperature and CO2 records since 1750 to examine warming trends; methodologically basic.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14205205","title":"Improvement of Typhoon Intensity Forecasting by Using a Novel Spatio-Temporal Deep Learning Model","authors":["Shuailong Jiang","Hanjie Fan","Chunzai Wang"],"date":"2022-10-18","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14205205","openalex":"W4306769739"},"links":{"paper":"https://doi.org/10.3390/rs14205205","pdf":"https://www.mdpi.com/2072-4292/14/20/5205/pdf?version=1666602111"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"TITP-Net spatio-temporal CNN forecasts typhoon intensity at 18-48 h, improving MAE by 5-7% over deep learning and official dynamical forecasts.","significance":3,"cited_by":30,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003309","title":"Correcting Systematic and State‐Dependent Errors in the NOAA FV3‐GFS Using Neural Networks","authors":["Tse‐Chun Chen","Stephen Gregory Penny","Jeffrey S. Whitaker","Sergey Frolov","Robert L. Pincus","Stefan N. Tulich"],"date":"2022-10-18","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003309","openalex":"W4306720403"},"links":{"paper":"https://doi.org/10.1029/2022ms003309","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003309"},"orgs":["noaa","columbia-leap"],"topic":"hybrid-parameterization","topics":["data-assimilation"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Neural networks learn FV3-GFS systematic error from data assimilation analysis increments and apply online corrections, improving 10-day forecast skill at all lead times.","significance":4,"cited_by":34,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.knosys.2022.110005","title":"A neural network with spatiotemporal encoding module for tropical cyclone intensity estimation from infrared satellite image","authors":["Zhe Zhang","Xuying Yang","Xin Wang","Bingbing Wang","Chao Wang","Zhenhong Du"],"date":"2022-10-18","year":2022,"venue":"Knowledge-Based Systems","venue_type":"journal","ids":{"doi":"10.1016/j.knosys.2022.110005","openalex":"W4306711535"},"links":{"paper":"https://doi.org/10.1016/j.knosys.2022.110005"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Neural network with a spatiotemporal encoding module estimates tropical cyclone intensity from infrared satellite imagery.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-cpe.7412","title":"A novel fuzzy based deep neural network for rain fall prediction using cloud images","authors":["S. Oswalt Manoj","Pon Harshavardhanan","Akila Victor","Sajeev Ram Arumugam"],"date":"2022-10-18","year":2022,"venue":"Concurrency and Computation Practice and Experience","venue_type":"journal","ids":{"doi":"10.1002/cpe.7412","openalex":"W4306687062"},"links":{"paper":"https://doi.org/10.1002/cpe.7412"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Fuzzy deep neural network predicts rainfall by classifying cloud images and detecting rainy clouds; the abstract gives no quantitative results.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.09958","title":"Layer-wise Relevance Propagation for Echo State Networks applied to Earth System Variability","authors":["Marco Landt-Hayen","Peer Kröger","Martin Claus","Willi Rath"],"date":"2022-10-18","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.09958"},"links":{"paper":"https://arxiv.org/abs/2210.09958","pdf":"https://arxiv.org/pdf/2210.09958"},"orgs":[],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"model","method":["rnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Applies layer-wise relevance propagation to echo state networks, showing they detect ENSO from sea surface temperature anomalies and explaining the learned features.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002954","title":"ClimateBench v1.0: A Benchmark for Data‐Driven Climate Projections","authors":["D. Watson‐Parris","Y. Rao","D. Olivié","Ø. Seland","P. Nowack","G. Camps‐Valls","P. Stier","S. Bouabid","M. Dewey","E. Fons","J. Gonzalez","P. Harder","K. Jeggle","J. Lenhardt","P. Manshausen","M. Novitasari","L. Ricard","C. Roesch"],"date":"2022-10-17","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002954","openalex":"W4296126282"},"links":{"paper":"https://doi.org/10.1029/2021ms002954"},"orgs":["eth-zurich","met-norway","university-of-oxford"],"topic":"benchmarks-data-eval","topics":["climate-emulation"],"type":"benchmark","method":["classical-ml","cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Introduces ClimateBench, a CMIP-based benchmark with baseline ML emulators predicting temperature and precipitation responses to emissions scenarios.","significance":6,"cited_by":97,"score":59,"highlight":true,"highlight_reason":"ClimateBench gives the first standard benchmark for ML emulation of climate projections under emission scenarios, and it is widely used.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-amt-15-5821-2022","title":"Machine learning-based prediction of Alpine foehn events using GNSS troposphere products: first results for Altdorf, Switzerland","authors":["Matthias Aichinger‐Rosenberger","E. Bröckmann","Laura Crocetti","Benedikt S. Soja","Gregor Möller"],"date":"2022-10-14","year":2022,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-15-5821-2022","openalex":"W4306167471"},"links":{"paper":"https://doi.org/10.5194/amt-15-5821-2022"},"orgs":["eth-zurich"],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Classification algorithms detect and predict Alpine foehn events from GNSS troposphere products at Altdorf, reaching 70-85% detection and alarm measures.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-math10203793","title":"Survey on the Application of Artificial Intelligence in ENSO Forecasting","authors":["Wei Fang","Yu Sha","Victor S. Sheng"],"date":"2022-10-14","year":2022,"venue":"Mathematics","venue_type":"journal","ids":{"doi":"10.3390/math10203793","openalex":"W4306391217"},"links":{"paper":"https://doi.org/10.3390/math10203793","pdf":"https://www.mdpi.com/2227-7390/10/20/3793/pdf?version=1666744391"},"orgs":["nuist","cma"],"topic":"s2s-seasonal","topics":[],"type":"review","method":["cnn","other"],"timescale":["seasonal"],"spatial":["global"],"data":[],"status":"research","summary":"Survey of AI methods for ENSO forecasting, reviewing deep learning approaches since Ham et al. (2019) and comparing them with traditional statistical and dynamical forecasts.","significance":3,"cited_by":26,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13101684","title":"Machine Learning-Based Fog Nowcasting for Aviation with the Aid of Camera Observations","authors":["Juraj Bartók","Peter Šišan","Lukáš Ivica","Ivana Bartoková","Irina Malkin Ondík","Ladislav Gaál"],"date":"2022-10-14","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13101684","openalex":"W4306362185"},"links":{"paper":"https://doi.org/10.3390/atmos13101684","pdf":"https://www.mdpi.com/2073-4433/13/10/1684/pdf?version=1666682106"},"orgs":[],"topic":"local-forecasting","topics":["nowcasting"],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"SVM, tree and KNN models using camera-derived visibility predict 30-minute fog onset at Poprad-Tatry airport with a 0.89 probability of detection.","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-17538947.2022.2130460","title":"Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data","authors":["Shaopeng Li","Bo Jiang","Shunlin Liang","Jianghai Peng","Hui Liang","Jiakun Han","Xiuwan Yin","Yunjun Yao","Xiaotong Zhang","Jie Cheng","Xiang H. Zhao","Qiang Liu","Kun Jia"],"date":"2022-10-14","year":2022,"venue":"International Journal of Digital Earth","venue_type":"journal","ids":{"doi":"10.1080/17538947.2022.2130460","openalex":"W4306318403"},"links":{"paper":"https://doi.org/10.1080/17538947.2022.2130460"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["classical-ml","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","stations"],"status":"research","summary":"Nine ML and DL methods estimate daily land surface net radiation from MODIS; deep learning generally beats classical methods, with ResNet most robust across conditions.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-electronics11203279","title":"Typhoon Tracks Prediction with ConvLSTM Fused Reanalysis Data","authors":["Peng Lü","Mingyu Xu","Ao Sun","Zhenhua Wang","Zongsheng Zheng"],"date":"2022-10-12","year":2022,"venue":"Electronics","venue_type":"journal","ids":{"doi":"10.3390/electronics11203279","openalex":"W4304688733"},"links":{"paper":"https://doi.org/10.3390/electronics11203279","pdf":"https://www.mdpi.com/2079-9292/11/20/3279/pdf?version=1665565251"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"ConvLSTM with an added convolutional layer predicts typhoon tracks from ERA5 reanalysis image sequences, reaching 54.69 km mean distance error.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2022.47020","title":"Weather Prediction","authors":["V Venkatrama Ravi","M Mukesh Reddy","K.S. Dhruva Teja","Ch Sai Niteesh","B. Sekhar Babu"],"date":"2022-10-11","year":2022,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2022.47020","openalex":"W4304177543"},"links":{"paper":"https://doi.org/10.22214/ijraset.2022.47020","pdf":"https://doi.org/10.22214/ijraset.2022.47020"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Generic report applying various machine learning algorithms to improve forecast accuracy for temperature, rain and humidity; no specific method or quantitative result is given.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2022-6573202","title":"Comparison of the Applicability of Two Reanalysis Products in Estimating Tall Tower Wind Based on Multiple Linear Regression and Artificial Neural Network in South China","authors":["Xiangxiang Li","Xiaochen Qin","Jun Yang","Weiming Xu"],"date":"2022-10-11","year":2022,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2022/6573202","openalex":"W4304588836"},"links":{"paper":"https://doi.org/10.1155/2022/6573202","pdf":"https://downloads.hindawi.com/journals/amete/2022/6573202.pdf"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["era5","stations","other"],"status":"research","summary":"Compares MLR and ANN downscaling of ERA5 and MERRA2 winds against South China tall-tower observations; ERA5 with ANN gives r=0.69 and RMSE 2.11 m/s.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.04554","title":"Comparing the carbon costs and benefits of low-resource solar nowcasting","authors":["Ben Dixon","María Pérez-Ortiz","Jacob Bieker"],"date":"2022-10-10","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.04554"},"links":{"paper":"https://arxiv.org/abs/2210.04554","pdf":"https://arxiv.org/pdf/2210.04554"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"evaluation","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"Compares low-resource CNN models nowcasting UK solar PV yield from satellite imagery over 1 to 4 hours, weighing carbon costs against benefits.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14195042","title":"Prediction of Radar Echo Space-Time Sequence Based on Improving TrajGRU Deep-Learning Model","authors":["Qiangyu Zeng","Haoran Li","Tao Zhang","Jianxin He","Fugui Zhang","Hao Wang","Zhipeng Qing","Qiu Yu","Bangyue Shen"],"date":"2022-10-09","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14195042","openalex":"W4303980578"},"links":{"paper":"https://doi.org/10.3390/rs14195042","pdf":"https://www.mdpi.com/2072-4292/14/19/5042/pdf?version=1665548448"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"T-UNet combines UNet with TrajGRU for radar echo extrapolation, improving CSI and HSS by up to 10.57% and 7.80% over 60-minute nowcasts.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.04001","title":"Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation","authors":["Raghul Parthipan","Damon J. Wischik"],"date":"2022-10-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.04001","openalex":"W4304700923"},"links":{"paper":"https://arxiv.org/abs/2210.04001","pdf":"https://arxiv.org/pdf/2210.04001","code":"https://github.com/raghul-parthipan/dont_waste_data"},"orgs":["university-of-cambridge"],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Transfer learning from unused high-resolution data improves machine-learnt emulators of chaotic systems, giving better stability, generalisation and forecast skill for climate-model emulation.","significance":3,"cited_by":2,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13101632","title":"Cloud Nowcasting with Structure-Preserving Convolutional Gated Recurrent Units","authors":["Samuel A. Kellerhals","Fons de Leeuw","Cristian Rodríguez Rivero"],"date":"2022-10-07","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13101632","openalex":"W4303613879"},"links":{"paper":"https://doi.org/10.3390/atmos13101632","pdf":"https://www.mdpi.com/2073-4433/13/10/1632/pdf?version=1665901128"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"ConvGRU with a structure-preserving loss forecasts European cloudiness 3 hours ahead from SEVIRI, outperforming optical flow by 12.43% in R2 across time steps.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.03324","title":"AutoML for Climate Change: A Call to Action","authors":["Renbo Tu","Nicholas Roberts","Vishak Prasad","Sibasis Nayak","Paarth Jain","Frederic Sala","Ganesh Ramakrishnan","Ameet Talwalkar","Willie Neiswanger","Colin White"],"date":"2022-10-07","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.03324","openalex":"W4304192680"},"links":{"paper":"https://arxiv.org/abs/2210.03324","pdf":"https://arxiv.org/pdf/2210.03324","code":"https://github.com/climate-change-automl/climate-change-automl"},"orgs":["stanford"],"topic":"benchmarks-data-eval","topics":["climate-emulation"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"Benchmarks off-the-shelf AutoML libraries on climate modelling and wind power forecasting; they fail to beat human-designed models, motivating spatiotemporal AutoML search spaces.","significance":3,"cited_by":4,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jas-d-22-0021.1","title":"Using Machine Learning to Estimate Nonorographic Gravity Wave Characteristics at Source Levels","authors":["Mozhgan Amiramjadi","Riwal Plougonven","Ali Reza Mohebalhojeh","Mohammad Mirzaei"],"date":"2022-10-06","year":2022,"venue":"Journal of the Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1175/jas-d-22-0021.1","openalex":"W4303182363"},"links":{"paper":"https://doi.org/10.1175/jas-d-22-0021.1","pdf":"https://journals.ametsoc.org/downloadpdf/view/journals/atsc/80/2/JAS-D-22-0021.1.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Random forests reconstruct nonorographic gravity wave variability at source levels from ERA5 columns with R2 near 0.85, finding local background wind most informative.","significance":4,"cited_by":10,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-21-0266.1","title":"The February 2021 Cold Air Outbreak in the United States: A Subseasonal Forecast of Opportunity","authors":["John R. Albers","Matthew Newman","Andrew Hoell","Melissa L. Breeden","Yan Wang","‪Jiale Lou"],"date":"2022-10-06","year":2022,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-21-0266.1","openalex":"W4302307328"},"links":{"paper":"https://doi.org/10.1175/bams-d-21-0266.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/bams/103/12/BAMS-D-21-0266.1.pdf"},"orgs":["noaa"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"application","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"A linear inverse model predicted the February 2021 cold air outbreak four weeks ahead, up to two weeks earlier than numerical models, and estimated it as a top-1% event.","significance":3,"cited_by":24,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ef002723","title":"Flash Drought: Review of Concept, Prediction and the Potential for Machine Learning, Deep Learning Methods","authors":["Shoobhangi Tyagi","Xiang Zhang","Dharmendra Saraswat","Sandeep Sahany","Saroj K. Mishra","Dev Niyogi"],"date":"2022-10-06","year":2022,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2022ef002723","openalex":"W4303195676"},"links":{"paper":"https://doi.org/10.1029/2022ef002723","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EF002723"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"review","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["other"],"status":"research","summary":"Review of flash drought concept and the potential of machine learning and deep learning for monitoring and subseasonal-to-seasonal prediction of rapid drought onset.","significance":3,"cited_by":88,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10489-022-04175-y","title":"A combination of supervised dimensionality reduction and learning methods to forecast solar radiation","authors":["Esteban García-Cuesta","Ricardo Aler","David Pozo‐Vázquez","Inés María Galván"],"date":"2022-10-06","year":2022,"venue":"Applied Intelligence","venue_type":"journal","ids":{"doi":"10.1007/s10489-022-04175-y","openalex":"W4302290904"},"links":{"paper":"https://doi.org/10.1007/s10489-022-04175-y","pdf":"https://link.springer.com/content/pdf/10.1007/s10489-022-04175-y.pdf"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Proposes supervised SLMVP dimensionality reduction for NWP-based solar irradiance forecasts, achieving about 3-5% lower MAE than PCA and LPP at Seville and Lisbon.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-7353-2022","title":"Repeatable high-resolution statistical downscaling through deep learning","authors":["Dánnell Quesada‐Chacón","Klemens Barfus","Christian Bernhofer"],"date":"2022-10-05","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-7353-2022","openalex":"W4301594512"},"links":{"paper":"https://doi.org/10.5194/gmd-15-7353-2022"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["era5","stations","other"],"status":"research","summary":"U-Net and U-Net++ deep learning perfect-prognosis downscaling produces daily 1 km precipitation for Saxony with improved skill and full reproducibility.","significance":4,"cited_by":29,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7885","title":"Climatic water balance forecasting with machine learning and deep learning models over Bangladesh","authors":["Md. Jalal Uddin","Yubin Li","Md. Abdus Sattar","Sunit Mistry"],"date":"2022-10-05","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7885","openalex":"W4301372060"},"links":{"paper":"https://doi.org/10.1002/joc.7885"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"evaluation","method":["classical-ml","rnn","cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"SHAP-explained SVM, RF, CNN and LSTM forecast climatic water balance 1-3 months ahead over Bangladesh; SVM performs best with antecedent CWB inputs.","significance":2,"cited_by":7,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-acp-2022-688","title":"Possible evidence of increased global cloudiness due to aerosol-cloud interactions","authors":["Alyson Douglas","Tristan L’Ecuyer"],"date":"2022-10-04","year":2022,"venue_type":"other","ids":{"doi":"10.5194/acp-2022-688","openalex":"W4301396795"},"links":{"paper":"https://doi.org/10.5194/acp-2022-688"},"orgs":["university-of-oxford"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Random forest and boosting models estimate pre-industrial cloudiness, suggesting aerosols increased global cloud fraction by 1.27% with about -0.42 W/m2 cooling.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jsen.2022.3210224","title":"Deep Learning and Self-Powered Sensors Enabled Edge Computing Platform for Predicting Microclimate at Urban Blocks","authors":["Xuechuan Geng","Yufei Zou","Lingkang Meng"],"date":"2022-10-04","year":2022,"venue":"IEEE Sensors Journal","venue_type":"journal","ids":{"doi":"10.1109/jsen.2022.3210224","openalex":"W4312806918"},"links":{"paper":"https://doi.org/10.1109/jsen.2022.3210224"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Deep learning on an edge computing platform with self-powered sensors predicts urban block microclimate indices in two cities, with small errors reported.","significance":1,"cited_by":6,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2210.01957","title":"Towards an Artificial-Intelligence-Based Optical Scintillometer: Scaling Issue","authors":["G. A. Filimonov","M. A. Vorontsov"],"date":"2022-10-04","year":2022,"venue_type":"preprint","ids":{"arxiv":"2210.01957"},"links":{"paper":"https://arxiv.org/abs/2210.01957","pdf":"https://arxiv.org/pdf/2210.01957"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A DNN estimating atmospheric turbulence (Cn2) from scintillation patterns can be reused at new propagation distances via analytic or wave-optics scaling, avoiding retraining.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35784-acs-2022-26","title":"HOW MACHINE LEARNING ALGORITHMS ARE USED IN METEOROLOGICAL DATA CLASSIFICATION: A COMPARATIVE APPROACH BETWEEN DT, LMT, M5-MT, GRADIENT BOOSTING AND GWLM-NARX MODELS","authors":["Sheikh Amir Fayaz","Majid Zaman","Muheet Ahmed Butt","Sameer Kaul"],"date":"2022-10-01","year":2022,"venue":"Applied Computer Science","venue_type":"journal","ids":{"doi":"10.35784/acs-2022-26","openalex":"W4320064879"},"links":{"paper":"https://doi.org/10.35784/acs-2022-26","pdf":"https://ph.pollub.pl/index.php/acs/article/download/3424/3042"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares decision trees, LMT, M5 model trees, gradient boosting and NARX for rainfall classification from three Kashmir stations; gradient boosting reaches 87.5% accuracy.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en15197233","title":"Sequential Data-Driven Long-Term Weather Forecasting Models’ Performance Comparison for Improving Offshore Operation and Maintenance Operations","authors":["Ravi Pandit","Davide Astolfi","Anh Minh Tang","David G. Infield"],"date":"2022-10-01","year":2022,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en15197233","openalex":"W4303700118"},"links":{"paper":"https://doi.org/10.3390/en15197233","pdf":"https://www.mdpi.com/1996-1073/15/19/7233/pdf?version=1664618818"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"evaluation","method":["rnn"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares LSTM, BiLSTM and GRU for long-term offshore wind speed and wave height forecasts from FINO3 station data, reporting better seasonal response and reliability.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0018.1","title":"Downscaling of Historical Wind Fields over Switzerland Using Generative Adversarial Networks","authors":["Ophélia Miralles","Daniel Steinfeld","Olivia Martius","Anthony C. Davison"],"date":"2022-10-01","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0018.1","openalex":"W4302424651"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0018.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/aop/AIES-D-22-0018.1/AIES-D-22-0018.1.pdf"},"orgs":[],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["era5","km-scale-sim"],"status":"research","summary":"GAN with gradient-penalized Wasserstein loss downscales ERA5 hourly winds over Switzerland from 25 km to 1.1 km, capturing orographic effects missed by ERA5.","significance":4,"cited_by":29,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002921","title":"Benefits of Stochastic Weight Averaging in Developing Neural Network Radiation Scheme for Numerical Weather Prediction","authors":["Hwan‐Jin Song","Soonyoung Roh","Juho Lee","Giung Nam","EungGu Yun","Jongmin Yoon","Park Sa Kim"],"date":"2022-10-01","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002921","openalex":"W4303579423"},"links":{"paper":"https://doi.org/10.1029/2021ms002921","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002921"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":["post-processing"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Stochastic weight averaging improves a neural radiation emulator in a Korean NWP model, giving a 60-fold radiation speedup and 12.6% week-long flux gains.","significance":4,"cited_by":12,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10584-022-03444-6","title":"A canary, a coal mine, and imperfect data: determining the efficacy of open-source climate change models in detecting and predicting extreme weather events in Northern and Western Kenya","authors":["Alvin M Igobwa","Jeremy Gachanja","Betsy Muriithi","John Olukuru","Angeline Wairegi","Isaac Rutenberg"],"date":"2022-10-01","year":2022,"venue":"Climatic Change","venue_type":"journal","ids":{"doi":"10.1007/s10584-022-03444-6","openalex":"W4306771028"},"links":{"paper":"https://doi.org/10.1007/s10584-022-03444-6","pdf":"https://link.springer.com/content/pdf/10.1007/s10584-022-03444-6.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Artificial neural networks and isolation forests on Kenyan station data predict drought and flood occurrences with 78-90% accuracy, supporting early warning.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13101607","title":"A Novel Tropical Cyclone Track Forecast Model Based on Attention Mechanism","authors":["Wei Fang","Wenhe Lu","Jiaxin Li","Zou Liyao"],"date":"2022-09-30","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13101607","openalex":"W4303614182"},"links":{"paper":"https://doi.org/10.3390/atmos13101607","pdf":"https://www.mdpi.com/2073-4433/13/10/1607/pdf?version=1666248255"},"orgs":["nuist","cma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"A ConvGRU with CBAM attention and a Deep&Cross CNN fusion forecasts tropical cyclone tracks from CMA and ERA-Interim data, outperforming prior deep learning baselines.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-22-0053.1","title":"Short-Term Visibility Prediction Using Tree-Based Machine Learning Algorithms and Numerical Weather Prediction Data","authors":["Bu-Yo Kim","Miloslav Belorid","Joo Wan Cha"],"date":"2022-09-30","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-22-0053.1","openalex":"W4298109833"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0053.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/37/12/WAF-D-22-0053.1.pdf"},"orgs":["kma"],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Tree-based XGBoost trained on LDAPS NWP output beats raw LDAPS for Seoul visibility (MAE 2.04 km vs 4.66 km, R 0.88 vs 0.40).","significance":3,"cited_by":25,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1142-s2811032322500011","title":"Deep Learning-Based Downscaling of Temperatures for Monitoring Local Climate Change Using Global Climate Simulation Data","authors":["Firas Gerges","Michel C. Boufadel","Elie R. Bou-Zeid","Hani H. Nassif","Jason T. L. Wang"],"date":"2022-09-30","year":2022,"venue":"World Scientific Annual Review of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1142/s2811032322500011","openalex":"W4298145914"},"links":{"paper":"https://doi.org/10.1142/s2811032322500011"},"orgs":["princeton-university"],"topic":"downscaling","topics":[],"type":"application","method":["cnn"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"An overview of ML downscaling of GCM output, with a deep-learning case study producing local weekly temperature projections for a New Jersey watershed.","significance":2,"cited_by":3,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.15585","title":"Cloud Classification with Unsupervised Deep Learning","authors":["Takuya Kurihana","Ian Foster","Rebecca Willett","Sydney Jenkins","Kathryn Koenig","Ruby Werman","Ricardo Barros Lourenco","Casper Neo","Elisabeth Moyer"],"date":"2022-09-30","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.15585"},"links":{"paper":"https://arxiv.org/abs/2209.15585","pdf":"https://arxiv.org/pdf/2209.15585"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Unsupervised deep learning on MODIS radiances learns cloud features and produces physically meaningful cloud classes without predefined categories.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w14193073","title":"Machine Learning Assessment of the Impact of Global Warming on the Climate Drivers of Water Supply to Australia’s Northern Murray-Darling Basin","authors":["Milton Samuel Speer","Joshua Hartigan","Lance M. Leslie"],"date":"2022-09-29","year":2022,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w14193073","openalex":"W4298145342"},"links":{"paper":"https://doi.org/10.3390/w14193073","pdf":"https://www.mdpi.com/2073-4441/14/19/3073/pdf?version=1665485578"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Regression-based machine learning ranks 45 climate attributes, linking declining April–May rainfall in the northern Murray-Darling Basin to global warming, ENSO, SAM and IOD.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-solr.202200652","title":"Single‐Site Forecasts for 130 Photovoltaic Systems at Distribution System Operator Level, Using a Hybrid‐Physical Approach, to Improve Grid‐Integration and Enable Future Smart‐Grid Operation","authors":["Daniel Köster","David Fiorelli","Pierrick Bruneau","Christian Braun"],"date":"2022-09-29","year":2022,"venue":"Solar RRL","venue_type":"journal","ids":{"doi":"10.1002/solr.202200652","openalex":"W4297995558"},"links":{"paper":"https://doi.org/10.1002/solr.202200652","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/solr.202200652"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn","physics-constrained"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A hybrid NWP-physical model plus LSTM gives intraday single-site PV forecasts for 130 distribution-grid systems, with NRMSE of 8.3% and 8.7% in 2020 and 2021.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.15424","title":"Accurate Long-term Air Temperature Prediction with a Fusion of Artificial Intelligence and Data Reduction Techniques","authors":["Dušan Fister","Jorge Pérez-Aracil","César Peláez-Rodríguez","Javier Del Ser","Sancho Salcedo-Sanz"],"date":"2022-09-29","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.15424","openalex":"W4300980417"},"links":{"paper":"https://arxiv.org/abs/2209.15424","pdf":"https://arxiv.org/pdf/2209.15424"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["era5"],"status":"research","summary":"Deep learning and classical ML with data reduction predict August fortnight air temperatures in Paris and Córdoba months ahead, using reanalysis inputs.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.15096","title":"AICCA: AI-driven Cloud Classification Atlas","authors":["Takuya Kurihana","Elisabeth Moyer","Ian Foster"],"date":"2022-09-29","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"arxiv":"2209.15096","doi":"10.3390/rs14225690","openalex":"W4300978536"},"links":{"paper":"https://doi.org/10.3390/rs14225690","pdf":"https://arxiv.org/pdf/2209.15096"},"orgs":["argonne","university-of-chicago"],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"benchmark","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A rotation-invariant autoencoder with clustering yields AICCA, a 22-year atlas of 42 unsupervised cloud classes from 198 million MODIS image patches.","significance":5,"cited_by":15,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.14782","title":"A case study of spatiotemporal forecasting techniques for weather forecasting","authors":["Shakir Showkat Sofi","Ivan Oseledets"],"date":"2022-09-29","year":2022,"venue":"Geoinformatica 2024","venue_type":"journal","ids":{"arxiv":"2209.14782","doi":"10.1007/s10707-024-00530-y"},"links":{"paper":"https://arxiv.org/abs/2209.14782","pdf":"https://arxiv.org/pdf/2209.14782"},"orgs":[],"topic":"regional-km-scale","topics":[],"type":"evaluation","method":["rnn","transformer","other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Comparison of spatiotemporal data-driven methods for regional gridded weather forecasting; tensor train DMD matches state-of-the-art accuracy without training.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.978942","title":"Spatiotemporal forecasting model based on hybrid convolution for local weather prediction post-processing","authors":["Xiang Li","Jie Xiang","Jiping Guan","Lifeng Zhang","Zenghui Cao","Jilu Xia"],"date":"2022-09-27","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.978942","openalex":"W4297311885"},"links":{"paper":"https://doi.org/10.3389/feart.2022.978942","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.978942/pdf"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"STCNet combines 2D and 1D convolutions to post-process NWP for station weather, outperforming a Seq2Seq RNN and yielding hourly forecasts from 3-hourly input.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-7203-2022","title":"Analog data assimilation for the selection of suitable general circulation models","authors":["Juan José Ruiz","Pierre Ailliot","Thi Tuyet Trang Chau","Pierre Le Bras","Valérie Monbet","Florian Sévellec","Pierre Tandeo"],"date":"2022-09-26","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-7203-2022","openalex":"W4297360110"},"links":{"paper":"https://doi.org/10.5194/gmd-15-7203-2022"},"orgs":["inria"],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Data-driven analog data assimilation with ML-emulated models selects the best GCM for observations, performing as well as using the true SPEEDY model.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ac94e7","title":"Early-onset trend in European summer caused by Greenland topographic effect","authors":["Jun‐Hyeok Son","Nam‐Hoon Kim","Go‐Eun Kim","Jung‐Eun Chu","Jae‐Heung Park","Jae‐Il Kwon","Ki‐Young Heo"],"date":"2022-09-26","year":2022,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ac94e7","openalex":"W4297094203"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ac94e7","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ac94e7/pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Explains a 42-year lengthening of European summer as early onset driven by Greenland topography and Rossby wave responses, building on CNN-detected trends.","significance":4,"cited_by":6,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.01345","title":"Generative machine learning methods for multivariate ensemble post-processing","authors":["Jieyu Chen","Tim Janke","Florian Steinke","Sebastian Lerch"],"date":"2022-09-26","year":2022,"venue":"Annals of Applied Statistics (2024), 18, 159-183","venue_type":"journal","ids":{"arxiv":"2211.01345","doi":"10.1214/23-aoas1784"},"links":{"paper":"https://arxiv.org/abs/2211.01345","pdf":"https://arxiv.org/pdf/2211.01345"},"orgs":[],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local","regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Generative neural network post-processing of ensemble forecasts captures multivariate dependencies better than copula methods for German station temperature and wind.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.12580","title":"Robust Causality and False Attribution in Data-Driven Earth Science Discoveries","authors":["Elizabeth Eldhose","Tejasvi Chauhan","Vikram Chandel","Subimal Ghosh","Auroop R. Ganguly"],"date":"2022-09-26","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.12580"},"links":{"paper":"https://arxiv.org/abs/2209.12580","pdf":"https://arxiv.org/pdf/2209.12580"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Shows transfer-entropy causal graphs can be spurious in climate and ecohydrology data and proposes a subsample ensemble approach for more robust causality analysis.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.12433","title":"Deep generative model super-resolves spatially correlated multiregional climate data","authors":["Norihiro Oyama","Noriko N. Ishizaki","Satoshi Koide","Hiroaki Yoshida"],"date":"2022-09-26","year":2022,"venue":"Scientific Reports","venue_type":"journal","ids":{"arxiv":"2209.12433","doi":"10.1038/s41598-023-32947-0","openalex":"W4366991492"},"links":{"paper":"https://doi.org/10.1038/s41598-023-32947-0","pdf":"https://arxiv.org/pdf/2209.12433"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","physics-constrained"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Physics-informed SRGAN downscales climate fields up to 50x while preserving inter-regional spatial correlations of temperature and precipitation.","significance":4,"cited_by":38,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36335-vnjhm.2022-741-.98-105","title":"Thử nghiệm khả năng dự báo số ngày nắng nóng trên lãnh thổ Việt Nam bằng mạng thần kinh nhân tạo","authors":["Tạ Hữu Chỉnh","Hoàng Phúc Lâm","Vũ Văn Thăng","Trương Bá Kiên"],"date":"2022-09-25","year":2022,"venue":"Journal of Hydro-meteorology","venue_type":"journal","ids":{"doi":"10.36335/vnjhm.2022(741).98-105","openalex":"W4297486138"},"links":{"paper":"https://doi.org/10.36335/vnjhm.2022(741).98-105","pdf":"http://tapchikttv.vn/article-file-download/3469"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"An artificial neural network with ENSO indices skilfully forecasts April–June hot-day counts in northern Vietnam but performs poorly in southern regions.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.geogeo.2022.100137","title":"Refinement of global gridded ray-traced Zenith tropospheric delay over Nigeria based on local GNSS network observations","authors":["Ifechukwu Ugochukwu Nzelibe","Timothy Oluwadare Idowu"],"date":"2022-09-24","year":2022,"venue":"Geosystems and Geoenvironment","venue_type":"journal","ids":{"doi":"10.1016/j.geogeo.2022.100137","openalex":"W4296970820"},"links":{"paper":"https://doi.org/10.1016/j.geogeo.2022.100137","pdf":"https://www.sciencedirect.com/science/article/pii/S2772883822001121/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Feedforward networks refine global VMF1 zenith tropospheric delay over Nigeria using local GNSS stations, lowering external RMSE to 0.03–0.04 m.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-22-0066.1","title":"Performance of New Near-Real-Time PERSIANN Product (PDIR-Now) for Atmospheric River Events over the Russian River Basin, California","authors":["Vesta Afzali Gorooh","Eric Jay Shearer","Phu Nguyen","Kuolin Hsu","Soroosh Sorooshian","Forest Cannon","Marty Ralph"],"date":"2022-09-23","year":2022,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-22-0066.1","openalex":"W4297013987"},"links":{"paper":"https://doi.org/10.1175/jhm-d-22-0066.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/hydr/23/12/JHM-D-22-0066.1.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"evaluation","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","radar","stations"],"status":"pre-operational","summary":"Evaluates the ANN-based PDIR-Now near-real-time satellite rainfall product during California atmospheric river events, validated against profilers and disdrometers.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.11497","title":"Time Series Causal Link Estimation under Hidden Confounding using Knockoff Interventions","authors":["Violeta Teodora Trifunov","Maha Shadaydeh","Joachim Denzler"],"date":"2022-09-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.11497"},"links":{"paper":"https://arxiv.org/abs/2209.11497","pdf":"https://arxiv.org/pdf/2209.11497"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Uses a VAE with knockoff interventions to estimate causal links under hidden confounding, applied to aerosol-cloud-climate time series with better accuracy than a deconfounding benchmark.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36375-prepare-u.foset.a350","title":"Application of Machine Learning for Atmospheric Characterization Using University of Calcutta ST Radar","authors":["Goutam Kr Das"],"date":"2022-09-22","year":2022,"venue_type":"other","ids":{"doi":"10.36375/prepare_u.foset.a350","openalex":"W4296654899"},"links":{"paper":"https://doi.org/10.36375/prepare_u.foset.a350","pdf":"https://preprint.prepare.org.in/index.php/foset/article/download/350/160"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["other"],"timescale":[],"spatial":["local"],"data":["radar"],"status":"research","summary":"Develops machine learning models of atmospheric parameters from a 53 MHz stratosphere-troposphere radar in India, aiming to predict winds outside the training interval.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms002995","title":"Deep Learning Provides Substantial Improvements to County‐Level Fire Weather Forecasting Over the Western United States","authors":["Rackhun Son","Po‐Lun Ma","Hailong Wang","Philp J. Rasch","Shih‐Yu Wang","Hyungjun Kim","Jee‐Hoon Jeong","Kyo‐Sun Sunny Lim","Jin‐Ho Yoon"],"date":"2022-09-22","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms002995","openalex":"W4296681037"},"links":{"paper":"https://doi.org/10.1029/2022ms002995","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS002995"},"orgs":["university-of-washington","mpi-biogeochemistry"],"topic":"extremes-hazards","topics":["downscaling"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"CFS-SR applies image super-resolution to CFSv2 to give 4 km county-level fire weather forecasts to 7 days, improving accuracy over the western US.","significance":4,"cited_by":15,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.10666","title":"Adaptive Bias Correction for Improved Subseasonal Forecasting","authors":["Soukayna Mouatadid","Paulo Orenstein","Genevieve Flaspohler","Judah Cohen","Miruna Oprescu","Ernest Fraenkel","Lester Mackey"],"date":"2022-09-21","year":2022,"venue":"Nature Communications","venue_type":"journal","ids":{"arxiv":"2209.10666","doi":"10.1038/s41467-023-38874-y","openalex":"W4380872517"},"links":{"paper":"https://doi.org/10.1038/s41467-023-38874-y","pdf":"https://arxiv.org/pdf/2209.10666"},"orgs":["microsoft-research","mit"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine-learning adaptive bias correction of ECMWF subseasonal forecasts raises contiguous-US temperature skill 60-90% and precipitation skill 40-69%.","significance":5,"cited_by":52,"score":75,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.978041","title":"Deep-learning-based post-processing for probabilistic precipitation forecasting","authors":["Yan Ji","Xiefei Zhi","Luying Ji","Yingxin Zhang","Cui Hao","Ting Peng"],"date":"2022-09-20","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.978041","openalex":"W4296482679"},"links":{"paper":"https://doi.org/10.3389/feart.2022.978041","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.978041/pdf"},"orgs":["nuist","cma"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"CNN post-processing of GEFS re-forecasts beats CSG EMOS and raw ensembles for 1–7 day China precipitation, especially for extremes above 50 mm/day.","significance":4,"cited_by":17,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2022.128455","title":"Improving daily precipitation estimation in the data scarce area by merging rain gauge and TRMM data with a transfer learning framework","authors":["Zhaoyu Liu","Qinli Yang","Junming Shao","Guoqing Wang","Hongyuan Liu","Xiongpeng Tang","Yunhong Xue","Linlong Bai"],"date":"2022-09-20","year":2022,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2022.128455","openalex":"W4296478616"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2022.128455"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Transfer learning merges rain gauge and TRMM satellite data to improve daily precipitation estimates in a data-scarce region.","significance":3,"cited_by":46,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.engappai.2022.105440","title":"Design and evaluation of adaptive deep learning models for weather forecasting","authors":["Nawaf Abdulla","Mehmet Demirci","Suat Özdemi̇r"],"date":"2022-09-20","year":2022,"venue":"Engineering Applications of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1016/j.engappai.2022.105440","openalex":"W4296770014"},"links":{"paper":"https://doi.org/10.1016/j.engappai.2022.105440"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Adaptive deep learning models for weather forecasting; abstract unavailable, so the target scale and gains cannot be verified.","significance":2,"cited_by":34,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W4296421826","title":"Occlusion-Perturbed Deep Learning for Probabilistic Solar Forecasting via Sky Images: Preprint","authors":["Cong Feng"],"date":"2022-09-19","year":2022,"venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","venue_type":"preprint","ids":{"openalex":"W4296421826"},"links":{"paper":"https://www.osti.gov/biblio/1887441","pdf":"https://www.osti.gov/biblio/1887441"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Occlusion-perturbed CNN forecasts 10-minute-ahead irradiance from sky images, reaching 5.62% nRMSE and a 2.77% nCRPS for probabilistic forecasts.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.11682","title":"Meteorological Satellite Images Prediction Based on Deep Multi-scales Extrapolation Fusion","authors":["Fang Huang","Wencong Cheng","PanFeng Wang","ZhiGang Wang","HongHong He"],"date":"2022-09-19","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.11682","openalex":"W4297162933"},"links":{"paper":"https://arxiv.org/abs/2209.11682","pdf":"https://arxiv.org/pdf/2209.11682"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Multi-scale extrapolation with a conditional GAN predicts FY-4A meteorological satellite images up to 2 hours ahead, capturing weather-system evolution in detail.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.47852-bonviewaia2202337","title":"UTrans-Net: A Model for Short-Term Precipitation Prediction","authors":["Hao Cao","Yirui Wu","Yansong Bao","Xi Feng","Shaohua Wan","Qian Cheng"],"date":"2022-09-18","year":2022,"venue":"Artificial Intelligence and Applications","venue_type":"journal","ids":{"doi":"10.47852/bonviewaia2202337","openalex":"W4296312164"},"links":{"paper":"https://doi.org/10.47852/bonviewaia2202337","pdf":"https://ojs.bonviewpress.com/index.php/AIA/article/download/337/191"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"UTrans-Net adds a transformer to a U-Net to predict short-term precipitation from prior observations, reaching 59%, 78% and 82% accuracy at 0.1, 3 and 100 mm thresholds.","significance":2,"cited_by":38,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14184654","title":"Evaluation and Calibration of Remotely Sensed High Winds from the HY-2B/C/D Scatterometer in Tropical Cyclones","authors":["Xiaohui Li","Jingsong Yang","Jiuke Wang","Guoqi Han"],"date":"2022-09-17","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14184654","openalex":"W4296365647"},"links":{"paper":"https://doi.org/10.3390/rs14184654","pdf":"https://www.mdpi.com/2072-4292/14/18/4654/pdf?version=1663413598"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","stations"],"status":"research","summary":"Backpropagation neural network corrects underestimated high winds from HY-2B/C/D scatterometers in tropical cyclones, cutting RMSE by 20.4% to 3.40 m/s.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-wes-7-1905-2022","title":"Statistical post-processing of reanalysis wind speeds at hub heights using a diagnostic wind model and neural networks","authors":["Sebastian Brune","Jan D. Keller"],"date":"2022-09-16","year":2022,"venue":"Wind energy science","venue_type":"journal","ids":{"doi":"10.5194/wes-7-1905-2022","openalex":"W4296281576"},"links":{"paper":"https://doi.org/10.5194/wes-7-1905-2022","pdf":"https://wes.copernicus.org/articles/7/1905/2022/wes-7-1905-2022.pdf"},"orgs":["dwd"],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Neural network and GLM correct COSMO-REA6 reanalysis wind speeds at 100 m after diagnostic wind-model downscaling, reducing RMSE by almost 30% in Central Europe.","significance":3,"cited_by":1,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-nhess-22-3015-2022","title":"Machine learning models to predict myocardial infarctions from past climatic and environmental conditions","authors":["Lennart Marien","Mahyar Valizadeh","Wolfgang zu Castell","Christine Nam","Diana Rechid","Alexandra Elisabeth Schneider","Christine Meisinger","Jakob Linseisen","Kathrin Wolf","Laurens M. Bouwer"],"date":"2022-09-16","year":2022,"venue":"Natural hazards and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/nhess-22-3015-2022","openalex":"W4296280755"},"links":{"paper":"https://doi.org/10.5194/nhess-22-3015-2022","pdf":"https://nhess.copernicus.org/articles/22/3015/2022/nhess-22-3015-2022.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Regression models predict annual myocardial infarction counts in Augsburg from weather, air pollution and demographics, reaching adjusted R² of 0.59 to 0.71.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-7051-2022","title":"Classification of tropical cyclone containing images using a convolutional neural network: performance and sensitivity to the learning dataset","authors":["Sébastien Gardoll","Oliviér Boucher"],"date":"2022-09-16","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-7051-2022","openalex":"W4296058502"},"links":{"paper":"https://doi.org/10.5194/gmd-15-7051-2022","pdf":"https://gmd.copernicus.org/articles/15/7051/2022/gmd-15-7051-2022.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"CNN classifies ERA5 and MERRA-2 fields for tropical cyclone presence, and ERA5-trained models transfer better to MERRA-2 than the reverse.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40808-022-01523-2","title":"Modeling drought-related yield losses using new geospatial technologies and machine learning approaches: case of the Gharb plain, North-West Morocco","authors":["Oualid Hakam","Abdennasser Baali","Atef Belhaj Ali"],"date":"2022-09-16","year":2022,"venue":"Modeling Earth Systems and Environment","venue_type":"journal","ids":{"doi":"10.1007/s40808-022-01523-2","openalex":"W4296041436"},"links":{"paper":"https://doi.org/10.1007/s40808-022-01523-2"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Geospatial data and machine learning model drought-related yield losses in Morocco's Gharb plain; the missing abstract limits assessment beyond this scope.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-15-5219-2022","title":"On the potential of a neural-network-based approach for estimating XCO 2 from OCO-2 measurements","authors":["François‐Marie Bréon","Leslie David","Pierre Chatelanaz","Frédéric Chevallier"],"date":"2022-09-15","year":2022,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-15-5219-2022","openalex":"W4296105625"},"links":{"paper":"https://doi.org/10.5194/amt-15-5219-2022"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","stations"],"status":"research","summary":"Revised neural network retrieves OCO-2 XCO2 without the weak CO2 band, capturing downwind emission plumes absent from training data, though latitude and date leakage was found.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-agriculture12091473","title":"Towards Resilient Agriculture to Hostile Climate Change in the Sahel Region: A Case Study of Machine Learning-Based Weather Prediction in Senegal","authors":["Chimango Nyasulu","Awa Diattara","Assitan Traore","Abdoulaye Dème","Cheikh Ba"],"date":"2022-09-15","year":2022,"venue":"Agriculture","venue_type":"journal","ids":{"doi":"10.3390/agriculture12091473","openalex":"W4296107732"},"links":{"paper":"https://doi.org/10.3390/agriculture12091473","pdf":"https://www.mdpi.com/2077-0472/12/9/1473/pdf?version=1663222560"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Ensemble of ten regressors forecasts daily rainfall, humidity and temperatures in Senegal, with R² of 0.82–0.93 for the ensemble model.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.10102","title":"Multi-time Predictions of Wildfire Grid Map using Remote Sensing Local Data","authors":["Hyung-Jin Yoon","Petros Voulgaris"],"date":"2022-09-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.10102"},"links":{"paper":"https://arxiv.org/abs/2209.10102","pdf":"https://arxiv.org/pdf/2209.10102"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["medium","s2s"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Distributed online learning across ten western US locations predicts wildfire grid maps one to four weeks ahead from remote sensing data, handling incomplete observations.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W4312197160","title":"Yapay Sinir Ağları ile Hava Durumu Tahmini ve Çok Katmanlı Ağ Modeli için LabVIEW Arayüz Tasarımı","authors":["Serdar Özkaya","Gökhan Atalı"],"date":"2022-09-14","year":2022,"venue":"DergiPark (Istanbul University)","venue_type":"preprint","ids":{"openalex":"W4312197160"},"links":{"paper":"https://dergipark.org.tr/tr/pub/joinssr/issue/74246/1175302","pdf":"https://dergipark.org.tr/tr/pub/joinssr/issue/74246/1175302"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A backpropagation neural network with a LabVIEW interface is built for weather condition forecasting; the abstract reports no quantitative results.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.rser.2022.112897","title":"A transfer method to estimate hub-height wind speed from 10 meters wind speed based on machine learning","authors":["Shuang Yu","Robert Vautard"],"date":"2022-09-14","year":2022,"venue":"Renewable and Sustainable Energy Reviews","venue_type":"journal","ids":{"doi":"10.1016/j.rser.2022.112897","openalex":"W4295780722"},"links":{"paper":"https://doi.org/10.1016/j.rser.2022.112897"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A machine learning transfer method estimates hub-height wind speed from 10 m wind for wind-energy resource assessment; the abstract is missing, so scope is inferred from the title.","significance":2,"cited_by":52,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-2024020-v1","title":"Machine Learning Weather Analogs for Renewable Forecasting","authors":["Weiming Hu","Guido Cervone","George S. Young","Luca Delle Monache"],"date":"2022-09-13","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-2024020/v1","openalex":"W4297890772"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-2024020/v1","pdf":"https://www.researchsquare.com/article/rs-2024020/latest.pdf"},"orgs":[],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml","other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Deep-learning latent similarity metric for analog ensembles outperforms the original AnEn in RMSE, bias and CRPS for wind and solar forecasts in Pennsylvania.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10546-022-00727-4","title":"Machine Learning for Improving Surface-Layer-Flux Estimates","authors":["Tyler C. McCandless","David John Gagne","Branko Kosović","Sue Ellen Haupt","Bai Yang","Charles Becker","John S. Schreck"],"date":"2022-09-13","year":2022,"venue":"Boundary-Layer Meteorology","venue_type":"journal","ids":{"doi":"10.1007/s10546-022-00727-4","openalex":"W4295422248"},"links":{"paper":"https://doi.org/10.1007/s10546-022-00727-4","pdf":"https://link.springer.com/content/pdf/10.1007/s10546-022-00727-4.pdf"},"orgs":["noaa","ncar"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural network and random forest estimate surface momentum, heat and moisture fluxes from tower observations, outperforming Monin-Obukhov similarity parametrizations used in atmospheric models.","significance":3,"cited_by":39,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.04947","title":"Kernel Learning for Explainable Climate Science","authors":["Vidhi Lalchand","Kenza Tazi","Talay M. Cheema","Richard E. Turner","Scott Hosking"],"date":"2022-09-11","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.04947"},"links":{"paper":"https://arxiv.org/abs/2209.04947","pdf":"https://arxiv.org/pdf/2209.04947"},"orgs":[],"topic":"observations-remote-sensing","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Gaussian processes with non-stationary Gibbs kernels reconstruct Upper Indus Basin precipitation patterns with uncertainty, outperforming stationary and deep GP baselines.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-asce-wr.1943-5452.0001612","title":"Downscaling of Precipitation for Climate Change Projections Using Multiple Machine Learning Techniques: Case Study of Shenzhen City, China","authors":["Jing‐Cheng Han","Wenting Zheng","Zhe Liu","Yang Zhou","Yuefei Huang","Bing Li"],"date":"2022-09-10","year":2022,"venue":"Journal of Water Resources Planning and Management","venue_type":"journal","ids":{"doi":"10.1061/(asce)wr.1943-5452.0001612","openalex":"W4295127842"},"links":{"paper":"https://doi.org/10.1061/(asce)wr.1943-5452.0001612"},"orgs":["tsinghua-university"],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"SVM and MLP downscale GCM output to daily precipitation at 10 Shenzhen stations, outperforming SDSM and projecting ensemble precipitation trends to 2100.","significance":3,"cited_by":13,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.04693","title":"Reconstruction of Long-Term Historical Demand Data","authors":["Reshmi Ghosh","Michael Craig","H. Scott Matthews","Constantine Samaras","Laure Berti-Equille"],"date":"2022-09-10","year":2022,"venue":"Proceedings of the 38 th International Conference on Machine Learning, PMLR 139, 2021","venue_type":"journal","ids":{"arxiv":"2209.04693"},"links":{"paper":"https://arxiv.org/abs/2209.04693","pdf":"https://arxiv.org/pdf/2209.04693"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine and deep learning back-forecasting models reconstruct multidecadal US electricity demand records to separate temperature-driven natural variability from climate change effects.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-2022-50","title":"Neural networks for data assimilation of surface and upper-air data in Rio de Janeiro","authors":["Vinícius Albuquerque de Almeida","Haroldo Fraga de Campos Velho","Gutemberg Borges França","Nelson F. F. Ebecken"],"date":"2022-09-09","year":2022,"venue_type":"other","ids":{"doi":"10.5194/gmd-2022-50","openalex":"W4295066991"},"links":{"paper":"https://doi.org/10.5194/gmd-2022-50","pdf":"https://gmd.copernicus.org/preprints/gmd-2022-50/gmd-2022-50.pdf"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"Neural networks emulate 3D-Var analysis of surface and upper-air variables in a WRF setup over Rio de Janeiro, cutting assimilation CPU time 25–121 times.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su141811310","title":"Learning the Indicative Patterns of Simulated Force Changes in Soil Moisture by BP Neural Networks and Finding Differences with SMAP Observations","authors":["Xiaoning Li","Hongwei Zhao","Chong Sun","Xiaofeng Li","Xiaolin Li","Yang Zhao","Xuezhi Wang"],"date":"2022-09-09","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su141811310","openalex":"W4295214844"},"links":{"paper":"https://doi.org/10.3390/su141811310","pdf":"https://www.mdpi.com/2071-1050/14/18/11310/pdf?version=1662711223"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip","satellite"],"status":"research","summary":"A neural network with Deep Taylor Decomposition attributes simulated soil moisture changes to forcing agents and compares the signals with SMAP observations.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.04259","title":"Knowledge-based Deep Learning for Modeling Chaotic Systems","authors":["Zakaria Elabid","Tanujit Chakraborty","Abdenour Hadid"],"date":"2022-09-09","year":2022,"venue":"2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)","venue_type":"journal","ids":{"arxiv":"2209.04259","doi":"10.1109/icmla55696.2022.00111"},"links":{"paper":"https://arxiv.org/abs/2209.04259","pdf":"https://arxiv.org/pdf/2209.04259"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Knowledge-based deep learning trains on simulated and real data plus physics losses to forecast extreme events in chaotic systems, including El Niño SST and precipitation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-022-17323-8","title":"Increasing typhoon impact and economic losses due to anthropogenic warming in Southeast China","authors":["Mingfeng Huang","Qing Wang","Maofeng Liu","Ning Lin","Yifan Wang","Renzhi Jing","Jian‐Ping Sun","Hiroyuki Murakami","Wenjuan Lou"],"date":"2022-09-08","year":2022,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-022-17323-8","openalex":"W4294993221"},"links":{"paper":"https://doi.org/10.1038/s41598-022-17323-8","pdf":"https://www.nature.com/articles/s41598-022-17323-8.pdf"},"orgs":["noaa","princeton-university"],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["km-scale-sim","other"],"status":"research","summary":"Convection-permitting simulations with ML damage models project 128% higher typhoon losses for Southeast China under RCP8.5 warming, with 50-year losses up 20–170%.","significance":3,"cited_by":56,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021jd036198","title":"Identifying Eastern US Atmospheric River Types and Evaluating Historical Trends","authors":["Craig A. Ramseyer","Tyler J. Stanfield","Zachary Van Tol","Tyler Gingrich","Parker Henry","Peter Forister","Bradley F. Lamkin","Shakira D. Stackhouse","Samrin Sumaiya Sauda"],"date":"2022-09-07","year":2022,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2021jd036198","openalex":"W4297183121"},"links":{"paper":"https://doi.org/10.1029/2021jd036198","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021JD036198"},"orgs":["university-of-oklahoma"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Self-organizing maps identify Eastern US atmospheric river types and show rising trends for Nor'easter and Gulf of Mexico ARs.","significance":3,"cited_by":13,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-nhess-22-2943-2022","title":"A satellite lightning observation operator for storm-scale numerical weather prediction","authors":["Pauline Combarnous","Félix Erdmann","Olivier Caumont","Éric Defer","Maud Martet"],"date":"2022-09-06","year":2022,"venue":"Natural hazards and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/nhess-22-2943-2022","openalex":"W4294752400"},"links":{"paper":"https://doi.org/10.5194/nhess-22-2943-2022","pdf":"https://nhess.copernicus.org/articles/22/2943/2022/nhess-22-2943-2022.pdf"},"orgs":["meteo-france"],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Machine-learning regression maps AROME proxy variables to pseudo MTG lightning flash extent, giving a learned observation operator for storm-scale EnVar assimilation.","significance":3,"cited_by":4,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-6747-2022","title":"Downscaling multi-model climate projection ensembles with deep learning (DeepESD): contribution to CORDEX EUR-44","authors":["Jorge Baño‐Medina","Rodrigo Manzanas","Ezequiel Cimadevilla","Jesús Fernández","José González-Abad","Antonio S. Cofiño","José Manuel Gutiérrez"],"date":"2022-09-06","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-6747-2022","openalex":"W4294723728"},"links":{"paper":"https://doi.org/10.5194/gmd-15-6747-2022"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"DeepESD, a CNN multi-model ensemble, downscales eight CMIP5 GCMs to CORDEX EUR-44, matching RCM climate change signals with smaller precipitation spread.","significance":5,"cited_by":62,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-esd-13-1289-2022","title":"Combining machine learning and SMILEs to classify, better understand, and project changes in ENSO events","authors":["Nicola Maher","Thibault Paul Tabarin","Sebastian Milinski"],"date":"2022-09-06","year":2022,"venue":"Earth System Dynamics","venue_type":"journal","ids":{"doi":"10.5194/esd-13-1289-2022","openalex":"W4294754909"},"links":{"paper":"https://doi.org/10.5194/esd-13-1289-2022"},"orgs":["ncar","mpi-meteorology"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"Supervised classifier trained on 18 observation and reanalysis datasets labels Central and Eastern Pacific El Niño types, then shows the observed CP increase lies within internal variability in large ensembles.","significance":4,"cited_by":11,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-21-0003.1","title":"Hybrid Neural Network Models for Postprocessing Medium-Range Forecasts of Tropical Cyclone Tracks over the Western North Pacific","authors":["Hung Ming Cheung","Chang-Hoi Ho","Minhee Chang"],"date":"2022-09-06","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-21-0003.1","openalex":"W4294845118"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0003.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/1/4/AIES-D-21-0003.1.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["cnn","rnn"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Hybrid CNN-RNN-MLP network post-processes GEFS western North Pacific tropical cyclone tracks at 2–6 day leads, reducing track error and correcting speed and direction bias.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4368","title":"Towards improved precipitation estimation with the GOES‐16 advanced baseline imager: Algorithm and evaluation","authors":["Shruti Ashok Upadhyaya","Pierre‐Emmanuel Kirstetter","Robert J. Kuligowski","Maresa Searls"],"date":"2022-09-06","year":2022,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4368","openalex":"W4294770795"},"links":{"paper":"https://doi.org/10.1002/qj.4368","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/qj.4368"},"orgs":["noaa","university-of-oklahoma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis","radar"],"status":"research","summary":"A Random Forest precipitation estimator using GOES-16 ABI infrared channels and RAP predictors over CONUS beats SCaMPR, with correlation 0.46 and HSS 0.91 vs 0.19.","significance":4,"cited_by":10,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30574-wjarr.2022.15.3.0834","title":"Testing Neural Network (NN) algorithms implemented in MATLAB for the study of rainfall distribution patterns at different locations in Nigeria","authors":["N. O. Okoro","G. A. Agbo","J. N. Ofoma","C. E. Mbamara"],"date":"2022-09-04","year":2022,"venue":"World Journal of Advanced Research and Reviews","venue_type":"journal","ids":{"doi":"10.30574/wjarr.2022.15.3.0834","openalex":"W4294716036"},"links":{"paper":"https://doi.org/10.30574/wjarr.2022.15.3.0834","pdf":"https://wjarr.com/sites/default/files/WJARR-2022-0834.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"MATLAB neural networks map daily ECMWF-derived rainfall across Nigerian locations, showing rainfall decreases with distance from 4°N; the ML contribution is minimal.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-15-5033-2022","title":"GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm","authors":["Simon Pfreundschuh","Paula J. Brown","Christian D. Kummerow","Patrick Eriksson","Teodor Norrestad​​​​​​​"],"date":"2022-09-02","year":2022,"venue":"Atmospheric Measurement Techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-15-5033-2022","openalex":"W4294238315"},"links":{"paper":"https://doi.org/10.5194/amt-15-5033-2022"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Probabilistic neural GPROF-NN retrieves GPM surface precipitation, with a 3D CNN variant, improving GMI mean absolute error from 0.079 to 0.059 mm/h.","significance":4,"cited_by":41,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos13091424","title":"Multi-Model Ensemble Prediction of Summer Precipitation in China Based on Machine Learning Algorithms","authors":["Yang Jie","Ying Hong Xiang","Jiali Sun","Xiazhen Xu"],"date":"2022-09-02","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13091424","openalex":"W4294988569"},"links":{"paper":"https://doi.org/10.3390/atmos13091424","pdf":"https://www.mdpi.com/2073-4433/13/9/1424/pdf?version=1662125871"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Tree-based ML (decision tree, random forest, AdaBoost) combines four seasonal forecast systems for China summer rainfall, reaching ACC 0.30 versus 0.21 for simple averaging in 2019–2021.","significance":3,"cited_by":17,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.974497","title":"Application of artificial intelligence technology in typhoon monitoring and forecasting","authors":["Guanbo Zhou","Xiang Fang","Qifeng Qian","Xinyan Lv","Jie Cao","Yuan Ying Jiang"],"date":"2022-09-01","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.974497","openalex":"W4294045176"},"links":{"paper":"https://doi.org/10.3389/feart.2022.974497","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.974497/pdf"},"orgs":["nuist","cma"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Deep learning on Himawari-8 and FY-4 imagery identifies typhoon vortices (88.6% accuracy above strong tropical storm grade) and estimates intensity with 3.8 m/s MAE.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11947-j.agcs.2022.20210117","title":"Estimating the ZTD accuracy of NWM model with PSO and extended RBF neural network","authors":["Shuang Zhang","CHEN Xihong","Qiang Liu","Zan Liu","WANG Qingli"],"date":"2022-09-01","year":2022,"venue":"DOAJ (DOAJ: Directory of Open Access Journals)","venue_type":"preprint","ids":{"doi":"10.11947/j.agcs.2022.20210117","openalex":"W4386112620"},"links":{"paper":"https://doi.org/10.11947/j.agcs.2022.20210117"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"PSO-tuned extended RBF network estimates NWM zenith tropospheric delay accuracy against GNSS references, with average error better than 4 mm.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003219","title":"Correcting a 200 km Resolution Climate Model in Multiple Climates by Machine Learning From 25 km Resolution Simulations","authors":["Spencer Koncius Clark","Noah Brenowitz","Brian Henn","Anna Kwa","Jeremy McGibbon","W. A. Perkins","Oliver Watt‐Meyer","Christopher S. Bretherton","Lucas Harris"],"date":"2022-09-01","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003219","openalex":"W4294219199"},"links":{"paper":"https://doi.org/10.1029/2022ms003219","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003219"},"orgs":["ai2","noaa"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Machine-learned corrective tendencies from 25 km simulations improve a 200 km FV3GFS model's land precipitation pattern error by 8–28% across four SST-perturbed climates.","significance":4,"cited_by":33,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021wr031910","title":"Leveraging Spatial Patterns in Precipitation Forecasts Using Deep Learning to Support Regional Water Management","authors":["Chen Zhang","Zachary Brodeur","Scott Steinschneider","Jonathan D. Herman"],"date":"2022-09-01","year":2022,"venue":"Water Resources Research","venue_type":"journal","ids":{"doi":"10.1029/2021wr031910","openalex":"W4296558750"},"links":{"paper":"https://doi.org/10.1029/2021wr031910"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["cnn","classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"CNNs on GEFS precipitation fields for 1–14 day Sacramento precipitation occurrence; skill matches bias-corrected ensemble mean but cost-tunable thresholds help water management.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.2098","title":"A transformer neural network for predicting near‐surface temperature","authors":["Emy Alerskans","Joachim Nyborg","Morten Birk","Eigil Kaas"],"date":"2022-09-01","year":2022,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.2098","openalex":"W4306857384"},"links":{"paper":"https://doi.org/10.1002/met.2098","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.2098"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["transformer"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Transformer post-processing of NWP 2 m temperature, trained on crowd-sourced stations, cuts STD to 1.13 °C versus 1.96 °C for raw NWP.","significance":3,"cited_by":40,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.06998","title":"Ensemble‐Based Experimental Design for Targeting Data Acquisition to Inform Climate Models","authors":["Oliver R. A. Dunbar","Michael F. Howland","Tapio Schneider","Andrew M. Stuart"],"date":"2022-09-01","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2201.06998","doi":"10.1029/2022ms002997","openalex":"W4283732814"},"links":{"paper":"https://doi.org/10.1029/2022ms002997","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS002997"},"orgs":["mit","caltech"],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"An ensemble-based algorithm targets data acquisition to regions and times that most reduce parametric uncertainty in a GCM convection scheme, within calibrate-emulate-sample.","significance":3,"cited_by":12,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.47611-jsrhs.v11i3.2659","title":"Python-based Prediction of Rapid Intensification from MIMIC-TC Ensemble (PRIME)","authors":["Lorenzo Pulmano","Leya Joykutty","Juliana Caulkins"],"date":"2022-08-31","year":2022,"venue":"Journal of Student Research","venue_type":"journal","ids":{"doi":"10.47611/jsrhs.v11i3.2659","openalex":"W4324356021"},"links":{"paper":"https://doi.org/10.47611/jsrhs.v11i3.2659","pdf":"https://www.jsr.org/hs/index.php/path/article/download/2659/1319"},"orgs":[],"topic":"global-medium-range","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Machine and deep learning models predict intensity of newly formed blocking events at onset with error comparable to GEFS, using less computation.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.47611-jsrhs.v11i3.2655","title":"Predicting the intensity of blocking events using machine and deep learning","authors":["Emir Sahin","Juliana Caulkins","Leya Joykutty"],"date":"2022-08-31","year":2022,"venue":"Journal of Student Research","venue_type":"journal","ids":{"doi":"10.47611/jsrhs.v11i3.2655","openalex":"W4324356442"},"links":{"paper":"https://doi.org/10.47611/jsrhs.v11i3.2655","pdf":"https://www.jsr.org/hs/index.php/path/article/download/2655/1318"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A CNN ensemble (PRIME) predicts tropical cyclone rapid intensification from MIMIC-TC microwave imagery, but overfits and reaches only about 30% correct No-RI classifications.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl099368","title":"Wildfire Danger Prediction and Understanding With Deep Learning","authors":["Spyros Kondylatos","Ioannis Prapas","Michele Ronco","Ioannis Papoutsis","Gustau Camps‐Valls","María Piles","Miguel‐Ángel Fernández‐Torres","Nuno Carvalhais"],"date":"2022-08-31","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl099368","openalex":"W4293919465"},"links":{"paper":"https://doi.org/10.1029/2022gl099368","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL099368"},"orgs":["mpi-biogeochemistry"],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"model","method":[],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Deep learning predicts next-day wildfire danger in the Eastern Mediterranean, beating the Fire Weather Index, with explainable AI attributing importance to wetness variables.","significance":3,"cited_by":168,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.01191","title":"Long-term hail risk assessment with deep neural networks","authors":["Ivan Lukyanenko","Mikhail Mozikov","Yury Maximov","Ilya Makarov"],"date":"2022-08-31","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.01191","openalex":"W4294782969"},"links":{"paper":"https://arxiv.org/abs/2209.01191","pdf":"https://arxiv.org/pdf/2209.01191"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["climate"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Combines convolutional and recurrent layers to classify hail-favourable atmospheric profiles and forecast changes in hail frequency over coming decades.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.14833","title":"Predicting spatial distribution of Palmer Drought Severity Index","authors":["V. Grabar","A. Lukashevich","A. Zaytsev"],"date":"2022-08-31","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.14833","openalex":"W4294431802"},"links":{"paper":"https://arxiv.org/abs/2208.14833","pdf":"https://arxiv.org/pdf/2208.14833"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":["seasonal","climate"],"spatial":["regional","global"],"data":["cmip","other"],"status":"research","summary":"Spatio-temporal neural network predicts Palmer Drought Severity Index across regions, reaching R² 0.90 versus 0.85 for gradient boosting, and projects drought under climate scenarios.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15680-ijmrset.2022.0508010","title":"Leveraging Machine Learning for Real-Time Short-Term Snowfall Forecasting Using MultiSource Atmospheric and Terrain Data Integration","authors":["Vimal Raja Gopinathan"],"date":"2022-08-30","year":2022,"venue":"International Journal of Multidisciplinary Research in Science, Engineering and Technology.","venue_type":"journal","ids":{"doi":"10.15680/ijmrset.2022.0508010","openalex":"W4408467528"},"links":{"paper":"https://doi.org/10.15680/ijmrset.2022.0508010","pdf":"https://doi.org/10.15680/ijmrset.2022.0508010"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Random Forest and SVM predict 12-hour snowfall occurrence from meteorological and terrain data, with RF RMSE of 3.2 cm versus 5.1 cm for regression.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14174256","title":"Three-Dimensional Gridded Radar Echo Extrapolation for Convective Storm Nowcasting Based on 3D-ConvLSTM Model","authors":["Nengli Sun","Zeming Zhou","Qian Li","Jinrui Jing"],"date":"2022-08-29","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14174256","openalex":"W4293661589"},"links":{"paper":"https://doi.org/10.3390/rs14174256","pdf":"https://www.mdpi.com/2072-4292/14/17/4256/pdf?version=1661839175"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"3D-ConvLSTM extrapolates multi-altitude radar volumes for convective storm nowcasting, outperforming optical flow and 2D deep baselines at longer leads for 35 and 45 dBZ echoes.","significance":4,"cited_by":24,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-22-0009.1","title":"Short-Term Weather Forecast Skill of Artificial Neural Networks","authors":["Christopher C. Hennon","Andrew Coleman","Andrew Hill"],"date":"2022-08-29","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-22-0009.1","openalex":"W4293731191"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0009.1"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Neural networks trained on MOS, HRRR and NWS guidance cut 1-day temperature error 20–30% versus MOS at 11 US cities, though gains over linear regression were not significant.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0015.1","title":"Automated Identification of “Dunkelflaute” Events: A Convolutional Neural Network–Based Autoencoder Approach","authors":["Bowen Li","Sukanta Basu","Simon Jonathan Watson"],"date":"2022-08-29","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0015.1","openalex":"W4293863745"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0015.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/1/4/AIES-D-22-0015.1.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["applications-impacts"],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","nwp-analysis","cmip"],"status":"research","summary":"WISRnet combines a CNN autoencoder with k-means to identify Dunkelflaute periods from reanalysis-type wind and solar patterns, finding most events fall in 5 of 25 clusters.","significance":4,"cited_by":6,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.envsoft.2022.105475","title":"Extending SC-PDSI-PM with neural network regression using GLDAS data and Permutation Feature Importance","authors":["Saul G. Ramirez","Riley Chad Hales","Gustavious Paul Williams","Norman L. Jones"],"date":"2022-08-29","year":2022,"venue":"Environmental Modelling & Software","venue_type":"journal","ids":{"doi":"10.1016/j.envsoft.2022.105475","openalex":"W4293733620"},"links":{"paper":"https://doi.org/10.1016/j.envsoft.2022.105475"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural network regression extends the global PDSI drought index from GLDAS data, achieving RMSE below 1 over 99.5% of the globe and providing an updated dataset.","significance":3,"cited_by":35,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.13825","title":"Differentiable Programming for Earth System Modeling","authors":["Maximilian Gelbrecht","Alistair White","Sebastian Bathiany","Niklas Boers"],"date":"2022-08-29","year":2022,"venue":"Geoscientific Model Development, 2023, Volume 16, Issue 11, 3123-3135","venue_type":"journal","ids":{"arxiv":"2208.13825","doi":"10.5194/gmd-16-3123-2023","openalex":"W4379230313"},"links":{"paper":"https://arxiv.org/abs/2208.13825","pdf":"https://arxiv.org/pdf/2208.13825"},"orgs":["pik","tum"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"position","method":["differentiable","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Argues that making Earth system models automatically differentiable enables objective calibration and hybrid ML components, targeting climate sensitivity, spatial biases and abrupt transitions.","significance":4,"cited_by":31,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijeecs.v28.i1.pp508-515","title":"Machine learning based smart weather prediction","authors":["Rajasekaran Meenal","Kiruthic Kailash","Prawin Angel Michael","Jeyaraj Jency Joseph","Francisxavier Thomas Josh","Rajasekaran Ekambaram"],"date":"2022-08-27","year":2022,"venue":"Indonesian Journal of Electrical Engineering and Computer Science","venue_type":"journal","ids":{"doi":"10.11591/ijeecs.v28.i1.pp508-515","openalex":"W4293324552"},"links":{"paper":"https://doi.org/10.11591/ijeecs.v28.i1.pp508-515","pdf":"https://ijeecs.iaescore.com/index.php/IJEECS/article/download/28819/16724"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares linear regression, SVM and decision trees with empirical models for station precipitation, humidity, wind and radiation forecasts in India, reporting MSE 0.1397.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w14172632","title":"Improved Monthly and Seasonal Multi-Model Ensemble Precipitation Forecasts in Southwest Asia Using Machine Learning Algorithms","authors":["Morteza Pakdaman","Iman Babaeian","Laurens M. Bouwer"],"date":"2022-08-26","year":2022,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w14172632","openalex":"W4293724423"},"links":{"paper":"https://doi.org/10.3390/w14172632","pdf":"https://www.mdpi.com/2073-4441/14/17/2632/pdf?version=1662022460"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"Random forest and ANN post-processing of four NMME models gives better monthly and seasonal precipitation forecasts over Southwest Asia than individual models.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11069-022-05546-x","title":"Comparison of different forecasting tools for short-range lightning strike risk assessment","authors":["Aurélie Bouchard","Magalie Buguet","Adrien Chan-Hon-Tong","Jean Dezert","P. Lalande"],"date":"2022-08-26","year":2022,"venue":"Natural Hazards","venue_type":"journal","ids":{"doi":"10.1007/s11069-022-05546-x","openalex":"W4293206995"},"links":{"paper":"https://doi.org/10.1007/s11069-022-05546-x","pdf":"https://link.springer.com/content/pdf/10.1007/s11069-022-05546-x.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Compares threshold, neural network and belief-function methods for 0–24 h lightning strike risk over the sea for aviation, with WWLLN ground truth.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2022.925068","title":"Predictability of sea surface temperature anomalies at the eastern pole of the Indian Ocean Dipole—using a convolutional neural network model","authors":["Ming Feng","Fabio Boschetti","Fenghua Ling","Xuebin Zhang","Jason R. Hartog","Akhtar Mahmood","Li Shi","Brint Gardner","Jing‐Jia Luo","Alistair James Hobday"],"date":"2022-08-25","year":2022,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2022.925068","openalex":"W4293036644"},"links":{"paper":"https://doi.org/10.3389/fclim.2022.925068","pdf":"https://www.frontiersin.org/articles/10.3389/fclim.2022.925068/pdf"},"orgs":["nuist","bom-australia"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A CNN trained on CMIP5/6 models forecasts eastern Indian Ocean Dipole SST anomalies up to 6 months ahead, matching the ACCESS-S2 dynamical model.","significance":3,"cited_by":23,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.24084-repqj20.297","title":"Wind Power Forecasting with Machine Learning: Single and combined methods","authors":["J. Rosa","S. Pestana","C. Leandro","Carlos Geraldes","J. Esteves","R&D NESTER, Centro de Investigação em Energia REN - State Grid, S.A. – Lisbon.      Portugal","D. Carvalho"],"date":"2022-08-25","year":2022,"venue":"Renewable Energy and Power Quality Journal","venue_type":"journal","ids":{"doi":"10.24084/repqj20.297","openalex":"W4293092153"},"links":{"paper":"https://doi.org/10.24084/repqj20.297","pdf":"https://doi.org/10.24084/repqj20.297"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine learning pipeline to improve NWP-based wind power forecasts in Portugal, targeting under 10% error; results are modest and the method is not novel.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijai.v11.i4.pp1535-1544","title":"Weather prediction performance evaluation on selected machine learning algorithms","authors":["Muyideen AbdulRaheem","Joseph Bamidele Awotunde","Abidemi Emmanuel Adeniyi","Idowu Dauda Oladipo","Sekinat Olaide Adekola"],"date":"2022-08-25","year":2022,"venue":"IAES International Journal of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.11591/ijai.v11.i4.pp1535-1544","openalex":"W4293093027"},"links":{"paper":"https://doi.org/10.11591/ijai.v11.i4.pp1535-1544","pdf":"https://ijai.iaescore.com/index.php/IJAI/article/download/21737/13496"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Compares decision tree, k-NN and logistic regression classifiers for weather prediction on a Kaggle dataset, with a Flask demo application; small-scale evaluation.","significance":1,"cited_by":14,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.07568","title":"Physically Constrained Generative Adversarial Networks for Improving Precipitation Fields from Earth System Models","authors":["Philipp Hess","Markus Drüke","Stefan Petri","Felix M. Strnad","Niklas Boers"],"date":"2022-08-25","year":2022,"venue":"Nature Machine Intelligence","venue_type":"journal","ids":{"arxiv":"2209.07568","doi":"10.1038/s42256-022-00540-1","openalex":"W4300861245"},"links":{"paper":"https://arxiv.org/abs/2209.07568","pdf":"https://arxiv.org/pdf/2209.07568"},"orgs":["pik","tum"],"topic":"downscaling","topics":["climate-emulation"],"type":"model","method":["gan-vae","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A physically constrained GAN corrects Earth system model precipitation, fixing local distributions and the double-peaked ITCZ while preserving global precipitation sums under future scenarios.","significance":5,"cited_by":93,"score":50,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2022gl098566","title":"Interpretable Deep Learning for Probabilistic MJO Prediction","authors":["Antoine P. Delaunay","Hannah M. Christensen"],"date":"2022-08-24","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl098566","openalex":"W4293088006"},"links":{"paper":"https://doi.org/10.1029/2022gl098566"},"orgs":["university-of-oxford"],"topic":"s2s-seasonal","topics":["probabilistic-ensembles","xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["global"],"data":["other"],"status":"research","summary":"A CNN gives skilful probabilistic MJO forecasts whose uncertainty tracks instantaneous predictability, using predicted standard deviation and Monte Carlo dropout.","significance":4,"cited_by":26,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.11619","title":"Calibrated and Enhanced NRLMSIS 2.0 Model with Uncertainty Quantification","authors":["Richard J. Licata","Piyush M. Mehta","Daniel R. Weimer","W. Kent Tobiska","Jean Yoshii"],"date":"2022-08-24","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.11619","doi":"10.1029/2022sw003267"},"links":{"paper":"https://arxiv.org/abs/2208.11619","pdf":"https://arxiv.org/pdf/2208.11619"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"ML exospheric temperature model calibrates NRLMSIS 2.0 against satellite density, cutting model-satellite differences by 25% with calibrated uncertainty intervals.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-esd-13-1157-2022","title":"Improving the prediction of the Madden–Julian Oscillation of the ECMWF model by post-processing","authors":["Riccardo Silini","Sebastian Lerch","Nikolaos Mastrantonas","Hölger Kantz","Marcelo Barreiro","Cristina Masoller"],"date":"2022-08-23","year":2022,"venue":"Earth System Dynamics","venue_type":"journal","ids":{"doi":"10.5194/esd-13-1157-2022","openalex":"W4292839024"},"links":{"paper":"https://doi.org/10.5194/esd-13-1157-2022","pdf":"https://esd.copernicus.org/articles/13/1157/2022/esd-13-1157-2022.pdf"},"orgs":["ecmwf","kit"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Machine learning post-processing of ECMWF forecasts improves MJO prediction, outperforming multiple linear regression in location and intensity skill.","significance":4,"cited_by":12,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.egyr.2022.08.159","title":"Wind power forecast based on variational mode decomposition and long short term memory attention network","authors":["Xiao Zhou","Chengxi Liu","Yongjian Luo","Baoying Wu","Nan Dong","Tianying Xiao","Haojun Zhu"],"date":"2022-08-23","year":2022,"venue":"Energy Reports","venue_type":"journal","ids":{"doi":"10.1016/j.egyr.2022.08.159","openalex":"W4292852496"},"links":{"paper":"https://doi.org/10.1016/j.egyr.2022.08.159"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["rnn","transformer"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"VMD decomposition with an attention-LSTM encoder-decoder improves wind power forecasts from NWP inputs over several benchmark models.","significance":2,"cited_by":30,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.egyr.2022.08.105","title":"Machine learning forecasts of Scandinavian numerical weather prediction wind model residuals with control theory for wind energy","authors":["Hao Chen","Qixia Zhang","Yngve Birkelund"],"date":"2022-08-22","year":2022,"venue":"Energy Reports","venue_type":"journal","ids":{"doi":"10.1016/j.egyr.2022.08.105","openalex":"W4293793656"},"links":{"paper":"https://doi.org/10.1016/j.egyr.2022.08.105"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine learning forecasts residuals of NWP wind speed and direction at an Arctic wind farm, enabling bias correction of NWP inputs for wind power forecasting.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w14162570","title":"Gated Attention Recurrent Neural Network: A Deeping Learning Approach for Radar-Based Precipitation Nowcasting","authors":["Guanchen Wu","Wenhui Chen","Hoe-Kyung Jung"],"date":"2022-08-20","year":2022,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w14162570","openalex":"W4292603718"},"links":{"paper":"https://doi.org/10.3390/w14162570","pdf":"https://www.mdpi.com/2073-4441/14/16/2570/pdf?version=1661238568"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Gated attention recurrent network with multi-order Markov memory predicts radar echo sequences for precipitation nowcasting, improving on first-order spatiotemporal models.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.09473","title":"Carefully choose the baseline: Lessons learned from applying XAI attribution methods for regression tasks in geoscience","authors":["Antonios Mamalakis","Elizabeth A. Barnes","Imme Ebert-Uphoff"],"date":"2022-08-19","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2208.09473","doi":"10.1175/aies-d-22-0058.1","openalex":"W4310442430"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0058.1","pdf":"https://arxiv.org/pdf/2208.09473"},"orgs":["colorado-state-university"],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Shows XAI attributions for a climate-signal network change substantially with the chosen baseline, using large-ensemble SSP3-7.0 simulations, so baseline choice must match the science question.","significance":4,"cited_by":47,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14164033","title":"Projection of Future Extreme Precipitation in China Based on the CMIP6 from a Machine Learning Perspective","authors":["Yilin Yan","Hao Wang","Guoping Li","Xia Jin","Fei Ge","Qiangyu Zeng","Xinyue Ren","Linyin Tan"],"date":"2022-08-18","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14164033","openalex":"W4292551447"},"links":{"paper":"https://doi.org/10.3390/rs14164033","pdf":"https://www.mdpi.com/2072-4292/14/16/4033/pdf?version=1660898857"},"orgs":["cma"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Machine learning ensemble of 27 CMIP6 models improves China extreme precipitation simulation and projects increases of up to 13.7% by late century.","significance":3,"cited_by":43,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl099012","title":"Showcasing MESMER‐X: Spatially Resolved Emulation of Annual Maximum Temperatures of Earth System Models","authors":["Yann Quilcaille","Lukas Gudmundsson","Lea Beusch","Mathias Hauser","Sonia Isabelle Seneviratne"],"date":"2022-08-18","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl099012","openalex":"W4292409458"},"links":{"paper":"https://doi.org/10.1029/2022gl099012","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL099012"},"orgs":["meteoswiss","eth-zurich"],"topic":"climate-emulation","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"MESMER-X statistical emulator reproduces spatially resolved annual maximum temperatures of Earth system models using global mean temperature as the driver.","significance":4,"cited_by":44,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10512196.1","title":"Physics-Incorporated Framework for Emulating Atmospheric Radiative Transfer and the Related Network Study","authors":["Yichen Yao","Xiaohui Zhong","Yongjun Zheng","Zhibin Wang"],"date":"2022-08-18","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10512196.1","openalex":"W4302081191"},"links":{"paper":"https://doi.org/10.1002/essoar.10512196.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10512196.1"},"orgs":["nuist","alibaba-damo"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["physics-constrained","rnn"],"timescale":[],"spatial":[],"data":["nwp-analysis","other"],"status":"research","summary":"Physics-incorporated network enforces energy conservation between fluxes and heating rates for fast radiative transfer emulation; Bi-LSTM performs best among tested architectures.","significance":3,"cited_by":4,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.09079","title":"A Multi-Modal Wildfire Prediction and Personalized Early-Warning System Based on a Novel Machine Learning Framework","authors":["Rohan Tan Bhowmik"],"date":"2022-08-18","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.09079"},"links":{"paper":"https://arxiv.org/abs/2208.09079","pdf":"https://arxiv.org/pdf/2208.09079"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["rnn","cnn"],"timescale":["medium"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"U-ConvLSTM wildfire prediction using environmental and meteorological data reaches over 97% accuracy and predicts 2018 California fires 5-14 days ahead, versus about 76% for CNNs.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.08956","title":"DeepClouds.ai: Deep learning enabled computationally cheap direct numerical simulations","authors":["Moumita Bhowmik","Manmeet Singh","Suryachandra Rao","Souvik Paul"],"date":"2022-08-18","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.08956","openalex":"W4292433510"},"links":{"paper":"https://arxiv.org/abs/2208.08956","pdf":"https://arxiv.org/pdf/2208.08956"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"A 3D U-Net emulates rising-cloud direct numerical simulations over larger domains, matching DNS score metrics without solving the dynamical core, aiming at cloud parameterization.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.08912","title":"Learning-based estimation of in-situ wind speed from underwater acoustics","authors":["Matteo Zambra","Dorian Cazau","Nicolas Farrugia","Alexandre Gensse","Sara Pensieri","Roberto Bozzano","Ronan Fablet"],"date":"2022-08-18","year":2022,"venue":"IEEE Journal of Oceanic Engineering","venue_type":"journal","ids":{"arxiv":"2208.08912","doi":"10.1109/joe.2023.3288970","openalex":"W4292434799"},"links":{"paper":"https://doi.org/10.1109/joe.2023.3288970","pdf":"https://arxiv.org/pdf/2208.08912"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["stations","era5"],"status":"research","summary":"A deep learning method that combines data assimilation ideas retrieves sea-surface wind speed time series from underwater acoustics, with up to 16% lower RMSE than prior data-driven methods.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.eswa.2022.118547","title":"Deep learning for downward longwave radiative flux forecasts in the Arctic","authors":["Dae-Hui Kim","Hyun Mee Kim"],"date":"2022-08-17","year":2022,"venue":"Expert Systems with Applications","venue_type":"journal","ids":{"doi":"10.1016/j.eswa.2022.118547","openalex":"W4292133429"},"links":{"paper":"https://doi.org/10.1016/j.eswa.2022.118547"},"orgs":[],"topic":"post-processing","topics":[],"type":"application","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["era5","nwp-analysis","stations"],"status":"research","summary":"CNN bias correction of ERA5 and PWRF downward longwave radiation in the Arctic reduces RMSE by 13–18% on independent 2020 data.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.37798-202170389","title":"Deep Neural Network Configuration Sensitivity Analysis in Wind Power Forecasting","authors":["Igor Kuzle","Josip Đaković","Bojan Franc","Yongqian Liu"],"date":"2022-08-16","year":2022,"venue":"Journal of Energy - Energija","venue_type":"journal","ids":{"doi":"10.37798/202170389","openalex":"W4292188496"},"links":{"paper":"https://doi.org/10.37798/202170389","pdf":"http://www.journalofenergy.com/index.php/joe/article/download/89/227"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"evaluation","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Deep recurrent networks trained on Croatian wind farm output and NWP forecasts are compared with operational tools, with a focus on configuration sensitivity.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.07581","title":"Regression modelling of spatiotemporal extreme U.S. wildfires via partially-interpretable neural networks","authors":["Jordan Richards","Raphaël Huser"],"date":"2022-08-16","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.07581"},"links":{"paper":"https://arxiv.org/abs/2208.07581","pdf":"https://arxiv.org/pdf/2208.07581"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Partially-interpretable neural networks for extreme quantile regression of U.S. wildfire risk, plus a point-process extreme value model avoiding finite lower-endpoint issues.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl098551","title":"Use of Machine Learning to Reduce Uncertainties in Particle Number Concentration and Aerosol Indirect Radiative Forcing Predicted by Climate Models","authors":["Fangqun Yu","Gan Luo","Arshad Arjunan Nair","Kostas Tsigaridis","Susanne Elizabeth Bauer"],"date":"2022-08-15","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl098551","openalex":"W4291383531"},"links":{"paper":"https://doi.org/10.1029/2022gl098551"},"orgs":["nasa"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Random forest surrogate for particle number concentration in GISS-ModelE2.1 reduces aerosol-cloud radiative forcing from -1.46 to -1.11 W m-2.","significance":4,"cited_by":19,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.08151","title":"Efficient Climate Simulation via Machine Learning Method","authors":["Xin Wang","Wei Xue","Yilun Han","Guangwen Yang"],"date":"2022-08-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.08151","openalex":"W4296556788"},"links":{"paper":"https://arxiv.org/abs/2209.08151","pdf":"https://arxiv.org/pdf/2209.08151","code":"https://github.com/x-w19/NeuroClim"},"orgs":["tsinghua-university"],"topic":"benchmarks-data-eval","topics":["hybrid-parameterization","infra-software"],"type":"benchmark","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"NeuroClim provides a hybrid climate modeling platform, open dataset, and stability and approximation metrics for learning climate simulation components.","significance":3,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.06848","title":"Urban precipitation downscaling using deep learning: a smart city application over Austin, Texas, USA","authors":["Manmeet Singh","Nachiketa Acharya","Sajad Jamshidi","Junfeng Jiao","Zong-Liang Yang","Marc Coudert","Zach Baumer","Dev Niyogi"],"date":"2022-08-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.06848","openalex":"W4296154993"},"links":{"paper":"https://arxiv.org/abs/2209.06848","pdf":"https://arxiv.org/pdf/2209.06848"},"orgs":["noaa"],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["local","regional"],"data":["satellite"],"status":"research","summary":"Iterative SRCNN downscales 10 km JAXA GsMAP satellite precipitation to 300 m over Austin, Texas, beating cubic interpolation on PSNR and mutual information.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.07004","title":"AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N","authors":["Tianyu Zhang","Andrew Williams","Soham Phade","Sunil Srinivasa","Yang Zhang","Prateek Gupta","Yoshua Bengio","Stephan Zheng"],"date":"2022-08-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.07004"},"links":{"paper":"https://arxiv.org/abs/2208.07004","pdf":"https://arxiv.org/pdf/2208.07004"},"orgs":[],"topic":"applications-impacts","topics":["climate-emulation"],"type":"model","method":["reinforcement-learning"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"RICE-N integrated assessment model with multi-agent reinforcement learning simulates climate-economy negotiations to test cooperation frameworks for climate mitigation agreements.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13081291","title":"Weather Radar Nowcasting for Extreme Precipitation Prediction Based on the Temporal and Spatial Generative Adversarial Network","authors":["Xunlai Chen","Mingjie Wang","Shuxin Wang","Yuanzhao Chen","Rui Wang","Chunyang Zhao","Xiao Hong Hu"],"date":"2022-08-14","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13081291","openalex":"W4291366335"},"links":{"paper":"https://doi.org/10.3390/atmos13081291","pdf":"https://www.mdpi.com/2073-4433/13/8/1291/pdf?version=1660462219"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["gan-vae","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"pre-operational","summary":"TSGAN uses spatio-temporal GAN with attention for radar nowcasting of strong convection, giving sharper forecasts than optical flow and deep baselines; it is reported as used in an operational system.","significance":4,"cited_by":25,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2209.06901","title":"Simulation of Atlantic Hurricane Tracks and Features: A Deep Learning Approach","authors":["Rikhi Bose","Adam L. Pintar","Emil Simiu"],"date":"2022-08-12","year":2022,"venue_type":"preprint","ids":{"arxiv":"2209.06901","openalex":"W4296154378"},"links":{"paper":"https://arxiv.org/abs/2209.06901","pdf":"https://arxiv.org/pdf/2209.06901"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning trajectory and intensity models trained on HURDAT2 generate synthetic Atlantic hurricanes whose landfall locations and wind speeds match historical records.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14163890","title":"NeXtNow: A Convolutional Deep Learning Model for the Prediction of Weather Radar Data for Nowcasting Purposes","authors":["Alexandra-Ioana Albu","Gabriela Czibula","Andrei Mihai","István Gergely Czibula","Sorin Burcea","Abdelkader Mezghani"],"date":"2022-08-11","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14163890","openalex":"W4290999163"},"links":{"paper":"https://doi.org/10.3390/rs14163890","pdf":"https://www.mdpi.com/2072-4292/14/16/3890/pdf?version=1660221985"},"orgs":["met-norway"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"NeXtNow, a ResNeXt-based encoder-decoder, predicts future radar frames from Romanian and Norwegian data, improving CSI by 1–17% over XNow.","significance":3,"cited_by":19,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app12168028","title":"Typhoon Track Prediction Based on Deep Learning","authors":["Jia Ren","Nan Xu","Yani Cui"],"date":"2022-08-11","year":2022,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app12168028","openalex":"W4291016023"},"links":{"paper":"https://doi.org/10.3390/app12168028","pdf":"https://www.mdpi.com/2076-3417/12/16/8028/pdf?version=1692764887"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A CNN-LSTM hybrid (C-LSTM) predicts South China Sea typhoon tracks using Granger-selected meteorological features, showing smaller errors than a plain LSTM.","significance":2,"cited_by":22,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-ep.13977","title":"Photovoltaic power intra‐ and day‐ahead predictions with differential learning producing PDE ‐modular models based on the node L‐transform derivatives","authors":["Ladislav Zjavka"],"date":"2022-08-11","year":2022,"venue":"Environmental Progress & Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1002/ep.13977","openalex":"W4291007263"},"links":{"paper":"https://doi.org/10.1002/ep.13977"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Differential polynomial neural network with PDE-modular structure predicts intra-day and day-ahead PV output from weather and plant records, compared against statistical and probabilistic baselines.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.05855","title":"Predicting Tornadoes days ahead with Machine Learning","authors":["Davide Alessandro Coccomini","Giuliano Zara"],"date":"2022-08-11","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.05855"},"links":{"paper":"https://arxiv.org/abs/2208.05855","pdf":"https://arxiv.org/pdf/2208.05855"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning system predicts tornadoes up to five days ahead with up to 84% probability on a new dataset of over 5,000 events.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021jd036214","title":"On the Application of an Observations‐Based Machine Learning Parameterization of Surface Layer Fluxes Within an Atmospheric Large‐Eddy Simulation Model","authors":["Domingo Muñoz‐Esparza","Charles Becker","Jeremy Sauer","David John Gagne","John S. Schreck","Branko Kosović"],"date":"2022-08-10","year":2022,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2021jd036214","openalex":"W4292466410"},"links":{"paper":"https://doi.org/10.1029/2021jd036214","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021JD036214"},"orgs":["ncar"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["km-scale-sim","other"],"status":"research","summary":"Replaces Monin-Obukhov surface-layer flux schemes with neural networks in large-eddy simulations, showing modified boundary-layer structure and highlighting risks of unphysical predictions.","significance":4,"cited_by":17,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su14169830","title":"Automated Analysis of Australian Tropical Cyclones with Regression, Clustering and Convolutional Neural Network","authors":["Fahim K Sufi","Edris Alam","Musleh Alsulami"],"date":"2022-08-09","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su14169830","openalex":"W4296450946"},"links":{"paper":"https://doi.org/10.3390/su14169830","pdf":"https://www.mdpi.com/2071-1050/14/16/9830/pdf?version=1660113723"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["cnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies regression, clustering and CNN analysis to 28,713 Australian tropical cyclone records, identifying drivers of low central pressure and anomaly root causes.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1921429-v1","title":"Applying the Deep Neural Network to Estimate Future Trend and Uncertainty of Rainfall under Climate Change","authors":["Shiu‐Shin Lin","Wei-Li Yeh","Kai-Yang Zhu","Yu-Dong Ho","Wei‐Cheng Wu"],"date":"2022-08-09","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1921429/v1","openalex":"W4300076486"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1921429/v1","pdf":"https://www.researchsquare.com/article/rs-1921429/latest.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Applies a deep neural network to estimate future rainfall trends and their uncertainty under climate change; abstract unavailable, so classification is based on title only.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl098635","title":"Incorporating Uncertainty Into a Regression Neural Network Enables Identification of Decadal State‐Dependent Predictability in CESM2","authors":["Emily M Gordon","Elizabeth A. Barnes"],"date":"2022-08-09","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl098635","openalex":"W4291720110"},"links":{"paper":"https://doi.org/10.1029/2022gl098635","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL098635"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["decadal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Uncertainty-aware regression network in CESM2 finds low-uncertainty initial states for decadal sea surface temperature predictability linked to Atlantic and Pacific variability.","significance":4,"cited_by":42,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11600-022-00849-w","title":"Tropical cyclone detection in South Pacific and Atlantic coastal area using optical flow estimation and RESNET deep learning model","authors":["Nagu Malothu","Varre Venkata Kanaka Durga Vara Prasad","Battula Tirumala Krishna"],"date":"2022-08-09","year":2022,"venue":"Acta Geophysica","venue_type":"journal","ids":{"doi":"10.1007/s11600-022-00849-w","openalex":"W4292457828"},"links":{"paper":"https://doi.org/10.1007/s11600-022-00849-w"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Detects tropical cyclones in South Pacific and Atlantic coastal imagery by combining optical flow estimation with a ResNet deep learning classifier. Abstract unavailable.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.05424","title":"Hard-Constrained Deep Learning for Climate Downscaling","authors":["Paula Harder","Alex Hernandez-Garcia","Venkatesh Ramesh","Qidong Yang","Prasanna Sattigeri","Daniela Szwarcman","Campbell Watson","David Rolnick"],"date":"2022-08-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.05424","openalex":"W4290855611"},"links":{"paper":"https://arxiv.org/abs/2208.05424","pdf":"https://arxiv.org/pdf/2208.05424"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["physics-constrained","cnn"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip","other"],"status":"research","summary":"Hard constraints enforce conservation laws in deep learning climate downscaling models, improving accuracy and physical consistency across architectures and datasets.","significance":4,"cited_by":8,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2208.05419","title":"FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators","authors":["Thorsten Kurth","Shashank Subramanian","Peter Harrington","Jaideep Pathak","Morteza Mardani","David Hall","Andrea Miele","Karthik Kashinath","Animashree Anandkumar"],"date":"2022-08-08","year":2022,"venue":"Proceedings of the Platform for Advanced Scientific Computing Conference","venue_type":"preprint","ids":{"arxiv":"2208.05419","doi":"10.1145/3592979.3593412","openalex":"W4382048606"},"links":{"paper":"https://arxiv.org/abs/2208.05419","pdf":"https://arxiv.org/pdf/2208.05419"},"orgs":["lbnl-nersc","nvidia"],"topic":"infra-software","topics":[],"type":"model","method":["neural-operator","transformer"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"FourCastNet uses adaptive Fourier neural operators to produce global medium-range forecasts about 80,000 times faster than NWP, scaling to thousands of GPUs.","significance":6,"cited_by":263,"score":69,"highlight":true,"highlight_reason":"HPC-focused companion to FourCastNet showing scaling to thousands of GPUs and huge ensemble speedups; important for infrastructure, less novel scientifically.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2208.04390","title":"A Spatiotemporal-Aware Climate Model Ensembling Method for Improving Precipitation Predictability","authors":["Ming Fan","Dan Lu","Deeksha Rastogi","Eric M. Pierce"],"date":"2022-08-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.04390","doi":"10.1002/essoar.10512289.1","openalex":"W4294653706"},"links":{"paper":"https://arxiv.org/abs/2208.04390","pdf":"https://arxiv.org/pdf/2208.04390"},"orgs":["ornl"],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Bayesian neural network weights CMIP6 models per location and season, improving monthly US precipitation predictions over simple ensemble baselines with interpretable weights.","significance":4,"cited_by":2,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.04127","title":"Site adaptation with machine learning for a Northern Europe gridded solar radiation product","authors":["Sebastian Zainali","Dazhi Yang","Tomas Landelius","Pietro E. Campana"],"date":"2022-08-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.04127"},"links":{"paper":"https://arxiv.org/abs/2208.04127","pdf":"https://arxiv.org/pdf/2208.04127"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional","local"],"data":["stations","other"],"status":"research","summary":"Compares nine machine-learning site-adaptation methods to calibrate the STRÅNG gridded solar irradiance product in Sweden using three stations; no single method wins everywhere.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.compeleceng.2022.108271","title":"Cloudy/clear weather classification using deep learning techniques with cloud images","authors":["Mürüvvet Kalkan","Erkan Bostancı","Mehmet Serdar Güzel","Buğrahan Kalkan","Şifa Özsarı","Omurhan Avni Soysal","Güven Köse"],"date":"2022-08-06","year":2022,"venue":"Computers & Electrical Engineering","venue_type":"journal","ids":{"doi":"10.1016/j.compeleceng.2022.108271","openalex":"W4292691751"},"links":{"paper":"https://doi.org/10.1016/j.compeleceng.2022.108271"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Pretrained CNNs classify clear versus cloudy sky from ground-based photos, with VGG-16 reaching 91.4% accuracy as a tool for cloud-cover observation.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14153750","title":"Fusion of CMONOC and ERA5 PWV Products Based on Backpropagation Neural Network","authors":["Dong Ren","Yong Wang","Guocheng Wang","Lintao Liu"],"date":"2022-08-05","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14153750","openalex":"W4292451565"},"links":{"paper":"https://doi.org/10.3390/rs14153750","pdf":"https://www.mdpi.com/2072-4292/14/15/3750/pdf?version=1659690385"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations","satellite"],"status":"research","summary":"Backpropagation neural network fuses GNSS precipitable water vapour with ERA5, cutting ERA5 RMSE by 18.5% in China and raising correlation to 0.99.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-22-0020.1","title":"Adaptive Blending of Probabilistic Precipitation Forecasts with Emphasis on Calibration and Temporal Forecast Consistency","authors":["Martin Rempel","Peter Schaumann","Reinhold Hess","Volker Schmidt","Ulrich Blahak"],"date":"2022-08-04","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-22-0020.1","openalex":"W4289845923"},"links":{"paper":"https://doi.org/10.1175/aies-d-22-0020.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/1/4/AIES-D-22-0020.1.pdf"},"orgs":["dwd"],"topic":"post-processing","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Neural network blends two precipitation ensembles into calibrated hourly exceedance probabilities for +1 to +6 h, outperforming both inputs at all lead times.","significance":3,"cited_by":1,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-21-0011.1","title":"Application of Deep Learning to Understanding ENSO Dynamics","authors":["Na-Yeon Shin","Yoo‐Geun Ham","Jeong-Hwan Kim","Minsu Cho","Jong‐Seong Kug"],"date":"2022-08-04","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-21-0011.1","openalex":"W4289835106"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0011.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/1/4/AIES-D-21-0011.1.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics","s2s-seasonal"],"type":"application","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"CNN predicts ENSO nine months ahead with about 0.82 correlation; contribution maps identify three precursors with asymmetric roles in El Nino and La Nina.","significance":4,"cited_by":25,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.02494","title":"Tokyo Kion-On: Query-Based Generative Sonification of Atmospheric Data","authors":["Stefano Kalonaris"],"date":"2022-08-04","year":2022,"venue_type":"preprint","ids":{"arxiv":"2208.02494","doi":"10.21785/icad2022.039"},"links":{"paper":"https://arxiv.org/abs/2208.02494","pdf":"https://arxiv.org/pdf/2208.02494"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM-with-attention sonification of Tokyo air temperature from 1876 to 2021 as an interactive tool for exploring climate change data.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-21-0786.1","title":"Spatiotemporal Reconstruction of Antarctic Near-Surface Air Temperature from MODIS Observations","authors":["Xueying Zhang","Xu Dong","Jing Zeng","Shugui Hou","Paul C. J. P. Smeets","Carleen H. Reijmer","Yetang Wang"],"date":"2022-08-03","year":2022,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-21-0786.1","openalex":"W4289667056"},"links":{"paper":"https://doi.org/10.1175/jcli-d-21-0786.1"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations","era5"],"status":"research","summary":"Neural network reconstructs a monthly 0.05° Antarctic air temperature product from MODIS and 119 stations, with MAE 2.23 °C and better agreement with in situ data than ERA5.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.02383","title":"A new paradigm for medium-range severe weather forecasts: probabilistic random forest-based predictions","authors":["Aaron J. Hill","Russ S. Schumacher","Israel Jirak"],"date":"2022-08-03","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"arxiv":"2208.02383","doi":"10.1175/waf-d-22-0143.1","openalex":"W4310576926"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0143.1","pdf":"https://arxiv.org/pdf/2208.02383"},"orgs":["colorado-state-university","noaa"],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Random forests trained on GEFS reforecasts and severe weather reports give probabilistic US severe-weather forecasts for days 4-8, comparable to SPC outlooks at days 4-5.","significance":4,"cited_by":30,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.01252","title":"A Novel Transformer Network with Shifted Window Cross-Attention for Spatiotemporal Weather Forecasting","authors":["Alabi Bojesomo","Hasan Al Marzouqi","Panos Liatsis"],"date":"2022-08-02","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2208.01252","doi":"10.1109/jstars.2023.3323729","openalex":"W4387623972"},"links":{"paper":"https://doi.org/10.1109/jstars.2023.3323729","pdf":"https://arxiv.org/pdf/2208.01252"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Video Swin-Transformer with cross-attention forecasts eight hours of hourly satellite weather frames on Weather4Cast 2021, reaching MSE 0.442 in transfer.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-5967-2022","title":"Rad-cGAN v1.0: Radar-based precipitation nowcasting model with conditional generative adversarial networks for multiple dam domains","authors":["Suyeon Choi","Yeonjoo Kim"],"date":"2022-08-01","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-5967-2022","openalex":"W4289201796"},"links":{"paper":"https://doi.org/10.5194/gmd-15-5967-2022","pdf":"https://gmd.copernicus.org/articles/15/5967/2022/gmd-15-5967-2022.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Rad-cGAN, a conditional GAN for radar precipitation nowcasting, outperforms ConvLSTM and U-Net, extending useful lead time to 80 minutes and transferring across Korean dam regions.","significance":4,"cited_by":44,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13081208","title":"Daily Weather Forecasting Based on Deep Learning Model: A Case Study of Shenzhen City, China","authors":["Guici Chen","Sijia Liu","Feng Jiang"],"date":"2022-08-01","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13081208","openalex":"W4289201669"},"links":{"paper":"https://doi.org/10.3390/atmos13081208","pdf":"https://www.mdpi.com/2073-4433/13/8/1208/pdf?version=1659334274"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"EMD-decomposed LSTM forecasts daily minimum and maximum weather variables for Shenzhen from 2015–2019 station data, reporting better precision than traditional models.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1887463-v1","title":"Evaluating the Dark Sky Weather Forecast Data Over Florida and Georgia","authors":["Haimanote  Kebede Bayabil","Fitsum  Tilahun Teshome","Songzi Wu","Ziwen Yu"],"date":"2022-08-01","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1887463/v1","openalex":"W4289261849"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1887463/v1","pdf":"https://www.researchsquare.com/article/rs-1887463/latest.pdf"},"orgs":[],"topic":"benchmarks-data-eval","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Evaluates Dark Sky daily forecasts against 124 Florida and Georgia stations; finds good yes/no rain detection (POD 0.91–1.0) but poor rainfall amounts.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ac8565","title":"A mid-troposphere perspective on the East African climate paradox","authors":["Thomas Mölg","Carolyne Pickler"],"date":"2022-08-01","year":2022,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ac8565","openalex":"W4291606005"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ac8565","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ac8565/pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Links high-mountain in-situ observations to a subset of GCMs via machine learning weather types, showing mid-troposphere drying in the past and moistening in the future for East Africa.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41561-022-00991-6","title":"Machine learning reveals climate forcing from aerosols is dominated by increased cloud cover","authors":["Ying Chen","Jim Haywood","Yu Wang","Florent F. Malavelle","George Jordan","Daniel G. Partridge","Jonathan Edward Fieldsend","Johannes de Leeuw","Anja Schmidt","Nayeong Cho","Lazaros Oreopoulos","Steven E. Platnick","Daniel Peter Grosvenor","Paul R. Field","Ulrike Lohmann"],"date":"2022-08-01","year":2022,"venue":"Nature Geoscience","venue_type":"journal","ids":{"doi":"10.1038/s41561-022-00991-6","openalex":"W4289261478"},"links":{"paper":"https://doi.org/10.1038/s41561-022-00991-6","pdf":"https://www.dora.lib4ri.ch/psi/dload/psi:43961/PDF2/view"},"orgs":["nasa","met-office","eth-zurich","university-of-cambridge"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":[],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Machine learning attributes aerosol climate forcing largely to increased cloud cover. Abstract unavailable; judged from the title only.","significance":5,"cited_by":115,"score":85,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003105","title":"Training Physics‐Based Machine‐Learning Parameterizations With Gradient‐Free Ensemble Kalman Methods","authors":["Ignacio Lopez‐Gomez","Costa Christopoulos","Haakon Ludvig Langeland Ervik","Oliver R. A. Dunbar","Yair Cohen","Tapio Schneider"],"date":"2022-08-01","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003105","openalex":"W4293744237"},"links":{"paper":"https://doi.org/10.1029/2022ms003105","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003105"},"orgs":["nasa","caltech"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Gradient-free Kalman inversion trains hybrid subgrid turbulence and convection parameterizations from large-eddy simulation data, with uncertainty estimates from unscented Kalman inversion.","significance":4,"cited_by":53,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms002994","title":"An Efficient Bayesian Approach to Learning Droplet Collision Kernels: Proof of Concept Using “Cloudy,” a New n ‐Moment Bulk Microphysics Scheme","authors":["Melanie Bieli","Oliver R. A. Dunbar","Emily K De Jong","Anna Jaruga","Tapio Schneider","Tobias Bischoff"],"date":"2022-08-01","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms002994","openalex":"W4293223814"},"links":{"paper":"https://doi.org/10.1029/2022ms002994","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS002994"},"orgs":["caltech"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Uses Calibrate-Emulate-Sample Bayesian learning to tune the Cloudy bulk microphysics scheme with far fewer model runs, learning a collision kernel parameter from particle-model output.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-022-02277-0","title":"Drought indicator analysis and forecasting using data driven models: case study in Jaisalmer, India","authors":["Ahmed Elbeltagi","Manish Kumar","Nand Lal Kushwaha","Chaitanya B. Pande","Pakorn Ditthakit","Dinesh Kumar Vishwakarma","Anakkallan Subeesh"],"date":"2022-08-01","year":2022,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-022-02277-0","openalex":"W4289278167"},"links":{"paper":"https://doi.org/10.1007/s00477-022-02277-0"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Data-driven forecasting of drought indicators for Jaisalmer, India; the abstract is unavailable, so the method and results are unverified.","significance":2,"cited_by":82,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2208.00971","title":"Probabilistic forecasts of extreme heatwaves using convolutional neural networks in a regime of lack of data","authors":["George Miloshevich","Bastien Cozian","Patrice Abry","Pierre Borgnat","Freddy Bouchet"],"date":"2022-08-01","year":2022,"venue":"Physical Review Fluids","venue_type":"journal","ids":{"arxiv":"2208.00971","doi":"10.1103/physrevfluids.8.040501","openalex":"W4289597912"},"links":{"paper":"https://doi.org/10.1103/physrevfluids.8.040501","pdf":"https://arxiv.org/pdf/2208.00971"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"CNN trained on long climate model runs forecasts France 14-day heatwaves up to 15 days ahead, showing skill from 500 hPa heights and soil moisture.","significance":4,"cited_by":53,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.envsoft.2022.105466","title":"Application of extreme gradient boosting and Shapley Additive explanations to predict temperature regimes inside forests from standard open-field meteorological data","authors":["Fatemeh Ghafarian","Ralf Wieland","Dietmar Lüttschwager","Claas Nendel"],"date":"2022-07-31","year":2022,"venue":"Environmental Modelling & Software","venue_type":"journal","ids":{"doi":"10.1016/j.envsoft.2022.105466","openalex":"W4288942164"},"links":{"paper":"https://doi.org/10.1016/j.envsoft.2022.105466","pdf":"https://www.sciencedirect.com/science/article/pii/S1364815222001700/pdf"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"XGBoost with SHAP predicts forest-interior temperatures from open-field weather data for Brandenburg sites, supporting climate-change ecosystem assessment.","significance":2,"cited_by":71,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15625-2615-9783-17373","title":"Assessment of machine learning techniques for prediction of integrated water vapor using meteorological data","authors":["Nirmala Bai Jadala","M. Sridhar","Venkata Ratnam Devanaboyina","Gopa Dutta"],"date":"2022-07-29","year":2022,"venue":"Vietnam Journal of Earth Sciences","venue_type":"journal","ids":{"doi":"10.15625/2615-9783/17373","openalex":"W4288713040"},"links":{"paper":"https://doi.org/10.15625/2615-9783/17373","pdf":"https://vjs.ac.vn/index.php/jse/article/download/17373/2543254556"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Gaussian process regression outperforms neural networks in estimating GPS integrated water vapour from surface meteorology in Hyderabad, with correlation 0.93.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.14679","title":"Leveraging data from nearby stations to improve short-term wind speed forecasts","authors":["Rachel Baïle","Jean-François Muzy"],"date":"2022-07-29","year":2022,"venue_type":"preprint","ids":{"arxiv":"2207.14679"},"links":{"paper":"https://arxiv.org/abs/2207.14679","pdf":"https://arxiv.org/pdf/2207.14679"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Shows that adding neighbouring station wind data improves 1-6 hour wind speed forecasts by up to 20% RMSE across linear and ML models.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12517-022-10640-2","title":"Assessment of machine learning model performance for seasonal precipitation simulation based on teleconnection indices in Iran","authors":["Jalil Helali","Mehdi Mohammadi Ghaleni","Seyed Asaad Hosseini","Ali Lotfi Siraei","Vahideh Saeidi","Farshad Safarpour","Mojgan Mirzaei","Mohammad Lotfi"],"date":"2022-07-28","year":2022,"venue":"Arabian Journal of Geosciences","venue_type":"journal","ids":{"doi":"10.1007/s12517-022-10640-2","openalex":"W4288443322"},"links":{"paper":"https://doi.org/10.1007/s12517-022-10640-2"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Assesses machine learning models for seasonal precipitation simulation in Iran using teleconnection indices as predictors; no abstract available.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w14152297","title":"Reconstruction of Hydrometeorological Data Using Dendrochronology and Machine Learning Approaches to Bias-Correct Climate Models in Northern Tien Shan, Kyrgyzstan","authors":["Erkin Isaev","Mariiash Ermanova","Roy C. Sidle","Vitalii Zaginaev","Maksim Kulikov","Dogdurbek Chontoev"],"date":"2022-07-24","year":2022,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w14152297","openalex":"W4287219332"},"links":{"paper":"https://doi.org/10.3390/w14152297","pdf":"https://www.mdpi.com/2073-4441/14/15/2297/pdf?version=1658885179"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations","other"],"status":"research","summary":"Uses tree-ring chronologies and machine learning to reconstruct precipitation and temperature back to 1886, then ranks CORDEX models and bias-corrects them in the Tien Shan.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11227-022-04686-y","title":"Correcting rainfall forecasts of a numerical weather prediction model using generative adversarial networks","authors":["Chang-Hoo Jeong","Mun Yong Yi"],"date":"2022-07-23","year":2022,"venue":"The Journal of Supercomputing","venue_type":"journal","ids":{"doi":"10.1007/s11227-022-04686-y","openalex":"W4286742083"},"links":{"paper":"https://doi.org/10.1007/s11227-022-04686-y"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"GAN-based post-processing corrects rainfall forecasts from a numerical weather prediction model; abstract unavailable, so scope is inferred from the title.","significance":3,"cited_by":31,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.11417","title":"Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers","authors":["Björn Lütjens","Catherine H. Crawford","Campbell D Watson","Christopher Hill","Dava Newman"],"date":"2022-07-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2207.11417","openalex":"W4288055557"},"links":{"paper":"https://arxiv.org/abs/2207.11417","pdf":"https://arxiv.org/pdf/2207.11417"},"orgs":["ibm-research","mit"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["neural-operator","physics-constrained"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Hybrid multiscale neural operator learns grid-independent closure parameterizations for coarse dynamics, demonstrated on the chaotic multiscale Lorenz96 model.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14153517","title":"F2F-NN: A Field-to-Field Wind Speed Retrieval Method of Microwave Radiometer Data Based on Deep Learning","authors":["Xinjie Shi","Boheng Duan","Kaijun Ren"],"date":"2022-07-22","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14153517","openalex":"W4287840556"},"links":{"paper":"https://doi.org/10.3390/rs14153517","pdf":"https://www.mdpi.com/2072-4292/14/15/3517/pdf?version=1658891008"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"F2F-NN, a CNN retrieving sea surface wind fields from FY-3D microwave imager data, reaches 0.26 m/s RMSE and beats five existing products in a hurricane case.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s42001-022-00174-8","title":"Sentimental wildfire: a social-physics machine learning model for wildfire nowcasting","authors":["Jake Lever","Rossella Arcucci"],"date":"2022-07-22","year":2022,"venue":"Journal of Computational Social Science","venue_type":"journal","ids":{"doi":"10.1007/s42001-022-00174-8","openalex":"W4286587760"},"links":{"paper":"https://doi.org/10.1007/s42001-022-00174-8","pdf":"https://link.springer.com/content/pdf/10.1007/s42001-022-00174-8.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Combines Twitter sentiment with Global Fire Atlas satellite data to predict wildfire attributes, treating social media as a human-sensor for wildfire nowcasting.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7813","title":"A multimodel ensemble machine learning approach for CMIP6 climate model projections in an Indian River basin","authors":["Aiendrila Dey","Debi Prasad Sahoo","Rohini Kumar","Renji Remesan"],"date":"2022-07-22","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7813","openalex":"W4286717666"},"links":{"paper":"https://doi.org/10.1002/joc.7813"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"ANN, random forest and SVM multimodel ensembles improve CMIP6 precipitation and temperature projections for an Indian river basin over simple averaging.","significance":2,"cited_by":94,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14143507","title":"Spaceborne GNSS-R Wind Speed Retrieval Using Machine Learning Methods","authors":["Changyang Wang","Kegen Yu","Fangyu Qu","Jinwei Bu","Shuai Han","K. F. Zhang"],"date":"2022-07-21","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14143507","openalex":"W4286433387"},"links":{"paper":"https://doi.org/10.3390/rs14143507","pdf":"https://www.mdpi.com/2072-4292/14/14/3507/pdf?version=1658471354"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Compares seven ML methods for CYGNSS GNSS-R sea surface wind retrieval; LightGBM gives RMSE 1.419 m/s at low winds.","significance":3,"cited_by":30,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.10552","title":"A Primer on Topological Data Analysis to Support Image Analysis Tasks in Environmental Science","authors":["Lander Ver Hoef","Henry Adams","Emily J. King","Imme Ebert-Uphoff"],"date":"2022-07-21","year":2022,"venue_type":"preprint","ids":{"arxiv":"2207.10552","doi":"10.1175/aies-d-22-0039.1"},"links":{"paper":"https://arxiv.org/abs/2207.10552","pdf":"https://arxiv.org/pdf/2207.10552"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Tutorial introducing persistent homology and persistence landscapes for classifying mesoscale cloud organization in satellite images, with interpretable results and example code.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2022.302","title":"A systematic quantitative review on the performance of some of the recent short-term rainfall forecasting techniques","authors":["Priya Shejule","Sreeja Pekkat"],"date":"2022-07-20","year":2022,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2022.302","openalex":"W4286008526"},"links":{"paper":"https://doi.org/10.2166/wcc.2022.302"},"orgs":[],"topic":"nowcasting","topics":["post-processing"],"type":"review","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Systematic PRISMA review of 110 studies on statistical, NWP and ML short-term rainfall forecasting, highlighting hybrid models for nowcasting.","significance":3,"cited_by":57,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1876116-v1","title":"Scientific strategies associated with mitigating the challenges in predicting track and intensity of cyclones across the world basins","authors":["Vivek Kumar Singh"],"date":"2022-07-20","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1876116/v1","openalex":"W4286007934"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1876116/v1","pdf":"https://www.researchsquare.com/article/rs-1876116/latest.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["llms-agents"],"type":"review","method":[],"timescale":["short"],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Systematic review of 51 studies on tropical cyclone track and intensity prediction using NWP, machine learning and satellite methods across basins.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-022-06343-9","title":"Regional climate model emulator based on deep learning: concept and first evaluation of a novel hybrid downscaling approach","authors":["Antoine Doury","Samuel Somot","Sebastien Gadat","Aurélien Ribes","Lola Corre"],"date":"2022-07-20","year":2022,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-022-06343-9","openalex":"W4285891375"},"links":{"paper":"https://doi.org/10.1007/s00382-022-06343-9"},"orgs":["meteo-france"],"topic":"downscaling","topics":["climate-emulation"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A neural-network RCM emulator hybrid-downscales daily 12 km near-surface temperature from large-scale predictors, reproducing RCM variability with training in under 2 hours and inference in under a minute.","significance":4,"cited_by":78,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.17342-kij.2022.131.2","title":"Track Clustering of Tropical Cyclones and Regional Loss Prediction Model: The Impact of Climate Change Scenarios and Applications to Machine Learning","authors":["Kwangmin Jung","Jonghun Kam","Seungjoon Lee"],"date":"2022-07-19","year":2022,"venue":"보험학회지","venue_type":"journal","ids":{"doi":"10.17342/kij.2022.131.2","openalex":"W4285792762"},"links":{"paper":"https://doi.org/10.17342/kij.2022.131.2"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Random forest predicts typhoon economic losses for Korea by region, projecting 6.5–14.8 times higher losses by 2100 under IPCC scenarios.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2022.128197","title":"Adaptive precipitation nowcasting using deep learning and ensemble modeling","authors":["Amirmasoud Amini","Mehri Dolatshahi","Reza Kerachian"],"date":"2022-07-19","year":2022,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2022.128197","openalex":"W4285810972"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2022.128197"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Adaptive deep learning ensemble for precipitation nowcasting; abstract unavailable, so details are inferred from the title and journal.","significance":3,"cited_by":50,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1134-s0097807822040133","title":"Forecast of Precipitation in Ai-Petri Area Based on Artificial Neuron Network Model","authors":["А.S. Lubkov","E. N. Voskresenskaya","Olga Sukhonos"],"date":"2022-07-18","year":2022,"venue":"Water Resources","venue_type":"journal","ids":{"doi":"10.1134/s0097807822040133","openalex":"W4285728043"},"links":{"paper":"https://doi.org/10.1134/s0097807822040133"},"orgs":[],"topic":"s2s-seasonal","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["era5","other"],"status":"research","summary":"Neural network using global climate indices forecasts monthly and seasonal precipitation in Crimea up to six months ahead, with about 55–62% forecast quality.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021jd036061","title":"An Objective Quality Control of Surface Contamination Observations for ABI Water Vapor Radiance Assimilation","authors":["Zhenglong Li","Zheng Ma","Pei Wang","Agnes H. N. Lim","Jun Li","James A. Jung","Timothy J. Schmit","Hung‐Lung Huang"],"date":"2022-07-18","year":2022,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2021jd036061","openalex":"W4285802394"},"links":{"paper":"https://doi.org/10.1029/2021jd036061","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021JD036061"},"orgs":["noaa","iap-cas","cma"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Machine-learning quality control for ABI water vapor radiances blends seven bands to reject surface-contaminated pixels, improving Hurricane Harvey track forecasts.","significance":3,"cited_by":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13071125","title":"Visibility Prediction Based on Machine Learning Algorithms","authors":["Yu Zhang","Yangjun Wang","Yingqian Zhu","Lizhi Yang","Lin Ge","Luo Chun"],"date":"2022-07-16","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13071125","openalex":"W4285732704"},"links":{"paper":"https://doi.org/10.3390/atmos13071125","pdf":"https://www.mdpi.com/2073-4433/13/7/1125/pdf?version=1661766633"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Six machine learning methods predict visibility from ground observations; PCA improves accuracy, and neural networks perform best among the methods tested.","significance":2,"cited_by":35,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app12147131","title":"Post-Processing Air Temperature Weather Forecast Using Artificial Neural Networks with Measurements from Meteorological Stations","authors":["Gustavo Araujo","Fabio A. A. Andrade"],"date":"2022-07-15","year":2022,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app12147131","openalex":"W4285733815"},"links":{"paper":"https://doi.org/10.3390/app12147131","pdf":"https://www.mdpi.com/2076-3417/12/14/7131/pdf?version=1657869650"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural networks post-process Norwegian 2.5 km air temperature forecasts with station data, beating GRIDPP in 74.8% of cases where its error exceeds 3 K.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2022.953262","title":"XCast: A python climate forecasting toolkit","authors":["Kyle Joseph Chen Hall","Nachiketa Acharya"],"date":"2022-07-15","year":2022,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2022.953262","openalex":"W4285592773"},"links":{"paper":"https://doi.org/10.3389/fclim.2022.953262","pdf":"https://www.frontiersin.org/articles/10.3389/fclim.2022.953262/pdf"},"orgs":["noaa","columbia-leap"],"topic":"infra-software","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Presents XCast, an open Python toolkit that applies scikit-learn-style methods gridpoint-by-gridpoint to gridded climate data, simplifying statistical and ML climate forecasting workflows.","significance":3,"cited_by":5,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.07589","title":"A two-step machine learning approach to statistical post-processing of weather forecasts for power generation","authors":["Ágnes Baran","Sándor Baran"],"date":"2022-07-15","year":2022,"venue":"Quarterly Journal of the Royal Meteorological Society 150 (2024), no. 759, 1029-1047","venue_type":"journal","ids":{"arxiv":"2207.07589","doi":"10.1002/qj.4635"},"links":{"paper":"https://arxiv.org/abs/2207.07589","pdf":"https://arxiv.org/pdf/2207.07589"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Two-step neural post-processing of ensemble forecasts for 100m wind and irradiance, improving on raw ensembles up to 48 h at the Hungarian Met Service.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.07390","title":"Machine learning applications for weather and climate need greater focus on extremes","authors":["Peter AG Watson"],"date":"2022-07-15","year":2022,"venue":"Env. Res. Lett., 17 (2022), 111004","venue_type":"journal","ids":{"arxiv":"2207.07390","doi":"10.1088/1748-9326/ac9d4e","openalex":"W4307642979"},"links":{"paper":"https://arxiv.org/abs/2207.07390","pdf":"https://arxiv.org/pdf/2207.07390"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Position review arguing ML weather and climate studies must evaluate and improve performance on rare, high-return-period extremes, which remain poorly assessed.","significance":5,"cited_by":32,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.07333","title":"Rain regime segmentation of Sentinel-1 observation learning from NEXRAD collocations with Convolution Neural Networks","authors":["Aurélien Colin","Pierre Tandeo","Charles Peureux","Romain Husson","Nicolas Longépé","Ronan Fablet"],"date":"2022-07-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2207.07333"},"links":{"paper":"https://arxiv.org/abs/2207.07333","pdf":"https://arxiv.org/pdf/2207.07333"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"CNN segments Sentinel-1 SAR images into three rain regimes learned from NEXRAD collocations, outperforming Koch's filters for high-resolution rain mapping over ocean.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13071113","title":"Classification and Estimation of Typhoon Intensity from Geostationary Meteorological Satellite Images Based on Deep Learning","authors":["Shuailong Jiang","Lijun Tao"],"date":"2022-07-14","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13071113","openalex":"W4285596527"},"links":{"paper":"https://doi.org/10.3390/atmos13071113","pdf":"https://www.mdpi.com/2073-4433/13/7/1113/pdf?version=1658728856"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"TICAENet, a LeNet/VGG-style CNN, classifies typhoon intensity from geostationary satellite images at 97.12% accuracy and estimates wind speed with 4.78 m/s MAE.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-022-16240-0","title":"The rise of Indian summer monsoon precipitation extremes and its correlation with long-term changes of climate and anthropogenic factors","authors":["Renaud Falga","Chien Wang"],"date":"2022-07-14","year":2022,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-022-16240-0","openalex":"W4285390365"},"links":{"paper":"https://doi.org/10.1038/s41598-022-16240-0","pdf":"https://www.nature.com/articles/s41598-022-16240-0.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Nonlinear ML regression shows urbanisation and land-use change most strongly explain 1901–2020 Indian monsoon precipitation extreme trends.","significance":3,"cited_by":67,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11063-022-10935-1","title":"Intelligent Solar Irradiance Forecasting Using Hybrid Deep Learning Model: A Meta-Heuristic-Based Prediction","authors":["N. P. Sebi"],"date":"2022-07-14","year":2022,"venue":"Neural Processing Letters","venue_type":"journal","ids":{"doi":"10.1007/s11063-022-10935-1","openalex":"W4285386496"},"links":{"paper":"https://doi.org/10.1007/s11063-022-10935-1"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Hybrid deep learning with metaheuristic tuning for solar irradiance forecasting; no abstract available, so the contribution is uncertain.","significance":1,"cited_by":22,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-cli10070106","title":"A Methodology for Bridging the Gap between Regional- and City-Scale Climate Simulations for the Urban Thermal Environment","authors":["Konstantina Koutroumanou-Kontosi","Constantinos Cartalis","Kostas Philippopoulos","Ilias Agathangelidis","Anastasios Polydoros"],"date":"2022-07-13","year":2022,"venue":"Climate","venue_type":"journal","ids":{"doi":"10.3390/cli10070106","openalex":"W4285392900"},"links":{"paper":"https://doi.org/10.3390/cli10070106","pdf":"https://www.mdpi.com/2225-1154/10/7/106/pdf?version=1657689898"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5","km-scale-sim"],"status":"research","summary":"Combines artificial neural networks and regression to downscale EURO-CORDEX temperatures from 12 km to 1 km over Athens, projecting Tmax and Tmin rises under RCP scenarios.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ea002233","title":"Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning","authors":["Sarah Albert"],"date":"2022-07-13","year":2022,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2022ea002233","openalex":"W4285391914"},"links":{"paper":"https://doi.org/10.1029/2022ea002233","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EA002233"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["stations","era5"],"status":"research","summary":"LSTM predicts atmospheric wind and temperature profiles up to 30 km from US radiosondes, matching or beating reanalysis in some cases for infrasound modeling.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-2022-146","title":"Data-driven Global Subseasonal Forecast Model (GSFM v1.0) for intraseasonal oscillation components","authors":["Chuhan Lu","Dingan Huang","Yichen Shen","Fei Xin"],"date":"2022-07-11","year":2022,"venue_type":"other","ids":{"doi":"10.5194/gmd-2022-146","openalex":"W4285043036"},"links":{"paper":"https://doi.org/10.5194/gmd-2022-146"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"GSFM uses SE-ResNet to predict intraseasonal Z500 and T850 components, substantially outperforming CFSv2 at 10–30 day leads.","significance":4,"cited_by":3,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.929115","title":"Tropical Cyclones Intensity Prediction in the Western North Pacific Using Gradient Boosted Regression Tree Model","authors":["Gangya Zhu","Qinglan Li","Wei Dong Zhao","Xinyan Lv","Chuanhai Qian","Qifeng Qian"],"date":"2022-07-11","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.929115","openalex":"W4285006523"},"links":{"paper":"https://doi.org/10.3389/feart.2022.929115","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.929115/pdf"},"orgs":["cma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Bayesian-optimised gradient boosted trees predict western North Pacific tropical cyclone intensity change at 12–72 h, beating linear regression by 4–8% in R².","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00703-022-00907-4","title":"Efficacy of linear multiple regression and artificial neural network for long-term rainfall forecasting in Western Australia","authors":["Anirban Khastagir","Iqbal Hossain","Faisal Anwar"],"date":"2022-07-11","year":2022,"venue":"Meteorology and Atmospheric Physics","venue_type":"journal","ids":{"doi":"10.1007/s00703-022-00907-4","openalex":"W4285042424"},"links":{"paper":"https://doi.org/10.1007/s00703-022-00907-4","pdf":"https://link.springer.com/content/pdf/10.1007/s00703-022-00907-4.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Linear regression with lagged ENSO and IOD indices matches or beats an MLP for seasonal spring rainfall in Western Australia.","significance":2,"cited_by":22,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-022-02259-2","title":"Temporal downscaling of precipitation from climate model projections using machine learning","authors":["Azin Al Kajbaf","Michelle Bensi","Kaye L. Brubaker"],"date":"2022-07-09","year":2022,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-022-02259-2","openalex":"W4284967519"},"links":{"paper":"https://doi.org/10.1007/s00477-022-02259-2"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Applies machine learning to temporally downscale precipitation from climate model projections to finer time steps; no abstract was available, so details are limited.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-x5zd1m","title":"Intercomparison of deep learning architectures for the prediction of precipitation fields","authors":["Noelia Otero","Pascal Horton"],"date":"2022-07-08","year":2022,"venue_type":"other","ids":{"doi":"10.31223/x5zd1m","openalex":"W4284898171"},"links":{"paper":"https://doi.org/10.31223/x5zd1m"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Compares deep learning architectures for European precipitation fields; U-Net performs best, and a single-level U-Net matches deeper versions on extremes.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1111-risa.13990","title":"Explainable deep learning powered building risk assessment model for proactive hurricane response","authors":["Shangde Gao","Yan Wang"],"date":"2022-07-08","year":2022,"venue":"Risk Analysis","venue_type":"journal","ids":{"doi":"10.1111/risa.13990","openalex":"W4284969429"},"links":{"paper":"https://doi.org/10.1111/risa.13990","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/risa.13990"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards","xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Deep feedforward networks with LIME explanations assess building-level hurricane wind and surge risk using updated forecasts for a Louisiana case.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.wace.2022.100477","title":"Seasonal prediction of summer extreme precipitation over the Yangtze River based on random forest","authors":["Wenguang Wei","Zhongwei Yan","Xuan Tong","Zuoqiang Han","Miaomiao Ma","Shuang Yu","Jiangjiang Xia"],"date":"2022-07-08","year":2022,"venue":"Weather and Climate Extremes","venue_type":"journal","ids":{"doi":"10.1016/j.wace.2022.100477","openalex":"W4284897852"},"links":{"paper":"https://doi.org/10.1016/j.wace.2022.100477","pdf":"https://www.sciencedirect.com/science/article/pii/S2212094722000597/pdf"},"orgs":["iap-cas"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Random forest on three preceding atmosphere-ocean indices gives a seasonal early warning of Yangtze summer extreme precipitation, including the 2020 event.","significance":3,"cited_by":34,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11280-022-01069-4","title":"Multi-source and heterogeneous marine hydrometeorology spatio-temporal data analysis with machine learning: a survey","authors":["Song Wu","Xiaoyong Li","Wei Dong","Senzhang Wang","Xiaojiang Zhang","Zichen Xu"],"date":"2022-07-08","year":2022,"venue":"World Wide Web","venue_type":"journal","ids":{"doi":"10.1007/s11280-022-01069-4","openalex":"W4284895373"},"links":{"paper":"https://doi.org/10.1007/s11280-022-01069-4"},"orgs":[],"topic":"benchmarks-data-eval","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Survey of machine learning for multi-source marine hydrometeorological spatio-temporal data; no abstract available, so scope is inferred from the title.","significance":1,"cited_by":19,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-2752-5295-ac7f4c","title":"Long-term ENSO prediction with echo-state networks","authors":["Forough Hassanibesheli","Jürgen Kurths","Niklas Boers"],"date":"2022-07-07","year":2022,"venue":"Environmental Research Climate","venue_type":"journal","ids":{"doi":"10.1088/2752-5295/ac7f4c","openalex":"W4284898586"},"links":{"paper":"https://doi.org/10.1088/2752-5295/ac7f4c","pdf":"https://iopscience.iop.org/article/10.1088/2752-5295/ac7f4c/pdf"},"orgs":["tum","pik"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Echo state network trained on low-frequency ENSO indices skilfully predicts El Niño up to 21 months ahead, with correlation above 0.5.","significance":4,"cited_by":24,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-hess-2022-235","title":"Machine-learning ensembled CMIP6 projection reveals socio-economic pathways will aggravate global warming and precipitation extreme","authors":["Piaoyin Zhang","Jianzhong Lu","Xiaoling Chen"],"date":"2022-07-06","year":2022,"venue_type":"other","ids":{"doi":"10.5194/hess-2022-235","openalex":"W4283823374"},"links":{"paper":"https://doi.org/10.5194/hess-2022-235","pdf":"https://hess.copernicus.org/preprints/hess-2022-235/hess-2022-235.pdf"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Uses regression, decision trees and deep networks to merge 16 CMIP6 models into a new ensemble; it outperforms single models (R=0.81 precipitation, 0.99 temperature) and projects 1.5 °C by 2024 under SSP5-8.5.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.51483-ijaiml.2.2.2022.12-20","title":"Machine Learning-Based Algorithms for Weather Forecasting","authors":["Ismaila Oshodi"],"date":"2022-07-05","year":2022,"venue":"International Journal of Artificial Intelligence and Machine Learning","venue_type":"journal","ids":{"doi":"10.51483/ijaiml.2.2.2022.12-20","openalex":"W4313059446"},"links":{"paper":"https://doi.org/10.51483/ijaiml.2.2.2022.12-20","pdf":"https://doi.org/10.51483/ijaiml.2.2.2022.12-20"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random forest, decision tree, naive Bayes and boosting classify Seattle daily weather from 2012-2015 data; Naive Bayes is best at 84.2% accuracy.","significance":1,"cited_by":13,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022jd036603","title":"An Improved Cluster‐Wise Typhoon Rainfall Forecasting Model Based on Machine Learning and Deep Learning Models Over the Northwestern Pacific Ocean","authors":["Md. Jalal Uddin","Yubin Li","Md. Abdus Sattar","Mingyang Liu","Nan Yang"],"date":"2022-07-05","year":2022,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2022jd036603","openalex":"W4283815051"},"links":{"paper":"https://doi.org/10.1029/2022jd036603"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["classical-ml","cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Cluster-wise typhoon rainfall model combines SVM, RF, AdaBoost, CNN and LSTM with grid-search tuning, claiming 45–90% forecast efficiency gains for 1–6 h lead times.","significance":3,"cited_by":17,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.isatra.2022.06.046","title":"A self-attention integrated spatiotemporal LSTM approach to edge-radar echo extrapolation in the Internet of Radars","authors":["Zhiyun Yang","Hao Ran Wu","Qi Liu","Xiaodong Liu","Yonghong Zhang","Xuefei Cao"],"date":"2022-07-04","year":2022,"venue":"ISA Transactions","venue_type":"journal","ids":{"doi":"10.1016/j.isatra.2022.06.046","openalex":"W4283789746"},"links":{"paper":"https://doi.org/10.1016/j.isatra.2022.06.046"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Self-attention spatiotemporal LSTM extrapolates edge-radar echoes for nowcasting in an Internet of Radars setting; the abstract is missing, so the assessment relies on the title.","significance":3,"cited_by":33,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.00808","title":"On the modern deep learning approaches for precipitation downscaling","authors":["Bipin Kumar","Kaustubh Atey","Bhupendra Bahadur Singh","Rajib Chattopadhyay","Nachiket Acharya","Manmeet Singh","Ravi S. Nanjundiah","Suryachandra A. Rao"],"date":"2022-07-02","year":2022,"venue":"Earth Science Informatics, 2023","venue_type":"journal","ids":{"arxiv":"2207.00808","doi":"10.1007/s12145-023-00970-4","openalex":"W4322718564"},"links":{"paper":"https://arxiv.org/abs/2207.00808","pdf":"https://arxiv.org/pdf/2207.00808"},"orgs":["noaa"],"topic":"downscaling","topics":[],"type":"evaluation","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional","local"],"data":["stations","other"],"status":"research","summary":"Compares DeepSD, ConvLSTM, U-Net and SR-GAN for precipitation downscaling against IMD station data; SR-GAN performs best.","significance":3,"cited_by":67,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.00745","title":"Scheduling Planting Time Through Developing an Optimization Model and Analysis of Time Series Growing Degree Units","authors":["Javad Ansarifar","Faezeh Akhavizadegan","Lizhi Wang"],"date":"2022-07-02","year":2022,"venue_type":"preprint","ids":{"arxiv":"2207.00745"},"links":{"paper":"https://arxiv.org/abs/2207.00745","pdf":"https://arxiv.org/pdf/2207.00745"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"application","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses a deep RNN weather forecast with Gaussian process uncertainty to schedule seed planting, cutting required capacity by up to 69%.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22271-maths.2022.v7.i4c.2250","title":"Stochastic differential equations and machine learning hybrid models for Indian monsoon prediction: Mathematical framework and computational implementation","authors":["Siva Gopal R"],"date":"2022-07-01","year":2022,"venue":"International Journal of Statistics and Applied Mathematics","venue_type":"journal","ids":{"doi":"10.22271/maths.2022.v7.i4c.2250","openalex":"W7127050133"},"links":{"paper":"https://doi.org/10.22271/maths.2022.v7.i4c.2250","pdf":"https://www.mathsjournal.com/pdf/2022/vol7issue4/PartC/11-1-21-161.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["probabilistic-ensembles"],"type":"model","method":["rnn","physics-constrained"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","era5"],"status":"research","summary":"LSTM-parameterised stochastic differential equations for probabilistic Indian monsoon rainfall forecasting from 40 years of station data.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-21-0002.1","title":"Challenges and Benchmark Datasets for Machine Learning in the Atmospheric Sciences: Definition, Status, and Outlook","authors":["Peter D. Dueben","Martin G. Schultz","Matthew Chantry","David John Gagne","David Matthew Hall","Amy McGovern"],"date":"2022-07-01","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-21-0002.1","openalex":"W4289828962"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0002.1"},"orgs":["ecmwf","juelich","ncar","nvidia","university-of-oklahoma"],"topic":"benchmarks-data-eval","topics":[],"type":"position","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Provides a recipe for building atmospheric-science ML benchmark datasets and lists domain-specific challenges and needed benchmarks for weather, climate and air quality.","significance":5,"cited_by":64,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2022ea002348","title":"Comparison of Climate Model Large Ensembles With Observations in the Arctic Using Simple Neural Networks","authors":["Zachary Michael Labe","Elizabeth A. Barnes"],"date":"2022-07-01","year":2022,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2022ea002348","openalex":"W4285042633"},"links":{"paper":"https://doi.org/10.1029/2022ea002348","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EA002348"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"evaluation","method":["other"],"timescale":[],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Trains a shallow neural network to identify which climate model produced Arctic temperature maps, then applies it to reanalysis, using attribution to reveal model-specific regional patterns.","significance":3,"cited_by":31,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.71465-ajml3012","title":"Artificial Intelligence and Machine Learning in Climate Modeling","authors":["Shrouk Wally"],"date":"2022-06-30","year":2022,"venue":"American Journal of Machine Learning","venue_type":"journal","ids":{"doi":"10.71465/ajml3012","openalex":"W7143836526"},"links":{"paper":"https://doi.org/10.71465/ajml3012","pdf":"https://australiansciencejournals.com/ml/article/download/3012/3329"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Generic overview of neural networks and deep learning for climate modeling and prediction, with no new method or quantitative result.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.18488-ijhr.v7i1.3047","title":"Is Climate Change Affecting the Monsoon Months in Pune, India?","authors":["Shalaka S. Shah","Shreenivas N. Londhe"],"date":"2022-06-30","year":2022,"venue":"International Journal of Hydrology Research","venue_type":"journal","ids":{"doi":"10.18488/ijhr.v7i1.3047","openalex":"W4367157363"},"links":{"paper":"https://doi.org/10.18488/ijhr.v7i1.3047","pdf":"https://archive.conscientiabeam.com/index.php/108/article/download/3047/6750"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"ANN statistical downscaling of five GCMs projects rising non-monsoon and falling monsoon rainfall for Pune, India.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00024-022-03088-8","title":"Severe Convective Weather Forecast Using Machine Learning Models","authors":["Jimmy Nogueira de Castro","Gutemberg Borges França","Vinícius Albuquerque de Almeida","Valdonel Manoel de Almeida"],"date":"2022-06-30","year":2022,"venue":"Pure and Applied Geophysics","venue_type":"journal","ids":{"doi":"10.1007/s00024-022-03088-8","openalex":"W4283731701"},"links":{"paper":"https://doi.org/10.1007/s00024-022-03088-8"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Applies machine learning models to forecast severe convective weather. The abstract is unavailable, so the classification relies on the title.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.15241","title":"Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Prediction","authors":["Taehyeon Kim","Namgyu Ho","Donggyu Kim","Se-Young Yun"],"date":"2022-06-30","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.15241","openalex":"W4283770210"},"links":{"paper":"https://arxiv.org/abs/2206.15241","pdf":"https://arxiv.org/pdf/2206.15241","code":"https://github.com/osilab-kaist/KoMet-Benchmark-Dataset"},"orgs":[],"topic":"benchmarks-data-eval","topics":["post-processing"],"type":"benchmark","method":[],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"KoMet benchmark pairs GDAPS-KIM NWP outputs with Korean station observations to test deep post-processing of precipitation, with open-source code.","significance":4,"cited_by":6,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13071045","title":"A Rainfall Forecast Model Based on GNSS Tropospheric Parameters and BP-NN Algorithm","authors":["Huanian Fu","Wenfeng Zhang","Chunjin Li","Zaihuang Hu"],"date":"2022-06-29","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13071045","openalex":"W4283714525"},"links":{"paper":"https://doi.org/10.3390/atmos13071045","pdf":"https://www.mdpi.com/2073-4433/13/7/1045/pdf?version=1657180739"},"orgs":[],"topic":"nowcasting","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["era5","stations","other"],"status":"research","summary":"Back-propagation neural network combines GNSS tropospheric delay with meteorological data for short-term rainfall warning in Ningbo, with 100% true detection rate.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32604-cmes.2022.022045","title":"CEMA-LSTM: Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets","authors":["Zhiyun Yang","Qi Liu","Hao Ran Wu","Xiaodong Liu","Yonghong Zhang"],"date":"2022-06-28","year":2022,"venue":"Computer Modeling in Engineering & Sciences","venue_type":"journal","ids":{"doi":"10.32604/cmes.2022.022045","openalex":"W4285163472"},"links":{"paper":"https://doi.org/10.32604/cmes.2022.022045","pdf":"https://file.techscience.com/ueditor/files/cmes/135-1/TSP_CMES_22045/TSP_CMES_22045.pdf"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"CEMA-LSTM adds contextual correlation and attention blocks to recurrent radar extrapolation, improving POD, FAR and CSI over PhyDNet and PredRNN++.","significance":4,"cited_by":21,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-22-0021.1","title":"Improving Probabilistic Quantitative Precipitation Forecasts Using Short Training Data through Artificial Neural Networks","authors":["Mohammadvaghef Ghazvinian","Yu Zhang","Thomas M. Hamill","Dong‐Jun Seo","Nelun Fernando"],"date":"2022-06-28","year":2022,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-22-0021.1","openalex":"W4283699647"},"links":{"paper":"https://doi.org/10.1175/jhm-d-22-0021.1","pdf":"https://repository.library.noaa.gov/view/noaa/53237/noaa_53237_DS1.pdf"},"orgs":["noaa"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"ANN-based postprocessing of GEFS forecasts with short 60-day training windows improves probabilistic 24-h precipitation forecasts over CONUS, especially for heavy rainfall thresholds.","significance":3,"cited_by":15,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002941","title":"Detection of Forced Change Within Combined Climate Fields Using Explainable Neural Networks","authors":["Jamin K. Rader","Elizabeth A. Barnes","Imme Ebert‐Uphoff","Chuck Anderson"],"date":"2022-06-27","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002941","openalex":"W4283587237"},"links":{"paper":"https://doi.org/10.1029/2021ms002941","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002941"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Explainable neural networks using layer-wise relevance propagation combine multivariate climate fields to detect forced climate change earlier than single fields.","significance":4,"cited_by":21,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.14573","title":"Separating internal and externally-forced contributions to global temperature variability using a Bayesian stochastic energy balance framework","authors":["Maybritt Schillinger","Beatrice Ellerhoff","Robert Scheichl","Kira Rehfeld"],"date":"2022-06-27","year":2022,"venue":"Chaos 32, 113146 (2022)","venue_type":"journal","ids":{"arxiv":"2206.14573","doi":"10.1063/5.0106123","openalex":"W4283738197"},"links":{"paper":"https://arxiv.org/abs/2206.14573","pdf":"https://arxiv.org/pdf/2206.14573"},"orgs":["eth-zurich"],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":["decadal","climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Bayesian inference on a stochastic energy balance model (ClimBayes) emulates global temperature variability and separates forced from internal variance across decadal to centennial scales.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-10.0011812","title":"Machine learning improves weather predictions for harvesting renewable energy","authors":["Avery Thompson"],"date":"2022-06-24","year":2022,"venue":"Scilight","venue_type":"journal","ids":{"doi":"10.1063/10.0011812","openalex":"W4283369425"},"links":{"paper":"https://doi.org/10.1063/10.0011812"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["other"],"timescale":["nowcast"],"spatial":[],"data":["other"],"status":"research","summary":"News summary of machine learning weather forecasts at 15-minute resolution that improve renewable energy harvesting, with potential savings of millions of dollars yearly.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.11669","title":"Short-range forecasts of global precipitation using deep learning-augmented numerical weather prediction","authors":["Manmeet Singh","Vaisakh S B","Nachiketa Acharya","Aditya Grover","Suryachandra A Rao","Bipin Kumar","Zong-Liang Yang","Dev Niyogi"],"date":"2022-06-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.11669","openalex":"W4283649880"},"links":{"paper":"https://arxiv.org/abs/2206.11669","pdf":"https://arxiv.org/pdf/2206.11669"},"orgs":["noaa","ucla"],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"UNet post-processing of CFSv2 cuts global precipitation bias from +5–7 mm/day to within ±1 mm/day over land at 1–3 day leads.","significance":3,"cited_by":8,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.55041-ijsrem16084","title":"Weather Forecasting using Decision Tree Regression","authors":["Amanpreet Kaur"],"date":"2022-06-22","year":2022,"venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","venue_type":"journal","ids":{"doi":"10.55041/ijsrem16084","openalex":"W4292178564"},"links":{"paper":"https://doi.org/10.55041/ijsrem16084","pdf":"https://ijsrem.com/download/weather-forecasting-using-decision-tree-regression/?wpdmdl=11955&refresh=63f2cd492b2991676856649"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Decision tree regression is applied to weather prediction, with a claimed long-term trend in forecast accuracy. The contribution is thin and not well documented.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-egusphere-2022-440","title":"Deep Learning Approach Towards Precipitation Nowcasting: Evaluating Regional Extrapolation Capabilities","authors":["Tarek Beutler","Annette Rudolph","Daniel Goehring","Nikki Vercauteren"],"date":"2022-06-21","year":2022,"venue_type":"other","ids":{"doi":"10.5194/egusphere-2022-440","openalex":"W4283214584"},"links":{"paper":"https://doi.org/10.5194/egusphere-2022-440"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"ConvLSTM precipitation nowcasting on German radar data shows that finetuning across locations and thresholds extends skill to 100 minutes.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41612-022-00269-z","title":"ESA-ECMWF Report on recent progress and research directions in machine learning for Earth System observation and prediction","authors":["Rochelle Schneider","Massimo Bonavita","Alan Geer","Rossella Arcucci","Peter Dominik Dueben","Claudia Vitolo","Bertrand Le Saux","Begüm Demir","Pierre-Philippe Mathieu"],"date":"2022-06-21","year":2022,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"doi":"10.1038/s41612-022-00269-z","openalex":"W4283207250"},"links":{"paper":"https://doi.org/10.1038/s41612-022-00269-z","pdf":"https://www.nature.com/articles/s41612-022-00269-z.pdf"},"orgs":["ecmwf"],"topic":"observations-remote-sensing","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Workshop report on machine learning for Earth system observation and prediction, outlining opportunities and challenges across satellite and forecasting applications.","significance":3,"cited_by":28,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5120-ijca2022922162","title":"Heat Wave Prediction using Machine Learning Techniques: A Review","authors":["F.S. Sourjah","W.P.J. Pemarathne"],"date":"2022-06-18","year":2022,"venue":"International Journal of Computer Applications","venue_type":"journal","ids":{"doi":"10.5120/ijca2022922162","openalex":"W4283120639"},"links":{"paper":"https://doi.org/10.5120/ijca2022922162","pdf":"https://doi.org/10.5120/ijca2022922162"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Reviews regression, KNN and deep learning approaches for predicting heat waves, comparing algorithms to guide future heatwave forecasting models.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14122925","title":"Attention-Unet-Based Near-Real-Time Precipitation Estimation from Fengyun-4A Satellite Imageries","authors":["Yanbo Gao","Jiping Guan","Fuhan Zhang","Xiaodong Wang","Zhiyong Long"],"date":"2022-06-18","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14122925","openalex":"W4283168768"},"links":{"paper":"https://doi.org/10.3390/rs14122925","pdf":"https://www.mdpi.com/2072-4292/14/12/2925/pdf?version=1655782629"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Attention-U-Net estimates near-real-time precipitation from FY-4A satellite imagery, beating operational satellite products and baseline deep learning models on POD, CSI and RMSE.","significance":3,"cited_by":48,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-hydrology9060111","title":"Monthly Rainfall Prediction at Catchment Level with the Facebook Prophet Model Using Observed and CMIP5 Decadal Data","authors":["Md Monowar Hossain","Faisal Anwar","Nikhil Garg","Mahesh Prakash","MA Bari"],"date":"2022-06-17","year":2022,"venue":"Hydrology","venue_type":"journal","ids":{"doi":"10.3390/hydrology9060111","openalex":"W4283009417"},"links":{"paper":"https://doi.org/10.3390/hydrology9060111","pdf":"https://www.mdpi.com/2306-5338/9/6/111/pdf?version=1655454871"},"orgs":["bom-australia"],"topic":"post-processing","topics":[],"type":"application","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Facebook Prophet and ML regressions using CMIP5 decadal hindcasts improve monthly rainfall prediction for the Brisbane River catchment.","significance":2,"cited_by":20,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.08832","title":"Prediction of Solar Radiation Based on Spatial and Temporal Embeddings for Solar Generation Forecast","authors":["Mohammad Alqudah","Tatjana Dokic","Mladen Kezunovic","Zoran Obradovic"],"date":"2022-06-17","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.08832"},"links":{"paper":"https://arxiv.org/abs/2206.08832","pdf":"https://arxiv.org/pdf/2206.08832"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Random Forest-based solar irradiance forecasting at 288 San Antonio sites from weather data, achieving R2 of 0.85 to 0.91.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl098663","title":"Quantifying the Effect of Climate Change on Midlatitude Subseasonal Prediction Skill Provided by the Tropics","authors":["Kirsten J. Mayer","Elizabeth A. Barnes"],"date":"2022-06-16","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl098663","openalex":"W4282962435"},"links":{"paper":"https://doi.org/10.1029/2022gl098663","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL098663"},"orgs":["colorado-state-university"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["s2s","climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Neural networks quantify how warming alters midlatitude subseasonal skill from tropical precipitation in CESM2 large ensemble, linked to seasonal variability changes.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.902596","title":"A Review on the Application of Machine Learning Methods in Tropical Cyclone Forecasting","authors":["Zhen Wang","Jun Zhao","Hong Huang","Xuezhong Wang"],"date":"2022-06-15","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.902596","openalex":"W4282961571"},"links":{"paper":"https://doi.org/10.3389/feart.2022.902596","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.902596/pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":["other"],"timescale":["short"],"spatial":["global"],"data":["satellite","radar","stations"],"status":"research","summary":"Reviews machine learning methods for tropical cyclone forecasting using satellite, radar and surface predictors, and discusses challenges for interpretability and precision.","significance":4,"cited_by":45,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-nhess-22-2031-2022","title":"Data-driven automated predictions of the avalanche danger level for dry-snow conditions in Switzerland","authors":["Cristina Pérez-Guillén","Frank Techel","Martin Hendrick","Michele Volpi","Alec van Herwijnen","Tasko Olevski","Guillaume Obozinski","Fernando Pérez‐Cruz","Jürg Schweizer"],"date":"2022-06-14","year":2022,"venue":"Natural hazards and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/nhess-22-2031-2022","openalex":"W4282824851"},"links":{"paper":"https://doi.org/10.5194/nhess-22-2031-2022"},"orgs":["eth-zurich","sdsc"],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Random forest classifiers predict Swiss avalanche danger levels from 20 years of station weather and snow simulations, reaching 72-78% accuracy.","significance":3,"cited_by":51,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-hess-26-2923-2022","title":"Quantifying the uncertainty of precipitation forecasting using probabilistic deep learning","authors":["Lei Xu","Nengcheng Chen","Chao Yang","Hongchu Yu","Zeqiang Chen"],"date":"2022-06-14","year":2022,"venue":"Hydrology and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/hess-26-2923-2022","openalex":"W4282825004"},"links":{"paper":"https://doi.org/10.5194/hess-26-2923-2022"},"orgs":[],"topic":"probabilistic-ensembles","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Deep learning precipitation forecasting that jointly models input, target and model uncertainty via error propagation and weight sampling, giving tighter predictive uncertainty than prior joint approaches.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7752","title":"Application of copula‐based approach as a new data‐driven model for downscaling the mean daily temperature","authors":["Mohammad Nazeri Tahroudi","Yousef Ramezani","Carlo De Michele","Rasoul Mirabbasi"],"date":"2022-06-14","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7752","openalex":"W4282918200"},"links":{"paper":"https://doi.org/10.1002/joc.7752"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Vine copula downscaling of daily mean temperature outperforms ANN, SVR, GP and ANFIS, reducing RMSE by 20–82% at one Iranian station.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-cpe.7141","title":"Weather parameters forecasting with time series using deep hybrid neural networks","authors":["Sercan Yalçın"],"date":"2022-06-14","year":2022,"venue":"Concurrency and Computation Practice and Experience","venue_type":"journal","ids":{"doi":"10.1002/cpe.7141","openalex":"W4282943735"},"links":{"paper":"https://doi.org/10.1002/cpe.7141"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid CNN-LSTM model forecasts temperature, humidity, pressure and wind speed time series, reporting lower errors than machine learning and deep learning baselines.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.08953","title":"Bayesian neural networks for the probabilistic forecasting of wind direction and speed using ocean data","authors":["Mariana C A Clare","Matthew D Piggott"],"date":"2022-06-14","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.08953"},"links":{"paper":"https://arxiv.org/abs/2206.08953","pdf":"https://arxiv.org/pdf/2206.08953"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Bayesian neural networks forecast offshore wind speed and direction at FINO1 from ocean variables, giving calibrated uncertainty for North Sea wind-resource prediction.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aiig.2022.06.001","title":"A convolutional recurrent neural network for strong convective rainfall nowcasting using weather radar data in Southeastern Brazil","authors":["Angélica Caseri","Leonardo Bacelar Lima Santos","Stephan Stephany"],"date":"2022-06-13","year":2022,"venue":"Artificial Intelligence in Geosciences","venue_type":"journal","ids":{"doi":"10.1016/j.aiig.2022.06.001","openalex":"W4282841766"},"links":{"paper":"https://doi.org/10.1016/j.aiig.2022.06.001","pdf":"https://www.sciencedirect.com/science/article/pii/S2666544122000211/pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"M5Images, a convolutional LSTM on radar images, nowcasts strong convective rainfall near Campinas, Brazil, outperforming persistence at all lead times.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10511598.1","title":"Calibration and Uncertainty Quantification of Gravity Wave Parameterization in an Intermediate Complexity Climate Model","authors":["Laura Mansfield","Aditi Sheshadri"],"date":"2022-06-12","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10511598.1","openalex":"W4282841074"},"links":{"paper":"https://doi.org/10.1002/essoar.10511598.1"},"orgs":["stanford"],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Calibrate-Emulate-Sample with a Gaussian process emulator quantifies gravity wave parameterization uncertainty; QBO parametric uncertainty is comparable to 2xCO2 internal variability.","significance":3,"cited_by":0,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.19614573","title":"AI-Based Climate Change Forecasting Models","authors":["Noah Ivanov","Daniel Dubois","Erik Ivanov"],"date":"2022-06-11","year":2022,"venue":"Bio-QI Journal","venue_type":"journal","ids":{"doi":"10.5281/zenodo.19614573","openalex":"W7203708720"},"links":{"paper":"https://doi.org/10.5281/zenodo.19614573","pdf":"https://stanfordgroup.org/index.php/BioQI/article/download/817/730"},"orgs":[],"topic":"benchmarks-data-eval","topics":["s2s-seasonal","downscaling"],"type":"evaluation","method":["cnn","gnn","neural-operator","transformer","physics-constrained","classical-ml"],"timescale":["seasonal"],"spatial":["global","regional"],"data":["era5","cmip","other"],"status":"research","summary":"Compares six AI approaches across four climate tasks, claiming hybrid physics-ML best at 6-month temperature RMSE; claims are unverified and methodology thin.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.05382","title":"Global Reduction in Ship-tracks from Sulfur Regulations for Shipping Fuel","authors":["Tianle Yuan","Hua Song","Robert Wood","Chenxi Wang","Lazaros Oreopoulos","Steven Platnick","Sophia von Hippel","Kerry Meyer","Siobhan Light","Eric Wilcox"],"date":"2022-06-11","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.05382"},"links":{"paper":"https://arxiv.org/abs/2206.05382","pdf":"https://arxiv.org/pdf/2206.05382"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"application","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Deep learning on Sentinel-1 satellite imagery yields the first multi-year global ship-track climatology, showing 2020 fuel rules cut ship-track frequency to decades-low levels.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-acp-22-7523-2022","title":"The roles of the Quasi-Biennial Oscillation and El Niño for entry stratospheric water vapor in observations and coupled chemistry–ocean CCMI and CMIP6 models","authors":["Shlomi Ziskin Ziv","Chaim I. Garfinkel","Sean Davis","Antara Banerjee"],"date":"2022-06-10","year":2022,"venue":"Atmospheric chemistry and physics","venue_type":"journal","ids":{"doi":"10.5194/acp-22-7523-2022","openalex":"W4281749594"},"links":{"paper":"https://doi.org/10.5194/acp-22-7523-2022"},"orgs":["noaa"],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Advanced machine learning and regression show the QBO matters more than ENSO for stratospheric water vapor; CMIP6 and CCMI models underrepresent the QBO link.","significance":3,"cited_by":9,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aosl.2022.100256","title":"Analysis of lower-boundary climate factors contributing to the summer heatwave frequency over eastern Europe using a machine-learning model","authors":["Ruizhi Zhang","Xiaojing Jia","Qifeng Qian"],"date":"2022-06-09","year":2022,"venue":"Atmospheric and Oceanic Science Letters","venue_type":"journal","ids":{"doi":"10.1016/j.aosl.2022.100256","openalex":"W4289689548"},"links":{"paper":"https://doi.org/10.1016/j.aosl.2022.100256","pdf":"https://www.sciencedirect.com/science/article/pii/S1674283422001349/pdf"},"orgs":["cma"],"topic":"extremes-hazards","topics":["s2s-seasonal","climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"LightGBM uses preceding-winter sea surface temperature, soil moisture and snow to simulate summer eastern European heatwave frequency, with SST contributing most.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.07012","title":"AutoML-Based Drought Forecast with Meteorological Variables","authors":["Shiheng Duan","Xiurui Zhang"],"date":"2022-06-09","year":2022,"venue_type":"preprint","ids":{"arxiv":"2207.07012","openalex":"W4285608184"},"links":{"paper":"https://arxiv.org/abs/2207.07012","pdf":"https://arxiv.org/pdf/2207.07012"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"AutoML framework forecasts US droughts from meteorological variables, matching deep temporal models with less training data and time.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-joe.2022.3162689","title":"Compounding Approaches for Wind Prediction From Underwater Noise by Supervised Learning","authors":["Andrea Trucco","Annalisa Barla","Roberto Bozzano","Emanuele Fava","Sara Pensieri","Alessandro Verri","David Solarna"],"date":"2022-06-08","year":2022,"venue":"IEEE Journal of Oceanic Engineering","venue_type":"journal","ids":{"doi":"10.1109/joe.2022.3162689","openalex":"W4285288749"},"links":{"paper":"https://doi.org/10.1109/joe.2022.3162689"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random forest regression with hourly compounding predicts wind speed from underwater noise, reaching MAE 0.62 m/s and correlation 0.96.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.03914","title":"Spatio-temporal Downscaling Emulator for Regional Climate Models: a Comparative Study","authors":["Luis A. Barboza","Shu Wei Chou-Chen","Marcela Alfaro‐Córdoba","Alfaro, Eric J.","Hidalgo, Hugo G."],"date":"2022-06-08","year":2022,"venue":"Environmetrics","venue_type":"journal","ids":{"arxiv":"2206.03914","doi":"10.1002/env.2815","openalex":"W4281942166"},"links":{"paper":"https://doi.org/10.1002/env.2815","pdf":"https://arxiv.org/pdf/2206.03914"},"orgs":[],"topic":"downscaling","topics":["climate-emulation"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Compares INLA and varycoef for a spatio-temporal varying-coefficient statistical emulator that downscales NARCCAP regional climate model output.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13060929","title":"Summer Precipitation Forecast Using an Optimized Artificial Neural Network with a Genetic Algorithm for Yangtze-Huaihe River Basin, China","authors":["Zhi-Cheng Zhang","Xin‐Min Zeng","Gen Li","Bo Lü","Mingzhong Xiao","Bing-Zeng Wang"],"date":"2022-06-07","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13060929","openalex":"W4281687187"},"links":{"paper":"https://doi.org/10.3390/atmos13060929","pdf":"https://www.mdpi.com/2073-4433/13/6/929/pdf?version=1655265813"},"orgs":["cma"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Genetic-algorithm-optimized backpropagation network forecasts summer precipitation in the Yangtze-Huaihe basin, reaching MAPE near 20% and beating SVM and linear regression.","significance":2,"cited_by":9,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.04015","title":"Improving trajectory calculations using deep learning inspired single image superresolution","authors":["Rüdiger Brecht","Lucie Bakels","Alex Bihlo","Andreas Stohl"],"date":"2022-06-07","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.04015"},"links":{"paper":"https://arxiv.org/abs/2206.04015","pdf":"https://arxiv.org/pdf/2206.04015"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Applies EDSR-style super-resolution to ERA5 winds, halving RMSE versus linear interpolation and reducing 48-hour FLEXPART trajectory errors by at least 49.5%.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.03207","title":"Omnivision forecasting: combining satellite observations with sky images for improved intra-hour solar energy predictions","authors":["Quentin Paletta","Guillaume Arbod","Joan Lasenby"],"date":"2022-06-07","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.03207","openalex":"W4281636147"},"links":{"paper":"https://arxiv.org/abs/2206.03207","pdf":"https://arxiv.org/pdf/2206.03207"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts","observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"Combines all-sky camera images with satellite observations in one ML framework, improving intra-hour solar irradiance forecasts up to 60 minutes ahead.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.03110","title":"Physics captured by data-based methods in El Niño prediction","authors":["G. Lancia","I. J. Goede","C. Spitoni","H. A. Dijkstra"],"date":"2022-06-07","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.03110","doi":"10.1063/5.0101668"},"links":{"paper":"https://arxiv.org/abs/2206.03110","pdf":"https://arxiv.org/pdf/2206.03110"},"orgs":[],"topic":"xai-uq-physics","topics":["s2s-seasonal"],"type":"evaluation","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Distorted-physics experiments show a CNN El Niño predictor corrects ocean adjustment distortions well but struggles with changes in upwelling feedback strength.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32604-iasc.2023.029644","title":"Using GAN Neural Networks for Super-Resolution Reconstruction of Temperature Fields","authors":["Tao Li","Zhiwei Jiang","Rui Han","Jinyue Xia","Yongjun Ren"],"date":"2022-06-06","year":2022,"venue":"Intelligent Automation & Soft Computing","venue_type":"journal","ids":{"doi":"10.32604/iasc.2023.029644","openalex":"W4281693665"},"links":{"paper":"https://doi.org/10.32604/iasc.2023.029644","pdf":"https://file.techscience.com/ueditor/files/iasc/TSP_IASC-35-1/TSP_IASC_29644/TSP_IASC_29644.pdf"},"orgs":["ibm-research","nuist"],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"GAN with sub-pixel convolution performs 8x super-resolution of ERA5 temperature fields, improving RMSE 37% over bicubic interpolation.","significance":3,"cited_by":5,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002836","title":"Toward Efficient Calibration of Higher‐Resolution Earth System Models","authors":["Christopher G. Fletcher","William McNally","John G. Virgin","Fraser King"],"date":"2022-06-04","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002836","openalex":"W4281732312"},"links":{"paper":"https://doi.org/10.1029/2021ms002836","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002836"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A CNN emulates perturbed-parameter ensembles of a higher-resolution Earth system model from few high-resolution runs, making calibration 20-40% more efficient.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.cageo.2022.105152","title":"Location-Refining neural network: A new deep learning-based framework for Heavy Rainfall Forecast","authors":["Xu Huang","Chuyao Luo","Yunming Ye","Xutao Li","Bowen Zhang"],"date":"2022-06-03","year":2022,"venue":"Computers & Geosciences","venue_type":"journal","ids":{"doi":"10.1016/j.cageo.2022.105152","openalex":"W4281746913"},"links":{"paper":"https://doi.org/10.1016/j.cageo.2022.105152"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Location-Refining neural network framework for heavy rainfall forecasting. The abstract is unavailable, so the classification relies on the title.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.07580","title":"Analysis, Characterization, Prediction and Attribution of Extreme Atmospheric Events with Machine Learning: a Review","authors":["Sancho Salcedo-Sanz","Jorge Pérez-Aracil","Guido Ascenso","Javier Del Ser","David Casillas-Pérez","Christopher Kadow","Dusan Fister","David Barriopedro","Ricardo García-Herrera","Marcello Restelli","Mateo Giuliani","Andrea Castelletti"],"date":"2022-06-03","year":2022,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"arxiv":"2207.07580","doi":"10.1007/s00704-023-04571-5","openalex":"W4386220319"},"links":{"paper":"https://doi.org/10.1007/s00704-023-04571-5","pdf":"https://arxiv.org/pdf/2207.07580"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Review of machine learning for analysing, predicting and attributing atmospheric extreme events, covering methods, examples and open perspectives.","significance":3,"cited_by":84,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su14116824","title":"Improvement in Solar-Radiation Forecasting Based on Evolutionary KNEA Method and Numerical Weather Prediction","authors":["Guosheng Duan","Lifeng Wu","Fa Liu","Yicheng Wang","Shaofei Wu"],"date":"2022-06-02","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su14116824","openalex":"W4281740937"},"links":{"paper":"https://doi.org/10.3390/su14116824","pdf":"https://www.mdpi.com/2071-1050/14/11/6824/pdf?version=1654166166"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["classical-ml","rnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Hybrid BA-KNEA post-processing of GEFSv12 forecasts improves 1–3 day solar radiation forecasts in Xinjiang, with RMSE 3.2–3.7 MJ m-2 d-1.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10511517.1","title":"Correcting a coarse-grid climate model in multiple climates by machine learning from global 25-km resolution simulations","authors":["Spencer Koncius Clark","Noah Brenowitz","Brian Henn","Anna Kwa","Jeremy McGibbon","W. A. Perkins","Oliver Watt‐Meyer","Christopher S. Bretherton","Lucas Harris"],"date":"2022-06-02","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10511517.1","openalex":"W4282824883"},"links":{"paper":"https://doi.org/10.1002/essoar.10511517.1"},"orgs":["ai2","noaa"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Machine-learned corrective tendencies from nudged 25 km runs improve land precipitation pattern errors by 17-30% in a coarse FV3GFS across four climates.","significance":4,"cited_by":2,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.810943","title":"Modulation of Pacific Sea Surface Temperature on Two Types of Tropical Cyclone Tracks Affecting Northeast China","authors":["Yiqiu Yu","Yihe Fang","Chunyu Zhao","Yi Lin","Yi Lin","Yitong Lin","Yitong Lin","Zhiqiang Gong","Yang Li"],"date":"2022-05-31","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.810943","openalex":"W4281733307"},"links":{"paper":"https://doi.org/10.3389/feart.2022.810943","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.810943/pdf"},"orgs":["cma"],"topic":"climate-analysis-attribution","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Hierarchical clustering separates northward-moving typhoon tracks affecting Northeast China and links each type to preceding Pacific SST anomalies, with numerical experiments confirming the mechanism.","significance":2,"cited_by":5,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2206.00060","title":"Universal Early Warning Signals of Phase Transitions in Climate Systems","authors":["Daniel Dylewsky","Timothy M. Lenton","Marten Scheffer","Thomas M. Bury","Christopher G. Fletcher","Madhur Anand","Chris T. Bauch"],"date":"2022-05-31","year":2022,"venue_type":"preprint","ids":{"arxiv":"2206.00060"},"links":{"paper":"https://arxiv.org/abs/2206.00060","pdf":"https://arxiv.org/pdf/2206.00060"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A network trained only on 2D Ising phase transitions detects early warning signals in real and simulated climate tipping systems, often beating standard statistical indicators.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.887842","title":"FC-ZSM: Spatiotemporal Downscaling of Rain Radar Data Using a Feature Constrained Zooming Slow-Mo Network","authors":["Haoran Chen","Huawang Qin","Yuewei Dai"],"date":"2022-05-30","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.887842","openalex":"W4281715839"},"links":{"paper":"https://doi.org/10.3389/feart.2022.887842","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.887842/pdf"},"orgs":["nuist"],"topic":"downscaling","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Feature-constrained Zooming Slow-Mo network spatiotemporally downscales rain radar fields, outperforming U-Net variants and interpolation on a public radar dataset.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00521-022-07384-1","title":"A real time prediction methodology for hurricane evolution using LSTM recurrent neural networks","authors":["Rikhi Bose","Adam L. Pintar","Emil Simiu"],"date":"2022-05-30","year":2022,"venue":"Neural Computing and Applications","venue_type":"journal","ids":{"doi":"10.1007/s00521-022-07384-1","openalex":"W4282017798"},"links":{"paper":"https://doi.org/10.1007/s00521-022-07384-1"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"LSTM recurrent networks give real-time predictions of hurricane evolution; no abstract was provided, so quantitative skill and data details are unknown.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10511494.1","title":"Implementation of a machine-learned gas optics parameterization in the ECMWF Integrated Forecasting System","authors":["Peter Ukkonen","Robin James Hogan"],"date":"2022-05-30","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.1002/essoar.10511494.1","openalex":"W4293070907"},"links":{"paper":"https://doi.org/10.5194/gmd-16-3241-2023","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10511494.1"},"orgs":["ecmwf","university-of-reading"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"pre-operational","summary":"Implements a neural-network gas optics scheme in ECMWF's IFS, speeding radiation by about one third with a similar model climate in 1-year coupled runs.","significance":5,"cited_by":10,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46647-ijetms.2022.v06i03.011","title":"Detection of Hurricane through Satellite Images","authors":["K.Sandhya Rani","Kandi Archana","Teegulla Sreenath","Damera Esther Evangelin","Bandi Manoj Kumar","V.Chandra Sekhar Reddy"],"date":"2022-05-28","year":2022,"venue":"International Journal of Engineering Technology and Management Sciences","venue_type":"journal","ids":{"doi":"10.46647/ijetms.2022.v06i03.011","openalex":"W4283381825"},"links":{"paper":"https://doi.org/10.46647/ijetms.2022.v06i03.011","pdf":"https://doi.org/10.46647/ijetms.2022.v06i03.011"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Compares SVM, Naive Bayes and pretrained AlexNet on satellite images to flag areas likely hit by hurricanes; methods are standard and evaluation is thin.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su14116624","title":"A Smart Post-Processing System for Forecasting the Climate Precipitation Based on Machine Learning Computations","authors":["Adel Ghazikhani","Iman Babaeian","Mohammad Gheibi","Mostafa Hajiaghaei–Keshteli","Amir M. Fathollahi‐Fard"],"date":"2022-05-28","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su14116624","openalex":"W4281999679"},"links":{"paper":"https://doi.org/10.3390/su14116624","pdf":"https://www.mdpi.com/2071-1050/14/11/6624/pdf?version=1654004070"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Random forest post-processing of CFSv2 precipitation forecasts over Iran (1982-2017) reaches correlation above 0.87, packaged as a GUI decision support tool.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14112548","title":"Function-Based Troposphere Tomography Technique for Optimal Downscaling of Precipitation","authors":["Saeid Haji-Aghajany","Yazdan Amerian","Alireza Amiri-Simkooei"],"date":"2022-05-26","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14112548","openalex":"W4281617113"},"links":{"paper":"https://doi.org/10.3390/rs14112548","pdf":"https://www.mdpi.com/2072-4292/14/11/2548/pdf?version=1653626065"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"GNSS tomography humidity fields improve statistical and ANN precipitation downscaling, cutting monthly precipitation RMSE by about 38% on average.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.13158","title":"SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation","authors":["Yuan Hu","Lei Chen","Zhibin Wang","Hao Li"],"date":"2022-05-26","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2205.13158","doi":"10.1029/2022ms003211","openalex":"W4320921606"},"links":{"paper":"https://arxiv.org/abs/2205.13158","pdf":"https://arxiv.org/pdf/2205.13158"},"orgs":["alibaba-damo","fudan-university"],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["transformer","gan-vae"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"SwinVRNN learns VAE-based distribution perturbations within a Swin transformer recurrent model, giving better ensemble accuracy and spread than other perturbation methods on WeatherBench.","significance":4,"cited_by":63,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"openalex-W4281564155","title":"Multimodel Ensemble Predictions of Precipitation using Bayesian Neural Networks","authors":["Patrick Fan"],"date":"2022-05-25","year":2022,"venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","venue_type":"preprint","ids":{"openalex":"W4281564155"},"links":{"paper":"https://www.osti.gov/biblio/1869077"},"orgs":["ornl"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Bayesian neural network learns spatiotemporally varying weights to combine climate-model precipitation ensembles, outperforming three ensemble methods and quantifying epistemic uncertainty.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-4105-2022","title":"Simulation, precursor analysis and targeted observation sensitive area identification for two types of ENSO using ENSO-MC v1.0","authors":["Bin Mu","Yuehan Cui","Shijin Yuan","Bo Qin"],"date":"2022-05-25","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-4105-2022","openalex":"W4281475877"},"links":{"paper":"https://doi.org/10.5194/gmd-15-4105-2022"},"orgs":[],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"ENSO-MC multichannel deep network forecasts spatial SST anomalies for eastern and central Pacific El Niño up to one year ahead; saliency maps locate precursors.","significance":4,"cited_by":18,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fpls.2022.862558","title":"An Algorithm for Precipitation Correction in Flood Season Based on Dendritic Neural Network","authors":["Tao Li","Chenwei Qiao","Lina Wang","Jie Chen","Yongjun Ren"],"date":"2022-05-24","year":2022,"venue":"Frontiers in Plant Science","venue_type":"journal","ids":{"doi":"10.3389/fpls.2022.862558","openalex":"W4281381350"},"links":{"paper":"https://doi.org/10.3389/fpls.2022.862558","pdf":"https://www.frontiersin.org/articles/10.3389/fpls.2022.862558/pdf"},"orgs":["nuist"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"A dendritic neural network corrects CWRF summer precipitation forecasts against station data, raising anomaly correlation by 0.1 and cutting MSE by about 26%.","significance":2,"cited_by":9,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-022-04103-7","title":"Hybrid deep learning approach for multi-step-ahead prediction for daily maximum temperature and heatwaves","authors":["Mohd Imran Khan","Rajib Maity"],"date":"2022-05-24","year":2022,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-022-04103-7","openalex":"W4281391190"},"links":{"paper":"https://doi.org/10.1007/s00704-022-04103-7"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid deep learning model gives multi-step-ahead forecasts of daily maximum temperature and heatwaves; no abstract was provided, so skill figures are unknown.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.12224","title":"GLObal Building heights for Urban Studies (UT-GLOBUS) for city- and street- scale urban simulations: Development and first applications","authors":["Harsh G. Kamath","Manmeet Singh","Neetiraj Malviya","Alberto Martilli","Liu He","Daniel Aliaga","Cenlin He","Fei Chen","Lori A. Magruder","Zong-Liang Yang","Dev Niyogi"],"date":"2022-05-24","year":2022,"venue":"Sci Data 11, 886 (2024)","venue_type":"journal","ids":{"arxiv":"2205.12224","doi":"10.1038/s41597-024-03719-w","openalex":"W4281571468"},"links":{"paper":"https://arxiv.org/abs/2205.12224","pdf":"https://arxiv.org/pdf/2205.12224"},"orgs":[],"topic":"benchmarks-data-eval","topics":["applications-impacts"],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other","satellite","km-scale-sim"],"status":"pre-operational","summary":"UT-GLOBUS uses machine learning on spaceborne altimetry to map building heights for 1200+ cities, improving WRF-Urban intra-urban air temperature RMSE by 55% over a table-based approach.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ea002221","title":"A Hybrid Statistical Downscaling Framework Based on Nonstationary Time Series Decomposition and Machine Learning","authors":["Xintong Li","Xiaodong Zhang","Shuguang Wang"],"date":"2022-05-23","year":2022,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2022ea002221","openalex":"W4281293346"},"links":{"paper":"https://doi.org/10.1029/2022ea002221","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022EA002221"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Bivariate EMD decomposition combined with machine learning downscales CanESM monthly precipitation and temperature at California stations, beating wavelet-based baselines.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.10972","title":"Global Extreme Heat Forecasting Using Neural Weather Models","authors":["Ignacio Lopez-Gomez","Amy McGovern","Shreya Agrawal","Jason Hickey"],"date":"2022-05-23","year":2022,"venue":"Artificial Intelligence for the Earth Systems (2023)","venue_type":"journal","ids":{"arxiv":"2205.10972","doi":"10.1175/aies-d-22-0035.1","openalex":"W4313407333"},"links":{"paper":"https://arxiv.org/abs/2205.10972","pdf":"https://arxiv.org/pdf/2205.10972"},"orgs":["caltech","google-research","university-of-oklahoma"],"topic":"extremes-hazards","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["medium","s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Convolutional neural weather models trained with extreme-focused losses improve global heatwave forecasts 1 to 28 days ahead, beating persistence and ECMWF S2S after two weeks.","significance":4,"cited_by":41,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1002-joc.7733","title":"Assessing statistical downscaling in Argentina: Daily maximum and minimum temperatures","authors":["Rocío Balmaceda-Huarte","María Laura Bettolli"],"date":"2022-05-22","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7733","openalex":"W4281251876"},"links":{"paper":"https://doi.org/10.1002/joc.7733"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","nwp-analysis","stations"],"status":"research","summary":"Compares analog, GLM and neural network statistical downscaling of daily Tx and Tn at 101 Argentine stations across three reanalyses, including a warm-period extrapolation test.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl097996","title":"Subseasonal Forecast Skill Improvement From Strongly Coupled Data Assimilation With a Linear Inverse Model","authors":["Gregory J. Hakim","Chris Snyder","Stephen Gregory Penny","Matthew Newman"],"date":"2022-05-21","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl097996","openalex":"W4281262425"},"links":{"paper":"https://doi.org/10.1029/2022gl097996","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL097996"},"orgs":["noaa","ncar","university-of-washington"],"topic":"data-assimilation","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Kalman filter with a trained linear inverse model performs strongly coupled assimilation, cutting SST analysis error over 20% and extending forecast skill to 50 days.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.susmat.2022.e00429","title":"Efficient daily solar radiation prediction with deep learning 4-phase convolutional neural network, dual stage stacked regression and support vector machine CNN-REGST hybrid model","authors":["Sujan Ghimire","Thong Nguyen‐Huy","Ravinesh Chand Deo","David Casillas-Pérez","Sancho Salcedo‐Sanz"],"date":"2022-05-20","year":2022,"venue":"Sustainable materials and technologies","venue_type":"journal","ids":{"doi":"10.1016/j.susmat.2022.e00429","openalex":"W4280550823"},"links":{"paper":"https://doi.org/10.1016/j.susmat.2022.e00429"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","cmip"],"status":"research","summary":"Hybrid CNN-REGST model predicts daily solar radiation at six Queensland farms from GCM and observation features, reported as more accurate than DL and ML baselines.","significance":2,"cited_by":89,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12145-022-00819-2","title":"A novel integrated learning model for rainfall prediction CEEMD- FCMSE -Stacking","authors":["Xianqi Zhang","Kai Wang","Zhiwen Zheng"],"date":"2022-05-20","year":2022,"venue":"Earth Science Informatics","venue_type":"journal","ids":{"doi":"10.1007/s12145-022-00819-2","openalex":"W4301406157"},"links":{"paper":"https://doi.org/10.1007/s12145-022-00819-2","pdf":"https://www.researchsquare.com/article/rs-1006290/latest.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Stacked ensemble with CEEMD decomposition is proposed for rainfall prediction; the abstract is missing, so the method and results cannot be verified.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10511429.1","title":"Climate change-induced peatland drying in Southeast Asia Authors","authors":["Nathan C. Dadap","Ale×ander R. Cobb","Alison May Hoyt","Charles F. Harvey","Andrew F. Feldman","Eun‐Soon Im","Alexandra G. Konings"],"date":"2022-05-20","year":2022,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1002/essoar.10511429.1","openalex":"W4281260359"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ac7969"},"orgs":["mit","nasa","stanford"],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","satellite"],"status":"research","summary":"Neural networks trained on SMAP soil moisture project Southeast Asian peat drying under RCP8.5, finding decreases about half as strong as recent El Niño droughts.","significance":3,"cited_by":25,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0116.1","title":"Tropical Cyclone Track Prediction with an Encoding-to-Forecasting Deep Learning Model","authors":["Pingping Dong","Jie Lian","Hui Yu","Jianguo Pan","Yuping Zhang","Guomin Chen"],"date":"2022-05-19","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0116.1","openalex":"W4280638202"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0116.1"},"orgs":["cma"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"A ConvLSTM encoder-decoder with spatial attention forecasts 24 h western North Pacific tropical cyclone tracks from satellite images, about 30 km better than ECMWF-HRES and GFS.","significance":3,"cited_by":26,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.apenergy.2022.119257","title":"Exogenous atmospheric variables as wind speed predictors in machine learning","authors":["Amaris Dalton","Bernard Bekker"],"date":"2022-05-19","year":2022,"venue":"Applied Energy","venue_type":"journal","ids":{"doi":"10.1016/j.apenergy.2022.119257","openalex":"W4280630919"},"links":{"paper":"https://doi.org/10.1016/j.apenergy.2022.119257"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Study of exogenous atmospheric variables as machine learning predictors of wind speed for energy applications; abstract unavailable, so scope is inferred from the title.","significance":2,"cited_by":27,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2022.042","title":"Downscaling model for rainfall based on the influence of typhoon under climate change","authors":["Shiu‐Shin Lin","Yanli Hu","Kai-Yang Zhu"],"date":"2022-05-18","year":2022,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2022.042","openalex":"W4280548806"},"links":{"paper":"https://doi.org/10.2166/wcc.2022.042"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"GA-RBF neural network downscales CMIP5 GCM output to monthly rainfall at Taichung and Hualien, Taiwan, with separate typhoon and non-typhoon rainfall modelling.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0194.1","title":"Predicting Rapid Intensification in North Atlantic and Eastern North Pacific Tropical Cyclones Using a Convolutional Neural Network","authors":["Sarah M. Griffin","Anthony Wimmers","Christopher S. Velden"],"date":"2022-05-18","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0194.1","openalex":"W4280638911"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0194.1"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"I-RI CNN uses satellite imagery and scalar features to predict tropical cyclone rapid intensification, beating operational guidance at 12- and 24-h leads in the Atlantic.","significance":4,"cited_by":33,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-10106049.2022.2076914","title":"Rainstorm prediction via a deep spatio-temporal-attributed affinity network","authors":["Tong Zhang","Jie Liu","Jianlong Wang"],"date":"2022-05-18","year":2022,"venue":"Geocarto International","venue_type":"journal","ids":{"doi":"10.1080/10106049.2022.2076914","openalex":"W4280599789"},"links":{"paper":"https://doi.org/10.1080/10106049.2022.2076914"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["gnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Graph convolutional network with learned spatio-temporal affinities and a class-imbalance loss predicts rare rainstorms better than competing methods on two datasets.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.09182","title":"Computing the ensemble spread from deterministic weather predictions using conditional generative adversarial networks","authors":["Rüdiger Brecht","Alex Bihlo"],"date":"2022-05-18","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"arxiv":"2205.09182","doi":"10.1029/2022gl101452","openalex":"W4317234252"},"links":{"paper":"https://doi.org/10.1029/2022gl101452","pdf":"https://arxiv.org/pdf/2205.09182"},"orgs":[],"topic":"probabilistic-ensembles","topics":["post-processing"],"type":"model","method":["gan-vae","cnn"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Conditional GANs predict ensemble spread of 500 hPa geopotential from a single deterministic forecast, avoiding costly operational ensemble runs.","significance":4,"cited_by":34,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-isprs-annals-v-2-2022-237-2022","title":"SEMANTIC SEGMENTATION OF HISTORICAL PHOTOGRAPHS OF THE ANTARCTICA PENINSULA","authors":["Felix Dahle","Julian Tanke","Bert Wouters","Roderik Lindenbergh"],"date":"2022-05-17","year":2022,"venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","venue_type":"journal","ids":{"doi":"10.5194/isprs-annals-v-2-2022-237-2022","openalex":"W4280557206"},"links":{"paper":"https://doi.org/10.5194/isprs-annals-v-2-2022-237-2022","pdf":"https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2022/237/2022/isprs-annals-V-2-2022-237-2022.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"First deep-learning semantic segmentation of scanned 1940-2000 US Navy Antarctic Peninsula photos, reaching 74% accuracy on eight test images despite analog and scanning artifacts.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-3923-2022","title":"Stable climate simulations using a realistic general circulation model with neural network parameterizations for atmospheric moist physics and radiation processes","authors":["Xin Wang","Yilun Han","Wei Xue","Guangwen Yang","Guang J. Zhang"],"date":"2022-05-16","year":2022,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-3923-2022","openalex":"W4280597599"},"links":{"paper":"https://doi.org/10.5194/gmd-15-3923-2022"},"orgs":["tsinghua-university"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Residual neural networks replace moist physics and radiation in a realistic GCM, giving stable simulations over 10+ years with improved tropical land precipitation.","significance":5,"cited_by":72,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos13050815","title":"Weather Radar Echo Extrapolation Method Based on Deep Learning","authors":["Fugui Zhang","Can Lai","Wanjun Chen"],"date":"2022-05-16","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13050815","openalex":"W4280567255"},"links":{"paper":"https://doi.org/10.3390/atmos13050815","pdf":"https://www.mdpi.com/2073-4433/13/5/815/pdf?version=1652772595"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A Conv-LSTM encoder-decoder with rain-weighted MSE extrapolates radar echoes for 2 h, reaching 0.42 CSI at 30 dBZ for 1 h, above CTREC.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-22-0019.1","title":"ProbSevere LightningCast: A Deep-Learning Model for Satellite-Based Lightning Nowcasting","authors":["John L. Cintineo","Michael J. Pavolonis","Justin M. Sieglaff"],"date":"2022-05-16","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-22-0019.1","openalex":"W4280565044"},"links":{"paper":"https://doi.org/10.1175/waf-d-22-0019.1","pdf":"https://repository.library.noaa.gov/view/noaa/52868/noaa_52868_DS1.pdf"},"orgs":["noaa"],"topic":"nowcasting","topics":["observations-remote-sensing","extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"pre-operational","summary":"LightningCast uses a CNN on GOES-16 ABI imagery to predict next-hour lightning over CONUS, giving about 20 min or more of lead time and transferring to GOES-West.","significance":5,"cited_by":30,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022ms003016","title":"Deep Learning to Estimate Model Biases in an Operational NWP Assimilation System","authors":["Patrick Laloyaux","Thorsten Kurth","Peter Dominik Dueben","David Matthew Hall"],"date":"2022-05-16","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2022ms003016","openalex":"W4280570141"},"links":{"paper":"https://doi.org/10.1029/2022ms003016","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003016"},"orgs":["nvidia","ecmwf"],"topic":"data-assimilation","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5","nwp-analysis","satellite"],"status":"research","summary":"Convolutional networks learn IFS model bias from radio occultation temperatures, pretrained on ERA5 and transfer-learned on one year of IFS data, as an alternative to weak-constraint 4D-Var.","significance":4,"cited_by":37,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asoc.2022.109003","title":"A spatio-temporal graph-guided convolutional LSTM for tropical cyclones precipitation nowcasting","authors":["Xuying Yang","Feng Zhang","Peng Sun","Xiaofan Li","Zhenhong Du","Renyi Liu"],"date":"2022-05-14","year":2022,"venue":"Applied Soft Computing","venue_type":"journal","ids":{"doi":"10.1016/j.asoc.2022.109003","openalex":"W4280650853"},"links":{"paper":"https://doi.org/10.1016/j.asoc.2022.109003"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","cnn","gnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"A graph-guided ConvLSTM nowcasts precipitation from tropical cyclones, combining spatio-temporal graph structure with convolutional recurrent modelling.","significance":3,"cited_by":25,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.6551525","title":"Machine learning of cloud types in satellite observations and climate models","authors":["Peter Kuma","Frida A.‐M. Bender","Alex J. Schuddeboom","Adrian McDonald","Øyvind Seland"],"date":"2022-05-13","year":2022,"venue":"Atmospheric chemistry and physics","venue_type":"journal","ids":{"doi":"10.5281/zenodo.6551525","openalex":"W4286780200"},"links":{"paper":"https://doi.org/10.5194/acp-23-523-2023","pdf":"https://zenodo.org/record/6891232"},"orgs":["met-norway"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"application","method":[],"timescale":[],"spatial":[],"data":["satellite","cmip"],"status":"research","summary":"Slide deck on machine learning classification of cloud types in satellite observations and climate models; no abstract or quantitative results provided.","significance":1,"cited_by":38,"score":39,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14102364","title":"Air–Sea Interface Parameters and Heat Flux from Neural Network and Advanced Microwave Scanning Radiometer Observations","authors":["Biao Zhang","Xiaotong Yu","William A. Perrie","Fenghua Zhou"],"date":"2022-05-13","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14102364","openalex":"W4280635490"},"links":{"paper":"https://doi.org/10.3390/rs14102364","pdf":"https://www.mdpi.com/2072-4292/14/10/2364/pdf?version=1652690950"},"orgs":["nuist"],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","stations","era5"],"status":"research","summary":"Neural network retrieves ocean surface wind, SST and near-surface air temperature and humidity from AMSR2, with heat flux RMSE of 18-40 W/m2 against buoys.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2022.42244","title":"Rainfall Prediction Model Using Machine Learning Techniques","authors":["Govind Wakure","Rahul Lotlikar","Pushant Mangilipelli","Saif Ahmad Khan"],"date":"2022-05-13","year":2022,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2022.42244","openalex":"W4280531755"},"links":{"paper":"https://doi.org/10.22214/ijraset.2022.42244","pdf":"https://doi.org/10.22214/ijraset.2022.42244"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Reviews 2013-2017 machine learning studies for rainfall prediction, summarizing data mining approaches and suggesting future directions.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13050783","title":"Tropical Cyclone Intensity Prediction Using Deep Convolutional Neural Network","authors":["Xiaoyan Xu","Min Shao","Pulong Chen","Qin’geng Wang"],"date":"2022-05-12","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13050783","openalex":"W4280581297"},"links":{"paper":"https://doi.org/10.3390/atmos13050783","pdf":"https://www.mdpi.com/2073-4433/13/5/783/pdf?version=1652351094"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Simplified VGG-16 CNN predicts tropical cyclone intensity from reanalysis predictors, outperforming LeNet-5 and AlexNet; SST, 500 hPa temperature and vertical wind shear are the top drivers.","significance":3,"cited_by":34,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1371-journal.pwat.0000016","title":"A bias correction method for precipitation through recognizing mesoscale precipitation systems corresponding to weather conditions","authors":["Takao Yoshikane","Kei Yoshimura"],"date":"2022-05-12","year":2022,"venue":"PLOS Water","venue_type":"journal","ids":{"doi":"10.1371/journal.pwat.0000016","openalex":"W4280620703"},"links":{"paper":"https://doi.org/10.1371/journal.pwat.0000016"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine learning bias correction of simulated hourly precipitation, combined with quantile mapping, improves spatial frequency distribution but not temporal distribution of local precipitation.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-022-11936-9","title":"ECMWF short-term prediction accuracy improvement by deep learning","authors":["Jaroslav Frnda","Marek Ďurica","Jan Rozhon","Mária Vojteková","Jan Nedoma","Radek Martínek"],"date":"2022-05-12","year":2022,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-022-11936-9","openalex":"W4280500345"},"links":{"paper":"https://doi.org/10.1038/s41598-022-11936-9","pdf":"https://www.nature.com/articles/s41598-022-11936-9.pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A neural network post-processes ECMWF forecasts of 2 m temperature and 24 h precipitation using station observations in 10 European cities, improving on raw ECMWF.","significance":3,"cited_by":72,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.06351","title":"Interpretable Climate Change Modeling With Progressive Cascade Networks","authors":["Charles Anderson","Jason Stock","David Anderson"],"date":"2022-05-12","year":2022,"venue_type":"preprint","ids":{"arxiv":"2205.06351"},"links":{"paper":"https://arxiv.org/abs/2205.06351","pdf":"https://arxiv.org/pdf/2205.06351"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Progressive cascade networks start from linear models and add complexity only as data supports, then map global temperature and precipitation to years to reveal climate change patterns.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14102314","title":"A Cloud Classification Method Based on a Convolutional Neural Network for FY-4A Satellites","authors":["Yuhang Jiang","Wei Xin Cheng","Feng Gao","Shaoqing Zhang","Shudong Wang","Chang Liu","Juanjuan Liu"],"date":"2022-05-11","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14102314","openalex":"W4280556915"},"links":{"paper":"https://doi.org/10.3390/rs14102314","pdf":"https://www.mdpi.com/2072-4292/14/10/2314/pdf?version=1652258701"},"orgs":["iap-cas","cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"U-Net based CLP-CNN classifies cloud types from FY-4A L1 data over China in 0.9 s per 800x800 scene, matching Himawari-8 products 76.8% of the time.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-asl.1100","title":"Hourly rolling correction of precipitation forecast via convolutional and long short‐term memory networks","authors":["Ruyi Yang","Jianli Mu","Shudong Wang","Lijuan Wang"],"date":"2022-05-11","year":2022,"venue":"Atmospheric Science Letters","venue_type":"journal","ids":{"doi":"10.1002/asl.1100","openalex":"W4280539749"},"links":{"paper":"https://doi.org/10.1002/asl.1100"},"orgs":["cma"],"topic":"post-processing","topics":["nowcasting"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"A CNN-LSTM predicts cloud-cluster evolution from geostationary IR imagery to rolling-correct 1-6 h GRAPES_Meso precipitation forecasts over China, improving rain/no-rain scores.","significance":3,"cited_by":2,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.28979-jarnas.984312","title":"Sensory Precipitation Forecast Using Artificial Neural Networks and Decision Trees","authors":["Hakkı Fırat ALTINBİLEK","Hakan Nar","Sefa AKSU","Ünal KIZIL"],"date":"2022-05-09","year":2022,"venue":"Journal of Advanced Research in Natural and Applied Sciences","venue_type":"journal","ids":{"doi":"10.28979/jarnas.984312","openalex":"W4280634249"},"links":{"paper":"https://doi.org/10.28979/jarnas.984312","pdf":"https://dergipark.org.tr/en/download/article-file/1931253"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml","other"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Low-cost station sensors (temperature, humidity, rain and others) feed an ANN and decision tree that classify rain with scores of 0.92 and 0.96.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2022.42151","title":"Rainfall Predictions Using Data Visualization Techniques","authors":["Kaushal Kailas Sarda"],"date":"2022-05-09","year":2022,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2022.42151","openalex":"W4229374343"},"links":{"paper":"https://doi.org/10.22214/ijraset.2022.42151","pdf":"https://doi.org/10.22214/ijraset.2022.42151"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Reviews machine learning rainfall prediction techniques and public datasets, classifying forecasting models and suggesting future research directions.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.04601","title":"Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence","authors":["Ashesh Chattopadhyay","Jaideep Pathak","Ebrahim Nabizadeh","Wahid Bhimji","Pedram Hassanzadeh"],"date":"2022-05-09","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2205.04601","doi":"10.1017/eds.2022.30","openalex":"W4315486744"},"links":{"paper":"https://doi.org/10.1017/eds.2022.30","pdf":"https://arxiv.org/pdf/2205.04601"},"orgs":["lbnl-nersc","nvidia"],"topic":"climate-emulation","topics":["probabilistic-ensembles"],"type":"model","method":["gan-vae","cnn"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"A convolutional VAE pretrained on imperfect quasi-geostrophic simulations and transfer-learned on noisy observations gives stable stochastic long-term rollouts with accurate climatology.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13050757","title":"Knowledge-Enhanced Deep Learning for Simulation of Extratropical Cyclone Wind Risk","authors":["Reda Snaiki","Teng Wu"],"date":"2022-05-08","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13050757","openalex":"W3128963373"},"links":{"paper":"https://doi.org/10.3390/atmos13050757","pdf":"https://www.mdpi.com/2073-4433/13/5/757/pdf?version=1652086000"},"orgs":[],"topic":"extremes-hazards","topics":["hybrid-parameterization"],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Physics-informed neural network estimates 3D boundary-layer winds of extratropical cyclones over eastern North America, coupled with a synthetic track database for wind risk.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21608-ijicis.2022.117060.1156","title":"Weather Classification using Fusion Of Convolutional Neural Networks and Traditional Classification Methods","authors":["Moshira S. Ghaleb","Hala Moushier","Howaida Shedeed","Mohamed Fahmy Tolba"],"date":"2022-05-06","year":2022,"venue":"International journal of intelligent computing and information sciences/International Journal of Intelligent Computing and Information Sciences","venue_type":"journal","ids":{"doi":"10.21608/ijicis.2022.117060.1156","openalex":"W4281257966"},"links":{"paper":"https://doi.org/10.21608/ijicis.2022.117060.1156","pdf":"https://ijicis.journals.ekb.eg/article_235120_f1935c8f88c28e3bb12a14992bba29e7.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["cnn","classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Compares CNN, CNN+decision tree and CNN+SVM for classifying five weather image categories, reaching 94% accuracy with the CNN+SVM fusion.","significance":1,"cited_by":13,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl098601","title":"Effects of Cloud Microphysics on the Universal Performance of Neural Network Radiation Scheme","authors":["Hwan‐Jin Song","Park Sa Kim"],"date":"2022-05-06","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl098601","openalex":"W4229023774"},"links":{"paper":"https://doi.org/10.1029/2022gl098601","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL098601"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":[],"type":"evaluation","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","km-scale-sim"],"status":"research","summary":"Tests a neural radiation emulator across 15 microphysics schemes; errors rise 8.6–41.3% in idealized cases, reducible by 26.5–50.4% with a compound parameterization.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.48175-ijarsct-3511","title":"Smart Whether Prediction using Machine Learning Algorithm","authors":["Amruta Kashid","Omkar Kolhe","Antariksh Labade","Mahesh Lokhande","Prof. S. R. Pandit"],"date":"2022-05-05","year":2022,"venue":"International Journal of Advanced Research in Science Communication and Technology","venue_type":"journal","ids":{"doi":"10.48175/ijarsct-3511","openalex":"W4229019135"},"links":{"paper":"https://doi.org/10.48175/ijarsct-3511"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares regression-style machine learning models on historical station data to predict minimum, maximum and average temperature and precipitation for different locations.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.isprsjprs.2022.03.007","title":"Multi-modal spatio-temporal meteorological forecasting with deep neural network","authors":["Xinbang Zhang","Qizhao Jin","Tingzhao Yu","Shiming Xiang","Qiuming Kuang","Véronique Prinet A","Chunhong Pan"],"date":"2022-05-05","year":2022,"venue":"ISPRS Journal of Photogrammetry and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1016/j.isprsjprs.2022.03.007","openalex":"W4229042773"},"links":{"paper":"https://doi.org/10.1016/j.isprsjprs.2022.03.007"},"orgs":["cma"],"topic":"global-medium-range","topics":[],"type":"model","method":["other"],"timescale":["medium"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A multi-modal spatio-temporal deep neural network for meteorological forecasting; the abstract is missing, so the topic is inferred from the title.","significance":2,"cited_by":40,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.02457","title":"MMINR: Multi-frame-to-Multi-frame Inference with Noise Resistance for Precipitation Nowcasting with Radar","authors":["Feng Sun","Cong Bai"],"date":"2022-05-05","year":2022,"venue_type":"preprint","ids":{"arxiv":"2205.02457"},"links":{"paper":"https://arxiv.org/abs/2205.02457","pdf":"https://arxiv.org/pdf/2205.02457"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A parallel multi-frame radar nowcasting model with noise dropout and semantic restore modules reduces error accumulation and achieves competitive scores against state-of-the-art methods.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s22093504","title":"Rainfall Prediction System Using Machine Learning Fusion for Smart Cities","authors":["Atta Rahman","Sagheer Abbas","Mohammed Abdul Salam Gollapalli","Rashad Ahmed","Shabib Aftab","Munir Ahmad","Muhammad Adnan Khan","Amir Hosein Mosavi"],"date":"2022-05-04","year":2022,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s22093504","openalex":"W4229023302"},"links":{"paper":"https://doi.org/10.3390/s22093504","pdf":"https://www.mdpi.com/1424-8220/22/9/3504/pdf?version=1652085887"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Fuzzy-logic fusion of decision tree, naive Bayes, KNN and SVM classifiers predicts rainfall for Lahore from 12 years of station data.","significance":1,"cited_by":170,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su14095494","title":"Deep Learning-Based Projection of Occurrence Frequency of Forest Fires under SSP Scenario: Exploring the Link between Drought Characteristics and Forest Fires","authors":["Jang Hyun Sung","Seung Beom Seo","Young Ryu"],"date":"2022-05-03","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su14095494","openalex":"W4229365204"},"links":{"paper":"https://doi.org/10.3390/su14095494","pdf":"https://www.mdpi.com/2071-1050/14/9/5494/pdf?version=1652236864"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Deep learning model using drought indices, humidity and wind projects South Korean summer forest-fire occurrence to rise, with July up 15% by 2071-2100 under SSPs.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asoc.2022.108941","title":"A multivariate EMD-LSTM model aided with Time Dependent Intrinsic Cross-Correlation for monthly rainfall prediction","authors":["Kavya Johny","Maya L. Pai","S. Adarsh"],"date":"2022-05-03","year":2022,"venue":"Applied Soft Computing","venue_type":"journal","ids":{"doi":"10.1016/j.asoc.2022.108941","openalex":"W4225310696"},"links":{"paper":"https://doi.org/10.1016/j.asoc.2022.108941"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid EMD-LSTM with time-dependent cross-correlation forecasts monthly rainfall; no abstract was provided, so skill figures are unknown.","significance":2,"cited_by":71,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-npg-29-171-2022","title":"Using neural networks to improve simulations in the gray zone","authors":["Raphael Kriegmair","Yvonne Ruckstuhl","Stephan Rasp","George C. Craig"],"date":"2022-05-02","year":2022,"venue":"Nonlinear processes in geophysics","venue_type":"journal","ids":{"doi":"10.5194/npg-29-171-2022","openalex":"W4225279804"},"links":{"paper":"https://doi.org/10.5194/npg-29-171-2022","pdf":"https://npg.copernicus.org/articles/29/171/2022/npg-29-171-2022.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["physics-constrained","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Neural network learns unresolved-scale error in a shallow water model mimicking convection, extending forecast skill to one day; a mass-conservation penalty delays drift.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-asr-19-13-2022","title":"Using machine learning to produce a cost-effective national building height map of Ireland to categorise local climate zones","authors":["Eoghan Keany","Geoffrey Bessardon","Emily Gleeson"],"date":"2022-05-02","year":2022,"venue":"Advances in science and research","venue_type":"journal","ids":{"doi":"10.5194/asr-19-13-2022","openalex":"W4225287117"},"links":{"paper":"https://doi.org/10.5194/asr-19-13-2022","pdf":"https://asr.copernicus.org/articles/19/13/2022/asr-19-13-2022.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["regional-km-scale"],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Builds the first open 10 m building height map of Ireland from Sentinel-1/2 features; CNN is most accurate, but ridge regression is chosen for realism and low cost.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-sym14050927","title":"Predictive Modelling of Statistical Downscaling Based on Hybrid Machine Learning Model for Daily Rainfall in East-Coast Peninsular Malaysia","authors":["Nurul Ainina Filza Sulaiman","Shazlyn Milleana Shaharudin","Shuhaida Binti Ismail","Nurul Hila Zainuddin","Mou Leong Tan","Yusri Abd Jalil"],"date":"2022-05-02","year":2022,"venue":"Symmetry","venue_type":"journal","ids":{"doi":"10.3390/sym14050927","openalex":"W4225371337"},"links":{"paper":"https://doi.org/10.3390/sym14050927","pdf":"https://www.mdpi.com/2073-8994/14/5/927/pdf?version=1651472789"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Two-phase SVC-RVM hybrid statistically downscales daily rainfall on Malaysia's east coast, outperforming SVR and ANN variants in wet-day classification and extremes.","significance":2,"cited_by":37,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenvs.2022.867434","title":"Urban Climate Informatics: An Emerging Research Field","authors":["Ariane Middel","Negin Nazarian","Matthias Demuzere","Benjamin Bechtel"],"date":"2022-05-02","year":2022,"venue":"Frontiers in Environmental Science","venue_type":"journal","ids":{"doi":"10.3389/fenvs.2022.867434","openalex":"W2999275215"},"links":{"paper":"https://doi.org/10.3389/fenvs.2022.867434","pdf":"https://www.frontiersin.org/articles/10.3389/fenvs.2022.867434/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Review introduces Urban Climate Informatics, combining new sensors, crowdsourced data and machine learning to study urban atmospheric states and climate.","significance":2,"cited_by":48,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl098173","title":"Predicting Slowdowns in Decadal Climate Warming Trends With Explainable Neural Networks","authors":["Zachary Michael Labe","Elizabeth A. Barnes"],"date":"2022-05-02","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl098173","openalex":"W4225321588"},"links":{"paper":"https://doi.org/10.1029/2022gl098173","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL098173"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["decadal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Neural network with explainability predicts decadal global warming slowdowns from ocean heat content in CESM2 large ensemble, linking them to Interdecadal Pacific Oscillation-like patterns and testing on observations.","significance":3,"cited_by":37,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.00865","title":"WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline models","authors":["Sagar Garg","Stephan Rasp","Nils Thuerey"],"date":"2022-05-02","year":2022,"venue_type":"preprint","ids":{"arxiv":"2205.00865","openalex":"W4225373634"},"links":{"paper":"https://arxiv.org/abs/2205.00865","pdf":"https://arxiv.org/pdf/2205.00865"},"orgs":["tum"],"topic":"benchmarks-data-eval","topics":["probabilistic-ensembles"],"type":"benchmark","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Extends WeatherBench with probabilistic metrics, an IFS ensemble baseline and three probabilistic ML models; Monte Carlo dropout underestimates uncertainty and no ML model matches IFS.","significance":5,"cited_by":21,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.00743","title":"Machine-learned cloud classes from satellite data for process-oriented climate model evaluation","authors":["A. Kaps","A. Lauer","G. Camps-Valls","P. Gentine","L. Gómez-Chova","V. Eyring"],"date":"2022-05-02","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2205.00743","doi":"10.1109/tgrs.2023.3237008","openalex":"W4317761500"},"links":{"paper":"https://arxiv.org/abs/2205.00743","pdf":"https://arxiv.org/pdf/2205.00743"},"orgs":["columbia-leap"],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite","cmip"],"status":"research","summary":"Deep-learning cloud-type classifier trained on MODIS and CloudSat labels is applied to coarse satellite data to enable process-oriented evaluation of clouds in climate models.","significance":4,"cited_by":15,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2112.07856","title":"Efficient high-dimensional variational data assimilation with machine-learned reduced-order models","authors":["Romit Maulik","Vishwas Rao","Jiali Wang","Gianmarco Mengaldo","Emil M. Constantinescu","Bethany Lusch","Prasanna Balaprakash","Ian T Foster","Veerabhadra Rao Kotamarthi"],"date":"2022-05-02","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"2112.07856","doi":"10.5194/gmd-15-3433-2022","openalex":"W4225286424"},"links":{"paper":"https://doi.org/10.5194/gmd-15-3433-2022"},"orgs":["argonne"],"topic":"data-assimilation","topics":[],"type":"model","method":["differentiable"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Replaces the forward model in variational data assimilation with a differentiable learned emulator, speeding geopotential height DA by four orders of magnitude.","significance":4,"cited_by":44,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002774","title":"Using Simple, Explainable Neural Networks to Predict the Madden‐Julian Oscillation","authors":["Zane Martin","Elizabeth A. Barnes","Eric Daniel Maloney"],"date":"2022-05-01","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002774","openalex":"W4225282967"},"links":{"paper":"https://doi.org/10.1029/2021ms002774","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002774"},"orgs":["colorado-state-university"],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Shallow neural networks predict the real-time MJO index out to about 18 days in October–March, outperforming linear models and explained via attribution techniques.","significance":4,"cited_by":34,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.2081","title":"PPNet : A more effective method of precipitation prediction","authors":["Lina Xun","Qiuyan Yao","Fuxin Ji","Teng Li","Jun Zhang","Kaichao Miao","Qing You Yan"],"date":"2022-05-01","year":2022,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.2081","openalex":"W4283656451"},"links":{"paper":"https://doi.org/10.1002/met.2081","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.2081"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Adds FlowNet optical-flow loss to a GAN-based McNet for radar echo extrapolation, improving precipitation nowcasting on Shenzhen radar data.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13050721","title":"Usefulness of Automatic Hyperparameter Optimization in Developing Radiation Emulator in a Numerical Weather Prediction Model","authors":["Park Sa Kim","Hwan‐Jin Song"],"date":"2022-04-30","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13050721","openalex":"W4225258117"},"links":{"paper":"https://doi.org/10.3390/atmos13050721","pdf":"https://www.mdpi.com/2073-4433/13/5/721/pdf?version=1652668245"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Automatic learning-rate tuning with Sherpa improves a neural radiation emulator in a Korean NWP model, reducing one-week flux and precipitation errors.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13050707","title":"Predicting Atlantic Hurricanes Using Machine Learning","authors":["Víctor Manuel Velasco Herrera","Raúl Martell‐Dubois","Willie Soon","Graciela Velasco Herrera","Sergio Cerdeira‐Estrada","Emmanuel Zúñiga","Laura Rosique‐de la Cruz"],"date":"2022-04-29","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13050707","openalex":"W4225143747"},"links":{"paper":"https://doi.org/10.3390/atmos13050707","pdf":"https://www.mdpi.com/2073-4433/13/5/707/pdf?version=1651899003"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Wavelet analysis and Bayesian ML project emergence windows for Atlantic hurricane categories 2–5, with category 5 storms expected between 2026 and 2031.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22541-au.165123532.22199704-v1","title":"A Hybrid Model of a Flexible Rough Neural Network and Genetic Algorithm (FRNN-GA) in Numerical Weather Forecasting Using Emotional Learning Strategy","authors":["Soheil Fateri","Mohammad Teshnehlab","Mahdi Aliyari Shoorehdeli"],"date":"2022-04-29","year":2022,"venue_type":"other","ids":{"doi":"10.22541/au.165123532.22199704/v1","openalex":"W4225114462"},"links":{"paper":"https://doi.org/10.22541/au.165123532.22199704/v1","pdf":"https://www.authorea.com/doi/pdf/10.22541/au.165123532.22199704/v1"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid flexible rough neural network with genetic algorithm and emotional learning forecasts Tehran station meteorological variables from 2008 to 2012.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-esd-13-851-2022","title":"MESMER-M: an Earth system model emulator for spatially resolved monthly temperature","authors":["Shruti Nath","Quentin Lejeune","Lea Beusch","Sonia Isabelle Seneviratne","Carl‐Friedrich Schleussner"],"date":"2022-04-28","year":2022,"venue":"Earth System Dynamics","venue_type":"journal","ids":{"doi":"10.5194/esd-13-851-2022","openalex":"W4302372615"},"links":{"paper":"https://doi.org/10.5194/esd-13-851-2022"},"orgs":["meteoswiss","eth-zurich"],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"MESMER-M extends an Earth system model emulator to monthly local temperatures, emulating 38 CMIP6 models with skewed, spatially correlated variability.","significance":4,"cited_by":51,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13050702","title":"Deep Learning for Predicting Winter Temperature in North China","authors":["Liang Gao","Young‐Min Yang","Qingqing Li","Yoo‐Geun Ham","Jeong-Hwan Kim"],"date":"2022-04-28","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13050702","openalex":"W4293239151"},"links":{"paper":"https://doi.org/10.3390/atmos13050702","pdf":"https://www.mdpi.com/2073-4433/13/5/702/pdf?version=1651154413"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"A CNN using Northeast Pacific SST predicts North China winter temperature with 0.65 correlation at 5-month lead, beating a state-of-the-art dynamical seasonal system.","significance":4,"cited_by":7,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenvs.2022.847475","title":"Merging and Downscaling Soil Moisture Data From CMIP6 Projections Using Deep Learning Method","authors":["Donghan Feng","Guojie Wang","Xikun Wei","Solomon Obiri Yeboah Amankwah","Yifan Hu","Zicong Luo","Daniel Fiifi Tawia Hagan","Waheed Ullah"],"date":"2022-04-28","year":2022,"venue":"Frontiers in Environmental Science","venue_type":"journal","ids":{"doi":"10.3389/fenvs.2022.847475","openalex":"W4224983778"},"links":{"paper":"https://doi.org/10.3389/fenvs.2022.847475","pdf":"https://www.frontiersin.org/articles/10.3389/fenvs.2022.847475/pdf"},"orgs":["nuist"],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A deep learning model fuses 25 CMIP6 ESMs and downscales soil moisture to 0.25° over China, outperforming individual models and the multi-model mean.","significance":3,"cited_by":23,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-21-0288.1","title":"Deep Learning Augmented Data Assimilation: Reconstructing Missing Information with Convolutional Autoencoders","authors":["Yueya Wang","Xiaoming Shi","Lili Lei","Jimmy Chi Hung Fung"],"date":"2022-04-26","year":2022,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-21-0288.1","openalex":"W4224993707"},"links":{"paper":"https://doi.org/10.1175/mwr-d-21-0288.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/150/8/MWR-D-21-0288.1.pdf"},"orgs":[],"topic":"data-assimilation","topics":["foundation-models"],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Convolutional autoencoder reconstructs missing observation fields before EnSRF assimilation, cutting analysis error in a barotropic vorticity testbed with sparse data.","significance":3,"cited_by":27,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11707-021-0931-8","title":"Ensemble forecast of tropical cyclone tracks based on deep neural networks","authors":["Chong Wang","Qing Xu","Yongcun Cheng","Yi Xin Pan","Hong Li"],"date":"2022-04-26","year":2022,"venue":"Frontiers of Earth Science","venue_type":"journal","ids":{"doi":"10.1007/s11707-021-0931-8","openalex":"W4225012630"},"links":{"paper":"https://doi.org/10.1007/s11707-021-0931-8"},"orgs":["cma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Deep neural network ensemble for tropical cyclone track forecasting; abstract unavailable, so no quantitative results can be reported.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1546284-v1","title":"Enhancing classification performance of binary class imbalanced Data for Weather Forecasting using Machine Learning Classifiers","authors":["Rahul Gupta","Anil Kumar Yadav","SK Jha","Pawan Kumar Pathak"],"date":"2022-04-25","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1546284/v1","openalex":"W4224861417"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1546284/v1","pdf":"https://www.researchsquare.com/article/rs-1546284/latest.pdf"},"orgs":[],"topic":"local-forecasting","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares logistic regression, tree ensembles and boosting for next-day rainfall classification on ten years of Australian station data with imbalance handling.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-wind2020013","title":"Mid-to-Long Range Wind Forecast in Brazil Using Numerical Modeling and Neural Networks","authors":["Ricardo M. Campos","Ronaldo Maia de Jesus Palmeira","Henrique P. P. Pereira","Laura Azevedo"],"date":"2022-04-22","year":2022,"venue":"Wind","venue_type":"journal","ids":{"doi":"10.3390/wind2020013","openalex":"W4224322614"},"links":{"paper":"https://doi.org/10.3390/wind2020013","pdf":"https://www.mdpi.com/2674-032X/2/2/13/pdf?version=1650618571"},"orgs":["noaa"],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":[],"timescale":["medium","s2s"],"spatial":["regional","local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Neural network post-processing of ECMWF ensemble mean corrects Brazilian wind-speed bias to within ±0.1 m/s and cuts RMSE by 10–30% for 1–46 day lead times.","significance":3,"cited_by":7,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1552614-v1","title":"A Sustainable Climate Forecast System for Post-processing of Precipitation With Application of Machine Learning Computations","authors":["Adel Ghazikhani","Iman Babaeian","Mohammad Gheibi","Mostafa Hajiaghaei–Keshteli","Amir M. Fathollahi‐Fard"],"date":"2022-04-22","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1552614/v1","openalex":"W4224301794"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1552614/v1","pdf":"https://www.researchsquare.com/article/rs-1552614/latest.pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Random forest post-processing of CFSv2 precipitation forecasts over Iran, with correlation above 0.87, packaged as a decision support system.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1364-oe.454094","title":"Retrieval of the planetary boundary layer height from lidar measurements by a deep-learning method based on the wavelet covariance transform","authors":["Liang Mei","Xiaoqi Wang","Zhenfeng Gong","Kun Liu","Dengxin Hua","XIAONA Wang"],"date":"2022-04-22","year":2022,"venue":"Optics Express","venue_type":"journal","ids":{"doi":"10.1364/oe.454094","openalex":"W4224257022"},"links":{"paper":"https://doi.org/10.1364/oe.454094"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"A VGG16-based CNN applied to wavelet covariance transform images retrieves planetary boundary layer height from lidar profiles without human intervention, validated against radiosondes and MPLNET.","significance":4,"cited_by":14,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s22093193","title":"Weather Classification by Utilizing Synthetic Data","authors":["Saad Minhas","Zeba Khanam","Shoaib Ehsan","Klaus Dieter McDonald-Maier","Aura Hernández-Sabaté"],"date":"2022-04-21","year":2022,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s22093193","openalex":"W4224315532"},"links":{"paper":"https://doi.org/10.3390/s22093193","pdf":"https://www.mdpi.com/1424-8220/22/9/3193/pdf?version=1651041299"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Synthetic driving-simulator images increase CNN weather-condition classification training efficiency by up to 74%, addressing dataset bias in vision-based weather recognition.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2022.03.017","title":"Statistical learning for NWP post-processing: A benchmark for solar irradiance forecasting","authors":["Hadrien Verbois","Yves‐Marie Saint‐Drenan","Alexandre H. Thiéry","Philippe Blanc"],"date":"2022-04-21","year":2022,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2022.03.017","openalex":"W4224291524"},"links":{"paper":"https://doi.org/10.1016/j.solener.2022.03.017"},"orgs":[],"topic":"post-processing","topics":[],"type":"benchmark","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A benchmark of statistical learning methods for post-processing NWP solar irradiance forecasts; abstract not available, so scope is inferred from the title.","significance":2,"cited_by":49,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00484-022-02287-1","title":"High-resolution wind speed forecast system coupling numerical weather prediction and machine learning for agricultural studies — a case study from South Korea","authors":["Ju‐Young Shin","Byunghoon Min","Kyu Rang Kim"],"date":"2022-04-21","year":2022,"venue":"International Journal of Biometeorology","venue_type":"journal","ids":{"doi":"10.1007/s00484-022-02287-1","openalex":"W4224255545"},"links":{"paper":"https://doi.org/10.1007/s00484-022-02287-1","pdf":"https://link.springer.com/content/pdf/10.1007/s00484-022-02287-1.pdf"},"orgs":["kma"],"topic":"downscaling","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Random forests best downscale NWP wind speed to 100 m over South Korea for agriculture, with 48-hour RMSE near 0.8 m/s.","significance":3,"cited_by":26,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.10022","title":"Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions","authors":["Andrew Jesson","Alyson Douglas","Peter Manshausen","Maëlys Solal","Nicolai Meinshausen","Philip Stier","Yarin Gal","Uri Shalit"],"date":"2022-04-21","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.10022"},"links":{"paper":"https://arxiv.org/abs/2204.10022","pdf":"https://arxiv.org/pdf/2204.10022"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Scalable sensitivity bounds with uncertainty-aware deep models for continuous-treatment causal effects, applied to how human emissions affect cloud properties in 15 years of satellite data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-022-02222-1","title":"Horizontal grid spacing comparison among Random Forest algorithms to nowcast Cloud-to-Ground lightning occurrence","authors":["Alice La Fata","Federico Amato","MARINA BERNARDI","Mirko D’Andrea","Renato Procopio","Elisabetta Fiori"],"date":"2022-04-20","year":2022,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-022-02222-1","openalex":"W4226028770"},"links":{"paper":"https://doi.org/10.1007/s00477-022-02222-1","pdf":"https://link.springer.com/content/pdf/10.1007/s00477-022-02222-1.pdf"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["other","nwp-analysis"],"status":"research","summary":"Random Forest nowcasts cloud-to-ground lightning over Italy and seas, finding that finest-resolution gridding of inputs gives the best skill.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.09362","title":"Wind power predictions from nowcasts to 4-hour forecasts: a learning approach with variable selection","authors":["Dimitri Bouche","Rémi Flamary","Florence d'Alché-Buc","Riwal Plougonven","Marianne Clausel","Jordi Badosa","Philippe Drobinski"],"date":"2022-04-20","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.09362","openalex":"W4224319581"},"links":{"paper":"https://arxiv.org/abs/2204.09362","pdf":"https://arxiv.org/pdf/2204.09362"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine learning combines NWP outputs with local observations to forecast wind speed and power 10 minutes to 4 hours ahead, comparing variable selection and linear versus nonlinear models.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.apenergy.2022.119063","title":"Boosting solar radiation predictions with global climate models, observational predictors and hybrid deep-machine learning algorithms","authors":["Sujan Ghimire","Ravinesh Chand Deo","David Casillas-Pérez","Sancho Salcedo‐Sanz"],"date":"2022-04-19","year":2022,"venue":"Applied Energy","venue_type":"journal","ids":{"doi":"10.1016/j.apenergy.2022.119063","openalex":"W4224262388"},"links":{"paper":"https://doi.org/10.1016/j.apenergy.2022.119063"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Hybrid deep and machine learning models use global climate model and observational predictors to boost solar radiation predictions; abstract not available, so scope is inferred from the title.","significance":2,"cited_by":99,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-021-1207-7","title":"Quantitative Precipitation Forecast Experiment Based on Basic NWP Variables Using Deep Learning","authors":["Kanghui Zhou","Jisong Sun","Yongguang Zheng","Yutao Zhang"],"date":"2022-04-19","year":2022,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-021-1207-7","openalex":"W4224235642"},"links":{"paper":"https://doi.org/10.1007/s00376-021-1207-7"},"orgs":["cma"],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Deep learning model forecasts quantitative precipitation from basic NWP variables; no abstract available, so the method and gains are unverified.","significance":3,"cited_by":30,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.08708","title":"Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models","authors":["Gunnar Behrens","Tom Beucler","Pierre Gentine","Fernando Iglesias-Suarez","Michael Pritchard","Veronika Eyring"],"date":"2022-04-19","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2204.08708","doi":"10.1029/2022ms003130","openalex":"W4285093643"},"links":{"paper":"https://doi.org/10.1029/2022ms003130","pdf":"https://arxiv.org/pdf/2204.08708"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Variational encoder-decoder compresses superparameterized aquaplanet convection into five latent nodes that separate convective regimes, offering an interpretable subgrid parameterization.","significance":4,"cited_by":34,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl096684","title":"Uncovering the Large‐Scale Meteorology That Drives Continental, Shallow, Green Cumulus Through Supervised Classification","authors":["Tom Dror","Vered Silverman","Orit Altaratz","Mickaël D. Chekroun","Ilan Koren"],"date":"2022-04-18","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl096684","openalex":"W4224069166"},"links":{"paper":"https://doi.org/10.1029/2021gl096684","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021GL096684"},"orgs":[],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Supervised classification of MODIS images builds the greenCuDb dataset, revealing that continental green cumulus form under similar large-scale conditions worldwide.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2022-6141966","title":"The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches","authors":["Bin Mu","Jing Li","Shijin Yuan","Xiaodan Luo"],"date":"2022-04-15","year":2022,"venue":"Computational Intelligence and Neuroscience","venue_type":"journal","ids":{"doi":"10.1155/2022/6141966","openalex":"W4223999067"},"links":{"paper":"https://doi.org/10.1155/2022/6141966","pdf":"https://downloads.hindawi.com/journals/cin/2022/6141966.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["rnn"],"timescale":["seasonal","short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"ENSO-driven machine learning predicts the NAO index about three months ahead at 68% accuracy, and a TrajGRU network improves short-term NAO forecasts.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-022-06277-2","title":"On deep learning-based bias correction and downscaling of multiple climate models simulations","authors":["Fang Wang","Di Tian"],"date":"2022-04-15","year":2022,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-022-06277-2","openalex":"W4224036482"},"links":{"paper":"https://doi.org/10.1007/s00382-022-06277-2"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Deep learning bias correction and downscaling of multiple CMIP climate model simulations; abstract not available, so scope is inferred from the title.","significance":3,"cited_by":102,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.08465","title":"Intelligent Spatial Interpolation-based Frost Prediction Methodology using Artificial Neural Networks with Limited Local Data","authors":["Ian Zhou","Justin Lipman","Mehran Abolhasan","Negin Shariati"],"date":"2022-04-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.08465"},"links":{"paper":"https://arxiv.org/abs/2204.08465","pdf":"https://arxiv.org/pdf/2204.08465"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Ensemble-learning neural networks interpolate neighbouring station data, terrain and NDVI to predict next-hour minimum temperature and frost at sites without local sensors, detecting 92.55% of frost events.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.07492","title":"A Machine Learning Tutorial for Operational Meteorology, Part I: Traditional Machine Learning","authors":["Randy J. Chase","David R. Harrison","Amanda Burke","Gary M. Lackmann","Amy McGovern"],"date":"2022-04-15","year":2022,"venue":"Weather and Forecasting 37 (2022) 1509-1529","venue_type":"journal","ids":{"arxiv":"2204.07492","doi":"10.1175/waf-d-22-0070.1"},"links":{"paper":"https://arxiv.org/abs/2204.07492","pdf":"https://arxiv.org/pdf/2204.07492"},"orgs":[],"topic":"infra-software","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Tutorial for operational meteorologists covering linear and logistic regression, decision trees, random forests, boosting, naive Bayes and SVMs, with reproducible notebooks.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su14084719","title":"Case Study: Development of the CNN Model Considering Teleconnection for Spatial Downscaling of Precipitation in a Climate Change Scenario","authors":["Jongsung Kim","Myungjin Lee","Heechan Han","Donghyun Kim","Yunghye Bae","Hung Soo Kim"],"date":"2022-04-14","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su14084719","openalex":"W4224305366"},"links":{"paper":"https://doi.org/10.3390/su14084719","pdf":"https://www.mdpi.com/2071-1050/14/8/4719/pdf?version=1650004545"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"CNN with teleconnection predictors downscales GCM precipitation at three Korean stations, outperforming quantile mapping with mean correlation of 69%.","significance":3,"cited_by":16,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.array.2022.100153","title":"A real-time collaborative machine learning based weather forecasting system with multiple predictor locations","authors":["Tulsi Pawan Fowdur","Rosun Mohammad Nassir-Ud-Diin Ibn Nazir"],"date":"2022-04-14","year":2022,"venue":"Array","venue_type":"journal","ids":{"doi":"10.1016/j.array.2022.100153","openalex":"W4223932797"},"links":{"paper":"https://doi.org/10.1016/j.array.2022.100153","pdf":"https://www.sciencedirect.com/science/article/pii/S2590005622000212/pdf"},"orgs":[],"topic":"local-forecasting","topics":["infra-software"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Collaborative regression and neural forecasts from multiple Mauritius stations via OpenWeather API data reduce MAPE by about 5% versus non-collaborative setups.","significance":1,"cited_by":30,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.47002-mst.v2i1.323","title":"APPLICATION OF INTELLIGENT SYSTEM WITH BACKPROPAGATION MODEL IN CLOUD IMAGE CLASSIFICATION","authors":["Mulyadi Mulyadi","Muhammad Ichwan","Muhammad Rizka","Mutammimul Ula"],"date":"2022-04-13","year":2022,"venue":"MULTICA SCIENCE AND TECHNOLOGY (MST)","venue_type":"journal","ids":{"doi":"10.47002/mst.v2i1.323","openalex":"W4379744764"},"links":{"paper":"https://doi.org/10.47002/mst.v2i1.323","pdf":"https://journal.universitasmulia.ac.id/index.php/mst/article/download/323/240"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A backpropagation neural network classifies cloud types from images with a 60.6% success rate on 92 training images.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenvs.2022.849965","title":"Parks Under Stress: Air Temperature Regulation of Urban Green Spaces Under Conditions of Drought and Summer Heat","authors":["Roland Kraemer","Nadja Kabisch"],"date":"2022-04-13","year":2022,"venue":"Frontiers in Environmental Science","venue_type":"journal","ids":{"doi":"10.3389/fenvs.2022.849965","openalex":"W4223426198"},"links":{"paper":"https://doi.org/10.3389/fenvs.2022.849965"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Machine learning maps fine-scale urban air temperature from dense in-situ sensors, showing park cooling of up to 1.1°C during a 2019 heatwave.","significance":2,"cited_by":101,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.engappai.2022.104860","title":"Hybrid deep CNN-SVR algorithm for solar radiation prediction problems in Queensland, Australia","authors":["Sujan Ghimire","Binayak Bhandari","David Casillas-Pérez","Ravinesh Chand Deo","Sancho Salcedo‐Sanz"],"date":"2022-04-13","year":2022,"venue":"Engineering Applications of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1016/j.engappai.2022.104860","openalex":"W4224138657"},"links":{"paper":"https://doi.org/10.1016/j.engappai.2022.104860","pdf":"https://www.sciencedirect.com/science/article/pii/S0952197622001099/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"A hybrid CNN-SVR model predicts daily global solar radiation at six Queensland solar farms from GCM and station variables, beating eight alternative DL and ML methods.","significance":2,"cited_by":106,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.06544","title":"Features of the Earth's seasonal hydroclimate: Characterizations and comparisons across the Koppen-Geiger climates and across continents","authors":["Georgia Papacharalampous","Hristos Tyralis","Yannis Markonis","Petr Maca","Martin Hanel"],"date":"2022-04-13","year":2022,"venue":"Progress in Earth and Planetary Science 10 (2023) 46","venue_type":"journal","ids":{"arxiv":"2204.06544","doi":"10.1186/s40645-023-00574-y"},"links":{"paper":"https://arxiv.org/abs/2204.06544","pdf":"https://arxiv.org/pdf/2204.06544"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["stations","other"],"status":"research","summary":"Analyzes seasonal temperature, precipitation and river flow features across Köppen-Geiger climates using explainable ML, finding autocorrelation and seasonality most informative.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1517899-v1","title":"Precipitation forecasting based on deep learning strategy using empirical wavelet transform, Markov chain-incorporated long-short term memory network","authors":["Jie YANG","Rui Tang","Kun Lan","Han Wang","Lin Zhang","Simon James Fong"],"date":"2022-04-12","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1517899/v1","openalex":"W4223589464"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1517899/v1","pdf":"https://www.researchsquare.com/article/rs-1517899/latest.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid empirical wavelet transform with Markov-chain-incorporated LSTM for precipitation forecasting; no abstract available to confirm the results.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl098174","title":"Machine Learning Gravity Wave Parameterization Generalizes to Capture the QBO and Response to Increased CO2","authors":["Zachary I. Espinosa","Aditi Sheshadri","Gerald R. Cain","Edwin Paul Gerber","Kevin DallaSanta"],"date":"2022-04-12","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl098174","openalex":"W4223593636"},"links":{"paper":"https://doi.org/10.1029/2022gl098174","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL098174"},"orgs":["nasa","stanford","nyu-m2lines"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural networks emulate a non-orographic gravity wave drag scheme and generalize to reproduce the QBO and the climate response to increased CO2 when coupled online.","significance":4,"cited_by":40,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022gl097872","title":"How to Calibrate a Dynamical System With Neural Network Based Physics?","authors":["Blanka Balogh","David Saint‐Martin","Aurélien Ribes"],"date":"2022-04-12","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2022gl097872","openalex":"W4223520325"},"links":{"paper":"https://doi.org/10.1029/2022gl097872","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022GL097872"},"orgs":["meteo-france"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Proposes ML parameterizations with parameters as inputs, calibrated online against long-term statistics, which significantly reduces long-term biases in two simple dynamical systems.","significance":3,"cited_by":7,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.05795","title":"Surrogate Ensemble Forecasting for Dynamic Climate Impact Models","authors":["Julian Kuehnert","Deborah McGlynn","Sekou L. Remy","Aisha Walcott-Bryant","Anne Jones"],"date":"2022-04-12","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.05795"},"links":{"paper":"https://arxiv.org/abs/2204.05795","pdf":"https://arxiv.org/pdf/2204.05795"},"orgs":["ibm-research"],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"application","method":["rnn","classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Random forest quantile regression and Bayesian LSTM surrogates emulate a malaria transmission model driven by seasonal temperature and rainfall ensembles, cutting computation while capturing forecast uncertainty.","significance":2,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.6426941","title":"Deep Learning augmented Weather Prediction based on Cubic Sphere for global precipitation forecasting","authors":["Manmeet Singh"],"date":"2022-04-09","year":2022,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.6426941","openalex":"W4297823341"},"links":{"paper":"https://doi.org/10.5281/zenodo.6426941"},"orgs":[],"topic":"global-medium-range","topics":["benchmarks-data-eval"],"type":"benchmark","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Dataset of inputs and targets for deep-learning-augmented cubic-sphere weather prediction for global precipitation forecasting.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14081815","title":"All-Sky 1 km MODIS Land Surface Temperature Reconstruction Considering Cloud Effects Based on Machine Learning","authors":["Dongjin Cho","Dukwon Bae","Cheolhee Yoo","Jungho Im","Yeonsu Lee","Siwoo Lee"],"date":"2022-04-09","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14081815","openalex":"W4224234945"},"links":{"paper":"https://doi.org/10.3390/rs14081815","pdf":"https://www.mdpi.com/2072-4292/14/8/1815/pdf?version=1649655731"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"LightGBM reconstructs all-sky 1 km MODIS land surface temperature using LDAPS analysis, improving cloudy-sky estimates over South Korea.","significance":3,"cited_by":38,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jas-d-21-0205.1","title":"Empirical Low-Dimensional Dynamics of Atmospheric Stable Boundary Layer Temperature Inversions","authors":["Elizabeth A. Ramsey","Adam H. Monahan"],"date":"2022-04-08","year":2022,"venue":"Journal of the Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1175/jas-d-21-0205.1","openalex":"W4228999044"},"links":{"paper":"https://doi.org/10.1175/jas-d-21-0205.1"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Gaussian process regression fits an empirical stochastic model to stable boundary layer inversions at tower sites, revealing bifurcation-like dynamics similar to idealized models.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41467-022-29543-7","title":"A deep learning-based hybrid model of global terrestrial evaporation","authors":["Akash Koppa","Dominik Rains","Petra Hulsman","Rafael Poyatos","Diego G. Miralles"],"date":"2022-04-08","year":2022,"venue":"Nature Communications","venue_type":"journal","ids":{"doi":"10.1038/s41467-022-29543-7","openalex":"W4225984022"},"links":{"paper":"https://doi.org/10.1038/s41467-022-29543-7","pdf":"https://www.nature.com/articles/s41467-022-29543-7.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","stations"],"status":"research","summary":"Deep learning models transpiration stress from in situ and satellite data, then couples it bidirectionally into a process model to improve global terrestrial evaporation estimates.","significance":4,"cited_by":182,"score":46,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-sat.1442","title":"Preliminary results on estimation of signal fading on telecommunication satellite telemetry signals with hybrid numerical weather prediction and artificial neural network approach under presence of aerosol effect","authors":["Arif Armağan Gözütok","Ümit Cezmi YILMAZ","Selman Demirel"],"date":"2022-04-08","year":2022,"venue":"International Journal of Satellite Communications and Networking","venue_type":"journal","ids":{"doi":"10.1002/sat.1442","openalex":"W4225985935"},"links":{"paper":"https://doi.org/10.1002/sat.1442"},"orgs":[],"topic":"applications-impacts","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","satellite","stations"],"status":"research","summary":"Feed-forward neural network driven by WRF rainfall output predicts rain attenuation fading on a geostationary satellite downlink during a dust-storm event.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.05102","title":"Convolutional autoencoders for spatially-informed ensemble post-processing","authors":["Sebastian Lerch","Kai L. Polsterer"],"date":"2022-04-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.05102","openalex":"W4223533121"},"links":{"paper":"https://arxiv.org/abs/2204.05102","pdf":"https://arxiv.org/pdf/2204.05102"},"orgs":["kit"],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Convolutional autoencoders compress spatial NWP fields into features that augment station-based neural post-processing of 2 m temperature ensemble forecasts over Germany.","significance":4,"cited_by":5,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.04313","title":"Machine learning model to predict solar radiation, based on the integration of meteorological data and data obtained from satellite images","authors":["Luis Eduardo Ordoñez Palacios","Víctor Bucheli Guerrero","Hugo Ordoñez"],"date":"2022-04-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.04313"},"links":{"paper":"https://arxiv.org/abs/2204.04313","pdf":"https://arxiv.org/pdf/2204.04313"},"orgs":[],"topic":"applications-impacts","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"Combines GOES-13 satellite image features with station meteorology in neural networks to estimate solar radiation; rRMSE stays above 20%, rated only fair.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.03911","title":"A posteriori learning for quasi-geostrophic turbulence parametrization","authors":["Hugo Frezat","Julien Le Sommer","Ronan Fablet","Guillaume Balarac","Redouane Lguensat"],"date":"2022-04-08","year":2022,"venue":"Journal of Advances in Modeling Earth Systems. Volume 14, Issue 11 (November 2022)","venue_type":"journal","ids":{"arxiv":"2204.03911","doi":"10.1029/2022ms003124","openalex":"W4297984003"},"links":{"paper":"https://arxiv.org/abs/2204.03911","pdf":"https://arxiv.org/pdf/2204.03911"},"orgs":["inria"],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["differentiable","cnn"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"End-to-end differentiable training of subgrid energy-backscatter parameterizations for 2D quasi-geostrophic turbulence yields models more stable and accurate than a priori-trained schemes.","significance":5,"cited_by":61,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.09019","title":"Hybrid Transformer Network for Different Horizons-based Enriched Wind Speed Forecasting","authors":["M. Madhiarasan","Partha Pratim Roy"],"date":"2022-04-07","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.09019"},"links":{"paper":"https://arxiv.org/abs/2204.09019","pdf":"https://arxiv.org/pdf/2204.09019"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["transformer","other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid ICEEMDAN decomposition, transformer and MLP error correction for multi-horizon wind speed forecasts at an Indian wind farm; reports very small error metrics.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s22072802","title":"Deep Tower Networks for Efficient Temperature Forecasting from Multiple Data Sources","authors":["Siri Sofie Eide","Michael Alexander Riegler","Hugo L. Hammer","John Bjørnar Bremnes"],"date":"2022-04-06","year":2022,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s22072802","openalex":"W4223456833"},"links":{"paper":"https://doi.org/10.3390/s22072802","pdf":"https://www.mdpi.com/1424-8220/22/7/2802/pdf?version=1649231788"},"orgs":["met-norway"],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"A tower network fusing multiple data streams gives 11% lower temperature forecast RMSE than yr.no, beating CNN and convLSTM baselines.","significance":3,"cited_by":4,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asoc.2022.108804","title":"A typhoon trajectory prediction model based on multimodal and multitask learning","authors":["Wanting Qin","Jun Tang","Cong Da Lu","Songyang Lao"],"date":"2022-04-06","year":2022,"venue":"Applied Soft Computing","venue_type":"journal","ids":{"doi":"10.1016/j.asoc.2022.108804","openalex":"W4226350101"},"links":{"paper":"https://doi.org/10.1016/j.asoc.2022.108804"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Multimodal multitask learning model for typhoon trajectory prediction; abstract unavailable, so performance cannot be verified.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.agrformet.2022.108920","title":"Understanding and reducing the uncertainties of land surface energy flux partitioning within CMIP6 land models","authors":["Kunxiaojia Yuan","Qing Zhu","W. J. Riley","Fa Li","Huayi Wu"],"date":"2022-04-06","year":2022,"venue":"Agricultural and Forest Meteorology","venue_type":"journal","ids":{"doi":"10.1016/j.agrformet.2022.108920","openalex":"W4225766290"},"links":{"paper":"https://doi.org/10.1016/j.agrformet.2022.108920","pdf":"https://www.sciencedirect.com/science/article/pii/S0168192322001137/pdf"},"orgs":["lbnl-nersc"],"topic":"climate-analysis-attribution","topics":["hybrid-parameterization"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"ML and causal inference reduce CMIP6 land model evaporative fraction biases at 64 FLUXNET sites, raising correlation from 0.47 to 0.80.","significance":3,"cited_by":54,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13040586","title":"Machine-Learning Based Analysis of Liquid Water Path Adjustments to Aerosol Perturbations in Marine Boundary Layer Clouds Using Satellite Observations","authors":["Lukas Zipfel","Hendrik Andersen","Jan Čermák"],"date":"2022-04-05","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13040586","openalex":"W4226054556"},"links":{"paper":"https://doi.org/10.3390/atmos13040586","pdf":"https://www.mdpi.com/2073-4433/13/4/586/pdf?version=1649226711"},"orgs":["kit"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics","observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Explainable ML with Shapley values on satellite and reanalysis data shows liquid water path rises nonlinearly with droplet number, with sensitivity dependent on precipitation and SST.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1071-wf21143","title":"Simulation-based high-resolution fire danger mapping using deep learning","authors":["Frédéric Allaire","Jean‐Baptiste Filippi","Vivien Mallet","Florence Vaysse"],"date":"2022-04-05","year":2022,"venue":"International Journal of Wildland Fire","venue_type":"journal","ids":{"doi":"10.1071/wf21143","openalex":"W3158150706"},"links":{"paper":"https://doi.org/10.1071/wf21143"},"orgs":["meteo-france","inria"],"topic":"extremes-hazards","topics":["downscaling"],"type":"model","method":[],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","other"],"status":"pre-operational","summary":"DeepFire neural emulator of fire spread turns high-resolution weather forecasts into next-day fire danger maps and ensembles for 13 Corsican fires.","significance":3,"cited_by":4,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-asl.1087","title":"A critical view on the suitability of machine learning techniques to downscale climate change projections: Illustration for temperature with a toy experiment","authors":["Alfonso Hernanz","Juan Andrés García Valero","Marta Domínguez","Ernesto Rodríguez Camino"],"date":"2022-04-05","year":2022,"venue":"Atmospheric Science Letters","venue_type":"journal","ids":{"doi":"10.1002/asl.1087","openalex":"W4225533012"},"links":{"paper":"https://doi.org/10.1002/asl.1087","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asl.1087"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Toy experiments show neural networks and SVR downscaling temperature extrapolate poorly outside calibration range, unlike multiple linear regression.","significance":3,"cited_by":47,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.02028","title":"A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts","authors":["Lucy Harris","Andrew T. T. McRae","Matthew Chantry","Peter D. Dueben","Tim N. Palmer"],"date":"2022-04-05","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2204.02028","doi":"10.1029/2022ms003120","openalex":"W4301373652"},"links":{"paper":"https://arxiv.org/abs/2204.02028","pdf":"https://arxiv.org/pdf/2204.02028"},"orgs":["ecmwf","university-of-oxford"],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"research","summary":"GAN and VAE-GAN downscale low-resolution forecasts to radar-scale precipitation maps with CRPS matching state-of-the-art pointwise post-processing, including heavy rain.","significance":5,"cited_by":198,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2110.05817","title":"Parameter Calibration to Improve the Prediction of Tropical Cyclones over the Bay of Bengal Using Machine Learning–Based Multiobjective Optimization","authors":["Harish Baki","Sandeep Chinta","Chakravarthy Balaji","Balaji Srinivasan"],"date":"2022-04-05","year":2022,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"arxiv":"2110.05817","doi":"10.1175/jamc-d-21-0184.1","openalex":"W4226469246"},"links":{"paper":"https://doi.org/10.1175/jamc-d-21-0184.1","pdf":"https://arxiv.org/pdf/2110.05817"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Surrogate-based multiobjective calibration of WRF parameters improves Bay of Bengal cyclone 10-m wind speed by 17.6% and precipitation by 8.2%.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0078.1","title":"Learning from Precipitation Events in the Wider Domain to Improve the Performance of a Deep Learning–Based Precipitation Nowcasting Model","authors":["Tsuyoshi Inoue","Ryohei Misumi"],"date":"2022-04-04","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0078.1","openalex":"W4224032897"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0078.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/37/6/WAF-D-21-0078.1.pdf"},"orgs":[],"topic":"nowcasting","topics":["benchmarks-data-eval"],"type":"model","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Training a deep learning radar nowcaster on all of Japan and then transfer learning to regions improves heavy-precipitation skill over locally trained models.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-21-0154.1","title":"A hybrid analog-ensemble, convolutional-neural-network method for post-processing precipitation forecasts","authors":["Yingkai Sha","David John Gagne","Gregory West","Roland B. Stull"],"date":"2022-04-04","year":2022,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-21-0154.1","openalex":"W4225553680"},"links":{"paper":"https://doi.org/10.1175/mwr-d-21-0154.1"},"orgs":["ncar"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["era5","nwp-analysis","stations"],"status":"research","summary":"Hybrid analog-ensemble and CNN post-processing of GEFS precipitation raises CRPSS about 10% over quantile-mapped baseline out to 7 days in British Columbia.","significance":4,"cited_by":10,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.energy.2022.123848","title":"A novel offshore wind farm typhoon wind speed prediction model based on PSO–Bi-LSTM improved by VMD","authors":["Jiale Li","Zihao Song","Xuefei Wang","Yanru Wang","Yaya Jia"],"date":"2022-04-04","year":2022,"venue":"Energy","venue_type":"journal","ids":{"doi":"10.1016/j.energy.2022.123848","openalex":"W4225243270"},"links":{"paper":"https://doi.org/10.1016/j.energy.2022.123848"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"PSO-optimized Bi-LSTM with VMD decomposition predicts typhoon wind speed at offshore wind farms; abstract unavailable, so accuracy is unreported.","significance":2,"cited_by":192,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.6405352","title":"Optimization of Neural Network Radiation Emulator using Sherpa","authors":["Pilkyo Kim","Hwan‐Jin Song"],"date":"2022-04-01","year":2022,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.6405352","openalex":"W4220867925"},"links":{"paper":"https://doi.org/10.5281/zenodo.6405352"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":["infra-software"],"type":"model","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Source code and weights for a neural network radiation emulator in WRF, with hyperparameters tuned by Sherpa to speed up the radiation scheme.","significance":3,"cited_by":0,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-essd-2021-460","title":"A 148-year precipitation oxygen isoscape for China generated based on data fusion and bias correction of iGCMs simulations","authors":["Jiacheng Chen","Jiacheng Chen","Jie Chen","Jie Chen","XC Zhang","Peiyi Peng","Camille Risi"],"date":"2022-04-01","year":2022,"venue_type":"other","ids":{"doi":"10.5194/essd-2021-460","openalex":"W4220713315"},"links":{"paper":"https://doi.org/10.5194/essd-2021-460"},"orgs":[],"topic":"downscaling","topics":[],"type":"benchmark","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Builds a 148-year, 50-60 km precipitation oxygen isoscape for China by CNN fusion and bias correction of eight isotope-enabled GCMs, correlation above 0.8.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14071707","title":"Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction","authors":["Junjun Cao","Huijing Wang","Jinxiao Li","Qun Tian","Dev Niyogi"],"date":"2022-04-01","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14071707","openalex":"W4226087885"},"links":{"paper":"https://doi.org/10.3390/rs14071707","pdf":"https://www.mdpi.com/2072-4292/14/7/1707/pdf?version=1648805412"},"orgs":["iap-cas","cma"],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","satellite","other"],"status":"research","summary":"Hybrid XGBoost models using S2S dynamical forecasts predict northern China winter wheat yield 3–4 months ahead with R² 0.85, beating observed climate inputs.","significance":3,"cited_by":58,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14071704","title":"Integrating Reanalysis and Satellite Cloud Information to Estimate Surface Downward Long-Wave Radiation","authors":["Francis M. Lopes","Emanuel Dutra","Isabel F. Trigo"],"date":"2022-04-01","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14071704","openalex":"W4226288100"},"links":{"paper":"https://doi.org/10.3390/rs14071704","pdf":"https://www.mdpi.com/2072-4292/14/7/1704/pdf?version=1648802200"},"orgs":[],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","satellite","stations"],"status":"research","summary":"MARS regression fusing ERA5 and Meteosat cloud data estimates surface downward longwave radiation with 18.8 W/m² RMSE, beating the LSA-SAF operational formula.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2022.844634","title":"Self-Organizing Maps Identify Windows of Opportunity for Seasonal European Summer Predictions","authors":["Julianna Carvalho Oliveira","Leonard Borchert","Eduardo Zorita","Johanna Baehr"],"date":"2022-04-01","year":2022,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2022.844634","openalex":"W4220887453"},"links":{"paper":"https://doi.org/10.3389/fclim.2022.844634"},"orgs":["mpi-meteorology"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"Self-organizing maps link North Atlantic spring SST to summer jet-stream teleconnections, identifying windows of opportunity for seasonal European summer predictions with MPI-ESM hindcasts.","significance":3,"cited_by":12,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3103-s1068373922040033","title":"Retrieval of Total Precipitable Water from Meteor-M No. 2-2 MTVZA-GYa Data Using a Neural Network Algorithm","authors":["A. A. Filei","Alexander I. Andreev","Кучма Михаил Олегович","А. B. Uspensky"],"date":"2022-04-01","year":2022,"venue":"Russian Meteorology and Hydrology","venue_type":"journal","ids":{"doi":"10.3103/s1068373922040033","openalex":"W4288071009"},"links":{"paper":"https://doi.org/10.3103/s1068373922040033"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations","nwp-analysis"],"status":"research","summary":"A neural network retrieves total precipitable water from Meteor-M No. 2-2 MTVZA-GYa microwave data, with RMSE under 3 mm over water versus radiosondes and AERONET.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1433874-v1","title":"Anthropocene Cyclogenesis over Bay of Bengal, Prediction by SMOreg, and Odisha Coast Landfall","authors":["Siba Prasad Mishra","Ananta Charan Ojha","Deepak Kumar Sahu"],"date":"2022-04-01","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1433874/v1","openalex":"W4220980790"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1433874/v1","pdf":"https://www.researchsquare.com/article/rs-1433874/latest.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Statistical trend analysis and SMOreg regression of 1891–2020 Bay of Bengal cyclone records project cyclogenesis to 2021; ML role is minor.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-21-0006.1","title":"Current Training and Validation Weaknesses in Classification-Based Radiation Fog Nowcast Using Machine Learning Algorithms","authors":["Michaela Vorndran","Adrian Schütz","Jörg Bendix","Boris Thies"],"date":"2022-04-01","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-21-0006.1","openalex":"W4389087004"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0006.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/1/2/AIES-D-21-0006.1.pdf"},"orgs":[],"topic":"local-forecasting","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"XGBoost radiation fog nowcasts are evaluated with persistence and guessing baselines, showing high validation scores can hide operational failure and that blockwise CV inflates skill.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ef002481","title":"Increasing Frequency of Anomalous Precipitation Events in Japan Detected by a Deep Learning Autoencoder","authors":["Hiroyuki Murakami","Thomas L. Delworth","William F. Cooke","Sarah Kapnick","Pang‐Chi Hsu"],"date":"2022-04-01","year":2022,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2021ef002481","openalex":"W4224255216"},"links":{"paper":"https://doi.org/10.1029/2021ef002481","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021EF002481"},"orgs":["noaa","ncar","princeton-university","nuist"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["gan-vae"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"A deep autoencoder detects anomalous heavy precipitation events in Japan and attributes their increase since 1977 partly to anthropogenic forcing, with more expected this century.","significance":3,"cited_by":11,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.gloei.2022.04.018","title":"Statistical downscaling of numerical weather prediction based on convolutional neural networks","authors":["Hongwei Yang","Jie Yan","Yongqian Liu","Zongpeng Song"],"date":"2022-04-01","year":2022,"venue":"Global Energy Interconnection","venue_type":"journal","ids":{"doi":"10.1016/j.gloei.2022.04.018","openalex":"W4281647130"},"links":{"paper":"https://doi.org/10.1016/j.gloei.2022.04.018","pdf":"https://www.sciencedirect.com/science/article/pii/S209651172200038X/pdf"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"application","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"CNN-based statistical downscaling of NWP fields to turbine hub height matches physical-model accuracy for wind power forecasting at one farm.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13351-022-1174-7","title":"Deep Learning for Seasonal Precipitation Prediction over China","authors":["Weixin Jin","Yong Ming Luo","Tongwen Wu","Xiaomeng Huang","Wei Xue","Chaoqing Yu"],"date":"2022-04-01","year":2022,"venue":"气象学报：英文版","venue_type":"journal","ids":{"doi":"10.1007/s13351-022-1174-7","openalex":"W4228999327"},"links":{"paper":"https://doi.org/10.1007/s13351-022-1174-7","pdf":"https://link.springer.com/content/pdf/10.1007/s13351-022-1174-7.pdf"},"orgs":["tsinghua-university","cma"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip","era5","stations"],"status":"pre-operational","summary":"A deep learning model pre-trained on GCM hindcasts and transfer-learned on ERA5 raises seasonal China precipitation correlation by 0.10-0.13 over raw GCM output; used operationally for guidance.","significance":4,"cited_by":39,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13131-021-1965-1","title":"Forecasting the western Pacific subtropical high index during typhoon activity using a hybrid deep learning model","authors":["Jianyin Zhou","Mingyang Sun","Jie Xiang","Jiping Guan","Huadong Du","Lei Zhou"],"date":"2022-04-01","year":2022,"venue":"Acta Oceanologica Sinica","venue_type":"journal","ids":{"doi":"10.1007/s13131-021-1965-1","openalex":"W4226144904"},"links":{"paper":"https://doi.org/10.1007/s13131-021-1965-1"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Hybrid deep learning forecasts the western Pacific subtropical high index during typhoon activity; abstract unavailable, so no metrics are reported.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.00649","title":"Knowledge distillation with error-correcting transfer learning for wind power prediction","authors":["Hao Chen"],"date":"2022-04-01","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.00649"},"links":{"paper":"https://arxiv.org/abs/2204.00649","pdf":"https://arxiv.org/pdf/2204.00649"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["other","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Knowledge distillation and transfer learning of forecast errors improve turbine-level wind power predictions at an Arctic wind park by 3.3% to 23.9%.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.00495","title":"Physics Informed Shallow Machine Learning for Wind Speed Prediction","authors":["Daniele Lagomarsino-Oneto","Giacomo Meanti","Nicolò Pagliana","Alessandro Verri","Andrea Mazzino","Lorenzo Rosasco","Agnese Seminara"],"date":"2022-04-01","year":2022,"venue":"Energy","venue_type":"journal","ids":{"arxiv":"2204.00495","doi":"10.1016/j.energy.2023.126628","openalex":"W4226513809"},"links":{"paper":"https://doi.org/10.1016/j.energy.2023.126628","pdf":"https://arxiv.org/pdf/2204.00495"},"orgs":["mit"],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares shallow supervised learners for 10 m wind speed forecasting at 32 Italian anemometer sites, finding well-designed shallow models competitive with deep networks.","significance":3,"cited_by":30,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2204.00411","title":"Synthetic Photovoltaic and Wind Power Forecasting Data","authors":["Stephan Vogt","Jens Schreiber","Bernhard Sick"],"date":"2022-04-01","year":2022,"venue_type":"preprint","ids":{"arxiv":"2204.00411","openalex":"W4226147206"},"links":{"paper":"https://arxiv.org/abs/2204.00411","pdf":"https://arxiv.org/pdf/2204.00411"},"orgs":[],"topic":"applications-impacts","topics":["benchmarks-data-eval"],"type":"benchmark","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Open dataset of synthetic hourly PV and wind power for 393 German plants over 500 days, built from ICON-EU weather inputs, with baseline forecasts.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl096560","title":"Diagnosing Two‐Way Coupling in Decadal North Atlantic SST Variability Using Time‐Evolving Self‐Organizing Maps","authors":["Qinxue Gu","Melissa Gervais"],"date":"2022-03-31","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl096560","openalex":"W4220996068"},"links":{"paper":"https://doi.org/10.1029/2021gl096560"},"orgs":["columbia-leap"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Applies time-evolving self-organizing maps to a CESM pre-industrial run, tracing a 10-year transition from positive NAO to AMV and weak negative NAO in North Atlantic SST.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.21685653","title":"Machine Learning based Rainfall Prediction","authors":["Vivek Rajendra Dhokane","Arunadevi Khaple","Rashmi Ashtagi"],"date":"2022-03-30","year":2022,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.21685653","openalex":"W7171689658"},"links":{"paper":"https://doi.org/10.5281/zenodo.21685653"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":[],"status":"research","summary":"Multiple linear regression predicts rainfall from Indian weather parameters and claims to beat textbook algorithms, but gives no quantitative results.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.16401","title":"Recognition of polar lows in Sentinel-1 SAR images with deep learning","authors":["Jakob Grahn","Filippo Maria Bianchi"],"date":"2022-03-30","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.16401","doi":"10.1109/tgrs.2022.3204886"},"links":{"paper":"https://arxiv.org/abs/2203.16401","pdf":"https://arxiv.org/pdf/2203.16401"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":[],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Deep learning detects polar lows in Sentinel-1 SAR images with F1 0.95, using a new public dataset labelled from ERA5; higher resolution improves detection.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.15601","title":"Photographic Visualization of Weather Forecasts with Generative Adversarial Networks","authors":["Christian Sigg","Flavia Cavallaro","Tobias Günther","Martin R. Oswald"],"date":"2022-03-29","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.15601"},"links":{"paper":"https://arxiv.org/abs/2203.15601","pdf":"https://arxiv.org/pdf/2203.15601"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["gan-vae"],"timescale":["nowcast"],"spatial":["local"],"data":["nwp-analysis","other"],"status":"research","summary":"Conditional GAN turns webcam images into photorealistic future weather views conditioned on COSMO-1 forecasts, matching forecast conditions in at least 89% of cases.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4038-ijms.v9i1.159","title":"Machine Learning Based Weather Prediction Model for Short Term Weather Prediction in Sri Lanka","authors":["K. M. S. A. Hennayake","Randima Dinalankara","Dulini Yasara Mudunkotuwa"],"date":"2022-03-28","year":2022,"venue":"International Journal of Multidisciplinary Studies","venue_type":"journal","ids":{"doi":"10.4038/ijms.v9i1.159","openalex":"W4285104070"},"links":{"paper":"https://doi.org/10.4038/ijms.v9i1.159"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["local"],"data":[],"status":"research","summary":"Machine learning model for short-term weather prediction in Sri Lanka; the abstract is only journal boilerplate, so the details are unverified.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.15558","title":"Wildfire risk forecast: An optimizable fire danger index","authors":["Eduardo Rodrigues","Bianca Zadrozny","Campbell Watson"],"date":"2022-03-28","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.15558"},"links":{"paper":"https://arxiv.org/abs/2203.15558","pdf":"https://arxiv.org/pdf/2203.15558"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["differentiable","physics-constrained"],"timescale":["short"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Makes the NFDRS fire danger index differentiable so its parameters can be tuned by gradient descent on observed US and European fire events.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.14814","title":"Using Probabilistic Machine Learning to Better Model Temporal Patterns in Parameterizations: a case study with the Lorenz 96 model","authors":["Raghul Parthipan","Hannah M. Christensen","J. Scott Hosking","Damon J. Wischik"],"date":"2022-03-28","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"2203.14814","doi":"10.17863/cam.97230","openalex":"W4294959203"},"links":{"paper":"https://doi.org/10.5194/gmd-16-4501-2023","pdf":"https://arxiv.org/pdf/2203.14814"},"orgs":["alan-turing-institute","university-of-cambridge","university-of-oxford"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["rnn","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A probabilistic physically informed recurrent network learns stochastic parameterizations in the Lorenz 96 atmosphere model, outperforming autoregressive and GAN baselines on temporal patterns.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.14812","title":"An attention mechanism based convolutional network for satellite precipitation downscaling over China","authors":["Yinghong Jing","Liupeng Lin","Xinghua Li","Tongwen Li","Huanfeng Shen"],"date":"2022-03-28","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.14812"},"links":{"paper":"https://arxiv.org/abs/2203.14812","pdf":"https://arxiv.org/pdf/2203.14812"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn","transformer"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Attention-based CNN downscales GPM IMERG monthly precipitation over China, using a physics-based degradation loss and in-situ measurements for correction.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33558-piksel.v10i1.4418","title":"Decision Tree-Based Weather Prediction","authors":["Achmad Noeman","Dwipa Handayani","Abrar Hiswara"],"date":"2022-03-26","year":2022,"venue":"PIKSEL Penelitian Ilmu Komputer Sistem Embedded and Logic","venue_type":"journal","ids":{"doi":"10.33558/piksel.v10i1.4418","openalex":"W4223932376"},"links":{"paper":"https://doi.org/10.33558/piksel.v10i1.4418","pdf":"https://jurnal.unismabekasi.ac.id/index.php/piksel/article/download/4418/2132"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":[],"status":"research","summary":"C4.5 decision tree classifies next-day weather as no rain, rain, light rain or heavy rain from weather variables; a simple classification study.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-15-1829-2022","title":"Identification of tropical cyclones via deep convolutional neural network based on satellite cloud images","authors":["Biao Tong","Xiangfei Sun","Jiyang Fu","Yuncheng He","Pak Wai Chan"],"date":"2022-03-25","year":2022,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-15-1829-2022","openalex":"W4221095210"},"links":{"paper":"https://doi.org/10.5194/amt-15-1829-2022"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A deep CNN identifies tropical cyclone fingerprints in satellite cloud images over the Northwest Pacific with 96% accuracy, with heat maps showing eye and rainband focus.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ea001908","title":"Non‐Gaussian Detection Using Machine Learning With Data Assimilation Applications","authors":["Michael Goodliff","Steven J. Fletcher","Anton J. Kliewer","Andrew S. Jones","John M. Forsythe"],"date":"2022-03-25","year":2022,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2021ea001908","openalex":"W3114575811"},"links":{"paper":"https://doi.org/10.1029/2021ea001908"},"orgs":["noaa","colorado-state-university"],"topic":"data-assimilation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"SVM detects shifts in the Lorenz-63 variable distribution to switch between Gaussian and mixed Gaussian-lognormal 3DVar, reducing analysis error.","significance":3,"cited_by":14,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-15-1779-2022","title":"Time evolution of temperature profiles retrieved from 13 years of infrared atmospheric sounding interferometer (IASI) data using an artificial neural network","authors":["Marie Bouillon","Sarah A. Safieddine","Simon Whitburn","Lieven Clarisse","Filipe Aires","Victor Pellet","Olivier Lezeaux","Noelle A. Scott","Marie Doutriaux","Cathy Clerbaux"],"date":"2022-03-24","year":2022,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-15-1779-2022","openalex":"W4221026156"},"links":{"paper":"https://doi.org/10.5194/amt-15-1779-2022"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5","stations"],"status":"research","summary":"Neural network retrieves 13 years of IASI temperature profiles trained on ERA5, agreeing within 0.5 K of radiosondes between 750 and 7 hPa.","significance":4,"cited_by":12,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13040511","title":"A Novel Reference-Based and Gradient-Guided Deep Learning Model for Daily Precipitation Downscaling","authors":["Xiang Li","Jie Xiang","Jiping Guan","Fuhan Zhang","Yanling Zhao","Lifeng Zhang"],"date":"2022-03-24","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13040511","openalex":"W4220765537"},"links":{"paper":"https://doi.org/10.3390/atmos13040511","pdf":"https://www.mdpi.com/2073-4433/13/4/511/pdf?version=1648088578"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Proposes a reference-based, gradient-guided deep network for daily precipitation downscaling from GPM and ERA5 with topography, outperforming baseline super-resolution methods.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.future.2022.03.029","title":"ATDNNS: An adaptive time–frequency decomposition neural network-based system for tropical cyclone wave height real-time forecasting","authors":["Fan Meng","Danya Xu","Tao Song"],"date":"2022-03-24","year":2022,"venue":"Future Generation Computer Systems","venue_type":"journal","ids":{"doi":"10.1016/j.future.2022.03.029","openalex":"W4220871809"},"links":{"paper":"https://doi.org/10.1016/j.future.2022.03.029"},"orgs":["alibaba-damo"],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Neural network system with time-frequency decomposition forecasts tropical cyclone wave height in real time; the abstract is missing, so the classification relies on the title.","significance":2,"cited_by":25,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.13263","title":"Precipitaion Nowcasting using Deep Neural Network","authors":["Mohamed Chafik Bakkay","Mathieu Serrurier","Valentin Kivachuk Burda","Florian Dupuy","Naty Citlali Cabrera-Gutierrez","Michael Zamo","Maud-Alix Mader","Olivier Mestre","Guillaume Oller","Jean-Christophe Jouhaud","Laurent Terray"],"date":"2022-03-24","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.13263","openalex":"W4226374996"},"links":{"paper":"https://arxiv.org/abs/2203.13263","pdf":"https://arxiv.org/pdf/2203.13263"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":[],"data":["radar"],"status":"research","summary":"Compares U-Net, ConvLSTM and SVG-LP for precipitation nowcasting on precipitation maps, adding a patch extraction scheme and a loss that reduces blurring.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.12529","title":"A Deep Learning Approach to Probabilistic Forecasting of Weather","authors":["Nick Rittler","Carlo Graziani","Jiali Wang","Rao Kotamarthi"],"date":"2022-03-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.12529"},"links":{"paper":"https://arxiv.org/abs/2203.12529","pdf":"https://arxiv.org/pdf/2203.12529"},"orgs":[],"topic":"probabilistic-ensembles","topics":["post-processing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Chains dimensional reduction with normalizing flows to produce conditional probabilistic forecasts of surface wind from 22 years of WRF simulation data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.12297","title":"Increasing the accuracy and resolution of precipitation forecasts using deep generative models","authors":["Ilan Price","Stephan Rasp"],"date":"2022-03-23","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.12297","openalex":"W4221151696"},"links":{"paper":"https://arxiv.org/abs/2203.12297","pdf":"https://arxiv.org/pdf/2203.12297"},"orgs":["alan-turing-institute","university-of-oxford"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"research","summary":"CorrectorGAN jointly bias-corrects and super-resolves global ensemble precipitation forecasts over the US against radar, approaching an operational regional model in seconds.","significance":5,"cited_by":39,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1038-s41467-022-28853-0","title":"Machine learning–based observation-constrained projections reveal elevated global socioeconomic risks from wildfire","authors":["Yan Yu","Jiafu Mao","Stan D. Wullschleger","Anping Chen","Xiaoying Shi","Yaoping Wang","Forrest M. Hoffman","Yulong Zhang","Eric M. Pierce"],"date":"2022-03-22","year":2022,"venue":"Nature Communications","venue_type":"journal","ids":{"doi":"10.1038/s41467-022-28853-0","openalex":"W4221047666"},"links":{"paper":"https://doi.org/10.1038/s41467-022-28853-0","pdf":"https://www.nature.com/articles/s41467-022-28853-0.pdf"},"orgs":["ornl","colorado-state-university"],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Uses a machine learning framework to observationally constrain 13 CMIP6 Earth system models, projecting higher socioeconomic wildfire exposure in Africa despite lower fire carbon emissions.","significance":4,"cited_by":84,"score":46,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2022.127748","title":"A spatiotemporal deep learning model ST-LSTM-SA for hourly rainfall forecasting using radar echo images","authors":["Jie Liu","Lei Xu","Nengcheng Chen"],"date":"2022-03-21","year":2022,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2022.127748","openalex":"W4221070765"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2022.127748"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Spatiotemporal LSTM with self-attention forecasts hourly rainfall from radar echo images; no abstract is available, so results are unverified.","significance":3,"cited_by":80,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.11141","title":"Can we integrate spatial verification methods into neural-network loss functions for atmospheric science?","authors":["Ryan Lagerquist","Imme Ebert-Uphoff"],"date":"2022-03-21","year":2022,"venue":"Artificial Intelligence for the Earth Systems (2022), 1 (4), pg. e220021","venue_type":"journal","ids":{"arxiv":"2203.11141","doi":"10.1175/aies-d-22-0021.1","openalex":"W4297239582"},"links":{"paper":"https://arxiv.org/abs/2203.11141","pdf":"https://arxiv.org/pdf/2203.11141"},"orgs":["colorado-state-university","noaa"],"topic":"benchmarks-data-eval","topics":["extremes-hazards","post-processing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Spatially enhanced loss functions using neighbourhood and spectral filters improve neural network convection forecasts, with spectral-filter models giving better-calibrated probabilities than pixelwise training.","significance":4,"cited_by":16,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-022-08786-w","title":"Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques","authors":["Dinu Maria Jose","Amala Mary Vincent","Gowdagere Siddaramaiah Dwarakish"],"date":"2022-03-18","year":2022,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-022-08786-w","openalex":"W4220659394"},"links":{"paper":"https://doi.org/10.1038/s41598-022-08786-w","pdf":"https://www.nature.com/articles/s41598-022-08786-w.pdf"},"orgs":[],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml","rnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Compares ML ensembling (RF, SVR, ETR, LSTM) of 34 GCMs for daily precipitation and temperature in an Indian basin; LSTM reaches R² of 0.9 for precipitation.","significance":3,"cited_by":213,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7611","title":"Evaluation of statistical downscaling methods for climate change projections over Spain: Present conditions with imperfect predictors (global climate model experiment)","authors":["Alfonso Hernanz","Juan Andrés García Valero","Marta Domínguez","Ernesto Rodríguez Camino"],"date":"2022-03-18","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7611","openalex":"W4221012211"},"links":{"paper":"https://doi.org/10.1002/joc.7611"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5","stations"],"status":"research","summary":"Compares five statistical downscaling methods, including ANN, SVM and kernel ridge, over 18 CMIP5 GCMs for Spain, quantifying errors from imperfect GCM predictors.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3233-jifs-219284","title":"A machine learning-based weather prediction model and its application on smart irrigation","authors":["Ala' Fathi Khalifeh","Abdullah Yousef Al-Qammaz","Laith Abualigah","Ahmad M. Khasawneh","Khalid Ahmad Darabkh"],"date":"2022-03-17","year":2022,"venue":"Journal of Intelligent & Fuzzy Systems","venue_type":"journal","ids":{"doi":"10.3233/jifs-219284","openalex":"W4220966645"},"links":{"paper":"https://doi.org/10.3233/jifs-219284"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"SSA-tuned least-squares SVM forecasts Amman temperature, pressure and soil humidity 24 to 72 h ahead for smart irrigation; a single-city study.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4265","title":"Wind‐Topo: Downscaling near‐surface wind fields to high‐resolution topography in highly complex terrain with deep learning","authors":["Jérôme Dujardin","Michael Lehning"],"date":"2022-03-14","year":2022,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4265","openalex":"W4220664068"},"links":{"paper":"https://doi.org/10.1002/qj.4265"},"orgs":[],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"Wind-Topo uses deep learning to downscale COSMO-1 near-surface winds to 50 m over Swiss Alpine topography, reproducing orographic effects at 60 validation stations.","significance":4,"cited_by":92,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.10114","title":"Seamless lightning nowcasting with recurrent-convolutional deep learning","authors":["Jussi Leinonen","Ulrich Hamann","Urs Germann"],"date":"2022-03-14","year":2022,"venue":"Artif. Intell. Earth Syst., 1, e220043 (2022)","venue_type":"journal","ids":{"arxiv":"2203.10114","doi":"10.1175/aies-d-22-0043.1","openalex":"W4221161511"},"links":{"paper":"https://arxiv.org/abs/2203.10114","pdf":"https://arxiv.org/pdf/2203.10114"},"orgs":["meteoswiss"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite","nwp-analysis","other"],"status":"research","summary":"A recurrent-convolutional network nowcasts lightning occurrence over Switzerland for 60 minutes, reaching CSI 0.75 at 5 minutes and 0.32 at 60 minutes.","significance":4,"cited_by":33,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-2085-2022","title":"From emission scenarios to spatially resolved projections with a chain of computationally efficient emulators: coupling of MAGICC (v7.5.1) and MESMER (v0.8.3)","authors":["Lea Beusch","Zebedee Nicholls","Lukas Gudmundsson","Mathias Hauser","Malte Alexander Meinshausen","Sonia Isabelle Seneviratne"],"date":"2022-03-11","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-2085-2022","openalex":"W4220689753"},"links":{"paper":"https://doi.org/10.5194/gmd-15-2085-2022"},"orgs":["eth-zurich"],"topic":"climate-emulation","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global","regional"],"data":["cmip"],"status":"research","summary":"Chains the MAGICC global emulator with the MESMER spatial emulator to produce millions of local temperature projections per emission pathway, validated against CMIP6 ensembles.","significance":4,"cited_by":62,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.05835","title":"MLRM: A Multiple Linear Regression based Model for Average Temperature Prediction of A Day","authors":["Ishu Gupta","Harsh Mittal","Deepak Rikhari","Ashutosh Kumar Singh"],"date":"2022-03-11","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.05835","openalex":"W4221154964"},"links":{"paper":"https://arxiv.org/abs/2203.05835","pdf":"https://arxiv.org/pdf/2203.05835"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Multiple linear regression predicts a day's average temperature from past station meteorological data with a reported error of 2.8 °C.","significance":1,"cited_by":24,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46267-j.1006-8775.2022.007","title":"A Neural Network Based Single Footprint Temperature Retrieval for Atmospheric Infrared Sounder Measurements and Its Application to Study on Stratospheric Gravity Wave","authors":["Zhigang Yao","HONG Jun","CUI Xing-dong","ZHAO Zeng-liang","HAN Zhi-gang"],"date":"2022-03-10","year":2022,"venue":"Journal of Tropical Meteorology","venue_type":"journal","ids":{"doi":"10.46267/j.1006-8775.2022.007","openalex":"W4226490337"},"links":{"paper":"https://doi.org/10.46267/j.1006-8775.2022.007"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Neural network retrieves stratospheric temperature from single-footprint AIRS sounder data, cutting error versus operational products and resolving gravity waves.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46267-j.1006-8775.2022.004","title":"Annual Frequency of Tropical Cyclones Directly Affecting Guangdong Province:Prediction Based on LSTM-FC","authors":["Yamin Hu","CHEN Yun-zhu","HE Jian","LIU Sheng-jun","YAN Wen-jie","Liang Zhao","WANG Ming-sheng","Zhihui Li","WANG Juan-huai","DONG Shao-rou","LIU Xin-ru"],"date":"2022-03-10","year":2022,"venue":"Journal of Tropical Meteorology","venue_type":"journal","ids":{"doi":"10.46267/j.1006-8775.2022.004","openalex":"W4225834426"},"links":{"paper":"https://doi.org/10.46267/j.1006-8775.2022.004"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["rnn","classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Predicts annual tropical cyclone frequency for Guangdong from winter precursors using LSTM-FC, which achieves lower error than MLR and GPR for 2010–2019.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl096690","title":"Greenland Ice Sheet Daily Surface Melt Flux Observed From Space","authors":["Lei Zheng","Xiao Yan Cheng","Xinyi Shang","Zhuoqi Chen","Qi Liang","Kang Wang"],"date":"2022-03-10","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl096690","openalex":"W4220682735"},"links":{"paper":"https://doi.org/10.1029/2021gl096690"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Estimates daily Greenland Ice Sheet surface melt at 3.125 km from spaceborne radiometers using a neural network trained on surface energy balance data, matching regional climate models.","significance":3,"cited_by":27,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.07080","title":"Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case","authors":["Odin Foldvik Eikeland","Finn Dag Hovem","Tom Eirik Olsen","Matteo Chiesa","Filippo Maria Bianchi"],"date":"2022-03-10","year":2022,"venue":"Energy Conversion and Management X","venue_type":"journal","ids":{"arxiv":"2203.07080","doi":"10.1016/j.ecmx.2022.100239","openalex":"W4221159239"},"links":{"paper":"https://doi.org/10.1016/j.ecmx.2022.100239","pdf":"https://arxiv.org/pdf/2203.07080"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Deep learning probabilistic day-ahead wind power forecasts for an Arctic site improve when measured weather and NWP are used as covariates to correct NWP biases.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-stats5010018","title":"Importance of Weather Conditions in a Flight Corridor","authors":["Gong Chen","Hartmut Fricke","Ostap Okhrin","Judith Rosenow"],"date":"2022-03-09","year":2022,"venue":"Stats","venue_type":"journal","ids":{"doi":"10.3390/stats5010018","openalex":"W4220971868"},"links":{"paper":"https://doi.org/10.3390/stats5010018","pdf":"https://www.mdpi.com/2571-905X/5/1/18/pdf?version=1648091661"},"orgs":[],"topic":"applications-impacts","topics":["downscaling"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Compares kriging, RBF, neural network and tree interpolation of GFS weather to high resolution for flight trajectories, with the choice shaping trajectory optimization.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.04511","title":"Revealing the Excitation Causality between Climate and Political Violence via a Neural Forward-Intensity Poisson Process","authors":["Schyler C. Sun","Bailu Jin","Zhuangkun Wei","Weisi Guo"],"date":"2022-03-09","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.04511"},"links":{"paper":"https://arxiv.org/abs/2203.04511","pdf":"https://arxiv.org/pdf/2203.04511"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml","other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural forward-intensity Poisson process models nonlinear excitation links between extreme climate events and political violence across countries over 20 years.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-1899-2022","title":"Building a machine learning surrogate model for wildfire activities within a global Earth system model","authors":["Qing Zhu","Fa Li","W. J. Riley","Li Xu","Lei Zhao","Kunxiaojia Yuan","Huayi Wu","Jianya Gong","James T. Randerson"],"date":"2022-03-08","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-1899-2022","openalex":"W4220977284"},"links":{"paper":"https://doi.org/10.5194/gmd-15-1899-2022","pdf":"https://gmd.copernicus.org/articles/15/1899/2022/gmd-15-1899-2022.pdf"},"orgs":["lbnl-nersc"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"A DNN surrogate replaces the process-based wildfire model in E3SM, matching observed burned area with R2 0.93 and far lower parameterization cost.","significance":3,"cited_by":45,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13030439","title":"Urban Climate Risk Mitigation via Optimal Spatial Resource Allocation","authors":["Ido Nevat","Muhammad Omer Mughal"],"date":"2022-03-08","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13030439","openalex":"W4220715732"},"links":{"paper":"https://doi.org/10.3390/atmos13030439","pdf":"https://www.mdpi.com/2073-4433/13/3/439/pdf?version=1646875118"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["other"],"status":"research","summary":"Builds a regression surrogate of outdoor thermal comfort from WRF climate simulations and a portfolio-based allocation method for urban cooling resources in Singapore.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-021-1368-4","title":"A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses","authors":["Lu Zhou","Rong‐Hua Zhang"],"date":"2022-03-08","year":2022,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-021-1368-4","openalex":"W4220888586"},"links":{"paper":"https://doi.org/10.1007/s00376-021-1368-4"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Hybrid neural network combined with principal oscillation pattern analysis for ENSO prediction; the abstract is missing, so the classification relies on the title.","significance":3,"cited_by":53,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.04060","title":"Classification of Middle Tropospheric Systems over the Arabian Sea and Western India","authors":["Pradeep Kushwaha","Jai Sukhatme","Ravi S. Nanjundiah"],"date":"2022-03-08","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.04060","doi":"10.1002/qj.4466"},"links":{"paper":"https://arxiv.org/abs/2203.04060","pdf":"https://arxiv.org/pdf/2203.04060"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Unsupervised clustering and cyclone tracking identify four weather patterns behind middle tropospheric cyclones that drive extreme rainfall over western India.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10510756.1","title":"Combining LSTM statistical analysis with dynamical models to investigate Typhoon Mangkhut (2018)","authors":["Clifford Evan Watkins","Sue Chen"],"date":"2022-03-07","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10510756.1","openalex":"W4220959695"},"links":{"paper":"https://doi.org/10.1002/essoar.10510756.1"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Trains an LSTM on COAMPS ensemble output to predict Typhoon Mangkhut's intensity and identify drivers of rapid intensification from asymmetry and heat flux features.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002875","title":"Exploring Pathways to More Accurate Machine Learning Emulation of Atmospheric Radiative Transfer","authors":["Peter Ukkonen"],"date":"2022-03-06","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002875","openalex":"W4220813674"},"links":{"paper":"https://doi.org/10.1029/2021ms002875"},"orgs":[],"topic":"hybrid-parameterization","topics":["benchmarks-data-eval"],"type":"model","method":["rnn","classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A bidirectional RNN emulates shortwave radiation with fewer parameters than feed-forward nets, achieving under 1% flux error and a 4-fold CPU speedup.","significance":4,"cited_by":72,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-forecast4010019","title":"Irradiance Nowcasting by Means of Deep-Learning Analysis of Infrared Images","authors":["Alessandro Niccolai","Seyedamir Orooji","Andrea Matteri","Emanuèle Ogliari","Sonia Leva"],"date":"2022-03-04","year":2022,"venue":"Forecasting","venue_type":"journal","ids":{"doi":"10.3390/forecast4010019","openalex":"W4221010848"},"links":{"paper":"https://doi.org/10.3390/forecast4010019","pdf":"https://www.mdpi.com/2571-9394/4/1/19/pdf?version=1646645412"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN on infrared all-sky images forecasts clear-sky index ranges 5 to 15 min ahead, reaching about 65% accuracy at 5 min for solar irradiance.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.renene.2022.02.095","title":"Wind speed forecasting using multi-site collaborative deep learning for complex terrain application in valleys","authors":["Dalei Qiao","Shun Wei Wu","Ge Li","Jiaxing You","Juan Zhang","Bilong Shen"],"date":"2022-03-04","year":2022,"venue":"Renewable Energy","venue_type":"journal","ids":{"doi":"10.1016/j.renene.2022.02.095","openalex":"W4214810046"},"links":{"paper":"https://doi.org/10.1016/j.renene.2022.02.095"},"orgs":["cma"],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Multi-site collaborative deep learning for wind speed forecasting in valley complex terrain; abstract unavailable, judged from title only.","significance":2,"cited_by":40,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2022.818671","title":"A Machine-Learning Based Tool for Diagnosing Inland Tropical Cyclone Maintenance or Intensification Events","authors":["Andrew Michael Thomas","James Marshall Shepherd"],"date":"2022-03-03","year":2022,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2022.818671","openalex":"W4214819053"},"links":{"paper":"https://doi.org/10.3389/feart.2022.818671","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2022.818671/pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A machine-learning tool diagnoses inland tropical cyclone maintenance or intensification events from MERRA-2 and IBTrACS, highlighting land-surface state importance.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13030408","title":"Data Filling of Micrometeorological Variables in Complex Terrain for High-Resolution Nowcasting","authors":["Nipun Gunawardena","Pierre Durand","Thierry Hedde","Florian Dupuy","Eric R. Pardyjak"],"date":"2022-03-02","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13030408","openalex":"W4214924628"},"links":{"paper":"https://doi.org/10.3390/atmos13030408","pdf":"https://www.mdpi.com/2073-4433/13/3/408/pdf?version=1646213526"},"orgs":["meteo-france"],"topic":"observations-remote-sensing","topics":["local-forecasting"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares linear regression and neural networks for filling gaps in micrometeorological station data in complex terrain, finding significant wind differences only in synoptic flow.","significance":2,"cited_by":5,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1339694-v1","title":"Use of artificial neural network for generation of ultra-high resolution meteorological fields over Chowkibal-Tangdhar region of North-West Himalaya","authors":["Jagdish Chandra Joshi","Prabhjot Kaur"],"date":"2022-03-02","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1339694/v1","openalex":"W4214883334"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1339694/v1","pdf":"https://www.researchsquare.com/article/rs-1339694/latest.pdf"},"orgs":[],"topic":"post-processing","topics":["regional-km-scale"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural networks post-process 2 km WRF output over the NW Himalaya and interpolate it to 90 m, with NSE above 0.75 at five stations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1117-1.jrs.16.014519","title":"Hail disaster recognition method based on artificial intelligence with Doppler radar data","authors":["Xia Chen","Haijiang Wang","Fudong Zhen","Ye Lu","Jing Li","Zili Xu","Qutie JieLa"],"date":"2022-03-02","year":2022,"venue":"Journal of Applied Remote Sensing","venue_type":"journal","ids":{"doi":"10.1117/1.jrs.16.014519","openalex":"W4214830757"},"links":{"paper":"https://doi.org/10.1117/1.jrs.16.014519"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Faster R-CNN recognizes hail areas in Doppler radar imagery with over 86% accuracy and 97% precision on a test set.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14529-jsfi220104","title":"Machine Learning Approaches to Extreme Weather Events Forecast in Urban Areas: Challenges and Initial Results","authors":["Fabio Andre Machado Porto","Mariza Ferro","Eduardo Ogasawara","Thiago Moeda","Claudio D. T. Barros","Anderson Chaves da Silva","Rocío Zorrilla","Rafael Silva Pereira","Rafaela Castro","João Victor Silva","Rebecca Pontes Salles","Augusto J. M. da Fonseca","Juliana Hermsdorff","Marcelo Magalhães","Vitor Sá","Antônio Adolfo Simões","Carlos Cardoso","Eduardo Bezerra"],"date":"2022-03-01","year":2022,"venue":"Supercomputing Frontiers and Innovations","venue_type":"journal","ids":{"doi":"10.14529/jsfi220104","openalex":"W4281488838"},"links":{"paper":"https://doi.org/10.14529/jsfi220104","pdf":"https://superfri.org/index.php/superfri/article/download/418/695"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["local"],"data":[],"status":"research","summary":"Ongoing project builds ML models for extreme urban rainfall forecasts in Rio de Janeiro, reporting early results and open challenges.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ea002168","title":"Effects of Learning Rates and Optimization Algorithms on Forecasting Accuracy of Hourly Typhoon Rainfall: Experiments With Convolutional Neural Network","authors":["Md. Jalal Uddin","Yubin Li","Md. Abdus Sattar","Zahan Most. Nasrin","Chunsong Lu"],"date":"2022-03-01","year":2022,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2021ea002168","openalex":"W4220952814"},"links":{"paper":"https://doi.org/10.1029/2021ea002168","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021EA002168"},"orgs":["nuist"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"evaluation","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Tests seven optimizers and eight learning rates for a CNN forecasting hourly typhoon rainfall 1–6 h ahead; moderate rates (0.1–0.001) work best.","significance":3,"cited_by":24,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.scitotenv.2022.154223","title":"Combining computational fluid dynamics and neural networks to characterize microclimate extremes: Learning the complex interactions between meso-climate and urban morphology","authors":["Kavan Javanroodi","Vahid M. Nik","Marco G. Giometto","Jean‐Louis Scartezzini"],"date":"2022-03-01","year":2022,"venue":"The Science of The Total Environment","venue_type":"journal","ids":{"doi":"10.1016/j.scitotenv.2022.154223","openalex":"W4214766670"},"links":{"paper":"https://doi.org/10.1016/j.scitotenv.2022.154223"},"orgs":["columbia-leap"],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Trains feedforward and deep neural networks on CFD simulations to downscale mesoscale wind and temperature to urban microscale, reaching R2 of 0.91 and 0.94.","significance":3,"cited_by":61,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2203.01277","title":"Deep Temporal Interpolation of Radar-based Precipitation","authors":["Michiaki Tatsubori","Takao Moriyama","Tatsuya Ishikawa","Paolo Fraccaro","Anne Jones","Blair Edwards","Julian Kuehnert","Sekou L. Remy"],"date":"2022-03-01","year":2022,"venue_type":"preprint","ids":{"arxiv":"2203.01277"},"links":{"paper":"https://arxiv.org/abs/2203.01277","pdf":"https://arxiv.org/pdf/2203.01277"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Self-supervised deep networks interpolate radar precipitation to 5-minute resolution, cutting error by up to 20% versus linear interpolation over southern France.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-axioms11030107","title":"RainPredRNN: A New Approach for Precipitation Nowcasting with Weather Radar Echo Images Based on Deep Learning","authors":["Do Ngoc Tuyen","Trần Mạnh Tuấn","Xuan-Hien Le","Nguyễn Thanh Tùng","Tran Kim Chau","Hai Van Pham","Vassilis C. Gerogiannis","Lê Hoàng Sơn"],"date":"2022-02-28","year":2022,"venue":"Axioms","venue_type":"journal","ids":{"doi":"10.3390/axioms11030107","openalex":"W4214628975"},"links":{"paper":"https://doi.org/10.3390/axioms11030107","pdf":"https://www.mdpi.com/2075-1680/11/3/107/pdf?version=1646209228"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"Combines a UNet with PredRNN_v2 to predict radar reflectivity fields in Vietnam, cutting training time to 30% while reaching SSIM 0.95 and CSI 0.94.","significance":3,"cited_by":40,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-21-0170.1","title":"Extreme Rainfall Indices Prediction with Atmospheric Parameters and Ocean–Atmospheric Teleconnections Using a Random Forest Model","authors":["Md. Jalal Uddin","Yubin Li","Md. Yahya Tamim","Md. Babul Miah","S. M. Shahriar Ahmed"],"date":"2022-02-28","year":2022,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-21-0170.1","openalex":"W4214604383"},"links":{"paper":"https://doi.org/10.1175/jamc-d-21-0170.1"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Random forest forecasts monthly extreme rainfall indices over Bangladesh 1–3 months ahead using CAPE, humidity, and ENSO/IOD/NAO teleconnections.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2022.127656","title":"Correcting the bias of daily satellite precipitation estimates in tropical regions using deep neural network","authors":["Xiaoying Yang","Shuai Yang","Mou Leong Tan","Hengyang Pan","Hongliang Zhang","Guoqing Wang","Ruimin He","Zimeng Wang"],"date":"2022-02-26","year":2022,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2022.127656","openalex":"W4214740551"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2022.127656"},"orgs":["fudan-university"],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"A deep neural network corrects bias in daily satellite precipitation estimates over tropical regions, using ground observations as the reference.","significance":3,"cited_by":69,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-nhess-22-577-2022","title":"Nowcasting thunderstorm hazards using machine learning: the impact of data sources on performance","authors":["Jussi Leinonen","Ulrich Hamann","Urs Germann","John R. Mecikalski"],"date":"2022-02-25","year":2022,"venue":"Natural hazards and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/nhess-22-577-2022","openalex":"W4225736959"},"links":{"paper":"https://doi.org/10.5194/nhess-22-577-2022"},"orgs":["meteoswiss"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite","nwp-analysis","other"],"status":"research","summary":"Gradient-boosted nowcasts of reflectivity, lightning and hail-related echo tops show radar is the most useful input and satellite helps across all hazards.","significance":4,"cited_by":55,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en15051718","title":"A Comparison between Analog Ensemble and Convolutional Neural Network Empirical-Statistical Downscaling Techniques for Reconstructing High-Resolution Near-Surface Wind","authors":["Christopher M. Rozoff","Stefano Alessandrini"],"date":"2022-02-25","year":2022,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en15051718","openalex":"W4214574029"},"links":{"paper":"https://doi.org/10.3390/en15051718","pdf":"https://www.mdpi.com/1996-1073/15/5/1718/pdf?version=1645772296"},"orgs":["ncar"],"topic":"downscaling","topics":["applications-impacts"],"type":"evaluation","method":["cnn","classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Compares analog ensemble and CNN empirical-statistical downscaling for 10 m winds over complex terrain, finding the analog ensemble has smaller errors than the CNN.","significance":3,"cited_by":11,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25303-1503da3943","title":"Rainfall Modeling and Prediction using Neural Networks: A Case Study of Maharashtra","authors":["Vatsal Desai","R.K. Kamat","K.S. Oza"],"date":"2022-02-25","year":2022,"venue":"Disaster Advances","venue_type":"journal","ids":{"doi":"10.25303/1503da3943","openalex":"W4221007415"},"links":{"paper":"https://doi.org/10.25303/1503da3943"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies a neural network autoregression on lagged station rainfall series to forecast monsoon rainfall in Maharashtra, India.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su14052663","title":"Precipitation Forecasting in Northern Bangladesh Using a Hybrid Machine Learning Model","authors":["Fabio Di Nunno","Francesco Granata","Quoc Bao Pham","Giovanni de Marinis"],"date":"2022-02-24","year":2022,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su14052663","openalex":"W4214646202"},"links":{"paper":"https://doi.org/10.3390/su14052663","pdf":"https://www.mdpi.com/2071-1050/14/5/2663/pdf?version=1645784751"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid M5P-SVR model forecasts station precipitation in northern Bangladesh, reaching R2 up to 0.92 at Sylhet.","significance":2,"cited_by":48,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.apenergy.2022.118777","title":"A short-term wind speed prediction method utilizing novel hybrid deep learning algorithms to correct numerical weather forecasting","authors":["Yan Han","Lihua Mi","Lian Shen","C. S. Steve Cai","Yuchen Liu","Kai Li","Guoji Xu"],"date":"2022-02-24","year":2022,"venue":"Applied Energy","venue_type":"journal","ids":{"doi":"10.1016/j.apenergy.2022.118777","openalex":"W4213450433"},"links":{"paper":"https://doi.org/10.1016/j.apenergy.2022.118777"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":[],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Hybrid deep learning corrects numerical weather forecasts of short-term wind speed; the abstract is unavailable, so the gain is unquantified.","significance":3,"cited_by":192,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.6036-nt10369","title":"PREDICTION OF MARS METEOROLOGICAL VARIABLES USING ARTIFICIAL NEURAL NETWORKS","authors":["Alejandro de-Cabo-Garcia","Alfonso Delgado-Bonal","BELEN PEREZ LANCHO","JORGE PLA GARCIA","GERMAN MARTINEZ"],"date":"2022-02-23","year":2022,"venue":"DYNA NEW TECHNOLOGIES","venue_type":"journal","ids":{"doi":"10.6036/nt10369","openalex":"W3046926176"},"links":{"paper":"https://doi.org/10.6036/nt10369"},"orgs":["nasa"],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Trains a neural network on Viking and Mars Science Laboratory measurements to predict next-day Martian temperature and pressure within 0.5 to 1% accuracy.","significance":2,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0077.1","title":"Machine Learning–Based Hurricane Wind Reconstruction","authors":["Qidong Yang","Chia‐Ying Lee","Michael K. Tippett","Daniel R. Chavas","Thomas R. Knutson"],"date":"2022-02-22","year":2022,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0077.1","openalex":"W4293226861"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0077.1"},"orgs":["noaa","columbia-leap","nyu-m2lines"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"XGBoost reconstructs hurricane surface wind fields from storm and ERA-Interim features, with errors below climatological variance, for synthetic risk applications.","significance":3,"cited_by":18,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-we.2718","title":"Machine learning‐based statistical downscaling of wind resource maps using multi‐resolution topographical data","authors":["Myeongchan Oh","Je-Hyun Lee","Jin Young Kim","Hyun‐Goo Kim"],"date":"2022-02-22","year":2022,"venue":"Wind Energy","venue_type":"journal","ids":{"doi":"10.1002/we.2718","openalex":"W4214607540"},"links":{"paper":"https://doi.org/10.1002/we.2718","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/we.2718"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","km-scale-sim"],"status":"research","summary":"Machine learning with new topography-derived variables downscales Weibull wind resource maps over South Korea, cutting RMSE by about 15% versus baseline inputs.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.11214","title":"FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators","authors":["Jaideep Pathak","Shashank Subramanian","Peter Harrington","Sanjeev Raja","Ashesh Chattopadhyay","Morteza Mardani","Thorsten Kurth","David Hall","Zongyi Li","Kamyar Azizzadenesheli","Pedram Hassanzadeh","Karthik Kashinath","Animashree Anandkumar"],"date":"2022-02-22","year":2022,"venue_type":"preprint","ids":{"arxiv":"2202.11214","openalex":"W4225906496"},"links":{"paper":"https://arxiv.org/abs/2202.11214","pdf":"https://arxiv.org/pdf/2202.11214"},"orgs":["caltech","lbnl-nersc","nvidia"],"topic":"global-medium-range","topics":[],"type":"model","method":["neural-operator","transformer"],"timescale":["short","medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"FourCastNet uses adaptive Fourier neural operators to forecast global 0.25 degree weather in under 2 seconds, matching IFS at short leads and beating it for precipitation.","significance":9,"cited_by":439,"score":81,"highlight":true,"highlight_reason":"Landmark FourCastNet paper: first global 0.25° AI model approaching IFS skill, triggering the wave of data-driven weather models and large-ensemble forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.21203-rs.3.rs-1308502-v1","title":"Merging multisatellite precipitation products using stacking and EMOS-CSG methods","authors":["Tuantuan Zhang","Zhongmin Liang","Haijun Wang","Jun Wang","Yiming Hu","Binquan Li"],"date":"2022-02-21","year":2022,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1308502/v1","openalex":"W4213227129"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1308502/v1","pdf":"https://www.researchsquare.com/article/rs-1308502/latest.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Stacking and EMOS-CSG merge four satellite precipitation products with gauges into a 1 km daily product with RMSE 4.33 mm in a basin study.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.09967","title":"A Deep Learning Model for Forecasting Global Monthly Mean Sea Surface Temperature Anomalies","authors":["John Taylor","Ming Feng"],"date":"2022-02-21","year":2022,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"arxiv":"2202.09967","doi":"10.3389/fclim.2022.932932","openalex":"W4297474326"},"links":{"paper":"https://doi.org/10.3389/fclim.2022.932932","pdf":"https://arxiv.org/pdf/2202.09967"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Unet-LSTM model forecasts global monthly SST anomalies up to 24 months ahead, capturing ENSO events such as the 2015-16 El Niño with RMSE below 0.75 °C.","significance":3,"cited_by":65,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-1467-2022","title":"GAN–argcPredNet v1.0: a generative adversarial model for radar echo extrapolation based on convolutional recurrent units","authors":["Kun Zheng","Yan Liu","Jinbiao Zhang","Cong Luo","Siyu Tang","Huihua Ruan","Qiya Tan","Yunlei Yi","Xiutao Ran"],"date":"2022-02-18","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-1467-2022","openalex":"W4213020131"},"links":{"paper":"https://doi.org/10.5194/gmd-15-1467-2022","pdf":"https://gmd.copernicus.org/articles/15/1467/2022/gmd-15-1467-2022.pdf"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A GAN with convolutional recurrent units extrapolates Shenzhen radar echoes, raising POD and CSI by 5.5% and 10.4% over rgcPredNet.","significance":3,"cited_by":28,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-21-0201.1","title":"Using Explainable Machine Learning Forecasts to Discover Subseasonal Drivers of High Summer Temperatures in Western and Central Europe","authors":["Chiem van Straaten","Kirien Whan","Dim Coumou","Bart van den Hurk","Maurice J. Schmeits"],"date":"2022-02-18","year":2022,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-21-0201.1","openalex":"W4212808191"},"links":{"paper":"https://doi.org/10.1175/mwr-d-21-0201.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/150/5/MWR-D-21-0201.1.pdf"},"orgs":["knmi","pik"],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Random forests with explainable AI on ERA5 identify drivers of subseasonal high summer temperatures in Europe, with useful skill for warm anomalies at 15-day lead.","significance":3,"cited_by":49,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.renene.2022.02.051","title":"Multi-step solar irradiation prediction based on weather forecast and generative deep learning model","authors":["Yuan Gao","Shohei Miyata","Yasunori Akashi"],"date":"2022-02-18","year":2022,"venue":"Renewable Energy","venue_type":"journal","ids":{"doi":"10.1016/j.renene.2022.02.051","openalex":"W4212816517"},"links":{"paper":"https://doi.org/10.1016/j.renene.2022.02.051"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":[],"timescale":["short"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Generative deep learning turns weather forecasts into multi-step solar irradiation predictions for energy use; the abstract is unavailable, so details are limited.","significance":2,"cited_by":58,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-nh.2022.094","title":"Wavelet-based predictor screening for statistical downscaling of precipitation and temperature using the artificial neural network method","authors":["Aida Hosseini Baghanam","Ehsan Norouzi","Vahid Nourani"],"date":"2022-02-17","year":2022,"venue":"Hydrology research","venue_type":"journal","ids":{"doi":"10.2166/nh.2022.094","openalex":"W4213346939"},"links":{"paper":"https://doi.org/10.2166/nh.2022.094"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Wavelet coherence predictor screening improves ANN statistical downscaling of CMIP5/CMIP6 precipitation and temperature, projecting precipitation declines of 7–29% for the study region.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2022-6760944","title":"Stochastic Simulation of Typhoon in Northwest Pacific Basin Based on Machine Learning","authors":["Yong Hui Fang","Yanhua Sun","Lu Zhang","Gengxin Chen","Mei Du","Yunxia Guo"],"date":"2022-02-17","year":2022,"venue":"Computational Intelligence and Neuroscience","venue_type":"journal","ids":{"doi":"10.1155/2022/6760944","openalex":"W4212807931"},"links":{"paper":"https://doi.org/10.1155/2022/6760944","pdf":"https://downloads.hindawi.com/journals/cin/2022/6760944.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Backpropagation neural network replaces regression in a typhoon full-track model to generate 1000 years of Northwest Pacific typhoon events for hazard risk.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tits.2022.3150715","title":"Using Vision Transformers for Spatial-Context-Aware Rain and Road Surface Condition Detection on Freeways","authors":["Amr Abdelraouf","Mohamed A. Abdel-Aty","Yina Wu"],"date":"2022-02-17","year":2022,"venue":"IEEE Transactions on Intelligent Transportation Systems","venue_type":"journal","ids":{"doi":"10.1109/tits.2022.3150715","openalex":"W4213052444"},"links":{"paper":"https://doi.org/10.1109/tits.2022.3150715"},"orgs":[],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["transformer"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Vision Transformers with spatial self-attention detect rain and road surface wetness from freeway CCTV cameras, reaching 96.7% and 98.1% F1.","significance":2,"cited_by":62,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.10555","title":"Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation","authors":["Jihoon Ko","Kyuhan Lee","Hyunjin Hwang","Seok-Geun Oh","Seok-Woo Son","Kijung Shin"],"date":"2022-02-17","year":2022,"venue":"Computers & Geosciences","venue_type":"journal","ids":{"arxiv":"2202.10555","doi":"10.1016/j.cageo.2022.105072","openalex":"W4213304302"},"links":{"paper":"https://arxiv.org/abs/2202.10555","pdf":"https://arxiv.org/pdf/2202.10555"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"U-Net nowcasting with a radar-prediction pre-training scheme and a new loss; heavy-rain CSI improves up to 95.7% and 43.6% at 5 h lead time.","significance":4,"cited_by":56,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.07575","title":"Forecasting Global Weather with Graph Neural Networks","authors":["Ryan Keisler"],"date":"2022-02-15","year":2022,"venue_type":"preprint","ids":{"arxiv":"2202.07575","openalex":"W4221149294"},"links":{"paper":"https://arxiv.org/abs/2202.07575","pdf":"https://arxiv.org/pdf/2202.07575"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["gnn"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"A graph neural network steps the global atmosphere forward six hours at a time, achieving skill comparable to GFS and ECMWF at 1-degree resolution and running live on operational GFS data.","significance":6,"cited_by":120,"score":34,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s40430-022-03386-1","title":"Neural networks to classify atmospheric turbulence from flight test data: an optimization of input parameters for a generic model","authors":["M.M. de Oliveira","Gabriel S. Mayor","Joao Paulo Macedo","Jorge Henrique Bidinotto"],"date":"2022-02-14","year":2022,"venue":"Journal of the Brazilian Society of Mechanical Sciences and Engineering","venue_type":"journal","ids":{"doi":"10.1007/s40430-022-03386-1","openalex":"W4212947390"},"links":{"paper":"https://doi.org/10.1007/s40430-022-03386-1"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Neural networks classify atmospheric turbulence encountered in aircraft flight test data, with input parameters optimized for a generic model.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1177-0309524x221078536","title":"A comprehensive country-based day-ahead wind power generation forecast model by coupling numerical weather prediction data and CatBoost with feature selection methods for Turkey","authors":["Cem Özen","Ali Deniz"],"date":"2022-02-13","year":2022,"venue":"Wind Engineering","venue_type":"journal","ids":{"doi":"10.1177/0309524x221078536","openalex":"W4213322063"},"links":{"paper":"https://doi.org/10.1177/0309524x221078536"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Couples ERA5 and ECMWF HRES inputs with a CatBoost model and grid selection to forecast Turkey's day-ahead national wind power, reaching 7.6% NRMSE.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-e24020264","title":"A Framework for Four-Dimensional Variational Data Assimilation Based on Machine Learning","authors":["Renze Dong","Hongze Leng","Juan Zhao","Junqiang Song","Shutian Liang"],"date":"2022-02-12","year":2022,"venue":"Entropy","venue_type":"journal","ids":{"doi":"10.3390/e24020264","openalex":"W4213298982"},"links":{"paper":"https://doi.org/10.3390/e24020264","pdf":"https://www.mdpi.com/1099-4300/24/2/264/pdf?version=1644986327"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Builds a pure data-driven 4D-Var framework (ML-4DVAR) using a bilinear neural network surrogate, tested on Lorenz-96 with better assimilation and faster computation than classical 4D-Var.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.pocean.2022.102763","title":"Improving cyclone wind fields using deep convolutional neural networks and their application in extreme events","authors":["Siva Srinivas Kolukula","P. L. N. Murty"],"date":"2022-02-12","year":2022,"venue":"Progress In Oceanography","venue_type":"journal","ids":{"doi":"10.1016/j.pocean.2022.102763","openalex":"W4211146548"},"links":{"paper":"https://doi.org/10.1016/j.pocean.2022.102763"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies deep convolutional neural networks to improve tropical cyclone wind field estimates for extreme event analysis.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en15041330","title":"Support Vector Quantile Regression for the Post-Processing of Meso-Scale Ensemble Prediction System Data in the Kanto Region: Solar Power Forecast Reducing Overestimation","authors":["Takahiro Takamatsu","Hideaki Ohtake","Takashi Oozeki"],"date":"2022-02-11","year":2022,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en15041330","openalex":"W4213012834"},"links":{"paper":"https://doi.org/10.3390/en15041330","pdf":"https://www.mdpi.com/1996-1073/15/4/1330/pdf?version=1645067226"},"orgs":["jma"],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Support vector quantile regression post-processes mesoscale ensemble solar irradiance forecasts, reducing serious overestimation at five Kanto sites.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.04996","title":"AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks","authors":["Yimin Yang","Siamak Mehrkanoon"],"date":"2022-02-10","year":2022,"venue_type":"preprint","ids":{"arxiv":"2202.04996"},"links":{"paper":"https://arxiv.org/abs/2202.04996","pdf":"https://arxiv.org/pdf/2202.04996"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"AA-TransUNet adds attention and depthwise convolutions to TransUNet for precipitation nowcasting, outperforming baselines on Dutch precipitation and French cloud cover data.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.04964","title":"Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data","authors":["Andreas Holm Nielsen","Alexandros Iosifidis","Henrik Karstoft"],"date":"2022-02-10","year":2022,"venue_type":"preprint","ids":{"arxiv":"2202.04964"},"links":{"paper":"https://arxiv.org/abs/2202.04964","pdf":"https://arxiv.org/pdf/2202.04964"},"orgs":[],"topic":"global-medium-range","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Deformable CNNs with transfer learning forecast North Atlantic-European weather regimes 1 to 15 days ahead, outperforming CNNs beyond 5-6 days lead time.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.04944","title":"Supervised machine learning to estimate instabilities in chaotic systems: estimation of local Lyapunov exponents","authors":["Daniel Ayers","Jack Lau","Javier Amezcua","Alberto Carrassi","Varun Ojha"],"date":"2022-02-10","year":2022,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"arxiv":"2202.04944","doi":"10.1002/qj.4450","openalex":"W4360946310"},"links":{"paper":"https://doi.org/10.1002/qj.4450","pdf":"https://arxiv.org/pdf/2202.04944"},"orgs":["university-of-reading"],"topic":"xai-uq-physics","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Regression trees, MLPs, CNNs and LSTMs estimate local Lyapunov exponents from trajectories of Lorenz-63 and Rössler systems, a feasibility study motivated by weather predictability.","significance":3,"cited_by":17,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14040812","title":"Tropical Cyclone Intensity Estimation Using Himawari-8 Satellite Cloud Products and Deep Learning","authors":["Jinkai Tan","Qidong Yang","Junjun Hu","Qiqiao Huang","Sheng Chen"],"date":"2022-02-09","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14040812","openalex":"W4211173294"},"links":{"paper":"https://doi.org/10.3390/rs14040812"},"orgs":["columbia-leap"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"CNN with residual and attention blocks estimates tropical cyclone intensity from Himawari-8 cloud products, reaching RMSE 4.06 m/s on independent tests.","significance":3,"cited_by":42,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en15041252","title":"Advanced Ensemble Methods Using Machine Learning and Deep Learning for One-Day-Ahead Forecasts of Electric Energy Production in Wind Farms","authors":["P. Piotrowski","Dariusz Baczyński","Marcin Kopyt","Tomasz Gulczyński"],"date":"2022-02-09","year":2022,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en15041252","openalex":"W4211194148"},"links":{"paper":"https://doi.org/10.3390/en15041252","pdf":"https://www.mdpi.com/1996-1073/15/4/1252/pdf?version=1644395916"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares ML and ensemble methods for day-ahead wind farm output using lagged NWP point forecasts, with a new averaging ensemble giving the lowest error at two farms.","significance":2,"cited_by":47,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2022.106037","title":"Near real-time hurricane rainfall forecasting using convolutional neural network models with Integrated Multi-satellitE Retrievals for GPM (IMERG) product","authors":["Taereem Kim","Tiantian Yang","Lujun Zhang","Yang E. Hong"],"date":"2022-02-09","year":2022,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2022.106037","openalex":"W4210854286"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2022.106037"},"orgs":["university-of-oklahoma"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Uses CNN models on IMERG satellite precipitation to forecast near-real-time rainfall from hurricanes, targeting flood-relevant extreme rainfall.","significance":3,"cited_by":40,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7557","title":"Dynamical–statistical seasonal forecasts of winter and summer precipitation for the Island of Ireland","authors":["Saeed Golian","Conor Murphy","Robert Leonard Wilby","Tom K. R. Matthews","Seán Donegan","Dáire Foran Quinn","Shaun Harrigan"],"date":"2022-02-09","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7557","openalex":"W4210899477"},"links":{"paper":"https://doi.org/10.1002/joc.7557"},"orgs":["ecmwf"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Hybrid neural-network and regression models using GloSea5 and SEAS5 pressure indices forecast Irish winter and summer rainfall up to 4 months ahead.","significance":3,"cited_by":19,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12205-022-1270-3","title":"Deep Learning-Based Prediction of Fire Occurrence with Hydroclimatic Condition and Drought Phase over South Korea","authors":["Jang Hyun Sung","Young Ryu","Kee‐Won Seong"],"date":"2022-02-08","year":2022,"venue":"KSCE Journal of Civil Engineering","venue_type":"journal","ids":{"doi":"10.1007/s12205-022-1270-3","openalex":"W4210837855"},"links":{"paper":"https://doi.org/10.1007/s12205-022-1270-3"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"A deep belief network driven by relative humidity, wind speed and drought index estimates monthly forest fire occurrence in South Korea with R² of 0.84.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.04152","title":"Multi-model Ensemble Analysis with Neural Network Gaussian Processes","authors":["Trevor Harris","Bo Li","Ryan Sriver"],"date":"2022-02-08","year":2022,"venue":"The Annals of Applied Statistics","venue_type":"journal","ids":{"arxiv":"2202.04152","doi":"10.1214/23-aoas1768","openalex":"W4388075235"},"links":{"paper":"https://doi.org/10.1214/23-aoas1768","pdf":"https://arxiv.org/pdf/2202.04152"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"NN-GPR combines multiple climate models into a 50 km projection without regional models, rivaling RCMs for temperature and precipitation tails.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.03407","title":"Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience","authors":["Antonios Mamalakis","Elizabeth A. Barnes","Imme Ebert-Uphoff"],"date":"2022-02-07","year":2022,"venue":"2022, Artificial Intelligence for the Earth Systems (AMS)","venue_type":"journal","ids":{"arxiv":"2202.03407","doi":"10.1175/aies-d-22-0012.1","openalex":"W4292133488"},"links":{"paper":"https://arxiv.org/abs/2202.03407","pdf":"https://arxiv.org/pdf/2202.03407"},"orgs":["colorado-state-university"],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"evaluation","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Benchmarks XAI attribution methods on a CNN that counts atmospheric rivers in climate simulations, exposing fidelity issues such as gradient shattering and sign ambiguity.","significance":3,"cited_by":94,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002808","title":"A Machine‐Learning‐Assisted Stochastic Cloud Population Model as a Parameterization of Cumulus Convection","authors":["Samson Hagos","Jingyi Chen","Katelyn A. Barber","Kôichi Sakaguchi","Robert Stephen Plant","Zhe Feng","Heng Lin Xiao"],"date":"2022-02-06","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002808","openalex":"W4210380440"},"links":{"paper":"https://doi.org/10.1029/2021ms002808","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002808"},"orgs":["university-of-reading"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"A neural-network-driven stochastic cloud population model parameterizes cumulus convection in WRF, reproducing realistic precipitation statistics, MJO propagation and diurnal cycle in regional tests.","significance":5,"cited_by":9,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002794","title":"Correcting Coarse‐Grid Weather and Climate Models by Machine Learning From Global Storm‐Resolving Simulations","authors":["Christopher S. Bretherton","Brian Henn","Anna Kwa","Noah D. Brenowitz","Oliver Watt‐Meyer","Jeremy McGibbon","W. Andre Perkins","Spencer K. Clark","Lucas Harris"],"date":"2022-02-05","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002794","openalex":"W4206971393"},"links":{"paper":"https://doi.org/10.1029/2021ms002794"},"orgs":["ai2","noaa","university-of-washington"],"topic":"hybrid-parameterization","topics":["global-medium-range"],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Machine-learned nudging tendencies correct a 200-km FV3GFS model toward 3-km X-SHiELD, gaining 18 hours of 3-7 day skill and 30% better precipitation.","significance":6,"cited_by":93,"score":59,"highlight":true,"highlight_reason":"Shows ML corrections learned from 3 km X-SHiELD improve a 200 km model's forecasts and precipitation, a key step toward ML-corrected climate models.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2021gl097571","title":"Reconstructing High Resolution ESM Data Through a Novel Fast Super Resolution Convolutional Neural Network (FSRCNN)","authors":["Linsey Sara Passarella","Salil Mahajan","Anikesh Pal","Matthew Ross Norman"],"date":"2022-02-04","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl097571","openalex":"W4210619949"},"links":{"paper":"https://doi.org/10.1029/2021gl097571","pdf":"https://www.osti.gov/servlets/purl/1864450"},"orgs":["ornl"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"FSRCNN-ESM super-resolves coarse Earth system model output from 1° to 0.25° over North America, outperforming other super-resolution methods on temperature, fluxes and precipitation.","significance":4,"cited_by":69,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.02253","title":"Detecting Distributional Differences in Labeled Sequence Data with Application to Tropical Cyclone Satellite Imagery","authors":["Trey McNeely","Galen Vincent","Kimberly M. Wood","Rafael Izbicki","Ann B. Lee"],"date":"2022-02-04","year":2022,"venue":"The Annals of Applied Statistics","venue_type":"journal","ids":{"arxiv":"2202.02253","doi":"10.1214/22-aoas1668","openalex":"W4367598646"},"links":{"paper":"https://doi.org/10.1214/22-aoas1668","pdf":"https://arxiv.org/pdf/2202.02253"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Nonparametric neural-network test links 24-hour tropical cyclone infrared image sequences to rapid intensification events, with guaranteed type I error control.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.7546-crabs.2022.01.10","title":"Comparison of BLSTM-Attention and BLSTM-Transformer Models for Wind Speed Prediction","authors":["Liu Zhifeng","Ding Feng","J. Y. Lu","Zhou Yue","Chu Hetao"],"date":"2022-02-02","year":2022,"venue":"Proceedings of the Bulgarian Academy of Sciences","venue_type":"journal","ids":{"doi":"10.7546/crabs.2022.01.10","openalex":"W4210832701"},"links":{"paper":"https://doi.org/10.7546/crabs.2022.01.10","pdf":"https://proceedings.bas.bg/index.php/cr/article/download/10/10"},"orgs":["nuist"],"topic":"local-forecasting","topics":[],"type":"model","method":["transformer","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"BLSTM-attention and BLSTM-Transformer models predict wind speed at seven Qingdao stations, cutting RMSE by about 44% versus ECMWF forecasts.","significance":2,"cited_by":5,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.01897","title":"AtmoDist: Self-supervised Representation Learning for Atmospheric Dynamics","authors":["Sebastian Hoffmann","Christian Lessig"],"date":"2022-02-02","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2202.01897","doi":"10.1017/eds.2023.1","openalex":"W4321461227"},"links":{"paper":"https://doi.org/10.1017/eds.2023.1","pdf":"https://arxiv.org/pdf/2202.01897"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Self-supervised network learns atmospheric dynamics by predicting temporal distance between ERA5 fields; the resulting distance loss improves downscaling and missing-data interpolation.","significance":4,"cited_by":10,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-wcd-3-113-2022","title":"Automated detection and classification of synoptic-scale fronts from atmospheric data grids","authors":["Stefan Niebler","Annette Miltenberger","Bertil Schmidt","Peter Spichtinger"],"date":"2022-02-01","year":2022,"venue":"Weather and Climate Dynamics","venue_type":"journal","ids":{"doi":"10.5194/wcd-3-113-2022","openalex":"W4226452176"},"links":{"paper":"https://doi.org/10.5194/wcd-3-113-2022"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A deep network with label deformation loss detects and classifies synoptic fronts in ERA5 over Europe and North America, with CSI above 62.9%.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-aies-d-21-0010.1","title":"Detection of Bow Echoes in Kilometer-Scale Forecasts Using a Convolutional Neural Network","authors":["Arnaud Mounier","Laure Raynaud","Lucie Rottner","Matthieu Plu","Philippe Arbogast","Michaël Kreitz","Léo Mignan","Benoît Touzé"],"date":"2022-02-01","year":2022,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"doi":"10.1175/aies-d-21-0010.1","openalex":"W4289827130"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0010.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/aies/1/2/AIES-D-21-0010.1.pdf"},"orgs":["meteo-france"],"topic":"extremes-hazards","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"pre-operational","summary":"A CNN detects bow echoes in French kilometre-scale model output with 86% hit rate and 39% false alarms, and forecasters found the products useful.","significance":3,"cited_by":12,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-2515-7620-ac5364","title":"Seasonal forecasts of Eurasian summer heat wave frequency","authors":["Rui Zhi Zhang","Xiao Jing Jia","Qifeng Qian"],"date":"2022-02-01","year":2022,"venue":"Environmental Research Communications","venue_type":"journal","ids":{"doi":"10.1088/2515-7620/ac5364","openalex":"W4211127680"},"links":{"paper":"https://doi.org/10.1088/2515-7620/ac5364","pdf":"https://iopscience.iop.org/article/10.1088/2515-7620/ac5364/pdf"},"orgs":["cma"],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Two machine learning models forecast summer Eurasian heatwave frequency from preceding SST, snow, soil moisture and sea ice, outperforming linear regression in 2010–2019 forecasts.","significance":3,"cited_by":18,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2022.106053","title":"Using a 3D convolutional neural network and gated recurrent unit for tropical cyclone track forecasting","authors":["Pingping Wang","Ping Wang","Cong Wang","Bing Xue","Di Wang"],"date":"2022-02-01","year":2022,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2022.106053","openalex":"W4210536790"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2022.106053"},"orgs":["cma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":[],"status":"research","summary":"A 3D CNN combined with a GRU forecasts tropical cyclone tracks, aiming to improve track prediction over conventional approaches.","significance":3,"cited_by":20,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13351-022-1140-4","title":"QpefBD: A Benchmark Dataset Applied to Machine Learning for Minute-Scale Quantitative Precipitation Estimation and Forecasting","authors":["Anyuan Xiong","Na Liu","Yujia Liu","Shulin Zhi","Linlin Wu","Yongjian Xin","Yan Hui Shi","Yun-Jian Zhan"],"date":"2022-02-01","year":2022,"venue":"气象学报：英文版","venue_type":"journal","ids":{"doi":"10.1007/s13351-022-1140-4","openalex":"W3215707958"},"links":{"paper":"https://doi.org/10.1007/s13351-022-1140-4"},"orgs":["cma"],"topic":"benchmarks-data-eval","topics":["nowcasting","observations-remote-sensing"],"type":"benchmark","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Introduces QpefBD, a minute-scale radar-based benchmark dataset for machine learning precipitation estimation and forecasting (abstract not provided; classified from title).","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.5932783","title":"Data Science and Machine Learning for hurricane forecasting","authors":["Stefan Schmainta"],"date":"2022-01-31","year":2022,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.5932783","openalex":"W4226167585"},"links":{"paper":"https://doi.org/10.5281/zenodo.5932783"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"position","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Argues that data science approaches can improve hurricane forecasting beyond traditional statistical methods; methods and results are only vaguely described.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en15031061","title":"Stacked LSTM Sequence-to-Sequence Autoencoder with Feature Selection for Daily Solar Radiation Prediction: A Review and New Modeling Results","authors":["Sujan Ghimire","Ravinesh Chand Deo","Hua Wang","Mohanad S. AL‐Musaylh","David Casillas-Pérez","Sancho Salcedo‐Sanz"],"date":"2022-01-31","year":2022,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en15031061","openalex":"W4210605514"},"links":{"paper":"https://doi.org/10.3390/en15031061","pdf":"https://www.mdpi.com/1996-1073/15/3/1061/pdf?version=1644394307"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations","cmip"],"status":"research","summary":"A stacked LSTM autoencoder with feature selection gives daily solar radiation prediction intervals at six Queensland farms, outperforming tree ensembles and persistence.","significance":2,"cited_by":98,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13020243","title":"South America Seasonal Precipitation Prediction by Gradient-Boosting Machine-Learning Approach","authors":["Vinicius Schmidt Monego","Juliana Aparecida Anochi","Haroldo Fraga de Campos Velho"],"date":"2022-01-31","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13020243","openalex":"W4210802227"},"links":{"paper":"https://doi.org/10.3390/atmos13020243","pdf":"https://www.mdpi.com/2073-4433/13/2/243/pdf?version=1644487156"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Applies gradient-boosted trees with Optuna tuning to seasonal precipitation over South America, outperforming INPE numerical models in some cases.","significance":3,"cited_by":44,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.13408","title":"Extreme precipitation forecasting using attention augmented convolutions","authors":["Weichen Huang"],"date":"2022-01-31","year":2022,"venue_type":"preprint","ids":{"arxiv":"2201.13408","openalex":"W4226143467"},"links":{"paper":"https://arxiv.org/abs/2201.13408","pdf":"https://arxiv.org/pdf/2201.13408"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["transformer","cnn"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Self-attention augmented convolutions with a highway layer forecast extreme precipitation up to 12 hours ahead from pressure and wind, outperforming CNNs by 12%.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11042-021-11794-z","title":"ArDHO-deep RNN: autoregressive deer hunting optimization based deep recurrent neural network in investigating atmospheric and oceanic parameters","authors":["Sundeep Raj","Sandesh Tripathi","K. C. Tripathi"],"date":"2022-01-28","year":2022,"venue":"Multimedia Tools and Applications","venue_type":"journal","ids":{"doi":"10.1007/s11042-021-11794-z","openalex":"W4220722253"},"links":{"paper":"https://doi.org/10.1007/s11042-021-11794-z"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","classical-ml","other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Proposes an optimized deep recurrent network for predicting atmospheric and oceanic parameters; the abstract is missing, so the claims cannot be verified.","significance":1,"cited_by":14,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-731-2022","title":"EuLerian Identification of ascending AirStreams (ELIAS 2.0) in numerical weather prediction and climate models – Part 2: Model application to different datasets","authors":["Julian Quinting","Christian Michael Grams","Annika Oertel","Moritz Pickl"],"date":"2022-01-27","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-731-2022","openalex":"W4210358850"},"links":{"paper":"https://doi.org/10.5194/gmd-15-731-2022"},"orgs":["kit"],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Applies the CNN warm conveyor belt identifier to reanalyses and ECMWF ensembles, showing CNN and trajectory methods agree on North Atlantic forecast biases.","significance":3,"cited_by":23,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-15-715-2022","title":"EuLerian Identification of ascending AirStreams (ELIAS 2.0) in numerical weather prediction and climate models – Part 1: Development of deep learning model","authors":["Julian Quinting","Christian Michael Grams"],"date":"2022-01-27","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-15-715-2022","openalex":"W4210730244"},"links":{"paper":"https://doi.org/10.5194/gmd-15-715-2022"},"orgs":["kit"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","nwp-analysis","cmip"],"status":"research","summary":"CNNs predict warm conveyor belt inflow, ascent and outflow footprints from gridded fields, reproducing trajectory-based climatology at much lower computational cost.","significance":4,"cited_by":30,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14030604","title":"Experimental Study of Cloud-to-Ground Lightning Nowcasting with Multisource Data Based on a Video Prediction Method","authors":["Shuchang Guo","Jinyan Wang","Ruhui Gan","Zhida Yang","Yi Yang"],"date":"2022-01-27","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14030604","openalex":"W4210548549"},"links":{"paper":"https://doi.org/10.3390/rs14030604","pdf":"https://www.mdpi.com/2072-4292/14/3/604/pdf?version=1644309175"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"CLSTM-LFN video-prediction model fuses lightning history with NWP variables to forecast 0-3 h cloud-to-ground lightning areas, outperforming parameterization schemes.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10483-022-2822-9","title":"A station-data-based model residual machine learning method for fine-grained meteorological grid prediction","authors":["Chuansai Zhou","Haochen Li","Yu Chen","Jiangjiang Xia","Pingwen Zhang"],"date":"2022-01-27","year":2022,"venue":"Applied Mathematics and Mechanics","venue_type":"journal","ids":{"doi":"10.1007/s10483-022-2822-9","openalex":"W4210757498"},"links":{"paper":"https://doi.org/10.1007/s10483-022-2822-9","pdf":"https://link.springer.com/content/pdf/10.1007/s10483-022-2822-9.pdf"},"orgs":["iap-cas"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"Model residual machine learning uses station forecasts to fit ECMWF residuals, producing high-resolution grids of temperature, humidity and wind that beat interpolation.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13020192","title":"MCCS-LSTM: Extracting Full-Image Contextual Information and Multi-Scale Spatiotemporal Feature for Radar Echo Extrapolation","authors":["Huantong Geng","Liangchao Geng"],"date":"2022-01-25","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13020192","openalex":"W4229023256"},"links":{"paper":"https://doi.org/10.3390/atmos13020192","pdf":"https://www.mdpi.com/2073-4433/13/2/192/pdf?version=1643118022"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"MCCS-LSTM adds criss-cross attention and multi-scale spatiotemporal blocks to radar echo extrapolation, improving accuracy at longer lead times on CIKM and Guangdong radar data.","significance":3,"cited_by":13,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.10544","title":"A deep mixture density network for outlier-corrected interpolation of crowd-sourced weather data","authors":["Charlie Kirkwood","Theo Economou","Henry Odbert","Nicolas Pugeault"],"date":"2022-01-25","year":2022,"venue_type":"preprint","ids":{"arxiv":"2201.10544"},"links":{"paper":"https://arxiv.org/abs/2201.10544","pdf":"https://arxiv.org/pdf/2201.10544"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"A Gaussian-uniform mixture density network interpolates crowd-sourced UK station temperatures while automatically rejecting spurious observations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.10123","title":"Analysis of various climate change parameters in India using machine learning","authors":["Rutvij Wamanse","Tushuli Patil"],"date":"2022-01-25","year":2022,"venue_type":"preprint","ids":{"arxiv":"2201.10123"},"links":{"paper":"https://arxiv.org/abs/2201.10123","pdf":"https://arxiv.org/pdf/2201.10123"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies linear, exponential and polynomial regression to 17 Indian climate parameters, projecting values to 2025–2035; a basic trend-extrapolation study.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl096408","title":"Machine Learning‐Based Model for Real‐Time GNSS Precipitable Water Vapor Sensing","authors":["Yuxin Zheng","Cuixian Lu","Zhilu Wu","Jianchi Liao","Yushan Zhang","Qiuyi Wang"],"date":"2022-01-24","year":2022,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl096408","openalex":"W4207039706"},"links":{"paper":"https://doi.org/10.1029/2021gl096408"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Stacked machine learning maps GNSS zenith delays to precipitable water vapor without meteorological inputs, achieving under 2.5 mm accuracy and 22-28% gains over GPT3.","significance":3,"cited_by":57,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13020180","title":"Machine Learning in Weather Prediction and Climate Analyses—Applications and Perspectives","authors":["Bogdan Bochenek","Zbigniew Ustrnul"],"date":"2022-01-23","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13020180","openalex":"W4206973253"},"links":{"paper":"https://doi.org/10.3390/atmos13020180","pdf":"https://www.mdpi.com/2073-4433/13/2/180/pdf?version=1642933984"},"orgs":[],"topic":"benchmarks-data-eval","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Bibliometric review of about 500 papers on ML for weather prediction and climate analysis, mapping topics, methods, variables and countries since 2018.","significance":3,"cited_by":330,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.09101","title":"HiSTGNN: Hierarchical Spatio-temporal Graph Neural Networks for Weather Forecasting","authors":["Minbo Ma","Peng Xie","Fei Teng","Tianrui Li","Bin Wang","Shenggong Ji","Junbo Zhang"],"date":"2022-01-22","year":2022,"venue":"Information Sciences","venue_type":"journal","ids":{"arxiv":"2201.09101","doi":"10.1016/j.ins.2023.119580","openalex":"W4221150816"},"links":{"paper":"https://doi.org/10.1016/j.ins.2023.119580","pdf":"https://arxiv.org/pdf/2201.09101"},"orgs":["tencent"],"topic":"local-forecasting","topics":[],"type":"model","method":["gnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"HiSTGNN uses hierarchical spatio-temporal graphs over station meteorological variables, reducing forecast errors by 4.2% to 11.6% versus baselines.","significance":3,"cited_by":96,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.10041","title":"A novel ensemble learning for post-processing of NWP Model's next-day maximum air temperature forecast in summer using deep learning and statistical approaches","authors":["Dongjin Cho","Cheolhee Yoo","Bokyung Son","Jungho Im","Donghyuck Yoon","Dong‐Hyun Cha"],"date":"2022-01-21","year":2022,"venue":"Weather and Climate Extremes","venue_type":"journal","ids":{"arxiv":"2022.10041","doi":"10.1016/j.wace.2022.100410","openalex":"W4206958054"},"links":{"paper":"https://doi.org/10.1016/j.wace.2022.100410"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml","rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Skill-score-weighted ensemble of MLR, SVR, GRU and CNN post-processors corrects LDAPS next-day maximum temperature, with CNN reaching 1.41 °C RMSE in South Korea.","significance":3,"cited_by":53,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-21-0099.1","title":"To Accurately and Lightly Downscale the Temperature Field by Deep Learning","authors":["Ruian Tie","Chunxiang Shi","Gang Wan","Lihua Kang","Lingling Ge"],"date":"2022-01-20","year":2022,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-21-0099.1","openalex":"W4206542980"},"links":{"paper":"https://doi.org/10.1175/jtech-d-21-0099.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atot/39/4/JTECH-D-21-0099.1.pdf"},"orgs":["cma"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Light-CLDASSD, a lightweight deep model with station data, downscales temperature from 1/16° to 0.01° and beats HRCLDAS by 0.08 °C RMSE.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10510222.1","title":"Improving the forecasting of winter crop yields in northern China with machine learning-dynamical hybrid subseasonal-to-seasonal ensemble prediction","authors":["Huijing Wang","Junjun Cao","Jinxiao Li","Qun Tian","Dev Niyogi"],"date":"2022-01-20","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10510222.1","openalex":"W4207023316"},"links":{"paper":"https://doi.org/10.1002/essoar.10510222.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10510222.1"},"orgs":["iap-cas","cma"],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Hybrid machine learning and S2S dynamical forecasts improve northern China winter wheat yield prediction over observation-based inputs.","significance":3,"cited_by":22,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.10672","title":"Classification of cloud images by using super resolution, semantic segmentation approaches and binary sailfish optimization method with deep learning model","authors":["Mesut Toğaçar","Burhan Ergen"],"date":"2022-01-20","year":2022,"venue":"Computers and Electronics in Agriculture","venue_type":"journal","ids":{"arxiv":"2022.10672","doi":"10.1016/j.compag.2022.106724","openalex":"W4206300742"},"links":{"paper":"https://doi.org/10.1016/j.compag.2022.106724"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Deep-learning pipeline with super-resolution and segmentation classifies cloud images; the abstract is missing, so scope is uncertain and significance is low.","significance":1,"cited_by":23,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ef002455","title":"Reduced Tropical Cyclone Genesis in the Future as Predicted by a Machine Learning Model","authors":["Qifeng Qian","Xiaojing Jia","Yanluan Lin"],"date":"2022-01-19","year":2022,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2021ef002455","openalex":"W4206254430"},"links":{"paper":"https://doi.org/10.1029/2021ef002455","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021EF002455"},"orgs":["tsinghua-university","cma"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Uses a MaxEnt model on environmental variables to project a significant decline in future tropical cyclone genesis across CMIP6 SSP scenarios, with a nonlinear link to potential intensity.","significance":3,"cited_by":13,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.11919","title":"Machine Learning Emulation of 3D Cloud Radiative Effects","authors":["David Meyer","Robin James Hogan","Peter Dominik Dueben","Shannon Mason"],"date":"2022-01-18","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2103.11919","doi":"10.1029/2021ms002550","openalex":"W3137372730"},"links":{"paper":"https://doi.org/10.1029/2021ms002550","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002550"},"orgs":["ecmwf","university-of-reading"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":[],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Neural networks correct the ecRad 1D radiation scheme for 3D cloud effects, recovering 3D signal with 20-30% error at about 1% extra runtime versus the 5x costlier SPARTACUS.","significance":4,"cited_by":43,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14020426","title":"A Novel Tropical Cyclone Size Estimation Model Based on a Convolutional Neural Network Using Geostationary Satellite Imagery","authors":["You-Hyun Baek","Il‐Ju Moon","Jungho Im","Ju‐Hyun Lee"],"date":"2022-01-17","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14020426","openalex":"W4206096691"},"links":{"paper":"https://doi.org/10.3390/rs14020426","pdf":"https://www.mdpi.com/2072-4292/14/2/426/pdf?version=1642578202"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A CNN with multi-task learning on geostationary IR images estimates western North Pacific tropical cyclone RMW and R34 with correlations of 0.95 and 0.93.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14020418","title":"Estimating Boundary Layer Height from LiDAR Data under Complex Atmospheric Conditions Using Machine Learning","authors":["Zhenxing Liu","Jianhua Chang","Hongxu Li","Sicheng Chen","Tengfei Dai"],"date":"2022-01-17","year":2022,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14020418","openalex":"W4205583597"},"links":{"paper":"https://doi.org/10.3390/rs14020418","pdf":"https://www.mdpi.com/2072-4292/14/2/418/pdf?version=1642504260"},"orgs":["nuist"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other","stations"],"status":"research","summary":"Mahalanobis transform K-near-means algorithm retrieves boundary layer height from micropulse LiDAR under cloudy conditions, matching radiosonde references better than three baselines.","significance":2,"cited_by":22,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7528","title":"Assimilating an expanded tree ring dataset to reconstruct the millennial air temperature fields for the Northern Hemisphere","authors":["Miao Fang","Jingyun Zheng","Jianglin Wang","Haifeng Zhu","Xuezhen Zhang"],"date":"2022-01-17","year":2022,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7528","openalex":"W4205229174"},"links":{"paper":"https://doi.org/10.1002/joc.7528"},"orgs":[],"topic":"climate-analysis-attribution","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Paleoclimate data assimilation with ANN proxy system models produces a millennial, spatially continuous Northern Hemisphere temperature reconstruction from tree rings.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.06173","title":"SunCast: Solar Irradiance Nowcasting from Geosynchronous Satellite Data","authors":["Dhileeban Kumaresan","Richard Wang","Ernesto Martinez","Richard Cziva","Alberto Todeschini","Colorado J Reed","Hossein Vahabi"],"date":"2022-01-17","year":2022,"venue_type":"preprint","ids":{"arxiv":"2201.06173","openalex":"W3211878498"},"links":{"paper":"https://arxiv.org/abs/2201.06173","pdf":"https://arxiv.org/pdf/2201.06173"},"orgs":["uc-berkeley"],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A ConvLSTM treats GOES satellite-based solar irradiance nowcasting as next-frame prediction, reaching 120 W/m2 RMSE for North America up to 3 hours ahead without a GPU.","significance":3,"cited_by":2,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54302-mausam.v73i1.5083","title":"Artificial neural network model for precipitation forecast over Western Himalaya using satellite images","authors":["Piyush Joshi","M. S. Shekhar","Ashavani Kumar","Jitender Kumar Quamara"],"date":"2022-01-15","year":2022,"venue":"MAUSAM","venue_type":"journal","ids":{"doi":"10.54302/mausam.v73i1.5083","openalex":"W4206130121"},"links":{"paper":"https://doi.org/10.54302/mausam.v73i1.5083","pdf":"https://mausamjournal.imd.gov.in/index.php/MAUSAM/article/download/5083/4795"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["satellite","stations"],"status":"pre-operational","summary":"An ANN trained on Kalpana IR and water-vapour satellite pixel values forecasts 24-hour precipitation at six Western Himalaya stations with a 0.78-0.95 probability of detection.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10510164.1","title":"How to calibrate a climate model with neural network based physics?","authors":["Blanka Balogh","David Saint‐Martin","Aurélien Ribes"],"date":"2022-01-14","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10510164.1","openalex":"W4226487331"},"links":{"paper":"https://doi.org/10.1002/essoar.10510164.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10510164.1"},"orgs":["meteo-france"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":[],"data":["other"],"status":"research","summary":"Proposes tunable neural-network climate parameterizations calibrated online against long-term statistics, reducing long-term biases of the ML model in a simple dynamical system.","significance":4,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.07000","title":"TCR-GAN: Predicting tropical cyclone passive microwave rainfall using infrared imagery via generative adversarial networks","authors":["Fan Meng","Tao Song","Danya Xu"],"date":"2022-01-14","year":2022,"venue_type":"preprint","ids":{"arxiv":"2201.07000","openalex":"W4226255285"},"links":{"paper":"https://arxiv.org/abs/2201.07000","pdf":"https://arxiv.org/pdf/2201.07000"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"TCR-GAN converts geostationary infrared images of tropical cyclones into passive microwave rainfall fields and releases a new benchmark dataset (TCIRRP).","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.00827","title":"Parameter Uncertainty Quantification in an Idealized GCM With a Seasonal Cycle","authors":["Michael F. Howland","Oliver R. A. Dunbar","Tapio Schneider"],"date":"2022-01-14","year":2022,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2108.00827","doi":"10.1029/2021ms002735","openalex":"W4226079007"},"links":{"paper":"https://doi.org/10.1029/2021ms002735","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002735"},"orgs":["caltech","mit"],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Calibrating a convection parameterization with seasonally averaged statistics cuts calibration error up to tenfold and narrows posterior spread by two to five times in an idealized GCM.","significance":3,"cited_by":30,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10510142.1","title":"Ensemble-Based Experimental Design for Targeted High-Resolution Simulations to Inform Climate Models","authors":["Oliver R. A. Dunbar","Michael F. Howland","Tapio Schneider","Andrew M. Stuart"],"date":"2022-01-13","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10510142.1","openalex":"W4206017582"},"links":{"paper":"https://doi.org/10.1002/essoar.10510142.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10510142.1"},"orgs":["mit","caltech"],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"An ensemble-based experimental design algorithm, using calibrate-emulate-sample, chooses high-resolution simulation regions that most reduce uncertainty in GCM convection parameters, with 10^2 rather than 10^5 model runs.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10510140.1","title":"Super Resolution Reconstruction of E3SM Data Using a FSRCNN","authors":["Linsey Sara Passarella","Salil Mahajan","Anikesh Pal","Matthew Ross Norman"],"date":"2022-01-13","year":2022,"venue_type":"other","ids":{"doi":"10.1002/essoar.10510140.1","openalex":"W4225934569"},"links":{"paper":"https://doi.org/10.1002/essoar.10510140.1"},"orgs":["ornl"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"FSRCNN-ESM, a modified fast super-resolution CNN, downscales E3SM climate output from 1° to 0.25° over North America with better accuracy than baselines.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.05663","title":"Upward Lightning at the Gaisberg Tower: Initiation Mechanism and Flash Type and the Atmospheric Influence","authors":["Isabell Stucke","Deborah Morgenstern","Gerhard Diendorfer","Georg J. Mayr","Hannes Pichler","Wolfgang Schulz","Thorsten Simon","Achim Zeileis"],"date":"2022-01-13","year":2022,"venue_type":"preprint","ids":{"arxiv":"2201.05663","doi":"10.1029/2022jd037776"},"links":{"paper":"https://arxiv.org/abs/2201.05663","pdf":"https://arxiv.org/pdf/2201.05663"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["era5","stations"],"status":"research","summary":"A random forest on ERA5 variables shows self-initiated upward lightning at a tall tower depends mainly on the height of the -10 C isotherm.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.07950","title":"Convolutional conditional neural processes for local climate downscaling","authors":["Anna Vaughan","Will Tebbutt","J. Scott Hosking","Richard E. Turner"],"date":"2022-01-13","year":2022,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"2101.07950","doi":"10.5194/gmd-15-251-2022","openalex":"W3124663847"},"links":{"paper":"https://doi.org/10.5194/gmd-15-251-2022"},"orgs":["alan-turing-institute","university-of-cambridge"],"topic":"downscaling","topics":["probabilistic-ensembles"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Convolutional conditional neural processes provide off-grid multisite temperature and precipitation downscaling over Europe, beating existing methods and improving extreme precipitation representation.","significance":4,"cited_by":47,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.12745","title":"Extreme precipitation prediction based on neural network model – A case study for southeastern Brazil","authors":["André de Sousa Araújo","Adma Raia","Luis Enrique Zárate"],"date":"2022-01-13","year":2022,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"arxiv":"2022.12745","doi":"10.1016/j.jhydrol.2022.127454","openalex":"W4205099694"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2022.127454"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Applies neural network models to predict extreme precipitation events in southeastern Brazil; the abstract is unavailable, so results are unknown.","significance":2,"cited_by":38,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.10819","title":"A neural network framework for fine-grained tropical cyclone intensity prediction","authors":["Zhe Zhang","Xuying Yang","Lingfei Shi","Bingbing Wang","Zhenhong Du","Feng Zhang","Renyi Liu"],"date":"2022-01-13","year":2022,"venue":"Knowledge-Based Systems","venue_type":"journal","ids":{"arxiv":"2022.10819","doi":"10.1016/j.knosys.2022.108195","openalex":"W4206634332"},"links":{"paper":"https://doi.org/10.1016/j.knosys.2022.108195"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":[],"status":"research","summary":"Proposes a neural network framework for fine-grained tropical cyclone intensity prediction; the abstract is unavailable, so details are limited.","significance":3,"cited_by":57,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2021.11043","title":"Artificial intelligence for hurricane storm surge hazard assessment","authors":["Mahmoud Ayyad","Muhammad R. Hajj","Reza Marsooli"],"date":"2022-01-11","year":2022,"venue":"Ocean Engineering","venue_type":"journal","ids":{"arxiv":"2021.11043","doi":"10.1016/j.oceaneng.2021.110435","openalex":"W4206271087"},"links":{"paper":"https://doi.org/10.1016/j.oceaneng.2021.110435"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies artificial intelligence to hurricane storm surge hazard assessment; abstract unavailable, so significance and scope are low-confidence.","significance":2,"cited_by":37,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.02928","title":"Frame invariant neural network closures for Kraichnan turbulence","authors":["Suraj Pawar","Omer San","Adil Rasheed","Prakash Vedula"],"date":"2022-01-09","year":2022,"venue":"Physica A Statistical Mechanics and its Applications","venue_type":"journal","ids":{"arxiv":"2201.02928","doi":"10.1016/j.physa.2022.128327","openalex":"W4221149404"},"links":{"paper":"https://doi.org/10.1016/j.physa.2022.128327","pdf":"https://arxiv.org/pdf/2201.02928"},"orgs":["university-of-oklahoma"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Symmetry-preserving CNN subgrid closures for 2D Kraichnan turbulence respect translation, Galilean and rotation invariance and stay stable in coarse simulations.","significance":3,"cited_by":20,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2022-5386341","title":"Health Monitoring Framework for Weather Radar Based on Long Short-Term Memory Network with a Real Case Study","authors":["Wei Li","Dalin Wang","Wei Zhou","Yimeng Wang","Chao Shen"],"date":"2022-01-07","year":2022,"venue":"Journal of Sensors","venue_type":"journal","ids":{"doi":"10.1155/2022/5386341","openalex":"W4205761860"},"links":{"paper":"https://doi.org/10.1155/2022/5386341","pdf":"https://downloads.hindawi.com/journals/js/2022/5386341.pdf"},"orgs":["tsinghua-university","cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"pre-operational","summary":"An LSTM-based health monitoring framework for CINRAD-SA weather radar flags early faults from deviations between predicted and measured monitoring parameters, reducing false alarms.","significance":2,"cited_by":1,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.02596","title":"Explainable deep learning for insights in El Niño and river flows","authors":["Yumin Liu","Kate Duffy","Jennifer G. Dy","Auroop R. Ganguly"],"date":"2022-01-07","year":2022,"venue":"Nat Commun 14, 339 (2023)","venue_type":"journal","ids":{"arxiv":"2201.02596","doi":"10.1038/s41467-023-35968-5","openalex":"W4317603815"},"links":{"paper":"https://arxiv.org/abs/2201.02596","pdf":"https://arxiv.org/pdf/2201.02596"},"orgs":["nasa"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global","regional"],"data":["era5","cmip","other"],"status":"research","summary":"Saliency-map explainable deep learning on global SST reveals ENSO-related information beyond indices and improves river flow prediction with uncertainty estimates.","significance":4,"cited_by":51,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos13010088","title":"Radar Echo Spatiotemporal Sequence Prediction Using an Improved ConvGRU Deep Learning Model","authors":["Wei He","Taisong Xiong","Hao Wang","Jianxin He","Xinyue Ren","Yilin Yan","Linyin Tan"],"date":"2022-01-06","year":2022,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos13010088","openalex":"W4205701977"},"links":{"paper":"https://doi.org/10.3390/atmos13010088","pdf":"https://www.mdpi.com/2073-4433/13/1/88/pdf?version=1642041151"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Proposes M-ConvGRU, a convolutional GRU with an encoder-forecaster design for radar echo prediction, cutting MAE 6.29% and MSE 10.25% versus ConvLSTM.","significance":3,"cited_by":25,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2022.214","title":"A statistical bias correction technique for global climate model predicted near-surface temperature in India using the generalized regression neural network","authors":["Diljit Dutta","Rajib Kumar Bhattacharjya"],"date":"2022-01-06","year":2022,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2022.214","openalex":"W4206200659"},"links":{"paper":"https://doi.org/10.2166/wcc.2022.214","pdf":"https://iwaponline.com/jwcc/article-pdf/13/2/854/1013868/jwc0130854.pdf"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"A generalized regression neural network bias-corrects CNRM-CM5 near-surface temperature over India, and the trained model is applied to RCP4.5 and RCP8.5 projections to 2100.","significance":3,"cited_by":17,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2022eo220015","title":"The AI Forecaster: Machine Learning Takes on Weather Prediction","authors":["Aaron Sidder"],"date":"2022-01-06","year":2022,"venue":"Eos","venue_type":"journal","ids":{"doi":"10.1029/2022eo220015","openalex":"W4205243269"},"links":{"paper":"https://doi.org/10.1029/2022eo220015"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Eos news piece on a CNN-based approach that produces exceptionally fast global weather forecasts from past weather data.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00521-021-06877-9","title":"Two-stream convolutional LSTM for precipitation nowcasting","authors":["Suting Chen","Xin Xu","Yanyan Zhang","Dongwei Shao","Song Zhang","Mingjian Zeng"],"date":"2022-01-06","year":2022,"venue":"Neural Computing and Applications","venue_type":"journal","ids":{"doi":"10.1007/s00521-021-06877-9","openalex":"W4206430005"},"links":{"paper":"https://doi.org/10.1007/s00521-021-06877-9"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Proposes a two-stream convolutional LSTM for radar-based precipitation nowcasting, combining two input streams to improve echo map prediction.","significance":3,"cited_by":28,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35842-ijicom.v3i2.35","title":"Weather Forecasting Analysis using Bayesian Regularization Algorithms","authors":["Indo Intan"],"date":"2022-01-05","year":2022,"venue":"International Journal of Informatics and Computation","venue_type":"journal","ids":{"doi":"10.35842/ijicom.v3i2.35","openalex":"W4289925480"},"links":{"paper":"https://doi.org/10.35842/ijicom.v3i2.35","pdf":"https://ijicom.respati.ac.id/index.php/ijicom/article/download/35/26"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies Bayesian-regularized neural networks to weather forecasting, reporting improved accuracy with more training data but no quantified headline result.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13369-021-06457-y","title":"BP Neural Network for Typhoon Warning and Prevention for Historical Buildings","authors":["Wang Chen","Yutong Tang","Mukhtar A. Kassem","Heng Li","Chen Ming Yan"],"date":"2022-01-05","year":2022,"venue":"Arabian Journal for Science and Engineering","venue_type":"journal","ids":{"doi":"10.1007/s13369-021-06457-y","openalex":"W4206626137"},"links":{"paper":"https://doi.org/10.1007/s13369-021-06457-y"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Uses a backpropagation neural network for typhoon warning relevant to historical buildings; the abstract is unavailable, so the weather component is unclear.","significance":1,"cited_by":13,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w14010096","title":"Accurate Storm Surge Prediction with a Parametric Cyclone and Neural Network Hybrid Model","authors":["Wei-Ting Chao","Chih‐Chieh Young"],"date":"2022-01-04","year":2022,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w14010096","openalex":"W4205636176"},"links":{"paper":"https://doi.org/10.3390/w14010096","pdf":"https://www.mdpi.com/2073-4441/14/1/96/pdf?version=1641302361"},"orgs":[],"topic":"extremes-hazards","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A parametric cyclone and neural network hybrid predicts typhoon storm surge at Longdong, Taiwan, with 33–40% lower RMSE than a pure network at 8 h lead.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2201.00417","title":"Non-local parameterization of atmospheric subgrid processes with neural networks","authors":["Peidong Wang","Janni Yuval","Paul A. O'Gorman"],"date":"2022-01-02","year":2022,"venue":"Journal of Advances in Modeling Earth Systems, 14(10), e2022MS002984","venue_type":"journal","ids":{"arxiv":"2201.00417","doi":"10.1029/2022ms002984","openalex":"W4226066465"},"links":{"paper":"https://arxiv.org/abs/2201.00417","pdf":"https://arxiv.org/pdf/2201.00417"},"orgs":["mit"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":[],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Neural-network subgrid parameterizations using non-local 3x3-column inputs improve offline skill, especially for momentum transport, with vertical velocity or divergence as key inputs.","significance":4,"cited_by":41,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7197936449","title":"Post-processing of Ensemble Forecasts of Various Weather and Hydrological Quantities Using Statistical and Machine Learning Methods","authors":["El Ayari Mehrez"],"date":"2022-01-01","year":2022,"venue":"University of Debrecen Electronic Archive (University of Debrecen)","venue_type":"preprint","ids":{"openalex":"W7197936449"},"links":{"paper":"http://hdl.handle.net/2437/331395"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Thesis develops probabilistic post-processing of ensemble forecasts for water level, solar irradiance and total cloud cover using statistical and machine learning methods.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7139865401","title":"画像学習を用いた日本空域における乱気流の予測システムの構築","authors":["ヨシアキ ミヤモト","Yoshiaki Miyamoto","佳明 宮本"],"date":"2022-01-01","year":2022,"venue":"Korean Society of Hazard Mitigation","venue_type":"journal","ids":{"doi":"10.9798/kosham.2018.18.2.483","openalex":"W7139865401"},"links":{"paper":"https://doi.org/10.9798/kosham.2018.18.2.483"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"A deep learning model trained on image-like wind fields around PIREP turbulence reports predicts Japanese airspace turbulence with accuracy comparable to existing grid-point indices.","significance":2,"cited_by":19,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.67228-30713498-ijadsmc-2022pii6x9j","title":"Hybrid CNN–LSTM Models for Weather Forecasting","authors":["Peter Okello"],"date":"2022-01-01","year":2022,"venue":"International Journal of Applied Data Science & Modern Computing","venue_type":"journal","ids":{"doi":"10.67228/30713498/ijadsmc-2022pii6x9j","openalex":"W7171250383"},"links":{"paper":"https://doi.org/10.67228/30713498/ijadsmc-2022pii6x9j","pdf":"https://worldcometresearchgroup.com/index.php/ijadsmc/article/download/143/133"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["cnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Reviews and proposes a hybrid CNN-LSTM pipeline for multi-step meteorological forecasting, reporting that it beats baselines on MAE, RMSE and R2.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54216-jaim.020204","title":"Weather Forecasting over Iraq Using Machine Learning","authors":["Israa Jasim ..","Bashar Talib Al-Nuaimi","Ther Intisar Baker"],"date":"2022-01-01","year":2022,"venue":"Journal of artificial intelligence and metaheuristics.","venue_type":"journal","ids":{"doi":"10.54216/jaim.020204","openalex":"W4366309794"},"links":{"paper":"https://doi.org/10.54216/jaim.020204"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Compares random forest, decision tree and gradient boosting for Iraq weather variables from NASA data; random forest reaches 92% accuracy.","significance":1,"cited_by":8,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54216-ijaaci.010201","title":"Modelling Weather Conditions Using Encoder-Decoder and Attention Based on LSTM Deep Regression Model","authors":["Khder Alakkar","Mostafa Salaheldin Abdelsalam Abotaleb","Amr Ahmed Badr","Аммар Мохаммад Яхья Кади","Abdullah Mohammad Ghazi Al khatib","Bayan Mohamad Alshaib","El-Sayed M. El-Kenawy M. El-Kenawy"],"date":"2022-01-01","year":2022,"venue":"International journal of advances in applied computational intelligence.","venue_type":"journal","ids":{"doi":"10.54216/ijaaci.010201","openalex":"W4293325086"},"links":{"paper":"https://doi.org/10.54216/ijaaci.010201"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Encoder-decoder LSTM outperforms attention LSTM for daily temperature, humidity and sunshine forecasts in Narmadapuram using 1977-2022 station data.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4209-aaqr.220183","title":"Machine Learning Applications to Dust Storms: A Meta-Analysis","authors":["Reem K. Alshammari","Omer Alrwais","Mehmet Sabih Aksoy"],"date":"2022-01-01","year":2022,"venue":"Aerosol and Air Quality Research","venue_type":"journal","ids":{"doi":"10.4209/aaqr.220183","openalex":"W4312533620"},"links":{"paper":"https://doi.org/10.4209/aaqr.220183","pdf":"https://aaqr.org/articles/aaqr-22-04-oa-0183.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Meta-analysis of machine learning for dust storm detection and prediction, finding SVMs dominate satellite detection and SVM/random forests dominate meteorological-data prediction.","significance":2,"cited_by":28,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3934-mbe.2022571","title":"A time series image prediction method combining a CNN and LSTM and its application in typhoon track prediction","authors":["Peng Lü","Ao Sun","Mingyu Xu","Zhenhua Wang","Zongsheng Zheng","Yating Xie","Wenjuan Wang"],"date":"2022-01-01","year":2022,"venue":"Mathematical Biosciences & Engineering","venue_type":"journal","ids":{"doi":"10.3934/mbe.2022571","openalex":"W4292601067"},"links":{"paper":"https://doi.org/10.3934/mbe.2022571"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"DeepTyphoon couples hybrid dilated CNN and LSTM on satellite image sequences to predict typhoon tracks, achieving 64.17 km mean error at 6 hours.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36893-iej.2022.v51i7.032-037","title":"Application of Cloudburst Prediction System: A Review","authors":["Indrakishor","Manish Kumar","Muskan","Vaibhav sharma"],"date":"2022-01-01","year":2022,"venue":"Industrial Engineering Journal","venue_type":"journal","ids":{"doi":"10.36893/iej.2022.v51i7.032-037","openalex":"W4389693070"},"links":{"paper":"https://doi.org/10.36893/iej.2022.v51i7.032-037","pdf":"https://doi.org/10.36893/iej.2022.v51i7.032-037"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"review","method":["cnn","classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"pre-operational","summary":"Reviews a CNN and data-mining based real-time cloudburst prediction system motivated by the 2023 Sikkim flood; no quantitative results reported.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33969-ais.2022040102","title":"Performance Evaluation of Machine Learning Models for Weather Forecasting","authors":["Iliyas Ibrahim Iliyas","Andra Umoru","Adati Elkanah Chahari","Mustapha Mallam Garba"],"date":"2022-01-01","year":2022,"venue":"Journal of Artificial Intelligence and Systems","venue_type":"journal","ids":{"doi":"10.33969/ais.2022040102","openalex":"W4312509337"},"links":{"paper":"https://doi.org/10.33969/ais.2022040102","pdf":"https://iecscience.org/uploads/jpapers/202210/WxoX6qJNAOCYDdfEyUPbTRUX3og3E9IbfSXWb13T.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Compares ridge, random forest, linear regression and decision tree for temperature prediction; the decision tree gets the lowest RMSE of 0.036.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33039-ami.2022.05.001","title":"Weather forecasting using DBSCAN clustering algorithm","authors":["Aida Chefrour"],"date":"2022-01-01","year":2022,"venue":"˜Az œEszterházy Károly Tanárképző Főiskola tudományos közleményei. Tanulmányok a matematikai tudományok köréből/˜Az œEszterházy Károly Főiskola tudományos közleményei. Tanulmányok a matematikai tudományok köréből/Annales mathematicae et informaticae","venue_type":"journal","ids":{"doi":"10.33039/ami.2022.05.001","openalex":"W4285219016"},"links":{"paper":"https://doi.org/10.33039/ami.2022.05.001"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Combines DBSCAN clustering with an ANN to group meteorological parameters and forecast weather in Annaba, Algeria, with no quantified headline result.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3178-hrl.16.67","title":"Use of deep learning to identify optimal meteorological inputs to forecast seasonal precipitation","authors":["Shingo Zenkoji","Taichi TEBAKARI","Kazutoshi Sakakibara"],"date":"2022-01-01","year":2022,"venue":"Hydrological Research Letters","venue_type":"journal","ids":{"doi":"10.3178/hrl.16.67","openalex":"W4312705051"},"links":{"paper":"https://doi.org/10.3178/hrl.16.67","pdf":"https://www.jstage.jst.go.jp/article/hrl/16/3/16_67/_pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"application","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Deep learning with optimized meteorological inputs predicts Thailand's seasonal precipitation two months ahead, with El Niño monitoring regions identified as key predictors.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25103-jestr.154.16","title":"Ensemble-based Model for Rainfall Nowcasting using Automatic Weather Station Data","authors":["Nita H. Shah","Bipasha Paul Shukla","Anupam Priamvada"],"date":"2022-01-01","year":2022,"venue":"Journal of Engineering Science and Technology Review","venue_type":"journal","ids":{"doi":"10.25103/jestr.154.16","openalex":"W4296504865"},"links":{"paper":"https://doi.org/10.25103/jestr.154.16","pdf":"https://doi.org/10.25103/jestr.154.16"},"orgs":[],"topic":"nowcasting","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random Forest and XGBoost ensembles trained on automatic weather station data predict 2-4 hour rainfall occurrence with about 80% accuracy.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.24138-jcomss-2022-0092","title":"In Search of Micromodels: Black-box Evaluation of Spatio-temporal Models in Normal and Extreme Conditions","authors":["Ivana Nižetić Kosović","Toni Mastelić","Domina Sokol","Diana Škurić Kuražić"],"date":"2022-01-01","year":2022,"venue":"Journal of Communications Software and Systems","venue_type":"journal","ids":{"doi":"10.24138/jcomss-2022-0092","openalex":"W4313128072"},"links":{"paper":"https://doi.org/10.24138/jcomss-2022-0092","pdf":"https://jcoms.fesb.unist.hr/pdfs/v18n3_2022-0092_nizetic_kosovic.pdf"},"orgs":[],"topic":"benchmarks-data-eval","topics":[],"type":"evaluation","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Black-box evaluation of NWP temperature and precipitation outputs under normal and extreme conditions to find scenarios for lightweight data-driven micromodels on Edge devices.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2208-jscejoe.78.2-i-475","title":"STUDY ON CORRECTION METHOD OF WIND FIELD FOR EMPIRICAL TYPHOON MODEL USING NEURAL NETWORK","authors":["Yoshihiko Ide","Takumi KORA","Masaru YAMASHIRO","Noriaki Hashimoto","Mitsuyoshi KODAMA"],"date":"2022-01-01","year":2022,"venue":"Journal of Japan Society of Civil Engineers Ser B3 (Ocean Engineering)","venue_type":"journal","ids":{"doi":"10.2208/jscejoe.78.2_i_475","openalex":"W4312647315"},"links":{"paper":"https://doi.org/10.2208/jscejoe.78.2_i_475","pdf":"https://www.jstage.jst.go.jp/article/jscejoe/78/2/78_I_475/_pdf"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A neural network corrects empirical typhoon model wind fields toward JMA mesoscale model output, enabling more realistic storm surge simulation for Typhoon 10 (2020).","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2151-jmsj.2022-048","title":"Tropical Cyclone Size Identification over the Western North Pacific Using Support Vector Machine and General Regression Neural Network","authors":["Xiaoqin Lu","Wai Kin Wong","Hui Yu","Xiaoming Yang"],"date":"2022-01-01","year":2022,"venue":"Journal of the Meteorological Society of Japan Ser II","venue_type":"journal","ids":{"doi":"10.2151/jmsj.2022-048","openalex":"W4293766037"},"links":{"paper":"https://doi.org/10.2151/jmsj.2022-048","pdf":"https://www.jstage.jst.go.jp/article/jmsj/advpub/0/advpub_2022-048/_pdf"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"SVM and general regression neural network models estimate western North Pacific tropical cyclone size parameters (RMW, R34, R50, R64) from infrared satellite imagery.","significance":2,"cited_by":26,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4266659","title":"Machine Learning-Inspired Weather Forecasting for Solar Photovoltaic Potential","authors":["Chika  Calistus Maduabuchi","Chinedu Candidus Nsude","Chibuoke Eneh","Emmanuel T. Eke","Kingsley Okoli","Emmanuel Okpara","Christian Idogho","Catur Harsito"],"date":"2022-01-01","year":2022,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4266659","openalex":"W4312763291"},"links":{"paper":"https://doi.org/10.2139/ssrn.4266659"},"orgs":["university-of-oklahoma"],"topic":"applications-impacts","topics":[],"type":"application","method":[],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Title-only record for ML-inspired weather forecasting applied to solar PV potential; no abstract is available to confirm methods or results.","significance":1,"cited_by":5,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4144317","title":"Nowcasting Extreme Weather with Machine Learning Techniques Applied to Different Input Datasets","authors":["Riccardo Biondi","Sandy Chkeir","Aikaterini Anesiadou","Alessandra Mascitelli"],"date":"2022-01-01","year":2022,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4144317","openalex":"W4285152439"},"links":{"paper":"https://doi.org/10.2139/ssrn.4144317"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":[],"timescale":["nowcast"],"spatial":[],"data":["other"],"status":"research","summary":"Applies machine learning to nowcast extreme weather using different input datasets; no abstract available, so details are inferred from the title.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4140237","title":"A Literature Review on Improvement of Weather Prediction By Using Machine Learning","authors":["Irshad Hussain","Chetan Waghmare"],"date":"2022-01-01","year":2022,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4140237","openalex":"W4285109831"},"links":{"paper":"https://doi.org/10.2139/ssrn.4140237"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":[],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Literature review of machine learning methods for improving weather prediction; no abstract available, so scope is inferred from the title.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.4075650","title":"Deep Learning-Based Postprocessing of Ecmwf Heavy Rainfall Forecasts","authors":["Qi Liu","Jiangjiang Xia","Yan Yan","Wenguang Wei","Xiao Lou","Zhongwei Yan","Jianli Mu","Bin Yuan","Xiaoliang Yang","Yun Sun"],"date":"2022-01-01","year":2022,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.4075650","openalex":"W4226146707"},"links":{"paper":"https://doi.org/10.2139/ssrn.4075650"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":[],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Applies deep learning to post-process ECMWF forecasts of heavy rainfall, correcting NWP output for extreme precipitation events.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.16993-tellusa.46","title":"A New Ensemble Index for Extracting Predictable Drought Features from Multiple Historical Simulations of Climate","authors":["Sun Yuanbin","Sadia Qamar","Zulfiqar Ali","Tao Yang","Amna Nazeer","Rabia Fayyaz"],"date":"2022-01-01","year":2022,"venue":"Tellus A Dynamic Meteorology and Oceanography","venue_type":"journal","ids":{"doi":"10.16993/tellusa.46","openalex":"W4226180054"},"links":{"paper":"https://doi.org/10.16993/tellusa.46"},"orgs":["tsinghua-university"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Proposes MMFSDI, a multi-model drought index built with forecastable component analysis and Gaussian mixtures over 23 CMIP6 models on the Tibetan Plateau, consistent with SPI.","significance":2,"cited_by":13,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.16993-tellusa.37","title":"Nowcasting Meso-γ-Scale Convective Storms Using Convolutional LSTM Models and High-Resolution Radar Observations","authors":["Dong-Kyun Kim","Tomoo Ushio"],"date":"2022-01-01","year":2022,"venue":"Tellus A Dynamic Meteorology and Oceanography","venue_type":"journal","ids":{"doi":"10.16993/tellusa.37","openalex":"W4226366356"},"links":{"paper":"https://doi.org/10.16993/tellusa.37"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["local","regional"],"data":["radar"],"status":"research","summary":"Convolutional LSTM nowcasts of meso-gamma convective storms from MP-PAWR radar over Tokyo; the ConvLSTM beats advection for total rain at 10 min lead time.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1615-jmachlearnmodelcomput.2022046715","title":"A SPATIOTEMPORAL-AWARE WEIGHTING SCHEME FOR IMPROVING CLIMATE MODEL ENSEMBLE PREDICTIONS","authors":["Ming Fan","Dan Lu","Deeksha Rastogi","Eric M. Pierce"],"date":"2022-01-01","year":2022,"venue":"Journal of Machine Learning for Modeling and Computing","venue_type":"journal","ids":{"doi":"10.1615/jmachlearnmodelcomput.2022046715","openalex":"W4312539167"},"links":{"paper":"https://doi.org/10.1615/jmachlearnmodelcomput.2022046715"},"orgs":["ornl"],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A Bayesian neural network ensemble weights CMIP6 models by location and season, calibrating projections to observations with interpretable weights and uncertainty growing away from constrained periods.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1590-1806-9649-2022v29e06","title":"Climate analysis using neural networks as supporting to the agriculture","authors":["Lucas de Carvalho Borella","Margareth Rodrigues de Carvalho Borella","Leandro Luís Corso"],"date":"2022-01-01","year":2022,"venue":"Gestão & Produção","venue_type":"journal","ids":{"doi":"10.1590/1806-9649-2022v29e06","openalex":"W4221087995"},"links":{"paper":"https://doi.org/10.1590/1806-9649-2022v29e06","pdf":"https://www.scielo.br/j/gp/a/tfwsXXjxvbJcH7cSrgLMCRB/?lang=en&format=pdf"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses artificial neural networks on INMET station climate records to forecast temperature and precipitation, linking forecasts to crop planting schedules.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1515-comp-2022-0254","title":"Rainfall prediction system for Bangladesh using long short-term memory","authors":["Mustain Billah","Md. Nasim Adnan","Mostafijur Rahman Akhond","Romana Rahman Ema","Md. Alam Hossain","Syed Md. Galib"],"date":"2022-01-01","year":2022,"venue":"Open Computer Science","venue_type":"journal","ids":{"doi":"10.1515/comp-2022-0254","openalex":"W4312232459"},"links":{"paper":"https://doi.org/10.1515/comp-2022-0254","pdf":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0254/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Two-layer LSTM predicts Bangladesh rainfall from 10 selected features with 97.14% accuracy, outperforming conventional ML baselines; the evaluation is limited.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1299-jsmemecj.2022.w052-02","title":"Application of AI in Atmospheric Science","authors":["Daisuke MATSUOKA"],"date":"2022-01-01","year":2022,"venue":"The Proceedings of Mechanical Engineering Congress Japan","venue_type":"journal","ids":{"doi":"10.1299/jsmemecj.2022.w052-02","openalex":"W4360896156"},"links":{"paper":"https://doi.org/10.1299/jsmemecj.2022.w052-02"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"position","method":["other"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Conference talk on integrating numerical simulation with machine learning for weather forecasting and improving typhoon forecasts through a data competition.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1162-dint-a-00131","title":"HPC-oriented Canonical Workflows for Machine Learning Applications in Climate and Weather Prediction","authors":["Amirpasha Mozaffari","Michael Langguth","Bing Gong","Jessica Ahring","Adrian Rojas Campos","Pascal Nieters","Otoniel José Campos Escobar","Martin Wittenbrink","Peter Baumann","Martin G. Schultz"],"date":"2022-01-01","year":2022,"venue":"Data Intelligence","venue_type":"journal","ids":{"doi":"10.1162/dint_a_00131","openalex":"W4220736327"},"links":{"paper":"https://doi.org/10.1162/dint_a_00131","pdf":"https://direct.mit.edu/dint/article-pdf/4/2/271/2012379/dint_a_00131.pdf"},"orgs":["dwd","juelich"],"topic":"infra-software","topics":[],"type":"position","method":[],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Conceptual proposal for FAIR, reproducible HPC-based workflows for ML weather and precipitation forecasting, using the DeepRain project as a case.","significance":2,"cited_by":11,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11578-dc.20221017.3","title":"MSU Disentanglement Analysis Software","authors":["Stephen Po–Chedley"],"date":"2022-01-01","year":2022,"venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","venue_type":"preprint","ids":{"doi":"10.11578/dc.20221017.3","openalex":"W4391048248"},"links":{"paper":"https://doi.org/10.11578/dc.20221017.3"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Software applies ridge, PLS and neural-network regression, trained across leave-one-out CMIP model ensembles, to separate forced from unforced tropospheric warming using surface temperature maps.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2022-8451812","title":"Machine Learning as a Downscaling Approach for Prediction of Wind Characteristics under Future Climate Change Scenarios","authors":["Abbas Yeganeh Bakhtiary","Hossein Eyvazoghli","Naser Shabakhty","Bahareh Kamranzad","Soroush Abolfathi"],"date":"2022-01-01","year":2022,"venue":"Complexity","venue_type":"journal","ids":{"doi":"10.1155/2022/8451812","openalex":"W4388686047"},"links":{"paper":"https://doi.org/10.1155/2022/8451812","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/2022/8451812"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"An M5' decision tree with model output statistics downscales BNU-ESM CMIP5 output, projecting North Atlantic wind speed declines and a 13–19% drop in wind energy by 2030–2040.","significance":3,"cited_by":64,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2022-5248308","title":"Integrating ANFIS and Qt Framework to Develop a Mobile‐Based Typhoon Rainfall Forecasting System","authors":["Shiu‐Shin Lin","Kai-Yang Zhu","Jun-yuan Wang","Ying-Po Liao"],"date":"2022-01-01","year":2022,"venue":"Wireless Communications and Mobile Computing","venue_type":"journal","ids":{"doi":"10.1155/2022/5248308","openalex":"W4280525838"},"links":{"paper":"https://doi.org/10.1155/2022/5248308","pdf":"https://downloads.hindawi.com/journals/wcmc/2022/5248308.pdf"},"orgs":["microsoft-research"],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"ANFIS models forecast typhoon rainfall at a Tamsui station up to three hours ahead and are packaged in a mobile app, with best RMSE of 7.9 mm.","significance":2,"cited_by":5,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1142-s0218194022500048","title":"Feature Selection and Spatial-Temporal Forecast of Oceanic Niño Index Using Deep Learning","authors":["Jahnavi Jonnalagadda","Mahdi Hashemi"],"date":"2022-01-01","year":2022,"venue":"International Journal of Software Engineering and Knowledge Engineering","venue_type":"journal","ids":{"doi":"10.1142/s0218194022500048","openalex":"W4213445549"},"links":{"paper":"https://doi.org/10.1142/s0218194022500048"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["rnn","cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A convolutional LSTM with backward stepwise feature selection forecasts the Oceanic Niño Index 1 to 12 months ahead, with SST the best predictor.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-5.0081858","title":"Accurate storm surge forecasting using the encoder–decoder long short term memory recurrent neural network","authors":["Long-Hu Bai","Hang Xu"],"date":"2022-01-01","year":2022,"venue":"Physics of Fluids","venue_type":"journal","ids":{"doi":"10.1063/5.0081858","openalex":"W4206720317"},"links":{"paper":"https://doi.org/10.1063/5.0081858"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Encoder-decoder LSTM predicts Florida hurricane storm surge 1 to 12 hours ahead from observed surge and meteorological inputs, outperforming a CNN in all cases.","significance":3,"cited_by":41,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-exp.2022.3","title":"Can machine learning models trained using atmospheric simulation data be applied to observation data?","authors":["Daisuke Matsuoka"],"date":"2022-01-01","year":2022,"venue":"Experimental Results","venue_type":"journal","ids":{"doi":"10.1017/exp.2022.3","openalex":"W4213443161"},"links":{"paper":"https://doi.org/10.1017/exp.2022.3"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":[],"timescale":[],"spatial":["regional"],"data":["satellite","km-scale-sim"],"status":"research","summary":"Tropical cyclone classifiers trained on simulated atmospheric data perform much worse on satellite observations, showing the simulation-observation gap must be bridged.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.4","title":"Modeling and simulating spatial extremes by combining extreme value theory with generative adversarial networks","authors":["Younes Boulaguiem","Jakob Zscheischler A","Edoardo Vignotto","Karin van der Wiel","Sebastian Engelke"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2111.00267","doi":"10.1017/eds.2022.4","openalex":"W4226161429"},"links":{"paper":"https://doi.org/10.1017/eds.2022.4","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/AA3CEBA3CF1EF3C9C8D182C108289D7F/S2634460222000048a.pdf/div-class-title-modeling-and-simulating-spatial-extremes-by-combining-extreme-value-theory-with-generative-adversarial-networks-div.pdf"},"orgs":["knmi"],"topic":"extremes-hazards","topics":["climate-emulation"],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Combines GANs with extreme value theory (evtGAN) to model spatial dependence of temperature and precipitation extremes over western Europe, outperforming classical GANs using a 2000-year simulation.","significance":4,"cited_by":45,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.23","title":"ResDeepD: A residual super-resolution network for deep downscaling of daily precipitation over India","authors":["Sumanta Chandra Mishra Sharma","Adway Mitra"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2022.23","openalex":"W4312875426"},"links":{"paper":"https://doi.org/10.1017/eds.2022.23","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/632DA59857B37DD74318E9C8BED71F4B/S2634460222000231a.pdf/div-class-title-resdeepd-a-residual-super-resolution-network-for-deep-downscaling-of-daily-precipitation-over-india-div.pdf"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"ResDeepD, a residual super-resolution CNN, downscales 1° Indian monsoon rainfall to 0.25° and outperforms SRCNN, DeepSD and Nest-UNet, including during cyclonic storms.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.22","title":"Physics-informed learning of aerosol microphysics","authors":["Paula Harder","Duncan Watson‐Parris","Philip Stier","Dominik Straßel","Nicolas R. Gauger","Janis Keuper"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2207.11786","doi":"10.1017/eds.2022.22","openalex":"W4312716706"},"links":{"paper":"https://doi.org/10.1017/eds.2022.22","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/C468660D2AEE8E25DC3BF507517FF91A/S263446022200022Xa.pdf/div-class-title-physics-informed-learning-of-aerosol-microphysics-div.pdf"},"orgs":["university-of-oxford"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["physics-constrained","classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Neural network emulates the M7 aerosol microphysics scheme in ECHAM-HAM with 77.1% mean R² and up to 64× GPU speed-up, with physical mass constraints.","significance":3,"cited_by":28,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.18","title":"Predicting cyclone landfall using mutual information and dilated recurrent neural network","authors":["Abhijit Mukherjee","Pabitra Mitra"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2022.18","openalex":"W4312840927"},"links":{"paper":"https://doi.org/10.1017/eds.2022.18","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/D4E54B8507F2E31858A8E6CA7476442C/S2634460222000188a.pdf/div-class-title-predicting-cyclone-landfall-using-mutual-information-and-dilated-recurrent-neural-network-div.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Dilated GRU recurrent network with mutual-information feature selection predicts North Indian Ocean cyclone landfall location and intensity 12 to 36 hours ahead.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.17","title":"Detection and attribution of climate change: A deep learning and variational approach","authors":["Constantin Bône","Guillaume Gastineau","Sylvie Thiria","Patrick Gallinari"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2022.17","openalex":"W4312794002"},"links":{"paper":"https://doi.org/10.1017/eds.2022.17","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/110E2AFF9666A50F44339FC56B67BFAE/S2634460222000176a.pdf/div-class-title-detection-and-attribution-of-climate-change-a-deep-learning-and-variational-approach-div.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip","stations"],"status":"research","summary":"A CNN emulator plus variational inversion attributes 1900–2014 warming to greenhouse gases (0.8–1.9 °C in 2014), aerosols and natural forcings.","significance":4,"cited_by":3,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.15","title":"Statistical mechanics in climate emulation: Challenges and perspectives","authors":["Ivan Sudakow","Michael Pokojovy","Dmitry A. Lyakhov"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2022.15","openalex":"W4312992034"},"links":{"paper":"https://doi.org/10.1017/eds.2022.15","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/637D69E34EC9C18B7E4B37231DED96A2/S2634460222000152a.pdf/div-class-title-statistical-mechanics-in-climate-emulation-challenges-and-perspectives-div.pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"position","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Perspective arguing that climate emulators grounded in statistical mechanics and machine learning can better capture physics, tipping points, and reduce computational cost.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.13","title":"Advancing interpretability of machine-learning prediction models","authors":["Laurie Trenary","Timothy DelSole"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2022.13","openalex":"W4313010265"},"links":{"paper":"https://doi.org/10.1017/eds.2022.13","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/3B15487EAC5F768F21672D0F2A94BBC0/S2634460222000139a.pdf/div-class-title-advancing-interpretability-of-machine-learning-prediction-models-div.pdf"},"orgs":[],"topic":"xai-uq-physics","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Introduces a skill-decomposition method for ML week 3–4 forecasts, finding western US temperature patterns predictable mainly through Pacific ENSO-related SST variability.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1017-eds.2022.11","title":"A spatiotemporal stochastic climate model for benchmarking causal discovery methods for teleconnections","authors":["Xavier‐Andoni Tibau","Christian Reimers","Andreas Gerhardus","Joachim Denzler","Veronika Eyring","Jakob Runge"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"doi":"10.1017/eds.2022.11","openalex":"W4312827554"},"links":{"paper":"https://doi.org/10.1017/eds.2022.11","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/0E066B8813BA2281D2B95279EF3272B4/S2634460222000115a.pdf/div-class-title-a-spatiotemporal-stochastic-climate-model-for-benchmarking-causal-discovery-methods-for-teleconnections-div.pdf"},"orgs":[],"topic":"benchmarks-data-eval","topics":["climate-analysis-attribution"],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A stochastic vector-autoregressive climate model generates gridded teleconnection benchmarks for causal discovery, plus a new grid-level causal method outperforming existing approaches by orders of magnitude.","significance":4,"cited_by":15,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2211.16654","title":"Stochastic parameterization of column physics using generative adversarial networks","authors":["Balasubramanya Nadiga","Xiaoming Sun","Cody Nash"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2211.16654","doi":"10.1017/eds.2022.32","openalex":"W4312839972"},"links":{"paper":"https://doi.org/10.1017/eds.2022.32","pdf":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/FC1B873F7D87BD791EF5099162E5FD84/S2634460222000322a.pdf/div-class-title-stochastic-parameterization-of-column-physics-using-generative-adversarial-networks-div.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Uses GANs to learn a stochastic distribution of column diabatic heating profiles from MERRA2 reanalysis, offering a probabilistic alternative to deterministic physics parameterizations.","significance":4,"cited_by":7,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2207.05833","title":"Earthformer: Exploring Space-Time Transformers for Earth System Forecasting","authors":["Zhihan Gao","Xingjian Shi","Hao Wang","Yi Zhu","Yuyang Wang","Mu Li","Dit-Yan Yeung"],"date":"2022-01-01","year":2022,"venue":"Advances in Neural Information Processing Systems 35","venue_type":"preprint","ids":{"arxiv":"2207.05833","doi":"10.52202/068431-1841","openalex":"W7133213766"},"links":{"paper":"https://arxiv.org/abs/2207.05833","pdf":"https://arxiv.org/pdf/2207.05833","code":"https://github.com/amazon-science/earth-forecasting-transformer"},"orgs":[],"topic":"nowcasting","topics":["benchmarks-data-eval"],"type":"model","method":["transformer"],"timescale":["nowcast","medium"],"spatial":["regional"],"data":["satellite","radar","other"],"status":"research","summary":"Earthformer is a space-time transformer with cuboid attention that reaches state-of-the-art precipitation nowcasting and ENSO forecasting on real benchmarks.","significance":5,"cited_by":140,"score":40,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2206.14786","title":"ENS-10: A Dataset For Post-Processing Ensemble Weather Forecasts","authors":["Saleh Ashkboos","Langwen Huang","Nikoli Dryden","Tal Ben-Nun","Peter Dueben","Lukas Gianinazzi","Luca Kummer","Torsten Hoefler"],"date":"2022-01-01","year":2022,"venue":"Advances in Neural Information Processing Systems 35","venue_type":"preprint","ids":{"arxiv":"2206.14786","doi":"10.52202/068431-1597","openalex":"W7133187106"},"links":{"paper":"https://arxiv.org/abs/2206.14786","pdf":"https://arxiv.org/pdf/2206.14786"},"orgs":["eth-zurich"],"topic":"benchmarks-data-eval","topics":["post-processing"],"type":"benchmark","method":[],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Introduces ENS-10, a 20-year, 10-member perturbed NWP ensemble dataset at 0.5° for ML post-processing, with baselines for 48-hour correction and extremes.","significance":5,"cited_by":8,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2206.04811","title":"Deep Learning-Enhanced Ensemble-Based Data Assimilation for High-Dimensional Nonlinear Dynamical Systems","authors":["Ashesh Chattopadhyay","Ebrahim Nabizadeh","Eviatar Bach","Pedram Hassanzadeh"],"date":"2022-01-01","year":2022,"venue":"Journal of Computational Physics","venue_type":"journal","ids":{"arxiv":"2206.04811","doi":"10.1016/j.jcp.2023.111918","openalex":"W4315477067"},"links":{"paper":"https://doi.org/10.1016/j.jcp.2023.111918"},"orgs":["caltech"],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep learning enhances ensemble-based data assimilation for high-dimensional nonlinear dynamical systems; the abstract is missing and atmospheric application is unclear.","significance":3,"cited_by":46,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2205.08967","title":"DL4DS - Deep Learning for empirical DownScaling","authors":["Carlos Alberto Gomez Gonzalez"],"date":"2022-01-01","year":2022,"venue":"Environmental Data Science","venue_type":"journal","ids":{"arxiv":"2205.08967","doi":"10.1017/eds.2022.26","openalex":"W4280611998"},"links":{"paper":"https://doi.org/10.1017/eds.2022.26","pdf":"https://arxiv.org/pdf/2205.08967","code":"https://github.com/carlos-gg/dl4ds"},"orgs":[],"topic":"downscaling","topics":["infra-software"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"DL4DS is a Python library for training configurable CNN downscaling models on gridded Earth data, demonstrated on CAMS air-quality fields over the Mediterranean.","significance":3,"cited_by":12,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2202.13336","title":"Dual-Branched Spatio-Temporal Fusion Network for Multihorizon Tropical Cyclone Track Forecast","authors":["Zili Liu","Kun Hao","Xiaoyi Geng","Zhengxia Zou","Zhenwei Shi"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2202.13336","doi":"10.1109/jstars.2022.3170299","openalex":"W4221146624"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3170299","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9656571/09763359.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["global-medium-range"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"DBF-Net fuses TC state vectors with reanalysis pressure fields to forecast Northwest Pacific tropical cyclone tracks at multiple horizons, improving accuracy over single-modality methods.","significance":3,"cited_by":41,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.06868","title":"NowCasting-Nets: Representation Learning to Mitigate Latency Gap of Satellite Precipitation Products Using Convolutional and Recurrent Neural Networks","authors":["Mohammad Reza Ehsani","Ariyan Zarei","Hoshin V. Gupta","Kobus Barnard","Eric Lyons","Ali Behrangi"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2108.06868","doi":"10.1109/tgrs.2022.3158888","openalex":"W4226289820"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3158888","pdf":"https://arxiv.org/pdf/2108.06868"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"CNN and RNN nowcasters applied to IMERG satellite precipitation extend forecasts to 4.5 h, mitigating the latency of satellite rainfall products over CONUS.","significance":3,"cited_by":67,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2023.16228","title":"Effects of Heatwave Features on Machine-Learning-Based Heat-Related Ambulance Calls Prediction Models in Japan","authors":["Deng Ke","Kiyoshi Takahashi","Jun’ya Takakura","Kaoru Takara","Bahareh Kamranzad"],"date":"2022-01-01","year":2022,"venue":"The Science of The Total Environment","venue_type":"journal","ids":{"arxiv":"2023.16228","doi":"10.1016/j.scitotenv.2023.162283","openalex":"W4321350836"},"links":{"paper":"https://doi.org/10.1016/j.scitotenv.2023.162283"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Compares machine-learning models of heat-related ambulance calls in Japan, examining how heatwave feature definitions affect prediction skill. Abstract not available.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.66915","title":"Evaluation of air temperature with machine learning regression methods using Seoul City meteorological data","authors":["Merve Apaydın","Mehmethan Yumuş","Ali Değırmencı","Ömer Karal"],"date":"2022-01-01","year":2022,"venue":"Pamukkale University Journal of Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2022.66915","doi":"10.5505/pajes.2022.66915","openalex":"W4307737321"},"links":{"paper":"https://doi.org/10.5505/pajes.2022.66915","pdf":"https://jag.journalagent.com/z4/download_fulltext.asp?pdir=pajes&plng=eng&un=PAJES-66915"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Comparison of 12 regression methods for next-day Seoul maximum and minimum temperature finds XGBoost and LightGBM most accurate.","significance":2,"cited_by":32,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.32213","title":"Wind Direction Retrieval From CYGNSS L1 Level Sea Surface Data Based on Machine Learning","authors":["Yun Zhang","Chen Xu","Wanting Meng","Shuhu Yang","Yanling Han","Zhonghua Hong","Jiwei Yin","Weiliang Liu"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.32213","doi":"10.1109/tgrs.2022.3221373","openalex":"W4312618507"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3221373"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"CNN retrieval from CYGNSS L1 delay-Doppler maps beats SVM and BP models for global sea surface wind direction, with filtered errors under 20°.","significance":2,"cited_by":15,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.32176","title":"Motion-Guided Global–Local Aggregation Transformer Network for Precipitation Nowcasting","authors":["Xichao Dong","Zewei Zhao","Yupei Wang","Jianping Wang","Cheng Hu"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.32176","doi":"10.1109/tgrs.2022.3217639","openalex":"W4313002791"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3217639","pdf":"https://repository.tudelft.nl/file/File_113f3010-ed45-4be9-8e85-4ba6de33c34f"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A motion-guided global-local Transformer with adversarial regularization improves radar echo extrapolation, giving sharper heavy-rain predictions and better skill scores than CNN and ConvRNN baselines.","significance":4,"cited_by":23,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.32163","title":"Research on Sand-Dust Storm Forecasting Based on Deep Neural Network With Stacking Ensemble Learning","authors":["Qing-Dao-Er-Ji Ren","Na Li","Weimin Zhang"],"date":"2022-01-01","year":2022,"venue":"IEEE Access","venue_type":"journal","ids":{"arxiv":"2022.32163","doi":"10.1109/access.2022.3216309","openalex":"W4312422636"},"links":{"paper":"https://doi.org/10.1109/access.2022.3216309","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09926087.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn","cnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Stacked LSTM-CNN ensembles with fully connected or SVM meta-classifiers improve sand-dust storm prediction over single LSTM or CNN models in Inner Mongolia.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.32129","title":"A Deep Learning-Based Wind Field Nowcasting Method With Extra Attention on Highly Variable Events","authors":["Hang Gao","Chun Shen","Yi Zhou","Xuesong Wang","Pak Wai Chan","K. K. Hon","Jianbing Li"],"date":"2022-01-01","year":2022,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"arxiv":"2022.32129","doi":"10.1109/lgrs.2022.3212904","openalex":"W4312747713"},"links":{"paper":"https://doi.org/10.1109/lgrs.2022.3212904"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":[],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"A variance-weighted loss improves neural lidar wind-field nowcasting during highly variable events, cutting errors by over 15.2% on wind shear onset and decay.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.32104","title":"A Deep-Learning-Based Microwave Radiative Transfer Emulator for Data Assimilation and Remote Sensing","authors":["Xingming Liang","Kevin Garrett","Quanhua Liu","Eric S. Maddy","Kayo Ide","Sid‐Ahmed Boukabara"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.32104","doi":"10.1109/jstars.2022.3210491","openalex":"W4312285240"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3210491"},"orgs":["noaa"],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"pre-operational","summary":"Fully connected network emulates the CRTM microwave radiative transfer model for ATMS brightness temperatures over ocean, with mean biases of hundredths of a kelvin for data assimilation.","significance":3,"cited_by":30,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.32033","title":"An Improved Deep Learning Model for High-Impact Weather Nowcasting","authors":["Shun Yao","Haonan Chen","Elizabeth Thompson","Robert C. Cifelli"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.32033","doi":"10.1109/jstars.2022.3203398","openalex":"W4294167273"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3203398","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/09873914.pdf"},"orgs":["noaa","colorado-state-university"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A self-attention GRU nowcasts radar echoes for landfalling hurricanes and extreme convective rainfall in the southeast US, aiming to improve skill beyond the first hour.","significance":4,"cited_by":40,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.32022","title":"Multimodal Information Fusion for Weather Systems and Clouds Identification From Satellite Images","authors":["Cong Bai","Dongxiaoyuan Zhao","Minjing Zhang","Jinglin Zhang"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.32022","doi":"10.1109/jstars.2022.3202246","openalex":"W4293499134"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3202246"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"MANET fuses satellite images with date, season and location metadata to classify weather systems, clouds and land cover better than image-only models.","significance":2,"cited_by":50,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31986","title":"Multisensor Machine Learning to Retrieve High Spatiotemporal Resolution Land Surface Temperature","authors":["Kate Marie Duffy","Thomas Vandal","Ramakrishna Nemani"],"date":"2022-01-01","year":2022,"venue":"IEEE Access","venue_type":"journal","ids":{"arxiv":"2022.31986","doi":"10.1109/access.2022.3198673","openalex":"W4291653582"},"links":{"paper":"https://doi.org/10.1109/access.2022.3198673"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A CNN fuses LEO and geostationary satellite data into 2 km, 10-minute land surface temperature, with 1.73 K mean absolute error against LEO targets.","significance":3,"cited_by":7,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31978","title":"NLED: Nonlocal Echo Dynamics Network for Radar Echo Extrapolation","authors":["Taisong Chen","Qian Li","Xuan Peng","Qi Lv","Jinrui Jing"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31978","doi":"10.1109/tgrs.2022.3197833","openalex":"W4293370510"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3197833"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"NLED uses spatiotemporal self-attention in an encoder-decoder to extrapolate radar echoes over Shanghai and Hong Kong, improving long-term nowcast accuracy.","significance":4,"cited_by":8,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31974","title":"Enhanced Resolution of FY4 Remote Sensing Visible Spectrum Images Utilizing Super-Resolution and Transfer Learning Techniques","authors":["Bo Zhang","Muyuan Ma","Mingqing Wang","Danfeng Hong","Le Yu","Jie Wang","Peng Gong","Xiaomeng Huang"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31974","doi":"10.1109/jstars.2022.3197401","openalex":"W4297819578"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3197401","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/09852675.pdf"},"orgs":["tsinghua-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"FY4-SR-Net uses transfer learning to super-resolve FY4 visible satellite images from 4 km to 1 km, cutting RMSE by 16.12% versus bicubic interpolation.","significance":2,"cited_by":9,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31963","title":"Short-Term Weather Forecasting Using Spatial Feature Attention Based LSTM Model","authors":["Masooma Ali Raza Suleman","S. Shridevi"],"date":"2022-01-01","year":2022,"venue":"IEEE Access","venue_type":"journal","ids":{"arxiv":"2022.31963","doi":"10.1109/access.2022.3196381","openalex":"W4289825471"},"links":{"paper":"https://doi.org/10.1109/access.2022.3196381","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09849651.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","transformer"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An attention-based encoder-decoder LSTM forecasts short-term surface temperature from multiple meteorological variables, with learned spatial feature attention weights validated against correlations.","significance":2,"cited_by":85,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31945","title":"Focal Frame Loss: A Simple but Effective Loss for Precipitation Nowcasting","authors":["Zhifeng Ma","Hao Zhang","Jie Liu"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31945","doi":"10.1109/jstars.2022.3194522","openalex":"W4288391634"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3194522","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/09844172.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Focal Frame Loss weights prediction frames by difficulty, improving several radar nowcasting models without extra training cost on two large radar datasets.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31934","title":"Dynamic Multiscale Fusion Generative Adversarial Network for Radar Image Extrapolation","authors":["Shengchao Chen","Ting Shu","Huan Qi Zhao","Qilin Wan","Jincan Huang","Cailing Li"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31934","doi":"10.1109/tgrs.2022.3193458","openalex":"W4287888016"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3193458"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"DMSF-GAN extrapolates radar images for 0-6 h typhoon nowcasting and outperforms optical-flow and RNN baselines; the abstract gives no quantitative results.","significance":3,"cited_by":16,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31890","title":"A Spatio-Temporal Neural Network for Fine-Scale Wind Field Nowcasting Based on Lidar Observation","authors":["Hang Gao","Chun Shen","Yi Zhou","Xuesong Wang","Pak Wai Chan","K. K. Hon","Dingfu Zhou","Jianbing Li"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31890","doi":"10.1109/jstars.2022.3189037","openalex":"W4285125734"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3189037","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/09817617.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"A ConvLSTM encoder-forecaster nowcasts 100 m fine-scale wind fields from Hong Kong airport lidar up to 27 minutes, beating nine baselines including optical flow.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31790","title":"Toward an Improved Global Longwave Downward Radiation Product by Fusing Satellite and Reanalysis Data","authors":["Shiyao Wang","Tianxing Wang","Wanchun Leng","Gaofeng Wang","Husi Letu"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31790","doi":"10.1109/tgrs.2022.3179017","openalex":"W4285224044"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3179017"},"orgs":[],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"A machine-learning fusion of CERES, ERA5 and GLDAS yields a global hourly 0.25° longwave downward radiation product with R=0.97 against ground measurements over land.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31776","title":"Experimental Study on Generative Adversarial Network for Precipitation Nowcasting","authors":["Chuyao Luo","Xutao Li","Yunming Ye","Shanshan Feng","Michael K. Ng"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31776","doi":"10.1109/tgrs.2022.3177625","openalex":"W4285106044"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3177625","code":"https://github.com/luochuyao/MultiScaleGAN"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Systematically compares GAN and Wasserstein GAN adversarial regularization for radar echo nowcasting; multi-scale Wasserstein GAN performs best across cases.","significance":3,"cited_by":31,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31748","title":"The Fusion of Physical, Textural, and Morphological Information in SAR Imagery for Hurricane Wind Speed Retrieval Based on Deep Learning","authors":["Shanshan Mu","Xiaofeng Li","Haoyu Wang"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31748","doi":"10.1109/tgrs.2022.3174824","openalex":"W4285216033"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3174824"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A residual deep network fusing SAR backscatter, texture and morphology retrieves hurricane sea-surface winds up to 75 m/s with RMSE 1.72 m/s.","significance":3,"cited_by":36,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31730","title":"Sea Surface Wind Direction Retrieval Based on Convolution Neural Network and Wavelet Analysis","authors":["Chaogang Guo","Weihua Ai","Shensen Hu","Xiaoyong Du","Nan Chen"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31730","doi":"10.1109/jstars.2022.3173001","openalex":"W4285287044"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3173001","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/09770385.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Transfer-learned Inception v3 identifies wind streaks in GF-3 SAR images to retrieve sea surface wind direction, reaching 92-95% accuracy with 9.12 RMSE against ECMWF.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31708","title":"Rainfall Estimation From TEMPEST-D CubeSat Observations: A Machine-Learning Approach","authors":["Chandrasekar Radhakrishnan","V. Chandrasekar","Steven C. Reising","Wesley K. Berg"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31708","doi":"10.1109/jstars.2022.3170835","openalex":"W3129908168"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3170835","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9656571/09764402.pdf"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"An artificial neural network maps CubeSat TEMPEST-D microwave brightness temperatures to surface rainfall, reaching 0.78 structural similarity on independent storms against MRMS radar.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31707","title":"Structure of High-Resolution SAR Winds Over the Venice Lagoon Area","authors":["stefano zecchetto","Andrea Zanchetta"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31707","doi":"10.1109/tgrs.2022.3170705","openalex":"W4293193736"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3170705"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"A ResNet extracts 500 m sea-surface wind fields from Sentinel-1 SAR over Venice, with 16° direction RMS against in-situ data and finer structure than ECMWF.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31674","title":"Video-Based Convolutional Neural Networks Forecasting for Rainfall Forecasting","authors":["Andrew Paul Barnes","Thomas Kjeldsen","Nick McCullen"],"date":"2022-01-01","year":2022,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"arxiv":"2022.31674","doi":"10.1109/lgrs.2022.3167456","openalex":"W4226417298"},"links":{"paper":"https://doi.org/10.1109/lgrs.2022.3167456","pdf":"https://ieeexplore.ieee.org/ielx7/8859/9651998/09757818.pdf"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Video CNNs using GloSEA5 pressure and temperature fields forecast monthly regional rainfall in Great Britain; an ensemble with GloSEA5 reduces RMSE to 31-32 mm.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31595","title":"Inductive Spatiotemporal Graph Convolutional Networks for Short-Term Quantitative Precipitation Forecasting","authors":["Yajing Wu","Xuebing Yang","Yongqiang Tang","Chenyang Zhang","Guoping Zhang","Wensheng Zhang"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31595","doi":"10.1109/tgrs.2022.3159530","openalex":"W4225984675"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3159530"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["gnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Introduces InstGCN, an inductive spatiotemporal graph network for radar-based short-term rainfall forecasting, with a novel elliptic graph construction and subgraph decomposition for unseen nodes.","significance":3,"cited_by":12,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31592","title":"A Machine Learning-Based Method for Wind Fields Forecasting Utilizing GNSS Radio Occultation Data","authors":["Xuezhao Chu","Weihua Bai","Yueqiang Sun","Wei Li","Congliang Liu","Hongqing Song"],"date":"2022-01-01","year":2022,"venue":"IEEE Access","venue_type":"journal","ids":{"arxiv":"2022.31592","doi":"10.1109/access.2022.3159231","openalex":"W4225670292"},"links":{"paper":"https://doi.org/10.1109/access.2022.3159231","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09736142.pdf"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"application","method":["rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"LSTM and CNN models using GNSS radio occultation profiles forecast regional wind fields over Beijing-Tianjin-Hebei, with about 1.4 m/s speed error and 1 s inference.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31556","title":"A Hybrid Method for Fine-Scale Wind Field Retrieval Based on Machine Learning and Data Assimilation","authors":["Hang Gao","Jie Zhou","Pak-Wai Chan","K. K. Hon","Jianbing Li"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31556","doi":"10.1109/tgrs.2022.3155662","openalex":"W4214946943"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3155662"},"orgs":[],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other","stations"],"status":"research","summary":"A hybrid method uses ML regression inside 3DVAR to retrieve fine-scale boundary-layer winds from lidar and in-situ data, improving 2-D and 3-D velocity estimates by 42.3% on average.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31528","title":"Simulating Tropical Cyclone Passive Microwave Rainfall Imagery Using Infrared Imagery via Generative Adversarial Networks","authors":["Fan Meng","Tao Song","Danya Xu"],"date":"2022-01-01","year":2022,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"arxiv":"2022.31528","doi":"10.1109/lgrs.2022.3152847","openalex":"W4212875953"},"links":{"paper":"https://doi.org/10.1109/lgrs.2022.3152847"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"TCR-GAN generates passive microwave rainfall images from TC infrared imagery and releases the TCIRRP benchmark dataset for IR-to-rainfall prediction.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31525","title":"Decomposing Satellite-Based Classification Uncertainties in Large Earth Science Datasets","authors":["Pedro Ortiz","Marko Orescanin","Veljko Petković","Scott W. Powell","Benjamin R. Marsh"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31525","doi":"10.1109/tgrs.2022.3152516","openalex":"W4225717283"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3152516","pdf":"https://www.techrxiv.org/articles/preprint/Decomposing_Satellite-Based_Classification_Uncertainties_in_Large_Earth_Science_Datasets/19071557/1/files/33897347.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Bayesian neural networks map GPM microwave imager data to precipitation type with calibrated uncertainty and decompose satellite retrieval errors.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31497","title":"Landsat Snow-Free Surface Albedo Estimation Over Sloping Terrain: Algorithm Development and Evaluation","authors":["Yichuan Ma","Tao He","Shunlin Liang","Jianguang Wen","Jean‐Philippe Gastellu‐Etchegorry","Jiang Chen","Anxin Ding","Siqi Feng"],"date":"2022-01-01","year":2022,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31497","doi":"10.1109/tgrs.2022.3149762","openalex":"W4210827273"},"links":{"paper":"https://doi.org/10.1109/tgrs.2022.3149762","pdf":"https://ieeexplore.ieee.org/ielx7/36/9633014/09706479.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Neural networks map Landsat TOA reflectance to horizontal and inclined surface albedo over sloping terrain, achieving RMSE of 0.029 for HHSA against in-situ data.","significance":2,"cited_by":27,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31494","title":"On the Use of Satellite Nightlights for Power Outages Prediction","authors":["Juan P. Montoya-Rincon","Shams Azad","Rabindra Pokhrel","Masoud Ghandehari","Michael P. Jensen","Jorge E. González"],"date":"2022-01-01","year":2022,"venue":"IEEE Access","venue_type":"journal","ids":{"arxiv":"2022.31494","doi":"10.1109/access.2022.3149485","openalex":"W4210866002"},"links":{"paper":"https://doi.org/10.1109/access.2022.3149485","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09706181.pdf"},"orgs":["nyu-m2lines"],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"VIIRS nightlight data and simulated hurricane weather feed machine learning that predicts Hurricane Maria power outages in Puerto Rico where outage records are missing.","significance":2,"cited_by":24,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.31404","title":"Medium- and Long-Term Precipitation Forecasting Method Based on Data Augmentation and Machine Learning Algorithms","authors":["Tiantian Tang","Donglai Jiao","Tao Chen","Guan Gui"],"date":"2022-01-01","year":2022,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2022.31404","doi":"10.1109/jstars.2022.3140442","openalex":"W4206347244"},"links":{"paper":"https://doi.org/10.1109/jstars.2022.3140442","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9656571/09670649.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml","rnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"K-means plus SMOTE augmentation improves random forest and XGBoost monthly grid precipitation forecasts for the Danjiangkou basin.","significance":2,"cited_by":72,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.11420","title":"Prediction of Extreme Precipitation Events Based on Grey Prediction and BP Neural Network","authors":["建华 王"],"date":"2022-01-01","year":2022,"venue":"Advances in Applied Mathematics","venue_type":"journal","ids":{"arxiv":"2022.11420","doi":"10.12677/aam.2022.114202","openalex":"W4225934565"},"links":{"paper":"https://doi.org/10.12677/aam.2022.114202"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Combines grey prediction with a BP neural network to forecast extreme precipitation events; the abstract is unavailable, so results are unknown.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.10650","title":"Improving Subseasonal-to-Seasonal Forecasts in Predicting the Occurrence of Extreme Precipitation Events Over the Contiguous U.S. Using Machine Learning Models","authors":["Lujun Zhang","Tiantian Yang","Shang Gao","Yang E. Hong","Qin Zhang","Xin Wen","Chuntian Cheng"],"date":"2022-01-01","year":2022,"venue":"Atmospheric Research","venue_type":"journal","ids":{"arxiv":"2022.10650","doi":"10.1016/j.atmosres.2022.106502","openalex":"W4308071692"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2022.106502"},"orgs":["noaa","university-of-oklahoma"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Machine learning post-processing of subseasonal-to-seasonal forecasts improves prediction of extreme precipitation occurrence over the contiguous US.","significance":3,"cited_by":36,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.10051","title":"Using neural networks to predict weather patterns and trends - challenges and opportunities","authors":["Sandeep Rajinder Mathur"],"date":"2022-01-01","year":2022,"venue":"International Journal of Computer Aided Engineering and Technology","venue_type":"journal","ids":{"arxiv":"2022.10051","doi":"10.1504/ijcaet.2022.10051499","openalex":"W4312987939"},"links":{"paper":"https://doi.org/10.1504/ijcaet.2022.10051499"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":["other"],"timescale":["medium"],"spatial":["global"],"data":[],"status":"research","summary":"Reviews neural network methods for weather and climate prediction, comparing their effectiveness against numerical weather prediction models and discussing challenges.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.10001","title":"Systematic review of nowcasting approaches for solar energy production based upon ground-based cloud imaging","authors":["Bruno Juncklaus Martins","Allan Cerentini","Sylvio Luiz Mantelli Neto","Thiago Zimmermann Loureiro Chaves","Nicolas Moreira Branco","Aldo von Wangenheim","Ricardo Rüther","Juliana Marian Arrais"],"date":"2022-01-01","year":2022,"venue":"Solar Energy Advances","venue_type":"journal","ids":{"arxiv":"2022.10001","doi":"10.1016/j.seja.2022.100019","openalex":"W4284964953"},"links":{"paper":"https://doi.org/10.1016/j.seja.2022.100019","pdf":"https://www.sciencedirect.com/science/article/pii/S2667113122000079/pdf"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"review","method":["classical-ml","cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Systematic review of 65 articles (2011-2020) on sky-camera cloud nowcasting for solar power, finding a shift from classical statistics toward neural networks and CNNs.","significance":2,"cited_by":28,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.03006","title":"Weather Forecasting Prediction Using Ensemble Machine Learning for Big Data Applications","authors":["Hadil Ahmed Shaiba","Radwa Marzouk","Mohamed K. Nour","Noha Negm","Anwer Mustafa Hilal","Abdullah Mohamed","Abdelwahed Motwakel","Ishfaq Yaseen","Abu Sarwar Zamani","Mohammed Rizwanullah"],"date":"2022-01-01","year":2022,"venue":"Computers, materials & continua/Computers, materials & continua (Print)","venue_type":"journal","ids":{"arxiv":"2022.03006","doi":"10.32604/cmc.2022.030067","openalex":"W4285273961"},"links":{"paper":"https://doi.org/10.32604/cmc.2022.030067"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Ensemble of gradient boosting, random forest, Bernoulli Naive Bayes and KNN reaches 95% weather prediction accuracy and runs in under 40 s for 5,000 nodes.","significance":1,"cited_by":22,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.02520","title":"Modelling the ZR Relationship of Precipitation Nowcasting Based on Deep Learning","authors":["Jianbing Ma","Xianghao Cui","Nan Jiang"],"date":"2022-01-01","year":2022,"venue":"Computers, materials & continua/Computers, materials & continua (Print)","venue_type":"journal","ids":{"arxiv":"2022.02520","doi":"10.32604/cmc.2022.025206","openalex":"W4213449301"},"links":{"paper":"https://doi.org/10.32604/cmc.2022.025206"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"A deep learning model learns the radar reflectivity-to-rainfall (Z-R) relation for Shenzhen, outperforming the traditional Z-R equation and matching a pure DL nowcaster.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.02339","title":"Hyperparameter Tuned Bidirectional Gated Recurrent Neural Network for Weather Forecasting","authors":["S. Manikandan","Balakrishnan Nagaraj"],"date":"2022-01-01","year":2022,"venue":"Intelligent Automation & Soft Computing","venue_type":"journal","ids":{"arxiv":"2022.02339","doi":"10.32604/iasc.2022.023398","openalex":"W4210869243"},"links":{"paper":"https://doi.org/10.32604/iasc.2022.023398","pdf":"https://file.techscience.com/ueditor/files/iasc/TSP_IASC-33-2/TSP_IASC_23398/TSP_IASC_23398.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","other"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Bird-mating-optimizer-tuned bidirectional GRU for weather forecasting reports RMSE 0.173, better than MLP-ANN at 0.202.","significance":1,"cited_by":6,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.01301","title":"A Machine Learning Approach to Weather Prediction in Wireless Sensor Networks","authors":["Suvarna S Patil","B. M. Vidyavathi"],"date":"2022-01-01","year":2022,"venue":"International Journal of Advanced Computer Science and Applications","venue_type":"journal","ids":{"arxiv":"2022.01301","doi":"10.14569/ijacsa.2022.0130131","openalex":"W4210635660"},"links":{"paper":"https://doi.org/10.14569/ijacsa.2022.0130131","pdf":"http://thesai.org/Downloads/Volume13No1/Paper_31-A_Machine_Learning_Approach_to_Weather_Prediction.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies multiple linear regression to Intel lab wireless sensor data to predict humidity, reporting about 11% minimum error.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2022.0126","title":"Spatial downscaling method and application of CMIP5 global climate models based on improved U-Net in Lake Poyang Basin","authors":["Kecheng Li","Jianzhong Lu","Kerui Zhang","Lu Chengyu","Chen Pu","Yuan Mingkun"],"date":"2022-01-01","year":2022,"venue":"Journal of Lake Sciences","venue_type":"journal","ids":{"arxiv":"2022.0126","doi":"10.18307/2022.0126","openalex":"W4205835099"},"links":{"paper":"https://doi.org/10.18307/2022.0126","pdf":"http://www.jlakes.org/ch/reader/create_pdf.aspx?file_no=20220126&flag=1&year_id=2022&quarter_id=1"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"An improved U-Net downscales CMIP5 projections over Lake Poyang Basin, outperforming linear regression and projecting warming and changing precipitation under RCP2.6 and RCP8.5.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.37727-jkdas.2021.23.6.2619","title":"Analysis of the Damage Rate of Astringent Persimmon Farms According to Typhoon Information","authors":["Su Hoon Choi","Jeong Hwa Yang","Sang-Hyun Lee","Min Soo Kim"],"date":"2021-12-31","year":2021,"venue":"The Korean Data Analysis Society","venue_type":"journal","ids":{"doi":"10.37727/jkdas.2021.23.6.2619","openalex":"W4205185009"},"links":{"paper":"https://doi.org/10.37727/jkdas.2021.23.6.2619"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"AutoML comparison finds XGBoost best at predicting persimmon farm fruit-drop damage rates from typhoon information, trained on 2016-2018 and tested on 2019 data.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.37109-weik.2021.25.4.165","title":"Regression Analysis on Global Wind Speed Using Reanalysis Data","authors":["정회원,한국에너지기술연구원, 공학박사","Je-Hyun Lee","Jin Young Kim","Chang Ki Kim","Hyun‐Goo Kim"],"date":"2021-12-31","year":2021,"venue":"한국풍공학회지","venue_type":"journal","ids":{"doi":"10.37109/weik.2021.25.4.165","openalex":"W4210630787"},"links":{"paper":"https://doi.org/10.37109/weik.2021.25.4.165"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Random forest on topographic features reproduces global ERA5 wind speed with R2 of 1.00, suggesting reanalysis wind can be downscaled for wind resource assessment.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5322-jesi.2021.30.12.1053","title":"Optimizing Hydrological Quantitative Precipitation Forecast (HQPF) based on Machine Learning for Rainfall Impact Forecasting","authors":["Han-Su Lee","Yongkeun Jee","Youngmi Lee","Byung-Sik Kim"],"date":"2021-12-30","year":2021,"venue":"Journal of Environmental Science International","venue_type":"journal","ids":{"doi":"10.5322/jesi.2021.30.12.1053","openalex":"W4205968882"},"links":{"paper":"https://doi.org/10.5322/jesi.2021.30.12.1053"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Machine learning refines hydrological quantitative precipitation forecasts for rainfall impact prediction; the abstract is missing, so the scope is inferred from the title.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21108-ijoict.v7i2.602","title":"The Effect of Number of Factors and Data on Monthly Weather Classification Performance Using Artificial Neural Networks","authors":["Shofura Shofura","Sri Suryani","Linda Salma","Sri Harini"],"date":"2021-12-30","year":2021,"venue":"International Journal on Information and Communication Technology (IJoICT)","venue_type":"journal","ids":{"doi":"10.21108/ijoict.v7i2.602","openalex":"W4206352619"},"links":{"paper":"https://doi.org/10.21108/ijoict.v7i2.602","pdf":"https://socj.telkomuniversity.ac.id/ojs/index.php/ijoict/article/download/602/325"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An artificial neural network using five factors including previous rainfall classifies monthly weather in Bogor, reaching 83.33% accuracy on 2017-2018 test data.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2021-4483907","title":"Weather Radar Image Superresolution Using a Nonlocal Residual Network","authors":["Haoxuan Yuan","Qiangyu Zeng","Jianxin He"],"date":"2021-12-30","year":2021,"venue":"Journal of Mathematics","venue_type":"journal","ids":{"doi":"10.1155/2021/4483907","openalex":"W4205270380"},"links":{"paper":"https://doi.org/10.1155/2021/4483907","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/2021/4483907"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Nonlocal residual CNN super-resolves weather radar echo images at x2 and x4, outperforming interpolation in quantitative metrics and edge detail.","significance":2,"cited_by":7,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ef002434","title":"Implications of Increasing Household Air Conditioning Use Across the United States Under a Warming Climate","authors":["Renee Obringer","Roshanak Nateghi","Debora Maia‐Silva","Sayanti Mukherjee","C. R. Vineeth","Douglas Brent McRoberts","Rohini Kumar"],"date":"2021-12-29","year":2021,"venue":"Earth s Future","venue_type":"journal","ids":{"doi":"10.1029/2021ef002434","openalex":"W4200177575"},"links":{"paper":"https://doi.org/10.1029/2021ef002434","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021EF002434"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Machine learning links weather to household air conditioning use, projecting 8–13% higher US residential demand under 1.5–2.0°C warming.","significance":3,"cited_by":79,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.knosys.2021.107900","title":"PredRANN: The spatiotemporal attention Convolution Recurrent Neural Network for precipitation nowcasting","authors":["Chuyao Luo","Xinyue Zhao","Yuxi Sun","Xutao Li","Yunming Ye"],"date":"2021-12-29","year":2021,"venue":"Knowledge-Based Systems","venue_type":"journal","ids":{"doi":"10.1016/j.knosys.2021.107900","openalex":"W4200157320"},"links":{"paper":"https://doi.org/10.1016/j.knosys.2021.107900"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"PredRANN adds spatiotemporal attention to a convolutional recurrent network for radar-based precipitation nowcasting.","significance":3,"cited_by":45,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-17445302.2021.2005357","title":"Extreme wave height detection based on the meteorological data, using hybrid NOF-ELM method","authors":["Kumars Mahmoodi","Hashem Nowruzi"],"date":"2021-12-28","year":2021,"venue":"Ships and Offshore Structures","venue_type":"journal","ids":{"doi":"10.1080/17445302.2021.2005357","openalex":"W4200212986"},"links":{"paper":"https://doi.org/10.1080/17445302.2021.2005357"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Hybrid NOF-ELM classifier uses hurricane meteorological data to detect extreme wave height occurrence in the Gulf of Mexico with over 99% mean accuracy.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jag.2021.102650","title":"DeepUrbanDownscale: A physics informed deep learning framework for high-resolution urban surface temperature estimation via 3D point clouds","authors":["Linwei Chen","Bowen Fang","Lei Zhao","Yu Zang","Weiquan Liu","Yiping Chen","Cheng Wang","Jonathan Li"],"date":"2021-12-28","year":2021,"venue":"International Journal of Applied Earth Observation and Geoinformation","venue_type":"journal","ids":{"doi":"10.1016/j.jag.2021.102650","openalex":"W4200242700"},"links":{"paper":"https://doi.org/10.1016/j.jag.2021.102650"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["physics-constrained","cnn"],"timescale":[],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"Physics-informed network downscales urban land surface temperature to 30 m using 3D point clouds, with errors under 0.2 K against satellite measurements.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.13974","title":"A Moment in the Sun: Solar Nowcasting from Multispectral Satellite Data using Self-Supervised Learning","authors":["Akansha Singh Bansal","Trapit Bansal","David Irwin"],"date":"2021-12-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.13974"},"links":{"paper":"https://arxiv.org/abs/2112.13974","pdf":"https://arxiv.org/pdf/2112.13974"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"Self-supervised CNN-LSTM models forecast GOES-R satellite irradiance to nowcast solar PV output, reaching errors close to ground-truth-based models at 25 sites.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14010104","title":"UATNet: U-Shape Attention-Based Transformer Net for Meteorological Satellite Cloud Recognition","authors":["Zhanjie Wang","Jianghua Zhao","Ran Zhang","Zheng Li","Qinghui Lin","Xuezhi Wang"],"date":"2021-12-26","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14010104","openalex":"W4200604770"},"links":{"paper":"https://doi.org/10.3390/rs14010104","pdf":"https://www.mdpi.com/2072-4292/14/1/104/pdf?version=1640670544"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["transformer","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"UATNet, a Swin-transformer U-shaped network, classifies cloud types in Chinese meteorological satellite images on a new nine-class dataset (CRMSCD).","significance":3,"cited_by":49,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31326-jisa.v4i2.911","title":"Climate Prediction Using RNN LSTM to Estimate Agricultural Products Based on Koppen Classification","authors":["Novia Andini","Wiranto Herry Utomo"],"date":"2021-12-26","year":2021,"venue":"JISA(Jurnal Informatika dan Sains)","venue_type":"journal","ids":{"doi":"10.31326/jisa.v4i2.911","openalex":"W4226078075"},"links":{"paper":"https://doi.org/10.31326/jisa.v4i2.911","pdf":"https://trilogi.ac.id/journal/ks/index.php/JISA/article/download/911/510"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["rnn"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses an LSTM to predict temperature, humidity, sunshine and rainfall for Köppen-class agricultural yield estimation, reporting 3.29% MAPE.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app12010181","title":"Storm Surge Prediction Based on Long Short-Term Memory Neural Network in the East China Sea","authors":["Kuo Chen","Cuiping Kuang","Lei Wang","Ke Chen","Xuejian Han","Jiadong Fan"],"date":"2021-12-24","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app12010181","openalex":"W4200045909"},"links":{"paper":"https://doi.org/10.3390/app12010181","pdf":"https://www.mdpi.com/2076-3417/12/1/181/pdf?version=1640570875"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["rnn"],"timescale":["nowcast","short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM model using multi-factor typhoon time series predicts storm-surge water level at a Yangtze Estuary station, giving 1 h accuracy and 15 h predictions, 41% better than traditional ML.","significance":3,"cited_by":51,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3138395","title":"A Remapping Technique of FY-3D MWRI Based on a Convolutional Neural Network for the Reduction of Representativeness Error","authors":["Ke Chen","Xulei Fan","Wei Han","Hongyi Xiao"],"date":"2021-12-24","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3138395","openalex":"W4206228727"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3138395"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"A CNN remaps FY-3D MWRI brightness temperatures to NWP grids, reducing observation minus background bias and spread in GRAPES 4D-Var.","significance":3,"cited_by":12,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.egyr.2021.10.102","title":"A combined model for short-term wind power forecasting based on the analysis of numerical weather prediction data","authors":["Boyu He","Lin Ye","Ming L. Pei","Peng Lu","Binhua Dai","Zhuo Li","Kaifeng Wang"],"date":"2021-12-24","year":2021,"venue":"Energy Reports","venue_type":"journal","ids":{"doi":"10.1016/j.egyr.2021.10.102","openalex":"W4200287216"},"links":{"paper":"https://doi.org/10.1016/j.egyr.2021.10.102","pdf":"https://www.sciencedirect.com/science/article/pii/S2352484721011215/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Weather-pattern-split CNN and LSTM models with IOWA combination forecast short-term wind power from NWP variables at a Chinese wind farm.","significance":2,"cited_by":93,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10509867.1","title":"Fourier Reservoir Computing for data-driven prediction of multi-scale coupled quasi-geostrophic dynamics","authors":["Hsin-Yi Lin","Stephen Gregory Penny"],"date":"2021-12-24","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10509867.1","openalex":"W4200527258"},"links":{"paper":"https://doi.org/10.1002/essoar.10509867.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10509867.1"},"orgs":["noaa"],"topic":"climate-emulation","topics":[],"type":"model","method":["rnn","other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Fourier reservoir computing with localization extends skillful forecast horizons for a coupled atmosphere-ocean quasi-geostrophic model beyond standard reservoir computing.","significance":3,"cited_by":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.12966","title":"Machine learning for Earth System Science (ESS): A survey, status and future directions for South Asia","authors":["Manmeet Singh","Bipin Kumar","Rajib Chattopadhyay","K Amarjyothi","Anup K Sutar","Sukanta Roy","Suryachandra A Rao","Ravi S. Nanjundiah"],"date":"2021-12-24","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.12966","openalex":"W4226383702"},"links":{"paper":"https://arxiv.org/abs/2112.12966","pdf":"https://arxiv.org/pdf/2112.12966"},"orgs":[],"topic":"downscaling","topics":[],"type":"review","method":[],"timescale":[],"spatial":["regional"],"data":[],"status":"research","summary":"Survey of machine learning across Earth system science in South Asia, covering atmospheric, ocean and other domains, with emphasis on downscaling and forecasting applications.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-hess-25-6523-2021","title":"Machine-learning methods to assess the effects of a non-linear damage spectrum taking into account soil moisture on winter wheat yields in Germany","authors":["Michael Peichl","Stephan Thober","Luis Samaniego","Bernd Hansjürgens","Andréas Marx"],"date":"2021-12-22","year":2021,"venue":"Hydrology and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/hess-25-6523-2021","openalex":"W4226057925"},"links":{"paper":"https://doi.org/10.5194/hess-25-6523-2021"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Random forests with monthly soil moisture and extreme-weather features predict German winter wheat yield anomalies, reaching test R-squared of about 0.70 and explaining 2003, 2014 and 2018 extremes.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs14010024","title":"Towards a More Realistic and Detailed Deep-Learning-Based Radar Echo Extrapolation Method","authors":["Yuan Hu","Lei Chen","Zhibin Wang","Xiang Pan","Hao Li"],"date":"2021-12-22","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs14010024","openalex":"W4200348065"},"links":{"paper":"https://doi.org/10.3390/rs14010024","pdf":"https://www.mdpi.com/2072-4292/14/1/24/pdf?version=1640221759"},"orgs":["alibaba-damo"],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Spatial and spectrum GANs with masked style loss sharpen ConvLSTM and U-Net radar echo extrapolations on SEVIR, plus a new power spectral density score.","significance":3,"cited_by":31,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.11429","title":"Machine Learning Emulation of Urban Land Surface Processes","authors":["David Meyer","Sue Grimmond","Peter Dueben","Robin Hogan","Maarten van Reeuwijk"],"date":"2021-12-21","year":2021,"venue":"Meyer, D., Grimmond, S., Dueben, P., Hogan, R., & van Reeuwijk, M. (2022). Machine Learning Emulation of Urban Land Surface Processes. Journal of Advances in Modeling Earth Systems, 14(3)","venue_type":"journal","ids":{"arxiv":"2112.11429","doi":"10.1029/2021ms002744"},"links":{"paper":"https://arxiv.org/abs/2112.11429","pdf":"https://arxiv.org/pdf/2112.11429"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"A neural network emulates an ensemble of urban land surface models and, coupled to WRF, is more accurate and cheaper than the reference TEB scheme.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.11317","title":"Deep Learning Based Cloud Cover Parameterization for ICON","authors":["Arthur Grundner","Tom Beucler","Pierre Gentine","Fernando Iglesias-Suarez","Marco A. Giorgetta","Veronika Eyring"],"date":"2021-12-21","year":2021,"venue":"Journal of Advances in Modeling Earth Systems (JAMES), 2022","venue_type":"journal","ids":{"arxiv":"2112.11317","doi":"10.1029/2021ms002959","openalex":"W4310896207"},"links":{"paper":"https://arxiv.org/abs/2112.11317","pdf":"https://arxiv.org/pdf/2112.11317"},"orgs":["columbia-leap","mpi-meteorology"],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global","regional"],"data":["km-scale-sim"],"status":"research","summary":"Neural network cloud cover parameterizations trained on ICON storm-resolving simulations generalise across regional and global data, with SHAP used to explain their feature use.","significance":4,"cited_by":68,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ecolind.2021.108496","title":"Modelling and reconstructing tree ring growth index with climate variables through artificial intelligence and statistical methods","authors":["Nasrin Salehnia","Jinho Ahn"],"date":"2021-12-20","year":2021,"venue":"Ecological Indicators","venue_type":"journal","ids":{"doi":"10.1016/j.ecolind.2021.108496","openalex":"W4200259227"},"links":{"paper":"https://doi.org/10.1016/j.ecolind.2021.108496","pdf":"https://www.sciencedirect.com/science/article/pii/S1470160X21011614/pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["applications-impacts"],"type":"model","method":["rnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["other","stations"],"status":"research","summary":"Compares regression with NARX-based neural models to link climate variables to tree-ring growth in NE Korea and reconstruct the growth index for 1999–2019.","significance":2,"cited_by":30,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10509727.1","title":"A Streaming Tensor Decomposition Analysis of of a Multi-Ceilometer Based Lidar Aerosol Network.","authors":["Samit S. Shivadekar","Milton Halem"],"date":"2021-12-20","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10509727.1","openalex":"W4200102702"},"links":{"paper":"https://doi.org/10.1002/essoar.10509727.1","pdf":"https://essopenarchive.org/doi/pdf/10.1002/essoar.10509727.1"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Streaming tensor decomposition of ceilometer lidar aerosol profiles across a US network tracks mixed boundary layer height in near real time over long archives.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w13243599","title":"Simulation of Daily Snow Depth Data in China Based on the NEX-GDDP","authors":["Hongju Chen","Jianping Yang","Yongjian Ding","Qingshan He","Qin Ji"],"date":"2021-12-15","year":2021,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w13243599","openalex":"W4200350921"},"links":{"paper":"https://doi.org/10.3390/w13243599"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Backpropagation neural network simulates daily snow depth from NEX-GDDP downscaled projections across China to 2065, validated with r = 0.94 for monthly snow cover duration.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-21-0084.1","title":"Low Cloud Detection in Multilayer Scenes Using Satellite Imagery with Machine Learning Methods","authors":["John M. Haynes","Yoo‐Jeong Noh","S. D. Miller","Katherine Haynes","Imme Ebert‐Uphoff","Andrew K. Heidinger"],"date":"2021-12-15","year":2021,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-21-0084.1","openalex":"W4200052465"},"links":{"paper":"https://doi.org/10.1175/jtech-d-21-0084.1"},"orgs":["noaa","colorado-state-university"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["classical-ml","rnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Random forest and neural network models on GOES-ABI imagery improve low-cloud detection in multilayer scenes, raising probability of detection from 0.685 to 0.815 versus the CCL product.","significance":4,"cited_by":24,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.08453","title":"The Need for Ethical, Responsible, and Trustworthy Artificial Intelligence for Environmental Sciences","authors":["Amy McGovern","Imme Ebert-Uphoff","David John Gagne","Ann Bostrom"],"date":"2021-12-15","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.08453","doi":"10.1017/eds.2022.5"},"links":{"paper":"https://arxiv.org/abs/2112.08453","pdf":"https://arxiv.org/pdf/2112.08453"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"position","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Position paper arguing AI in environmental sciences risks bias and injustice, with weather and climate examples; calls for responsible AI practice.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.08217","title":"Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization","authors":["Lorenzo Pacchiardi","Rilwan Adewoyin","Peter Dueben","Ritabrata Dutta"],"date":"2021-12-15","year":2021,"venue":"Journal of Machine Learning Research, 25(45), 2024","venue_type":"journal","ids":{"arxiv":"2112.08217","openalex":"W4308788288"},"links":{"paper":"https://arxiv.org/abs/2112.08217","pdf":"https://arxiv.org/pdf/2112.08217"},"orgs":[],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Generative networks trained with prequential scoring rules, avoiding adversarial training, improve probabilistic calibration on chaotic models and a global weather benchmark.","significance":4,"cited_by":5,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-x5n91s","title":"A continuous vertically resolved ozone dataset from the fusion of chemistry climate models with observations using a Bayesian neural network","authors":["Matt Amos","Ushnish Sengupta","Paul J. Young","J. Scott Hosking"],"date":"2021-12-14","year":2021,"venue_type":"other","ids":{"doi":"10.31223/x5n91s","openalex":"W4200047192"},"links":{"paper":"https://doi.org/10.31223/x5n91s"},"orgs":["university-of-cambridge","alan-turing-institute"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","stations","cmip"],"status":"research","summary":"Uses a Bayesian neural network to fuse chemistry-climate model output with sparse satellite and sonde data, producing a continuous vertically resolved stratospheric ozone record with uncertainty.","significance":4,"cited_by":1,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.08440","title":"Climate-Invariant Machine Learning","authors":["Tom Beucler","Pierre Gentine","Janni Yuval","Ankitesh Gupta","Liran Peng","Jerry Lin","Sungduk Yu","Stephan Rasp","Fiaz Ahmed","Paul A. O'Gorman","J. David Neelin","Nicholas J. Lutsko","Michael Pritchard"],"date":"2021-12-14","year":2021,"venue":"Science Advances","venue_type":"journal","ids":{"arxiv":"2112.08440","doi":"10.1126/sciadv.adj7250","openalex":"W4391629221"},"links":{"paper":"https://arxiv.org/abs/2112.08440","pdf":"https://arxiv.org/pdf/2112.08440"},"orgs":["columbia-leap","google-research","mit","nvidia","ucla"],"topic":"xai-uq-physics","topics":["climate-emulation"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Climate-invariant ML embeds physical knowledge into parameterization emulators so they generalize across climate regimes, maintaining offline accuracy in three atmospheric models.","significance":6,"cited_by":108,"score":89,"highlight":true,"highlight_reason":"Physics-based input transformations improve ML parameterization generalization across climates, addressing a key obstacle for hybrid climate models.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-tc-15-5639-2021","title":"Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf","authors":["Zhongyang Hu","Peter Kuipers Munneke","Stef Lhermitte","Maaike Izeboud","M. R. van den Broeke"],"date":"2021-12-13","year":2021,"venue":"˜The œcryosphere","venue_type":"journal","ids":{"doi":"10.5194/tc-15-5639-2021","openalex":"W4200359611"},"links":{"paper":"https://doi.org/10.5194/tc-15-5639-2021"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","satellite","nwp-analysis"],"status":"research","summary":"Deep MLP corrects RACMO2 Antarctic surface melt using automatic weather station and MODIS albedo data, outperforming random forest and XGBoost on cross-validation.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2021.127301","title":"Convolutional neural network-based statistical post-processing of ensemble precipitation forecasts","authors":["Wentao Li","Baoxiang Pan","Jiangjiang Xia","Qingyun Duan"],"date":"2021-12-13","year":2021,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2021.127301","openalex":"W4200309788"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2021.127301"},"orgs":["iap-cas"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"CNN-based statistical post-processing corrects ensemble precipitation forecasts, improving on raw ensemble output for rainfall prediction.","significance":3,"cited_by":107,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.06571","title":"Extension of Convolutional Neural Network along Temporal and Vertical Directions for Precipitation Downscaling","authors":["Takeyoshi Nagasato","Kei Ishida","Ali Ercan","Tongbi Tu","Masato Kiyama","Motoki Amagasaki","Kazuki Yokoo"],"date":"2021-12-13","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.06571","openalex":"W4200631285"},"links":{"paper":"https://arxiv.org/abs/2112.06571","pdf":"https://arxiv.org/pdf/2112.06571"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":[],"status":"research","summary":"3D CNNs extended in time and vertical directions improve watershed-scale daily precipitation downscaling over a 2D CNN, with the vertical variant best on RMSE and NSE.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.06543","title":"Efficient spatio-temporal weather forecasting using U-Net","authors":["Akshay Punjabi","Pablo Izquierdo Ayala"],"date":"2021-12-13","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.06543","openalex":"W4226276684"},"links":{"paper":"https://arxiv.org/abs/2112.06543","pdf":"https://arxiv.org/pdf/2112.06543"},"orgs":[],"topic":"nowcasting","topics":[],"type":"application","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"SmaAt-UNet, a lightweight U-Net autoencoder, forecasts eight hours of satellite-based weather fields from one hour of input in the Weather4cast 2021 challenge.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-essd-2021-418","title":"Deep-Learning-Based Harmonization and Super-Resolution of Near-Surface Air Temperature from CMIP6 Models (1850–2100)","authors":["Xikun Wei","Guojie Wang","Donghan Feng","Zheng Duan","Daniel Fiifi Tawia Hagan","Liangliang Tao","Lijuan Miao","Buda Su","Tong Jiang"],"date":"2021-12-10","year":2021,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.5194/essd-2021-418","openalex":"W4200489093"},"links":{"paper":"https://doi.org/10.1002/joc.7926"},"orgs":["nuist"],"topic":"downscaling","topics":["post-processing"],"type":"benchmark","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Super-resolution deep learning merges 31 CMIP6 models into a 0.5° monthly near-surface temperature dataset (1850–2100) with bias correction and downscaling.","significance":3,"cited_by":12,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.05254","title":"Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion","authors":["Ken C. L. Wong","Hongzhi Wang","Etienne E. Vos","Bianca Zadrozny","Campbell D. Watson","Tanveer Syeda-Mahmood"],"date":"2021-12-10","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.05254","openalex":"W4200633850"},"links":{"paper":"https://arxiv.org/abs/2112.05254","pdf":"https://arxiv.org/pdf/2112.05254"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Late fusion of multiple neural networks with a denormalization layer improves long-range 2m temperature forecasts, beating 30-year climate normals; no headline number given.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12121657","title":"Visibility and Ceiling Nowcasting Using Artificial Intelligence Techniques for Aviation Applications","authors":["Fabricio Magalhães Cordeiro","Gutemberg Borges França","Francisco Leite de Albuquerque Neto","Ismail Gültepe"],"date":"2021-12-09","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12121657","openalex":"W4200019380"},"links":{"paper":"https://doi.org/10.3390/atmos12121657","pdf":"https://www.mdpi.com/2073-4433/12/12/1657/pdf?version=1639103291"},"orgs":["eccc"],"topic":"local-forecasting","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning regression on ten years of airport station data nowcasts visibility and ceiling height up to 1 h, with MAE of about 324 m and 167 m.","significance":3,"cited_by":17,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.04963","title":"Model-Agnostic Hybrid Numerical Weather Prediction and Machine Learning Paradigm for Solar Forecasting in the Tropics","authors":["Nigel Yuan Yun Ng","Harish Gopalan","Venugopalan S. G. Raghavan","Chin Chun Ooi"],"date":"2021-12-09","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.04963","openalex":"W4200632154"},"links":{"paper":"https://arxiv.org/abs/2112.04963","pdf":"https://arxiv.org/pdf/2112.04963"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"ML error correction of WRF solar irradiance forecasts in the tropics cuts NRMSE by 40-50% and makes results across four radiation schemes comparable.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.11330","title":"Integrated causal-predictive machine learning models for tropical cyclone epidemiology","authors":["Rachel C. Nethery","Nina Katz‐Christy","Marianthi‐Anna Kioumourtzoglou","Robbie M. Parks","Andrea Schumacher","G. Brooke Anderson"],"date":"2021-12-09","year":2021,"venue":"Biostatistics","venue_type":"journal","ids":{"arxiv":"2010.11330","doi":"10.1093/biostatistics/kxab047","openalex":"W3094260149"},"links":{"paper":"https://doi.org/10.1093/biostatistics/kxab047","pdf":"https://academic.oup.com/biostatistics/advance-article-pdf/doi/10.1093/biostatistics/kxab047/41941385/kxab047.pdf"},"orgs":["columbia-leap","colorado-state-university"],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Causal-predictive ML links tropical cyclone exposure to mortality and hospitalization in Medicare recipients, finding substantial respiratory hospitalization increases with wind speed as main driver.","significance":3,"cited_by":4,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3134007","title":"Tropical Cyclone Intensity Estimation Using Multidimensional Convolutional Neural Network From Multichannel Satellite Imagery","authors":["Wei Tian","Xinxin Zhou","Wei Huang","Yonghong Zhang","Pengfei Zhang","Shifeng Hao"],"date":"2021-12-08","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3134007","openalex":"W4206610887"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3134007"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"3D-attention CNN estimates tropical cyclone intensity from multichannel IR, water vapour and microwave imagery, with RMSE 9.48 kt, 25% better than the Advanced Dvorak Technique.","significance":3,"cited_by":17,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1071-wf21061","title":"Modelling chamise fuel moisture content across California: a machine learning approach","authors":["Scott B. Capps","Wei Zhuang","Rui Liu","Tom Rolinski","Xin Qu"],"date":"2021-12-08","year":2021,"venue":"International Journal of Wildland Fire","venue_type":"journal","ids":{"doi":"10.1071/wf21061","openalex":"W4206710461"},"links":{"paper":"https://doi.org/10.1071/wf21061","pdf":"https://www.publish.csiro.au/wf/pdf/WF21061"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"pre-operational","summary":"Random forest on dynamically downscaled weather produces a daily gridded chamise fuel moisture product for California, reaching R2 0.79 for new growth, to support wildfire danger.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.04278","title":"DMRVisNet: Deep Multi-head Regression Network for Pixel-wise Visibility Estimation Under Foggy Weather","authors":["Jing You","Shaocheng Jia","Xin Pei","Danya Yao"],"date":"2021-12-08","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.04278"},"links":{"paper":"https://arxiv.org/abs/2112.04278","pdf":"https://arxiv.org/pdf/2112.04278"},"orgs":[],"topic":"observations-remote-sensing","topics":["local-forecasting"],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Physics-informed CNN estimates pixel-wise fog visibility from single images via Koschmieder's law, trained on a 3,000-image synthetic AirSim dataset.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.03566","title":"More layers! End-to-end regression and uncertainty on tabular data with deep learning","authors":["Ivan Bondarenko"],"date":"2021-12-07","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.03566","openalex":"W4200634208"},"links":{"paper":"https://arxiv.org/abs/2112.03566","pdf":"https://arxiv.org/pdf/2112.03566","code":"https://github.com/bond005/yandex-shifts-weather"},"orgs":["huawei"],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Deep ensemble of self-normalizing networks with Gaussian outputs wins top-3 in Yandex Shifts weather temperature regression challenge under distribution shift.","significance":3,"cited_by":1,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4208-cicp.oa-2020-0158","title":"A Deep Spatio-Temporal Forecasting Model for Multi-Site Weather Prediction Post-Processing","authors":["Wenjia Kong","Haochen Li","Chen Yu","Jiangjiang Xia","Yanyan Kang","Pingwen Zhang"],"date":"2021-12-05","year":2021,"venue":"Communications in Computational Physics","venue_type":"journal","ids":{"doi":"10.4208/cicp.oa-2020-0158","openalex":"W4200479603"},"links":{"paper":"https://doi.org/10.4208/cicp.oa-2020-0158","pdf":"https://global-sci.org/intro/article_detail/auth/20020.html"},"orgs":["iap-cas"],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["transformer","cnn"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"DeepSTF combines CNN and attention encoder-decoder to post-process multi-site forecasts at 226 Beijing stations, improving on MOS benchmarks.","significance":3,"cited_by":20,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12121618","title":"A Machine-Learning Approach Combining Wavelet Packet Denoising with Catboost for Weather Forecasting","authors":["Dan Niu","Li Diao","Zengliang Zang","Hongshu Che","Tianbao Zhang","Xisong Chen"],"date":"2021-12-04","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12121618","openalex":"W4200061747"},"links":{"paper":"https://doi.org/10.3390/atmos12121618","pdf":"https://www.mdpi.com/2073-4433/12/12/1618/pdf?version=1638774718"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Wavelet packet denoising with CatBoost combines station observations and NWP priors to beat LSTM and random forest for short-term Beijing weather forecasts.","significance":2,"cited_by":39,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.02447","title":"Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data","authors":["Fantine Huot","R. Lily Hu","Nita Goyal","Tharun Sankar","Matthias Ihme","Yi-Fan Chen"],"date":"2021-12-04","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"2112.02447","doi":"10.1109/tgrs.2022.3192974","openalex":"W4225363088"},"links":{"paper":"https://arxiv.org/abs/2112.02447","pdf":"https://arxiv.org/pdf/2112.02447"},"orgs":["google-research"],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"benchmark","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","era5","other"],"status":"research","summary":"Curated nearly decade-long US wildfire spread dataset combining satellite fire data with weather and fuel variables, plus a neural network baseline for next-day spread.","significance":4,"cited_by":156,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-nhess-21-3679-2021","title":"Applying machine learning for drought prediction in a perfect model framework using data from a large ensemble of climate simulations","authors":["Elizaveta Felsche","Ralf Ludwig"],"date":"2021-12-03","year":2021,"venue":"Natural hazards and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/nhess-21-3679-2021","openalex":"W4200540997"},"links":{"paper":"https://doi.org/10.5194/nhess-21-3679-2021"},"orgs":["tum"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Applies neural networks and SHAP to predict European drought one month ahead from a 50-member regional climate large ensemble, with about 55–60% correct event classification.","significance":3,"cited_by":68,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3132395","title":"Tropical Cyclone Forecast Using Multitask Deep Learning Framework","authors":["Yuqiao Wu","Xiaoyi Geng","Zili Liu","Zhenwei Shi"],"date":"2021-12-03","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3132395","openalex":"W4205380839"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3132395"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Multitask framework uses an improved GAN to predict tropical cyclone fields, then networks extract track and intensity, with 24-h track error 116 km and intensity error 13.06 kt.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3131638","title":"A Deep Learning Framework for the Detection of Tropical Cyclones From Satellite Images","authors":["Aravind Nair","K. S. S. Sai Srujan","Sayali R. Kulkarni","Kshitij Alwadhi","Navya Jain","Hariprasad Kodamana","S. Sandeep","Viju Oommen John"],"date":"2021-12-03","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3131638","openalex":"W4246227656"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3131638","pdf":"https://www.techrxiv.org/articles/preprint/A_Deep_Learning_Framework_for_the_Detection_of_Tropical_Cyclones_from_Satellite_Images/16432641/1/files/30440400.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Mask R-CNN detector, wind speed filter and CNN classifier detect tropical cyclones in satellite images with 97.10% precision on test images.","significance":2,"cited_by":43,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.01085","title":"PTCT: Patches with 3D-Temporal Convolutional Transformer Network for Precipitation Nowcasting","authors":["Ziao Yang","Xiangrui Yang","Qifeng Lin"],"date":"2021-12-02","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.01085","openalex":"W4309384924"},"links":{"paper":"https://arxiv.org/abs/2112.01085","pdf":"https://arxiv.org/pdf/2112.01085"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["transformer","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"PTCT combines patch-based Transformer with 3D temporal convolution for autoregressive radar echo nowcasting, reporting state-of-the-art results on Guangzhou and HKO-7 datasets.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.16183-j.cnki.jsjtu.2021.s2.004","title":"Real-Time Risk Evaluation Method of Power System Equipment and N-m Fault Contingency Plan Generation Under Typhoon Meteorological Environment","authors":["QIN Kangping ZHOU Yi"],"date":"2021-12-01","year":2021,"venue":"DOAJ (DOAJ: Directory of Open Access Journals)","venue_type":"preprint","ids":{"doi":"10.16183/j.cnki.jsjtu.2021.s2.004","openalex":"W4226266005"},"links":{"paper":"https://doi.org/10.16183/j.cnki.jsjtu.2021.s2.004"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"pre-operational","summary":"Machine learning uses typhoon meteorological and grid data to quantify fault risk and generate N-m contingency plans for power grid dispatch, aimed at early warning.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1186-s40645-021-00459-y","title":"Classification of imbalanced cloud image data using deep neural networks: performance improvement through a data science competition","authors":["Daisuke Matsuoka"],"date":"2021-12-01","year":2021,"venue":"Progress in Earth and Planetary Science","venue_type":"journal","ids":{"doi":"10.1186/s40645-021-00459-y","openalex":"W4225697294"},"links":{"paper":"https://doi.org/10.1186/s40645-021-00459-y"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Competition-derived deep networks with oversampling, ensembles and cost-sensitive losses classify imbalanced cloud images for tropical cyclone precursors, improving performance by 65.4% over conventional methods.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1134-s0001433821120070","title":"The Use of Artificial Neuron Networks for Retrieval Temperature and Humidity Sounding of the Atmosphere According to the Data of the MTVZA-GY Microwave Radiometer Installed on the Meteor-M No. 2-2 Satellite","authors":["A. A. Filei","Alexander I. Andreev","А. B. Uspensky"],"date":"2021-12-01","year":2021,"venue":"Izvestiya Atmospheric and Oceanic Physics","venue_type":"journal","ids":{"doi":"10.1134/s0001433821120070","openalex":"W4226187568"},"links":{"paper":"https://doi.org/10.1134/s0001433821120070"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","stations","nwp-analysis"],"status":"research","summary":"Neural network retrieval of temperature and humidity profiles from Meteor-M MTVZA-GY microwave data achieves about 2-3 K temperature RMSE against radiosondes.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.rser.2021.111909","title":"Ensemble solar forecasting and post-processing using dropout neural network and information from neighboring satellite pixels","authors":["Gokhan Mert Yagli","Dazhi Yang","Dipti Srinivasan"],"date":"2021-12-01","year":2021,"venue":"Renewable and Sustainable Energy Reviews","venue_type":"journal","ids":{"doi":"10.1016/j.rser.2021.111909","openalex":"W3217232257"},"links":{"paper":"https://doi.org/10.1016/j.rser.2021.111909"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Dropout neural networks with neighboring satellite pixel inputs produce ensemble solar irradiance forecasts with post-processing for renewable energy applications.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10584-021-03272-0","title":"Machine learning reveals complex effects of climatic means and weather extremes on wheat yields during different plant developmental stages","authors":["Florian Schierhorn","Max Hofmann","Taras Gagalyuk","Igor Ostapchuk","Daniel Müller"],"date":"2021-12-01","year":2021,"venue":"Climatic Change","venue_type":"journal","ids":{"doi":"10.1007/s10584-021-03272-0","openalex":"W4200210215"},"links":{"paper":"https://doi.org/10.1007/s10584-021-03272-0","pdf":"https://link.springer.com/content/pdf/10.1007/s10584-021-03272-0.pdf"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning links daily climate and weather extremes to Ukrainian winter wheat yields, explaining 54% of variability and identifying heat, frost and drought during grain filling as key losses.","significance":3,"cited_by":50,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.01283","title":"Detecting Extratropical Cyclones of the Northern Hemisphere with Single Shot Detector","authors":["Minjing Shi","Pengfei He","Yuli Shi"],"date":"2021-12-01","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.01283"},"links":{"paper":"https://arxiv.org/abs/2112.01283","pdf":"https://arxiv.org/pdf/2112.01283"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":[],"status":"research","summary":"Applies a Single Shot Detector to detect Northern Hemisphere extratropical cyclones at developing, mature and declining stages, reaching 86.64% mAP for mature cyclones.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.01221","title":"Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs","authors":["Harshini Mangipudi","Griffin Mooers","Mike Pritchard","Tom Beucler","Stephan Mandt"],"date":"2021-12-01","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.01221"},"links":{"paper":"https://arxiv.org/abs/2112.01221","pdf":"https://arxiv.org/pdf/2112.01221"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"A multi-channel VAE jointly embeds vertical wind, temperature and water vapour from storm-resolving simulations, yielding unsupervised weather-pattern clusters with more interpretable latent structure.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2112.00570","title":"Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark","authors":["Alexandre Lacoste","Evan David Sherwin","Hannah Kerner","Hamed Alemohammad","Björn Lütjens","Jeremy Irvin","David Dao","Alex Chang","Mehmet Gunturkun","Alexandre Drouin","Pau Rodriguez","David Vazquez"],"date":"2021-12-01","year":2021,"venue_type":"preprint","ids":{"arxiv":"2112.00570"},"links":{"paper":"https://arxiv.org/abs/2112.00570","pdf":"https://arxiv.org/pdf/2112.00570"},"orgs":[],"topic":"foundation-models","topics":["benchmarks-data-eval"],"type":"benchmark","method":[],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Proposes a climate-change-oriented benchmark to develop foundation models for Earth observation imagery, with a call for community collaboration on evaluation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-14-7435-2021","title":"Support vector machine tropical wind speed retrieval in the presence of rain for Ku-band wind scatterometry","authors":["Xingou Xu","Ad Stoffelen"],"date":"2021-11-30","year":2021,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-14-7435-2021","openalex":"W3184706518"},"links":{"paper":"https://doi.org/10.5194/amt-14-7435-2021"},"orgs":["knmi"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Support vector regression corrects rain-affected Ku-band scatterometer winds over the tropics, reducing rain-induced bias against ASCAT as reference.","significance":2,"cited_by":9,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4236-cweee.2022.111001","title":"Development of Trees Management System Using Radial Basis Function Neural Network for Rain Forecast","authors":["Hasnul Auzani","Khairusy Syakirin Has-Yun","Farah Aniza Nazri"],"date":"2021-11-30","year":2021,"venue":"Computational Water Energy and Environmental Engineering","venue_type":"journal","ids":{"doi":"10.4236/cweee.2022.111001","openalex":"W3215910923"},"links":{"paper":"https://doi.org/10.4236/cweee.2022.111001","pdf":"https://content.scirp.org/pdf/cweee_2021113015171346.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Radial basis function network predicts Malaysian rainfall for tree management, reaching 57% accuracy; a small study with limited scope.","significance":1,"cited_by":6,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12040-021-01725-9","title":"Prediction of heavy rainfall days over a peninsular Indian station using the machine learning algorithms","authors":["Kandula Venkata Subrahmanyam","Chandravel Ramsenthil","A Girach Imran","Aniket Chakravorty","R Sreedhar","E. Ezhilrajan","D. Bala Subrahamanyam","Radhika Ramachandran","Karanam Kishore Kumar","M Rajasekhar","C. S. Jha"],"date":"2021-11-30","year":2021,"venue":"Journal of Earth System Science","venue_type":"journal","ids":{"doi":"10.1007/s12040-021-01725-9","openalex":"W3215668777"},"links":{"paper":"https://doi.org/10.1007/s12040-021-01725-9"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies classical machine learning classifiers to predict heavy rainfall days at one peninsular Indian station; the abstract is missing, so results are unreported.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.15605","title":"Synthetic weather radar using hybrid quantum-classical machine learning","authors":["Graham R. Enos","Matthew J. Reagor","Maxwell P. Henderson","Christina Young","Kyle Horton","Mandy Birch","Chad Rigetti"],"date":"2021-11-30","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.15605"},"links":{"paper":"https://arxiv.org/abs/2111.15605","pdf":"https://arxiv.org/pdf/2111.15605"},"orgs":[],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"model","method":["cnn","other"],"timescale":[],"spatial":["global"],"data":["radar","satellite","nwp-analysis"],"status":"research","summary":"Hybrid quantum-classical CNNs generate synthetic weather radar from satellite and NWP inputs, proposed as a benchmark for quantum advantage. No quantitative results given in the abstract.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en14237970","title":"Hybrid Machine Learning for Solar Radiation Prediction in Reduced Feature Spaces","authors":["Abdel-Rahman Hedar","Majid Almaraashi","Alaa E. Abdel-Hakim","Mahmoud Abdulrahim"],"date":"2021-11-29","year":2021,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en14237970","openalex":"W3217689365"},"links":{"paper":"https://doi.org/10.3390/en14237970","pdf":"https://www.mdpi.com/1996-1073/14/23/7970/pdf?version=1638187214"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Hybrid machine learning with rough-set feature reduction and WRF outputs improves solar radiation prediction in Saudi Arabia, with classification rates up to 8.5% higher.","significance":2,"cited_by":30,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12121596","title":"A Novel Multi-Input Multi-Output Recurrent Neural Network Based on Multimodal Fusion and Spatiotemporal Prediction for 0–4 Hour Precipitation Nowcasting","authors":["Fuhan Zhang","Xiaodong Wang","Jiping Guan"],"date":"2021-11-29","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12121596","openalex":"W3217658907"},"links":{"paper":"https://doi.org/10.3390/atmos12121596","pdf":"https://www.mdpi.com/2073-4433/12/12/1596/pdf?version=1638275899"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis","other"],"status":"research","summary":"MFSP-Net, a multi-input recurrent network, fuses precipitation grids, radar echoes and reanalysis for 0–4 h precipitation nowcasting, improving heavy-rain nowcasts over Southeast China.","significance":3,"cited_by":25,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2021.731803","title":"Wind Speed Forecasting in Fishing Harbor Anchorage Using a Novel Deep Convolutional Neural Network","authors":["Caifen He","Qiaote Chen","Xuyuan Fang","Yangzhang Zhou","Randi Fu","Wei Jin"],"date":"2021-11-29","year":2021,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2021.731803","openalex":"W3216144411"},"links":{"paper":"https://doi.org/10.3389/feart.2021.731803","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2021.731803/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"A 1D and 2D CNN combining station observations with NWP output forecasts harbor wind speed one hour ahead, with MAE of 0.3945 m/s.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.14724","title":"Encoding Causal Macrovariables","authors":["Benedikt Höltgen"],"date":"2021-11-29","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.14724"},"links":{"paper":"https://arxiv.org/abs/2111.14724","pdf":"https://arxiv.org/pdf/2111.14724"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Information-bottleneck method learns causal macrovariables from high-dimensional data and recovers both known El Niño variants in real climate data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.14671","title":"ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models","authors":["Salva Rühling Cachay","Venkatesh Ramesh","Jason N. S. Cole","Howard Barker","David Rolnick"],"date":"2021-11-29","year":2021,"venue":"35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks","venue_type":"journal","ids":{"arxiv":"2111.14671","openalex":"W3203714988"},"links":{"paper":"https://arxiv.org/abs/2111.14671","pdf":"https://arxiv.org/pdf/2111.14671","code":"https://github.com/RolnickLab/climart"},"orgs":["eccc"],"topic":"benchmarks-data-eval","topics":["hybrid-parameterization"],"type":"benchmark","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"ClimART offers over 10 million radiative transfer samples from climate conditions to benchmark neural emulators, showing shortcomings of prior datasets and architectures.","significance":4,"cited_by":8,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2111.14038","title":"Learning Wildfire Model from Incomplete State Observations","authors":["Alissa Chavalithumrong","Hyung-Jin Yoon","Petros Voulgaris"],"date":"2021-11-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.14038"},"links":{"paper":"https://arxiv.org/abs/2111.14038","pdf":"https://arxiv.org/pdf/2111.14038"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Deep neural network with online estimation predicts burned area at five western US locations from climate and fire history data.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41612-021-00214-6","title":"RETRACTED ARTICLE: Machine learning prediction of the Madden-Julian oscillation","authors":["Riccardo Silini","Marcelo Barreiro","Cristina Masoller"],"date":"2021-11-25","year":2021,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"doi":"10.1038/s41612-021-00214-6","openalex":"W3155438109"},"links":{"paper":"https://doi.org/10.1038/s41612-021-00214-6","pdf":"https://www.nature.com/articles/s41612-021-00214-6.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Retracted article: feed-forward and recurrent networks predict the Madden–Julian oscillation with about 26–27 days skill, reaching 60 days for some initial phases.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl093531","title":"Deep Residual Convolutional Neural Network Combining Dropout and Transfer Learning for ENSO Forecasting","authors":["Jie Hu","Bin Weng","Tianqiang Huang","Jianyun Gao","Feng Ye","Lijun You"],"date":"2021-11-25","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl093531","openalex":"W3164275894"},"links":{"paper":"https://doi.org/10.1029/2021gl093531","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021GL093531"},"orgs":["cma"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"A deep residual CNN with dropout and transfer learning extends ENSO Niño3.4 forecast skill to a 20-month lead, three months beyond the previous optimal model.","significance":4,"cited_by":54,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11356-021-17668-z","title":"Weather forecasting based on data-driven and physics-informed reservoir computing models","authors":["Yslam D. Mammedov","Ezutah Udoncy Olugu","Guleid A. Farah"],"date":"2021-11-25","year":2021,"venue":"Environmental Science and Pollution Research","venue_type":"journal","ids":{"doi":"10.1007/s11356-021-17668-z","openalex":"W3201318708"},"links":{"paper":"https://doi.org/10.1007/s11356-021-17668-z","pdf":"https://www.researchsquare.com/article/rs-884990/latest.pdf"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["other","physics-constrained"],"timescale":["medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Data-driven and physics-informed reservoir computing models are proposed for weather forecasting. The abstract is unavailable, so the scope is uncertain.","significance":2,"cited_by":24,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en14237878","title":"A Fast and Accurate Wind Speed and Direction Nowcasting Model for Renewable Energy Management Systems","authors":["Saira Al-Zadjali","Ahmed Al Maashri","Amer Al‐Hinai","Rashid S. Al Abri","Swaroop Gajare","Sultan Al-Yahyai","Mostafa Bakhtvar"],"date":"2021-11-24","year":2021,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en14237878","openalex":"W3217770689"},"links":{"paper":"https://doi.org/10.3390/en14237878","pdf":"https://www.mdpi.com/1996-1073/14/23/7878/pdf?version=1637755238"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Ensemble neural networks trained on perturbed observations nowcast wind speed and direction for wind farm output, with better accuracy and runtime than alternatives.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12121554","title":"Impact of the Madden–Julian Oscillation on North Indian Ocean Cyclone Intensity","authors":["Meer Mohammed Ali","Uppalapati Naga Tanusha","C. Purna Chand","Borra Himasri","Mark A. Bourassa","Yangxing Zheng"],"date":"2021-11-24","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12121554","openalex":"W3216537882"},"links":{"paper":"https://doi.org/10.3390/atmos12121554","pdf":"https://www.mdpi.com/2073-4433/12/12/1554/pdf?version=1637852584"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"An artificial neural network links MJO indices to North Indian Ocean cyclone wind intensity over 1974–2019, with scatter index falling from 0.45 for depressions to 0.03 for super cyclones.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7464","title":"Evaluation of statistical downscaling methods for climate change projections over Spain: Future conditions with pseudo reality (transferability experiment)","authors":["Alfonso Hernanz","Juan Andrés García Valero","Marta Domínguez","Ernesto Rodríguez Camino"],"date":"2021-11-24","year":2021,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7464","openalex":"W3215637970"},"links":{"paper":"https://doi.org/10.1002/joc.7464","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.7464"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Intercomparison of five statistical downscaling methods, including ANN, SVM and kernel ridge regression, reveals transferability problems for future climate over Spain.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3130406","title":"A 3-D Storm Motion Estimation Method Based on Point Cloud Learning and Doppler Weather Radar Data","authors":["Zhuoyu Zhang","Zhenghao He","Jin Shui Yang","Yuchen Liu","Riyang Bao","Shuping Gao"],"date":"2021-11-23","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3130406","openalex":"W4255647317"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3130406"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A point-cloud network with attention estimates 3-D storm motion from radar volumes, trained on synthetic Perlin-noise data, with 5-15% lower endpoint error.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3213268027","title":"New ways for dynamical prediction of extreme heat waves: rare event simulations and stochastic process-based machine learning.","authors":["Freddy Bouchet","Francesco Ragone","Dario Lucente","George Miloshevich","Corentin Herbert"],"date":"2021-11-22","year":2021,"venue":"Bulletin of the American Physical Society","venue_type":"journal","ids":{"openalex":"W3213268027"},"links":{"paper":"https://meetings.aps.org/Meeting/DFD21/Session/H02.5"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Conference abstract proposing rare-event simulation and stochastic process-based machine learning for dynamical prediction of extreme heatwaves; no details are available.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w13223294","title":"Seasonal Prediction of Summer Precipitation in the Middle and Lower Reaches of the Yangtze River Valley: Comparison of Machine Learning and Climate Model Predictions","authors":["Chentao He","Jiangfeng Wei","Yuanyuan Song","Jing‐Jia Luo"],"date":"2021-11-21","year":2021,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w13223294","openalex":"W3216328498"},"links":{"paper":"https://doi.org/10.3390/w13223294","pdf":"https://www.mdpi.com/2073-4441/13/22/3294/pdf?version=1637478478"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"evaluation","method":["classical-ml","cnn","rnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Random forest predicts Yangtze summer precipitation with 0.473 skill from December, outperforming eight climate models in several respects.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13224673","title":"A Machine Learning Based Downscaling Approach to Produce High Spatio-Temporal Resolution Land Surface Temperature of the Antarctic Dry Valleys from MODIS Data","authors":["Maite Lezama Valdes","Marwan Katurji","Hanna Meyer"],"date":"2021-11-19","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13224673","openalex":"W3215375995"},"links":{"paper":"https://doi.org/10.3390/rs13224673","pdf":"https://www.mdpi.com/2072-4292/13/22/4673/pdf?version=1637565766"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"Machine learning downscales MODIS land surface temperature from 1 km to 30 m over Antarctic Dry Valleys using Landsat 8 as reference, achieving R² of 0.78.","significance":2,"cited_by":33,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-ai2040036","title":"MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain","authors":["Gabriele Accarino","Marco Chiarelli","Francesco Immorlano","Valeria Aloisi","Andrea Gatto","Giovanni Aloisio"],"date":"2021-11-19","year":2021,"venue":"AI","venue_type":"journal","ids":{"doi":"10.3390/ai2040036","openalex":"W3215607457"},"links":{"paper":"https://doi.org/10.3390/ai2040036","pdf":"https://www.mdpi.com/2673-2688/2/4/36/pdf?version=1638260477"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"MSG-GAN-SD, a multi-scale gradient GAN, downscales ERA-Interim 2-m temperature from 83 km to 14 km over the EURO-CORDEX domain.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.09954","title":"MS-nowcasting: Operational Precipitation Nowcasting with Convolutional LSTMs at Microsoft Weather","authors":["Sylwester Klocek","Haiyu Dong","Matthew Dixon","Panashe Kanengoni","Najeeb Kazmi","Pete Luferenko","Zhongjian Lv","Shikhar Sharma","Jonathan Weyn","Siqi Xiang"],"date":"2021-11-18","year":2021,"venue":"NeurIPS 2021 Workshop on Tackling Climate Change with Machine Learning, 2021. https://www.climatechange.ai/papers/neurips2021/19","venue_type":"journal","ids":{"arxiv":"2111.09954","openalex":"W3217077725"},"links":{"paper":"https://arxiv.org/abs/2111.09954","pdf":"https://arxiv.org/pdf/2111.09954"},"orgs":["microsoft-research"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"operational","summary":"Microsoft's operational ConvLSTM radar nowcasting model, conditioned on HRRR, beats optical flow and HRRR by 20–25% for lead times up to 6 hours.","significance":4,"cited_by":18,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-14-6977-2021","title":"ENSO-ASC 1.0.0: ENSO deep learning forecast model with a multivariate air–sea coupler","authors":["Bin Mu","Bo Qin","Shijin Yuan"],"date":"2021-11-17","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-14-6977-2021","openalex":"W3192776183"},"links":{"paper":"https://doi.org/10.5194/gmd-14-6977-2021"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["gnn","transformer"],"timescale":["seasonal"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"A graph-based air-sea coupler inside an ENSO deep learning model reaches Niño3.4 correlation of 0.78 at 6-month lead and outperforms other ENSO forecast models.","significance":4,"cited_by":71,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app112210852","title":"Forecasting the Daily Maximal and Minimal Temperatures from Radiosonde Measurements Using Neural Networks","authors":["Gregor Skok","Doruntina Hoxha","Žiga Zaplotnik"],"date":"2021-11-17","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app112210852","openalex":"W3214317286"},"links":{"paper":"https://doi.org/10.3390/app112210852","pdf":"https://www.mdpi.com/2076-3417/11/22/10852/pdf?version=1637143410"},"orgs":[],"topic":"local-forecasting","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["medium","s2s","seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Dense neural networks predict daily max and min 2 m temperatures from radiosonde profiles up to 500 days ahead, beating persistence but not climatology beyond day 2-3.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11069-021-05116-7","title":"Modeling of tropical cyclone activity over the North Indian Ocean using generalised additive model and machine learning techniques: role of Boreal summer intraseasonal oscillation","authors":["Md Wahiduzzaman","Jing‐Jia Luo"],"date":"2021-11-17","year":2021,"venue":"Natural Hazards","venue_type":"journal","ids":{"doi":"10.1007/s11069-021-05116-7","openalex":"W3213586462"},"links":{"paper":"https://doi.org/10.1007/s11069-021-05116-7"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Generalised additive and machine learning models link North Indian Ocean tropical cyclone activity to boreal summer intraseasonal oscillation; no abstract was available, so this rests on the title.","significance":2,"cited_by":7,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-1035885-v1","title":"Effect of Climate Change on the Rainfall Trends: A case study of Pune, India","authors":["Shalaka Shah","Shreenivas N. Londhe"],"date":"2021-11-16","year":2021,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-1035885/v1","openalex":"W3215239254"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-1035885/v1","pdf":"https://www.researchsquare.com/article/rs-1035885/latest.pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"application","method":["other"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Artificial neural network downscales five GCMs' rainfall over Pune, India, giving a higher correlation than distribution-based scaling for the best models.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-07055900.2021.1992341","title":"A Deep Learning Approach for the Identification of Long-Duration Mixed Precipitation in Montréal (Canada)","authors":["Magdalena Mittermeier","Émilie Bresson","Dominique Paquin","Ralf Ludwig"],"date":"2021-11-16","year":2021,"venue":"ATMOSPHERE-OCEAN","venue_type":"journal","ids":{"doi":"10.1080/07055900.2021.1992341","openalex":"W3214124917"},"links":{"paper":"https://doi.org/10.1080/07055900.2021.1992341","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/07055900.2021.1992341?needAccess=true"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional","local"],"data":["cmip","era5"],"status":"research","summary":"CNN identifies long-duration freezing rain and ice pellet synoptic patterns in CRCM5 output over Montréal, reaching a Matthews correlation of 0.50.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.08626","title":"Adjoint-Matching Neural Network Surrogates for Fast 4D-Var Data Assimilation","authors":["Austin Chennault","Andrey A. Popov","Amit N. Subrahmanya","Rachel Cooper","Ali Haisam Muhammad Rafid","Anuj Karpatne","Adrian Sandu"],"date":"2021-11-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.08626","openalex":"W3214050492"},"links":{"paper":"https://arxiv.org/abs/2111.08626","pdf":"https://arxiv.org/pdf/2111.08626"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Trains neural surrogates using adjoint information to speed up 4D-Var assimilation, showing better results than forward-only surrogates on Lorenz-63.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7457","title":"Southwest Pacific tropical cyclone development classification utilizing machine learning and synoptic composites","authors":["Rupsa Bhowmick","Jill C. Trepanier","Alex M. Haberlie"],"date":"2021-11-15","year":2021,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7457","openalex":"W3212130345"},"links":{"paper":"https://doi.org/10.1002/joc.7457","pdf":"https://www.osti.gov/servlets/purl/1834538"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Random forest classifies whether southwest Pacific tropical depressions develop into storms with 91% test accuracy, with aerosol optical depth among the top predictors.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosenv.2021.118850","title":"Improving the accuracy and spatial resolution of precipitable water vapor dataset using a neural network-based downscaling method","authors":["Xiongwei Ma","Yibin Yao","Bao Zhang","Mengjia Yang","Hang Liu"],"date":"2021-11-14","year":2021,"venue":"Atmospheric Environment","venue_type":"journal","ids":{"doi":"10.1016/j.atmosenv.2021.118850","openalex":"W3213752028"},"links":{"paper":"https://doi.org/10.1016/j.atmosenv.2021.118850"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Neural network downscaling raises the spatial resolution of a precipitable water vapor dataset; the abstract is missing, so accuracy gains are unreported.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.07470","title":"Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks","authors":["Lasse Espeholt","Shreya Agrawal","Casper Sønderby","Manoj Kumar","Jonathan Heek","Carla Bromberg","Cenk Gazen","Rob Carver","Marcin Andrychowicz","Jason Hickey","Aaron Bell","Nal Kalchbrenner"],"date":"2021-11-14","year":2021,"venue":"Nature Communications","venue_type":"journal","ids":{"arxiv":"2111.07470","doi":"10.1038/s41467-022-32483-x","openalex":"W4294068833"},"links":{"paper":"https://arxiv.org/abs/2111.07470","pdf":"https://arxiv.org/pdf/2111.07470"},"orgs":["google-research"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"A large-context neural network forecasts precipitation 12 hours ahead over CONUS, beating HRRR and HREF in skill.","significance":5,"cited_by":254,"score":85,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.37936-ecti-cit.2021153.240957","title":"Cascading Models of CNN and GRU with Autoencoder Loss for Precipitation Forecast in Thailand","authors":["Fuenglada Manokij","Peerapon Vateekul","Kanoksri Sarinnapakorn"],"date":"2021-11-13","year":2021,"venue":"ECTI Transactions on Computer and Information Technology (ECTI-CIT)","venue_type":"journal","ids":{"doi":"10.37936/ecti-cit.2021153.240957","openalex":"W3214575438"},"links":{"paper":"https://doi.org/10.37936/ecti-cit.2021153.240957","pdf":"https://ph01.tci-thaijo.org/index.php/ecticit/article/download/240957/167660"},"orgs":[],"topic":"local-forecasting","topics":["nowcasting"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"A CNN classifies rain events and a GRU forecasts hourly rainfall in Thailand, with focal and autoencoder losses. It outperforms ARIMA and CNN-GRU on RMSE in most regions.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3128076","title":"Predicting Tropical Cyclone Rapid Intensification From Satellite Microwave Data and Neural Networks","authors":["Francisco Javier Tapiador","Andrés Navarro","Raúl Martín Martín","Svetla M. Hristova‐Veleva","Ziad S. Haddad"],"date":"2021-11-13","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3128076","openalex":"W3212474793"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3128076"},"orgs":["nasa","caltech"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A neural network using a microwave rain index and 24 h wind changes identifies tropical cyclone rapid intensification with near-perfect skill and reveals environmental drivers up to 1050 km away.","significance":3,"cited_by":10,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en14227581","title":"Photovoltaic Energy All-Day and Intra-Day Forecasting Using Node by Node Developed Polynomial Networks Forming PDE Models Based on the L-Transformation","authors":["Ladislav Zjavka"],"date":"2021-11-12","year":2021,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en14227581","openalex":"W3211792557"},"links":{"paper":"https://doi.org/10.3390/en14227581","pdf":"https://www.mdpi.com/1996-1073/14/22/7581/pdf?version=1636971489"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Differential polynomial neural networks forecast photovoltaic output from recent weather and power data, as an alternative to delayed NWP cloud forecasts.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.06841","title":"A posteriori learning of quasi-geostrophic turbulence parametrization: an experiment on integration steps","authors":["Hugo Frezat","Julien Le Sommer","Ronan Fablet","Guillaume Balarac","Redouane Lguensat"],"date":"2021-11-12","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.06841","openalex":"W4221140700"},"links":{"paper":"https://arxiv.org/abs/2111.06841","pdf":"https://arxiv.org/pdf/2111.06841"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"A neural subgrid closure trained jointly with a quasi-geostrophic solver using an a posteriori loss gives stable, realistic 2D turbulence simulations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-14-7079-2021","title":"The University of Washington Ice–Liquid Discriminator (UWILD) improves single-particle phase classifications of hydrometeors within Southern Ocean clouds using machine learning","authors":["Rachel L. Atlas","Johannes Mohrmann","Joseph A. Finlon","Jeremy Lu","Ian Hsiao","Robert Wood","Minghui Diao"],"date":"2021-11-11","year":2021,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-14-7079-2021","openalex":"W3168290198"},"links":{"paper":"https://doi.org/10.5194/amt-14-7079-2021"},"orgs":["university-of-washington"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"UWILD random forest classifies ice versus liquid particles in Southern Ocean clouds from 2D-S probe images with 95% accuracy, beating two existing methods.","significance":3,"cited_by":14,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36909-jer.iccemme.15635","title":"Weather Forecasting Using Decision Tree","authors":["Rashmi Bhardwaj","Varsha Duhoon"],"date":"2021-11-11","year":2021,"venue":"Journal of Engineering Research","venue_type":"journal","ids":{"doi":"10.36909/jer.iccemme.15635","openalex":"W3213003852"},"links":{"paper":"https://doi.org/10.36909/jer.iccemme.15635","pdf":"https://kuwaitjournals.org/jer/index.php/JER/article/download/15635/2727"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Decision tree methods, including M5P, REP Tree and Random Forest, forecast daily maximum and minimum temperature in Delhi from 17 months of data. Random Forest is best.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.patrec.2021.11.012","title":"SAF-Net: A spatio-temporal deep learning method for typhoon intensity prediction","authors":["Guangning Xu","Kenghong Lin","Xutao Li","Yunming Ye"],"date":"2021-11-11","year":2021,"venue":"Pattern Recognition Letters","venue_type":"journal","ids":{"doi":"10.1016/j.patrec.2021.11.012","openalex":"W3212309402"},"links":{"paper":"https://doi.org/10.1016/j.patrec.2021.11.012"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["regional"],"data":[],"status":"research","summary":"SAF-Net proposes a spatio-temporal deep learning model for typhoon intensity prediction; no abstract was available, so this rests on the title alone.","significance":2,"cited_by":43,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.06447","title":"Observation Error Covariance Specification in Dynamical Systems for Data assimilation using Recurrent Neural Networks","authors":["Sibo Cheng","Mingming Qiu"],"date":"2021-11-11","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.06447"},"links":{"paper":"https://arxiv.org/abs/2111.06447","pdf":"https://arxiv.org/pdf/2111.06447"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Uses LSTM networks to learn observation error covariances for data assimilation, outperforming DI01 and D05 tuning on Lorenz-63 and shallow-water twin experiments.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.06240","title":"Improvements to short-term weather prediction with recurrent-convolutional networks","authors":["Jussi Leinonen"],"date":"2021-11-11","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.06240","doi":"10.1109/bigdata52589.2021.9671869"},"links":{"paper":"https://arxiv.org/abs/2111.06240","pdf":"https://arxiv.org/pdf/2111.06240"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Improves a recurrent-convolutional satellite nowcasting model for the Weather4cast 2021 competition via a shallower variant, AdaBelief and ensembling.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.06011","title":"Climate Modeling with Neural Diffusion Equations","authors":["Jeehyun Hwang","Jeongwhan Choi","Hwangyong Choi","Kookjin Lee","Dongeun Lee","Noseong Park"],"date":"2021-11-11","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.06011"},"links":{"paper":"https://arxiv.org/abs/2111.06011","pdf":"https://arxiv.org/pdf/2111.06011"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Proposes neural diffusion equations, combining neural ODEs with diffusion, for climate modeling; it beats eleven baselines on two real and one synthetic dataset.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3126419","title":"Global Tropical Cyclone Precipitation Estimation via a Multitask Convolutional Neural Network Based on HURSAT-B1 Data","authors":["Mei Xue","Renlong Hang","Xiao–Tong Yuan","Pengfei Xiao","Qingshan Liu"],"date":"2021-11-09","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3126419","openalex":"W3214712601"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3126419"},"orgs":["nuist"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A multitask CNN estimates global tropical cyclone precipitation from HURSAT-B1 imagery, reaching 0.68 detection probability and beating MLR and random forest baselines.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.05303","title":"Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach","authors":["Magdalena Mittermeier","Maximilian Weigert","David Rügamer"],"date":"2021-11-09","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.05303","openalex":"W3211961146"},"links":{"paper":"https://arxiv.org/abs/2111.05303","pdf":"https://arxiv.org/pdf/2111.05303"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"A smoothed CNN classifies six anticyclonic circulation types linked to European drought and heat, to help identify their drivers in climate simulations.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.04665","title":"Evaluating Predictive Uncertainty and Robustness to Distributional Shift Using Real World Data","authors":["Kumud Lakara","Akshat Bhandari","Pratinav Seth","Ujjwal Verma"],"date":"2021-11-08","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.04665","openalex":"W3212858590"},"links":{"paper":"https://arxiv.org/abs/2111.04665","pdf":"https://arxiv.org/pdf/2111.04665"},"orgs":[],"topic":"xai-uq-physics","topics":["benchmarks-data-eval"],"type":"evaluation","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Proposes uncertainty and robustness-to-shift metrics for regression, evaluated with baselines on the Shifts weather prediction dataset under distributional shift.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijece.v12i1.pp639-648","title":"A novel weather parameters prediction scheme and their effects on crops","authors":["Naveen Lingaraju","Hosaagrahara Savalegowda Mohan"],"date":"2021-11-05","year":2021,"venue":"International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering","venue_type":"journal","ids":{"doi":"10.11591/ijece.v12i1.pp639-648","openalex":"W3185994196"},"links":{"paper":"https://doi.org/10.11591/ijece.v12i1.pp639-648","pdf":"https://ijece.iaescore.com/index.php/IJECE/article/download/24879/15368"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Fitness-tuned adaptive neural network forecasts Karnataka rainfall and temperature for 2021-2030 and maps effects on five crops; validation is limited.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.03476","title":"A Variational U-Net for Weather Forecasting","authors":["Pak Hay Kwok","Qi Qi"],"date":"2021-11-05","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.03476","openalex":"W3213235731"},"links":{"paper":"https://arxiv.org/abs/2111.03476","pdf":"https://arxiv.org/pdf/2111.03476"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Variational U-Net combining VAE probabilistic modelling with U-Net detail recovery placed third in the Weather4cast satellite forecasting challenge.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-x5w61x","title":"Regional analysis of climate projections using Bias Corrected spatial disaggregated super-resolution convolutional neural networks","authors":["Akash Awasthi","Syed Rizvi","Jaer Nizam","Kelan Wu"],"date":"2021-11-04","year":2021,"venue_type":"other","ids":{"doi":"10.31223/x5w61x","openalex":"W4200586078"},"links":{"paper":"https://doi.org/10.31223/x5w61x"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Bias-corrected super-resolution CNN downscales six GCMs' daily precipitation and temperature from 1.25° to 0.25° over India, targeting extremes better than SRCNN and LSTM.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.02736","title":"Deep Learning Methods for Daily Wildfire Danger Forecasting","authors":["Ioannis Prapas","Spyros Kondylatos","Ioannis Papoutsis","Gustau Camps-Valls","Michele Ronco","Miguel-Ángel Fernández-Torres","Maria Piles Guillem","Nuno Carvalhais"],"date":"2021-11-04","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.02736"},"links":{"paper":"https://arxiv.org/abs/2111.02736","pdf":"https://arxiv.org/pdf/2111.02736"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"ConvLSTM on harmonized Earth observation and weather covariates forecasts next-day national fire danger with AUC 0.926, beating a random forest baseline.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-wes-6-1363-2021","title":"Assessing boundary condition and parametric uncertainty in numerical-weather-prediction-modeled, long-term offshore wind speed through machine learning and analog ensemble","authors":["Nicola Bodini","Weiming Hu","Mike Optis","Guido Cervone","Stefano Alessandrini"],"date":"2021-11-03","year":2021,"venue":"Wind energy science","venue_type":"journal","ids":{"doi":"10.5194/wes-6-1363-2021","openalex":"W3163360998"},"links":{"paper":"https://doi.org/10.5194/wes-6-1363-2021"},"orgs":["ncar"],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Gradient boosting and analog ensembles extrapolate NWP wind-speed uncertainty from one year of ensemble runs to 20 years for offshore wind siting, with R2 above 0.75.","significance":3,"cited_by":17,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-hess-25-5667-2021","title":"Easy-to-use spatial random-forest-based downscaling-calibration method for producing precipitation data with high resolution and high accuracy","authors":["Chuanfa Chen","Baojian Hu","Yanyan Li"],"date":"2021-11-03","year":2021,"venue":"Hydrology and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/hess-25-5667-2021","openalex":"W3208227771"},"links":{"paper":"https://doi.org/10.5194/hess-25-5667-2021"},"orgs":[],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Spatial random forest downscales and calibrates IMERG satellite precipitation in Sichuan using gauges and covariates, outperforming GWR, ANN and kriging.","significance":3,"cited_by":86,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-bdcc5040062","title":"Prediction of Cloud Fractional Cover Using Machine Learning","authors":["Hanna Svennevik","Michael Alexander Riegler","Steven Alexander Hicks","Trude Storelvmo","Hugo L. Hammer"],"date":"2021-11-03","year":2021,"venue":"Big Data and Cognitive Computing","venue_type":"journal","ids":{"doi":"10.3390/bdcc5040062","openalex":"W3209528543"},"links":{"paper":"https://doi.org/10.3390/bdcc5040062","pdf":"https://www.mdpi.com/2504-2289/5/4/62/pdf?version=1635945239"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Compares ConvLSTM and multiple regression for statistical downscaling of future cloud fractional cover; regression performs best overall, while ConvLSTM wins in coastal and mountain areas.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32604-cmc.2022.021015","title":"Artificial Intelligence Based Solar Radiation Predictive Model Using Weather Forecasts","authors":["Talha Ahmed Khan","Khizar Abbas","Muhammad Afaq","Wang‐Cheol Song"],"date":"2021-11-03","year":2021,"venue":"Computers, materials & continua/Computers, materials & continua (Print)","venue_type":"journal","ids":{"doi":"10.32604/cmc.2022.021015","openalex":"W3210620853"},"links":{"paper":"https://doi.org/10.32604/cmc.2022.021015","pdf":"https://file.techscience.com/ueditor/files/cmc/TSP_CMC-71-1/TSP_CMC_21015/TSP_CMC_21015.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"An Elman neural network tuned by Mayfly Optimization predicts solar irradiance from weather forecast data, with Hadoop preprocessing. Results beat comparison methods.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-20-0291.1","title":"A Novel Deep Learning Model by BiGRU with Attention Mechanism for Tropical Cyclone Track Prediction in the Northwest Pacific","authors":["Tao Song","Ying Li","Fan Meng","Pengfei Xie","Danya Xu"],"date":"2021-11-03","year":2021,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-20-0291.1","openalex":"W3210553524"},"links":{"paper":"https://doi.org/10.1175/jamc-d-20-0291.1"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A BiGRU with attention predicts Northwest Pacific tropical cyclone tracks at 6–72 h, outperforming RNN, LSTM and GRU baselines and beating agency forecasts at longer leads.","significance":3,"cited_by":56,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.02121","title":"Spatiotemporal Weather Data Predictions with Shortcut Recurrent-Convolutional Networks: A Solution for the Weather4cast challenge","authors":["Jussi Leinonen"],"date":"2021-11-03","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.02121"},"links":{"paper":"https://arxiv.org/abs/2111.02121","pdf":"https://arxiv.org/pdf/2111.02121","code":"https://github.com/jleinonen/weather4cast-stage1"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Encoder-forecaster with residual ConvGRU and U-Net-style shortcuts for Weather4cast satellite image prediction; early forecasts stay sharp, later ones blur.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3215726990","title":"Implementation on Solar Forecasting Analysis based on Regression Analysis and Classification Technique using Machine Learning","authors":["Aditya Vijay Patil"],"date":"2021-11-01","year":2021,"venue":"Journal of Emerging Technologies and Innovative Research","venue_type":"journal","ids":{"openalex":"W3215726990"},"links":{"paper":"https://www.jetir.org/papers/JETIR2111317.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"SVM and regression models forecast one solar plant's output from meteorological measurements; the case study has limited novelty.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54302-mausam.v72i4.3546","title":"A precipitation forecasting model using machine learning on big data in clouds environment","authors":["Mahboob Alam","Mohd Amjad"],"date":"2021-11-01","year":2021,"venue":"MAUSAM","venue_type":"journal","ids":{"doi":"10.54302/mausam.v72i4.3546","openalex":"W3210652048"},"links":{"paper":"https://doi.org/10.54302/mausam.v72i4.3546"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"A machine learning approach to precipitation level prediction and mapping is proposed on a cloud big-data environment. The abstract is truncated and gives no quantitative results.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54302-mausam.v72i4.3545","title":"A comparison of different weather forecasting models for the monthly forecast of Lahore city","authors":["Sajid Ali","ZAHEER ABBAS","Muhammad Moeen Butt"],"date":"2021-11-01","year":2021,"venue":"MAUSAM","venue_type":"journal","ids":{"doi":"10.54302/mausam.v72i4.3545","openalex":"W3208008575"},"links":{"paper":"https://doi.org/10.54302/mausam.v72i4.3545"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml","rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares time-series regression, SARFIMA and neural networks for monthly weather forecasts in Lahore. The ANN with moving-average preprocessing has the lowest RMSE.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-2515-7620-ac371f","title":"Statistical and machine learning methods applied to the prediction of different tropical rainfall types","authors":["Jiayi Wang","Raymond K. W. Wong","Mikyoung Jun","Courtney Schumacher","Ramalingam Saravanan","Chunmei Sun"],"date":"2021-11-01","year":2021,"venue":"Environmental Research Communications","venue_type":"journal","ids":{"doi":"10.1088/2515-7620/ac371f","openalex":"W4225716456"},"links":{"paper":"https://doi.org/10.1088/2515-7620/ac371f","pdf":"https://iopscience.iop.org/article/10.1088/2515-7620/ac371f/pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"Neural network and random forest predict tropical Pacific rain type from MERRA-2 large-scale state, but neither beats a GLM and all miss extreme rates.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.egyr.2021.11.021","title":"Short-term regional wind power forecasting for small datasets with input data correction, hybrid neural network, and error analysis","authors":["Weichao Dong","Hexu Sun","Jianxin Tan","Zheng Li","Jingxuan Zhang","Yu Yang Zhao"],"date":"2021-11-01","year":2021,"venue":"Energy Reports","venue_type":"journal","ids":{"doi":"10.1016/j.egyr.2021.11.021","openalex":"W3217093429"},"links":{"paper":"https://doi.org/10.1016/j.egyr.2021.11.021","pdf":"https://www.sciencedirect.com/science/article/pii/S2352484721011665/pdf"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Autoencoder correction of regional NWP feeds a hybrid neural network that forecasts regional wind power, needing only about three months of training data.","significance":2,"cited_by":33,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.2041","title":"Machine learning in calibrating tropical cyclone intensity forecast of ECMWF EPS","authors":["Ming Hei Kenneth Chan","Wai Kin Wong","Kin Chung Au‐Yeung"],"date":"2021-11-01","year":2021,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.2041","openalex":"W4200534661"},"links":{"paper":"https://doi.org/10.1002/met.2041","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.2041"},"orgs":["eth-zurich"],"topic":"post-processing","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"An XGBoost model post-processes ECMWF EPS outputs to correct systematic negative biases in tropical cyclone maximum wind forecasts over the western North Pacific, 2016–2019.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.12683","title":"Data-Based Models for Hurricane Evolution Prediction: A Deep Learning Approach","authors":["Rikhi Bose","Adam Pintar","Emil Simiu"],"date":"2021-10-30","year":2021,"venue_type":"preprint","ids":{"arxiv":"2111.12683","openalex":"W3217628838"},"links":{"paper":"https://arxiv.org/abs/2111.12683","pdf":"https://arxiv.org/pdf/2111.12683"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Many-to-many RNN models predict hurricane trajectories from HURDAT2 data, running faster than NHC ensembles with comparable errors for 12-hour forecasts.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4018-ijamc.290538","title":"An Optimal K-Nearest Neighbor for Weather Prediction Using Whale Optimization Algorithm","authors":["Rajalakshmi Shenbaga Moorthy","Pabitha Parameshwaran"],"date":"2021-10-29","year":2021,"venue":"International Journal of Applied Metaheuristic Computing","venue_type":"journal","ids":{"doi":"10.4018/ijamc.290538","openalex":"W4200384359"},"links":{"paper":"https://doi.org/10.4018/ijamc.290538","pdf":"https://www.igi-global.com/ViewTitle.aspx?TitleId=290538&isxn=9781799885405"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Whale Optimization tuning of k-nearest neighbours for weather prediction, reporting better accuracy and lower run time than plain K-NN on an unspecified dataset.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10508538.1","title":"A Rainfall Disaggregation Scheme for Generating Fine Time-scale Extreme Rainfall under Climate Change","authors":["Wenpeng Zhao","Tsuyoshi Kinouchi"],"date":"2021-10-29","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10508538.1","openalex":"W3208997047"},"links":{"paper":"https://doi.org/10.1002/essoar.10508538.1"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"An artificial neural network disaggregates 3-hourly rainfall to hourly extreme rainfall for Cambodia using ERA5 covariates, reaching R2 of 0.93.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2111.00124","title":"Predicting Atlantic Multidecadal Variability","authors":["Glenn Liu","Peidong Wang","Matthew Beveridge","Young-Oh Kwon","Iddo Drori"],"date":"2021-10-29","year":2021,"venue":"Tackling Climate Change with Machine Learning workshop at NeurIPS 2021","venue_type":"journal","ids":{"arxiv":"2111.00124","openalex":"W3211297378"},"links":{"paper":"https://arxiv.org/abs/2111.00124","pdf":"https://arxiv.org/pdf/2111.00124"},"orgs":["mit"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Multiple machine learning models predict Atlantic Multidecadal Variability from North Atlantic SST, salinity and sea level pressure maps, beating persistence in CESM-LE.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.9798-kosham.2021.21.5.49","title":"Development of Heatwave Probability Prediction Model Based on Recurrent Neural Network: A Case of Seoul Metropolitan Government","authors":["Dongwook Kim","Cho-Rok Jang","Jung-Yun Cho","Moon-Yup Jang","Juil Song"],"date":"2021-10-28","year":2021,"venue":"Korean Society of Hazard Mitigation","venue_type":"journal","ids":{"doi":"10.9798/kosham.2021.21.5.49","openalex":"W3210156284"},"links":{"paper":"https://doi.org/10.9798/kosham.2021.21.5.49","pdf":"http://www.j-kosham.or.kr/upload/pdf/KOSHAM-2021-21-5-49.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A GRU recurrent network predicts heatwave onset probability for Seoul from daily weather, reproducing 86% of test-period heatwave days.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54302-mausam.v72i2.616","title":"An effective tropical cyclone intensity estimation model using Convolutional Neural Networks","authors":["M Swarna","N Sudhakar","Nagesh Vadaparthi"],"date":"2021-10-28","year":2021,"venue":"MAUSAM","venue_type":"journal","ids":{"doi":"10.54302/mausam.v72i2.616","openalex":"W3182360148"},"links":{"paper":"https://doi.org/10.54302/mausam.v72i2.616","pdf":"https://mausamjournal.imd.gov.in/index.php/MAUSAM/article/download/616/533"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A simple CNN estimates tropical cyclone intensity for Indian-basin storms, claimed to beat state-of-the-art methods with lower computation, with few quantitative details in the abstract.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13214334","title":"Near-Surface Air Temperature Retrieval Using a Deep Neural Network from Satellite Observations over South Korea","authors":["Sungwon Choi","Donghyun Jin","Noh-Hun Seong","Daeseong Jung","Suyoung Sim","Jongho Woo","Uujin Jeon","Yugyeong Byeon","Kyung‐Soo Han"],"date":"2021-10-28","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13214334","openalex":"W3208401743"},"links":{"paper":"https://doi.org/10.3390/rs13214334","pdf":"https://www.mdpi.com/2072-4292/13/21/4334/pdf?version=1635420915"},"orgs":[],"topic":"observations-remote-sensing","topics":["local-forecasting"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"A deep neural network retrieves near-surface air temperature over South Korea from satellite land surface temperature and vegetation indices, reaching R of 0.98 and RMSE of 2.19 K.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2110.15084","title":"Using Non-Linear Causal Models to Study Aerosol-Cloud Interactions in the Southeast Pacific","authors":["Andrew Jesson","Peter Manshausen","Alyson Douglas","Duncan Watson-Parris","Yarin Gal","Philip Stier"],"date":"2021-10-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2110.15084","openalex":"W3211167271"},"links":{"paper":"https://arxiv.org/abs/2110.15084","pdf":"https://arxiv.org/pdf/2110.15084"},"orgs":["university-of-oxford"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Non-linear causal machine learning reveals how aerosol effects on cloud droplet radius vary across meteorological regimes in the Southeast Pacific.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3209705079","title":"WEATHER FORECASTING USING ARTIFICIAL NEURAL NETWORK","authors":["Mohamed Arsh Salim Khatib","Sanketh Subbaiah","Vinit Patil","Debirupa Hore"],"date":"2021-10-27","year":2021,"venue_type":"other","ids":{"openalex":"W3209705079"},"links":{"paper":"http://thedesignengineering.com/index.php/DE/article/view/5763"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Shallow backpropagation neural networks are tuned to forecast a year of daily weather from historical records, mainly comparing hidden-layer and neuron choices.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-2021-302","title":"Time evolution of temperature profiles retrieved from 13 years of IASI data using an artificial neural network","authors":["Marie Bouillon","Sarah A. Safieddine","Simon Whitburn","Lieven Clarisse","Filipe Aires","Victor Pellet","Olivier Lezeaux","Noelle A. Scott","Marie Doutriaux","Cathy Clerbaux"],"date":"2021-10-27","year":2021,"venue_type":"other","ids":{"doi":"10.5194/amt-2021-302","openalex":"W3208248471"},"links":{"paper":"https://doi.org/10.5194/amt-2021-302","pdf":"https://doi.org/10.5194/amt-2021-302"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","era5","stations"],"status":"research","summary":"Neural network retrieves 13 years of IASI temperature profiles, agreeing with ERA5 and radiosondes within 0.5 K between 750 and 7 hPa.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10508492.1","title":"Using an Interpretable Machine Learning Approach to Characterize Earth System Model Errors: Application of SHAP Analysis to Modeling Lightning Flash Occurrence","authors":["Sam James Silva","Christoph A. Keller","Joseph Clinton Hardin"],"date":"2021-10-26","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1002/essoar.10508492.1","openalex":"W3211797298"},"links":{"paper":"https://doi.org/10.1029/2021ms002881"},"orgs":["nasa"],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"XGBoost with SHAP predicts and explains NASA GEOS lightning-occurrence errors, linking them to convection and land-surface characteristics.","significance":3,"cited_by":74,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-14-6373-2021","title":"A Gaussian process emulator for simulating ice sheet–climate interactions on a multi-million-year timescale: CLISEMv1.0","authors":["Jonas Van Breedam","Philippe Huybrechts","Michel C. Crucifix"],"date":"2021-10-25","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-14-6373-2021","openalex":"W3165038243"},"links":{"paper":"https://doi.org/10.5194/gmd-14-6373-2021"},"orgs":[],"topic":"climate-emulation","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A Gaussian process emulator couples the HadSM3 climate model to an ice sheet model, enabling efficient million-year ice sheet–climate simulations and sensitivity tests.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13214285","title":"Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting","authors":["Dan Niu","Junhao Huang","Zengliang Zang","Liujia Xu","Hongshu Che","Yuanqing Tang"],"date":"2021-10-25","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13214285","openalex":"W3209270025"},"links":{"paper":"https://doi.org/10.3390/rs13214285","pdf":"https://www.mdpi.com/2072-4292/13/21/4285/pdf?version=1635320371"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Two-stage spatiotemporal RNN with detail refinement improves radar echo nowcasting over PredRNN++ and ConvLSTM, reaching CSI 0.195 at 45 dBZ with 2 h lead.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-21-0089.1","title":"Toward an Adaptive Artificial Neural Network–Based Postprocessor","authors":["Paul J. Roebber"],"date":"2021-10-22","year":2021,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-21-0089.1","openalex":"W3208107959"},"links":{"paper":"https://doi.org/10.1175/mwr-d-21-0089.1","pdf":"https://repository.library.noaa.gov/view/noaa/60488/noaa_60488_DS1.pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"An adaptive neural-network postprocessor evolved in a predator–prey ensemble matches or beats linear regression and standard ANNs on a demonstration circulation model.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2110.12010","title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","authors":["Nicolas Webersinke","Mathias Kraus","Julia Anna Bingler","Markus Leippold"],"date":"2021-10-22","year":2021,"venue_type":"preprint","ids":{"arxiv":"2110.12010","openalex":"W4286896917"},"links":{"paper":"https://arxiv.org/abs/2110.12010","pdf":"https://arxiv.org/pdf/2110.12010"},"orgs":["eth-zurich"],"topic":"llms-agents","topics":[],"type":"model","method":["transformer"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"ClimateBERT is a language model pretrained on climate-related text; it does not target the atmosphere or climate system itself.","significance":2,"cited_by":13,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2110.11059","title":"Analyzing the Impact of Meteorological Parameters on Rainfall Prediction","authors":["Muhammad Salman Pathan","Jiantao Wu","Yee Hui Lee","Jianzhuo Yan","Soumyabrata Dev"],"date":"2021-10-21","year":2021,"venue_type":"preprint","ids":{"arxiv":"2110.11059"},"links":{"paper":"https://arxiv.org/abs/2110.11059","pdf":"https://arxiv.org/pdf/2110.11059"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses machine-learning feature selection on five years of single-station meteorological data to rank which parameters most influence rainfall.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36647-ciml-02.02.a005","title":"Analysis of PCA based AdaBoost Machine Learning Model for Predict Mid-Term Weather Forecasting","authors":["Susmita Sen","Sumit Saha","Sudipta Chaki","Payel Saha","Pijush Dutta"],"date":"2021-10-20","year":2021,"venue":"Computational Intelligence and Machine Learning","venue_type":"journal","ids":{"doi":"10.36647/ciml/02.02.a005","openalex":"W4312670749"},"links":{"paper":"https://doi.org/10.36647/ciml/02.02.a005"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"PCA-reduced AdaBoost on station records predicts mid-term temperature with R2 of 0.992, reported as beating other tested models.","significance":1,"cited_by":14,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su132111596","title":"Research on Precipitation Forecast Based on LSTM–CP Combined Model","authors":["Yan Qin Guo","Wei Tang","Guanghua Hou","Fei Pan","Yübo Wang","Wang Wei"],"date":"2021-10-20","year":2021,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su132111596","openalex":"W3207482727"},"links":{"paper":"https://doi.org/10.3390/su132111596","pdf":"https://www.mdpi.com/2071-1050/13/21/11596/pdf?version=1635430940"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An LSTM plus Chebyshev-polynomial network forecasts Yibin City precipitation with lower error than LSTM, SVR, ARIMA and MLP baselines.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11269-021-03007-x","title":"Prediction of Seasonal Rainfall with One-year Lead Time Using Climate Indices: A Wavelet Neural Network Scheme","authors":["Meysam Ghamariadyan","Monzur Alam Imteaz"],"date":"2021-10-20","year":2021,"venue":"Water Resources Management","venue_type":"journal","ids":{"doi":"10.1007/s11269-021-03007-x","openalex":"W3213608400"},"links":{"paper":"https://doi.org/10.1007/s11269-021-03007-x"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A wavelet neural network uses climate indices to predict seasonal rainfall with a one-year lead time.","significance":2,"cited_by":22,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.scitotenv.2021.151029","title":"Projection of future drought and its impact on simulated crop yield over South Asia using ensemble machine learning approach","authors":["Foyez Ahmed Prodhan","Jiahua Zhang","Til Prasad Pangali Sharma","Lkhagvadorj Nanzad","Da Zhang","Ayalkibet Mekonnen Seka","Naveed Ahmed","Shaikh Shamim Hasan","Muhammad Ziaul Hoque","Hasiba Pervin Mohana"],"date":"2021-10-19","year":2021,"venue":"The Science of The Total Environment","venue_type":"journal","ids":{"doi":"10.1016/j.scitotenv.2021.151029","openalex":"W3206696729"},"links":{"paper":"https://doi.org/10.1016/j.scitotenv.2021.151029"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Ensemble machine learning projects future South Asian drought and its effect on simulated crop yield under climate scenarios.","significance":2,"cited_by":138,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-14-6695-2021","title":"Twenty-four-hour cloud cover calculation using a ground-based imager with machine learning","authors":["Bu-Yo Kim","Joo Wan Cha","Ki-Ho Chang"],"date":"2021-10-18","year":2021,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-14-6695-2021","openalex":"W3206237479"},"links":{"paper":"https://doi.org/10.5194/amt-14-6695-2021"},"orgs":["kma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Machine learning estimates 24-hour cloud cover from ground-based sky images, with support vector regression giving RMSE 1.45 tenths against human observers.","significance":3,"cited_by":19,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11209728","title":"Soft Periodic Convolutional Recurrent Network for Spatiotemporal Climate Forecast","authors":["Ekasit Phermphoonphiphat","Tomohiko Tomita","Takashi Morita","Masayuki Numao","Ken–ichi Fukui"],"date":"2021-10-18","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11209728","openalex":"W3206052500"},"links":{"paper":"https://doi.org/10.3390/app11209728","pdf":"https://www.mdpi.com/2076-3417/11/20/9728/pdf?version=1634562965"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Soft periodic convolutional recurrent network adds periodic-depth representations to forecast ERA-Interim Z300 and SST, improving accuracy and capturing an ENSO-related four-year periodicity.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11356-021-16964-y","title":"Application of ensemble machine learning model in downscaling and projecting climate variables over different climate regions in Iran","authors":["Seyed Babak Haji Seyed Asadollah","Ahmad Sharafati","Shamsuddin Shahid"],"date":"2021-10-18","year":2021,"venue":"Environmental Science and Pollution Research","venue_type":"journal","ids":{"doi":"10.1007/s11356-021-16964-y","openalex":"W3205285071"},"links":{"paper":"https://doi.org/10.1007/s11356-021-16964-y"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Ensemble machine learning downscales and projects climate variables across Iran's climate regions, using GCM output for regional climate projections.","significance":2,"cited_by":45,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl095302","title":"Improving Nowcasting of Convective Development by Incorporating Polarimetric Radar Variables Into a Deep‐Learning Model","authors":["Xiang Pan","Yinghui Lu","Kun Zhao","Hao Huang","Mingjun Wang","Haonan Chen"],"date":"2021-10-17","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl095302","openalex":"W3207011416"},"links":{"paper":"https://doi.org/10.1029/2021gl095302","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021GL095302"},"orgs":["noaa","colorado-state-university"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Adding polarimetric radar variables KDP and ZDR to a deep-learning nowcasting model raises CSI by 13.2% at 30 min and 17.4% at 60 min.","significance":4,"cited_by":149,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3205607661","title":"Ambient Temperature Forecasting Using Non-linear Autoregressive Neural Networks Anas Kabbori","authors":["Anas Kabbori","Jilali Antari","Radouane Iqdour","Zine El Abidine El Morjani"],"date":"2021-10-16","year":2021,"venue_type":"other","ids":{"openalex":"W3205607661"},"links":{"paper":"https://thedesignengineering.com/index.php/DE/article/view/5427"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Nonlinear autoregressive and NARX neural networks forecast 12 years of Marrakesh temperature, with NARX giving better training and test performance.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002625","title":"Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles","authors":["Yao‐Sheng Chen","Takanobu Yamaguchi","Peter Bogenschutz","Graham Feingold"],"date":"2021-10-16","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002625","openalex":"W3206256424"},"links":{"paper":"https://doi.org/10.1029/2021ms002625","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002625"},"orgs":["noaa"],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"evaluation","method":["other"],"timescale":[],"spatial":["regional"],"data":["cmip","era5","satellite"],"status":"research","summary":"Neural network ensembles compare marine low cloud fraction relationships in E3SM at two vertical resolutions against ERA5-CERES, showing shifts in meteorological drivers dominate differences.","significance":3,"cited_by":10,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-hydro.2021.091","title":"Impact of climate change on hydro-climatological parameters in North Cyprus: application of artificial intelligence-based statistical downscaling models","authors":["Gözen Elkiran","Vahid Nourani","Ogodor Elvis","Jazuli Abdullahi"],"date":"2021-10-14","year":2021,"venue":"Journal of Hydroinformatics","venue_type":"journal","ids":{"doi":"10.2166/hydro.2021.091","openalex":"W3205264100"},"links":{"paper":"https://doi.org/10.2166/hydro.2021.091"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"ANN, ANFIS and MLR statistical downscaling of BNU-ESM CMIP5 predictors projects up to 22% less rainfall in Famagusta and Nicosia by 2040 under RCP4.5.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-21-0106.1","title":"Probabilistic Predictions from Deterministic Atmospheric River Forecasts with Deep Learning","authors":["William Eric Chapman","Luca Delle Monache","Stefano Alessandrini","Aneesh C. Subramanian","Fred Martin Ralph","Shang‐Ping Xie","Sebastian Lerch","Negin Hayatbini"],"date":"2021-10-14","year":2021,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-21-0106.1","openalex":"W3206359964"},"links":{"paper":"https://doi.org/10.1175/mwr-d-21-0106.1"},"orgs":["ncar","kit"],"topic":"post-processing","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Deep-learning postprocessing turns deterministic West-WRF atmospheric river IVT forecasts into reliable probabilistic forecasts that rival calibrated GEFS out to 120 h.","significance":3,"cited_by":57,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1142-s263053482150008x","title":"IMPROVING THE NORTH AMERICAN MULTI-MODEL ENSEMBLE (NMME) PRECIPITATION FORECASTS AT SEASONAL SCALE OVER THE HIMALAYAN REGION USING MACHINE LEARNING","authors":["Sourabh Shrivastava","Ram Avtar","Prasanta Kumar Bal"],"date":"2021-10-12","year":2021,"venue":"International Journal of Big Data Mining for Global Warming","venue_type":"journal","ids":{"doi":"10.1142/s263053482150008x","openalex":"W3206716911"},"links":{"paper":"https://doi.org/10.1142/s263053482150008x"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Five tree-based ML models correct NMME seasonal precipitation over the Himalayas, cutting the 20 mm/day multi-model wet bias with RMSE near 2 mm/day.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ejrh.2021.100923","title":"Daily maximum temperature forecasting in changing climate using a hybrid of Multi-dimensional Complementary Ensemble Empirical Mode Decomposition and Radial Basis Function Neural Network","authors":["Ming-Liang Lin","Christina W.-S. Tsai","Chun-Kuang Chen"],"date":"2021-10-12","year":2021,"venue":"Journal of Hydrology Regional Studies","venue_type":"journal","ids":{"doi":"10.1016/j.ejrh.2021.100923","openalex":"W3206180624"},"links":{"paper":"https://doi.org/10.1016/j.ejrh.2021.100923","pdf":"https://www.sciencedirect.com/science/article/pii/S221458182100152X/pdf"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A hybrid MCEEMD decomposition and RBF neural network forecasts Taipei daily maximum temperature 7 days ahead, aimed at heatwave risk under warming.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2021.09.073","title":"IrradianceNet: Spatiotemporal deep learning model for satellite-derived solar irradiance short-term forecasting","authors":["Andreas Holm Nielsen","Alexandros Iosifidis","Henrik Karstoft"],"date":"2021-10-11","year":2021,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2021.09.073","openalex":"W3206368551"},"links":{"paper":"https://doi.org/10.1016/j.solener.2021.09.073","pdf":"https://www.sciencedirect.com/science/article/pii/S0038092X21008306/pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"IrradianceNet is a satellite-based deep network forecasting surface solar irradiance up to 4 h over Europe, beating persistence, TV-L1 and ERA5 baselines via fewer cloud errors.","significance":4,"cited_by":72,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl095043","title":"Compound Parameterization to Improve the Accuracy of Radiation Emulator in a Numerical Weather Prediction Model","authors":["Hwan‐Jin Song","Soonyoung Roh","Hyesook Park"],"date":"2021-10-09","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl095043","openalex":"W3203363257"},"links":{"paper":"https://doi.org/10.1029/2021gl095043","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021GL095043"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Two compound parameterizations correct errors of a neural-network radiation emulator in a Korean NWP model, keeping its 60-fold speedup with lower error.","significance":4,"cited_by":13,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.37868-sei.v3i2.id146","title":"An evaluation of CNN and ANN in prediction weather forecasting: A review","authors":["Shahab Wahhab Kareem","Zhala Jameel Hamad","Shavan K. Askar"],"date":"2021-10-08","year":2021,"venue":"Sustainable Engineering and Innovation","venue_type":"journal","ids":{"doi":"10.37868/sei.v3i2.id146","openalex":"W3205977913"},"links":{"paper":"https://doi.org/10.37868/sei.v3i2.id146","pdf":"https://sei.ardascience.com/index.php/journal/article/download/146/143"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["cnn","classical-ml"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"A general review of ANN and CNN approaches to weather prediction, with qualitative claims that ANNs are more efficient and little quantitative evidence.","significance":1,"cited_by":43,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0054.1","title":"Using an Artificial Neural Network to improve operational wind prediction in a small unresolved valley","authors":["Sinclair Chinyoka","Gert‐Jan Steeneveld","Thierry Hedde"],"date":"2021-10-08","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0054.1","openalex":"W3201899184"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0054.1"},"orgs":[],"topic":"post-processing","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"An ANN post-processing of 3-km WRF forecasts raises 10 m wind direction accuracy in a small southeast French valley from 56% to 79%.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-2150704x.2021.1978581","title":"Detection of weather events in optical satellite data using deep convolutional neural networks","authors":["Ye Li","Mostafa Momen"],"date":"2021-10-08","year":2021,"venue":"Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1080/2150704x.2021.1978581","openalex":"W3206891735"},"links":{"paper":"https://doi.org/10.1080/2150704x.2021.1978581"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"InceptionV3, ResNet50 and VGG models classify 9081 optical satellite images into five weather events, with InceptionV3 reaching 92% average accuracy.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002490","title":"Advancing Artificial Neural Network Parameterization for Atmospheric Turbulence Using a Variational Multiscale Model","authors":["Martin Janssens","Steven J. Hulshoff"],"date":"2021-10-08","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002490","openalex":"W3204915624"},"links":{"paper":"https://doi.org/10.1029/2021ms002490","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002490"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other","physics-constrained"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Variational multiscale neural closure for atmospheric turbulence is shown to need training on intra-step nonphysical states to stabilise implicit time stepping.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0056.1","title":"Machine learning classification of significant tornadoes and hail in the U.S. using ERA5 proximity soundings","authors":["Vittorio A. Gensini","Cody Converse","Walker S. Ashley","Mateusz Taszarek"],"date":"2021-10-07","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0056.1","openalex":"W3203266641"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0056.1"},"orgs":["university-of-oklahoma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Random forest trained on 150,000 ERA5 proximity soundings best classifies significant tornadoes and hail, with SHAP-derived thresholds for operational nowcasting.","significance":4,"cited_by":32,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-20-0234.1","title":"Investigation of Machine Learning Using Satellite-Based Advanced Dvorak Technique Analysis Parameters to Estimate Tropical Cyclone Intensity","authors":["Timothy L. Olander","Anthony Wimmers","Christopher S. Velden","James P. Kossin"],"date":"2021-10-07","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-20-0234.1","openalex":"W3202987464"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0234.1"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Simple machine learning models refine satellite-based advanced Dvorak technique features, cutting global tropical cyclone wind RMSE by 23–30% over 2017–2018 test years.","significance":4,"cited_by":21,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-21-0046.1","title":"Spatially Coherent Postprocessing of Cloud Cover Ensemble Forecasts","authors":["Y. Dai","Stephan Hemri"],"date":"2021-10-07","year":2021,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-21-0046.1","openalex":"W3214954120"},"links":{"paper":"https://doi.org/10.1175/mwr-d-21-0046.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/149/12/MWR-D-21-0046.1.pdf"},"orgs":["meteoswiss","eth-zurich"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["gan-vae","other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","satellite"],"status":"research","summary":"Conditional GAN and dense networks postprocess COSMO-E and IFS cloud cover ensembles over Switzerland, with cGAN producing realistic scenarios without copula or shuffle templates.","significance":4,"cited_by":15,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2110.03614","title":"Exploring the tropical Pacific manifold in models and observations","authors":["Fabrizio Falasca","Annalisa Bracco"],"date":"2021-10-07","year":2021,"venue":"Physical Review X","venue_type":"journal","ids":{"arxiv":"2110.03614","doi":"10.1103/physrevx.12.021054","openalex":"W4282813406"},"links":{"paper":"https://doi.org/10.1103/physrevx.12.021054","pdf":"https://arxiv.org/pdf/2110.03614"},"orgs":["nyu-m2lines"],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Manifold learning characterizes the tropical Pacific climate attractor, revealing model biases that diverge between historical and warming-scenario climate model simulations.","significance":4,"cited_by":15,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijdm.b1615.111221","title":"Design and Implementation of Rainfall Prediction Model using Supervised Machine Learning Data Mining Technique s","authors":["Deepak Sharma","Priti Sharma"],"date":"2021-10-05","year":2021,"venue":"Indian Journal of Data Mining","venue_type":"journal","ids":{"doi":"10.35940/ijdm.b1615.111221","openalex":"W4226310129"},"links":{"paper":"https://doi.org/10.35940/ijdm.b1615.111221","pdf":"https://doi.org/10.35940/ijdm.b1615.111221"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["stations"],"status":"research","summary":"Data-mining workflow trains an artificial neural network on preprocessed weather records to predict rainfall, with no quantitative results in the abstract.","significance":1,"cited_by":8,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.scib.2021.10.001","title":"Extreme fire weather is the major driver of severe bushfires in southeast Australia","authors":["Bin Wang","Allan C. Spessa","Puyu Feng","Xin Hou","Chao Yue","Jing‐Jia Luo","Philippe Ciais","Cathy Waters","Annette Cowie","Rachael H. Nolan","Tadas Nikonovas","Huidong Jin","Henry Walshaw","Jinghua Wei","Xiaowei Guo","De Li Liu","Qiang Yu"],"date":"2021-10-05","year":2021,"venue":"中国科学通报：英文版","venue_type":"journal","ids":{"doi":"10.1016/j.scib.2021.10.001","openalex":"W3203699112"},"links":{"paper":"https://doi.org/10.1016/j.scib.2021.10.001","pdf":"https://www.sciencedirect.com/science/article/pii/S2095927321006411/pdf"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"ML diagnostic model explains over 80% of monthly burnt-area variance in southeast Australian forests, showing extreme fire weather, linked to SAM and IOD, as the primary driver.","significance":4,"cited_by":48,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2110.01843","title":"Short-term precipitation prediction using deep learning","authors":["Guoxing Chen","Wei-Chyung Wang"],"date":"2021-10-05","year":2021,"venue":"Geophysical Research Letters, 49 (2022)","venue_type":"journal","ids":{"arxiv":"2110.01843","doi":"10.1029/2022gl097904","openalex":"W4224022129"},"links":{"paper":"https://arxiv.org/abs/2110.01843","pdf":"https://arxiv.org/pdf/2110.01843"},"orgs":["fudan-university"],"topic":"regional-km-scale","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["short","medium"],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"A 3D CNN from one meteorology frame predicts daily CONUS precipitation, beating operational weather models up to 5-day leads and improving them when combined.","significance":4,"cited_by":68,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-21-0096.1","title":"Machine learning for precipitation forecasts post-processing — Multi-model comparison and experimental investigation","authors":["Yuhang Zhang","Aizhong Ye"],"date":"2021-10-04","year":2021,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-21-0096.1","openalex":"W3203335272"},"links":{"paper":"https://doi.org/10.1175/jhm-d-21-0096.1"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A comparison of 21 machine-learning post-processors for GEFS precipitation reforecasts up to 8 days finds extra-trees regression performs best in the Yalong basin.","significance":3,"cited_by":35,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-02533839.2021.1977715","title":"Modeling of neural networks for weather forecasting in debre markos, Ethiopia","authors":["Daniel Limenew Meheretie","Bing Ji","Mazin Mohammed Mogadem","Tariku Sinshaw Tamir"],"date":"2021-10-04","year":2021,"venue":"Journal of the Chinese Institute of Engineers","venue_type":"journal","ids":{"doi":"10.1080/02533839.2021.1977715","openalex":"W3201987504"},"links":{"paper":"https://doi.org/10.1080/02533839.2021.1977715"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Feedforward backpropagation networks forecast next-day maximum temperature and sunshine hours in Debre Markos, Ethiopia, with regression above 0.98.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-021-02103-z","title":"Prediction of heat waves using meteorological variables in diverse regions of Iran with advanced machine learning models","authors":["Seyed Babak Haji Seyed Asadollah","Najeebullah Khan","Ahmad Sharafati","Shamsuddin Shahid","‪Eun‐Sung Chung","Xiaojun Wang"],"date":"2021-10-04","year":2021,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-021-02103-z","openalex":"W3204400791"},"links":{"paper":"https://doi.org/10.1007/s00477-021-02103-z"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Advanced machine learning models predict heatwaves across diverse Iranian regions from meteorological variables; the abstract is missing, so details are limited.","significance":2,"cited_by":43,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10508127.1","title":"Detecting the presence of Tropical Cyclones using Deep Learning Techniques","authors":["Daniel Galea","Bryan Lawrence","Julian Martin Kunkel"],"date":"2021-10-04","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10508127.1","openalex":"W4250077267"},"links":{"paper":"https://doi.org/10.1002/essoar.10508127.1"},"orgs":["university-of-reading"],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"A lightweight deep learning filter detects tropical cyclones in running simulations with 92% recall and 36% precision, so models save only relevant output.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3212348872","title":"Medium-Term Wind Speed Prediction using Bayesian Neural Network (BNN)","authors":["Sana Mohsin","Sofia Najwa Ramli","Maria Imdad"],"date":"2021-10-03","year":2021,"venue":"International journal of systematic innovation","venue_type":"journal","ids":{"openalex":"W3212348872"},"links":{"paper":"https://ojs.ijosi.org/index.php/IJOSI/article/view/462","pdf":"https://ojs.ijosi.org/index.php/IJOSI/article/download/462/430"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["other"],"timescale":["medium"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Bayesian neural network post-processes NWP inputs to forecast medium-term wind speed, beating LASSO on MAPE and NMAE across several horizons.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2110.01035","title":"RAP-Net: Region Attention Predictive Network for Precipitation Nowcasting","authors":["Chuyao Luo","ZhengZhang","Rui Ye","Xutao Li","Yunming Ye"],"date":"2021-10-03","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"2110.01035","doi":"10.5194/gmd-15-5407-2022","openalex":"W4298205742"},"links":{"paper":"https://doi.org/10.5194/gmd-15-5407-2022","pdf":"https://arxiv.org/pdf/2110.01035"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"RAP-Net embeds a region attention block and recall attention mechanism into ConvRNN to improve radar-based precipitation nowcasting in heavy-rain regions.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2110.00695","title":"Deep Learning for Rain Fade Prediction in Satellite Communications","authors":["Aidin Ferdowsi","David Whitefield"],"date":"2021-10-02","year":2021,"venue_type":"preprint","ids":{"arxiv":"2110.00695"},"links":{"paper":"https://arxiv.org/abs/2110.00695","pdf":"https://arxiv.org/pdf/2110.00695"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"application","method":["other"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Deep learning forecasts satellite rain fade from satellite and radar imagery plus link power, outperforming prior methods in near- and long-term predictions.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-19-0346.a","title":"Air—Surface Exchange in CHEESEHEAD19: Food for Machine Learning To Scale Energy Fluxes","authors":["Brian Butterworth","Ankur Rashmikant Desai","Stefan Metzger","Philip A. Townsend","Mark D. Schwartz","Grant W. Petty","Matthias R. Mauder","Hannes Vogelmann","Christian G. Andresen","Travis J. Augustine","Timothy H. Bertram","William O. Brown","Michael Buban","Patricia Cleary","David Durden","Christopher Florian","Trevor J. Iglinski","Eric L. Kruger","Kathleen Lantz","Temple R. Lee","Tilden P. Meyers","James K. Mineau","Erik R. Olson","Steven P. Oncley","Sreenath Paleri","Rosalyn A. Pertzborn","Claire Pettersen","David M. Plummer","Laura Riihimaki","Eliceo Ruíz Guzmán","Joseph Sedlar","Elizabeth Smith","Johannes Speidel","Paul C. Stoy","Matthias Sühring","Jonathan E. Thom","David D. Turner","Michael P. Vermeuel","Timothy J. Wagner","Zhien Wang","Luise Wanner","Loren D. White","James M. Wilczak","Daniel Benjamin Wright","Ting Zheng"],"date":"2021-10-01","year":2021,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-19-0346.a","openalex":"W4387919988"},"links":{"paper":"https://doi.org/10.1175/bams-d-19-0346.a","pdf":"https://journals.ametsoc.org/downloadpdf/journals/bams/102/10/BAMS-D-19-0346.A.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["hybrid-parameterization"],"type":"position","method":["other"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"CHEESEHEAD19 land-atmosphere flux observations are presented as training data for machine learning to scale energy fluxes across heterogeneous surfaces to model grid cells.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002609","title":"Improved Weather Forecasting Using Neural Network Emulation for Radiation Parameterization","authors":["Hwan‐Jin Song","Soonyoung Roh"],"date":"2021-10-01","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002609","openalex":"W3192107387"},"links":{"paper":"https://doi.org/10.1029/2021ms002609"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"A neural-network emulator replaces KMA's radiation scheme in an operational model, giving a 60-fold speedup and 22–34% lower skin temperature and flux errors.","significance":5,"cited_by":44,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002509","title":"Learning to Correct Climate Projection Biases","authors":["Baoxiang Pan","Gemma J. Anderson","André Ricardo Gonçalves","Donald D. Lucas","C. Bonfils","Jiwoo Lee","Yang Tian","Hsi‐Yen Ma"],"date":"2021-10-01","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002509","openalex":"W3203217919"},"links":{"paper":"https://doi.org/10.1029/2021ms002509","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002509"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","physics-constrained"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Regularized adversarial domain adaptation corrects climate model daily precipitation biases over the contiguous US across moments while keeping spatiotemporal consistency.","significance":4,"cited_by":83,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.apenergy.2021.117834","title":"Machine Learning techniques for solar irradiation nowcasting: Cloud type classification forecast through satellite data and imagery","authors":["Alfredo Nespoli","Alessandro Niccolai","Emanuèle Ogliari","Giovanni Perego","Elena Collino","Dario Attilio Ronzio"],"date":"2021-10-01","year":2021,"venue":"Applied Energy","venue_type":"journal","ids":{"doi":"10.1016/j.apenergy.2021.117834","openalex":"W3203933526"},"links":{"paper":"https://doi.org/10.1016/j.apenergy.2021.117834"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Machine learning nowcasts solar irradiation by classifying cloud types from satellite imagery; the abstract is missing, so details are limited.","significance":2,"cited_by":80,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4177","title":"A new approach to extended‐range multimodel forecasting: Sequential learning algorithms","authors":["Paula L. M. Gonzalez","David James Brayshaw","Florian Ziel"],"date":"2021-10-01","year":2021,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4177","openalex":"W3202316997"},"links":{"paper":"https://doi.org/10.1002/qj.4177","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/qj.4177"},"orgs":["columbia-leap","university-of-reading"],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Online sequential-learning combinations of NWP and statistical extended-range forecasts improve probabilistic skill by 5-15% over standard multimodel methods up to lead week 5.","significance":4,"cited_by":13,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.15239","title":"Multi Scale Graph Wavenet for Wind Speed Forecasting","authors":["Neetesh Rathore","Pradeep Rathore","Arghya Basak","Sri Harsha Nistala","Venkataramana Runkana"],"date":"2021-09-30","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.15239"},"links":{"paper":"https://arxiv.org/abs/2109.15239","pdf":"https://arxiv.org/pdf/2109.15239"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["gnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Multi Scale Graph WaveNet combines dilated convolutions with graph convolutions to forecast wind speed at Danish cities, outperforming baselines by 4-5% across horizons.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13193904","title":"Generating 1 km Spatially Seamless and Temporally Continuous Air Temperature Based on Deep Learning over Yangtze River Basin, China","authors":["Rui Si Li","Tailai Huang","Yu Song","Shuzhe Huang","Xiang Zhang"],"date":"2021-09-29","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13193904","openalex":"W3205440767"},"links":{"paper":"https://doi.org/10.3390/rs13193904","pdf":"https://www.mdpi.com/2072-4292/13/19/3904/pdf?version=1632995461"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations","era5"],"status":"research","summary":"Deep belief network fuses satellite, model and station data to produce 1 km daily air temperature over the Yangtze basin, with RMSE 1.96 °C.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2110.05196","title":"Learning and Dynamical Models for Sub-seasonal Climate Forecasting: Comparison and Collaboration","authors":["Sijie He","Xinyan Li","Laurie Trenary","Benjamin A Cash","Timothy DelSole","Arindam Banerjee"],"date":"2021-09-29","year":2021,"venue_type":"preprint","ids":{"arxiv":"2110.05196"},"links":{"paper":"https://arxiv.org/abs/2110.05196","pdf":"https://arxiv.org/pdf/2110.05196"},"orgs":[],"topic":"s2s-seasonal","topics":["benchmarks-data-eval"],"type":"evaluation","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Comparison of modern ML models against SubX dynamical models for US sub-seasonal forecasting finds ML wins on average, and feeding dynamical forecasts into ML improves skill.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3210473833","title":"The Time Series Analysis and Forecasting of Precipitation (Rainfall) Data: Statistical, Machine learning and Deep learning approaches for Precipitation Forecasting","authors":["Janhavi Talhar","Atharva Ramgirkar","Pravat Kumar Jena"],"date":"2021-09-28","year":2021,"venue":"SPAST Abstracts","venue_type":"journal","ids":{"openalex":"W3210473833"},"links":{"paper":"https://spast.org/techrep/article/view/1204"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares statistical, machine learning and deep learning models for rainfall forecasting at four Maharashtra talukas using local station records.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.5533638","title":"Challenges when preparing machine learning tools for use in operational weather predictions","authors":["Peter Dominik Dueben"],"date":"2021-09-28","year":2021,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.5533638","openalex":"W3216879477"},"links":{"paper":"https://doi.org/10.5281/zenodo.5533638"},"orgs":["ecmwf"],"topic":"infra-software","topics":[],"type":"position","method":[],"timescale":[],"spatial":[],"data":[],"status":"pre-operational","summary":"Talk slides on the challenges of preparing machine learning tools for operational weather prediction; abstract gives no quantitative results.","significance":2,"cited_by":0,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4167","title":"A deep learning framework for lightning forecasting with multi‐source spatiotemporal data","authors":["Yangli‐ao Geng","Qingyong Li","Tianyang Lin","Wen Yao","Liangtao Xu","Dong Zheng","Xinyuan Zhou","Liming Zheng","Weitao Lyu","Yijun Zhang"],"date":"2021-09-28","year":2021,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4167","openalex":"W3203572917"},"links":{"paper":"https://doi.org/10.1002/qj.4167"},"orgs":["fudan-university","cma"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["radar","stations","nwp-analysis"],"status":"research","summary":"LightNet+ fuses radar, station and NWP data in a deep network for lightning forecasting, beating three established schemes and improving as data sources are added.","significance":4,"cited_by":44,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2021.742840","title":"Long-Term Maximum and Minimum Temperature Projections Over Metro Vancouver, Canada","authors":["Chuyin Tian","Guohe Huang","Yanli Liu","Denghua Yan","Feng Wang","Ruixin Duan"],"date":"2021-09-27","year":2021,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2021.742840","openalex":"W3204861523"},"links":{"paper":"https://doi.org/10.3389/feart.2021.742840"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"model","method":["rnn"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"GRU recurrent network statistically downscales WRF/MPI-ESM-LR RCP8.5 output to project Metro Vancouver daily temperature extremes to 2100, with warming near 3°C.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-21-0096.1","title":"Using Deep Learning to Nowcast the Spatial Coverage of Convection from Himawari-8 Satellite Data","authors":["Ryan Lagerquist","Jebb Q. Stewart","Imme Ebert‐Uphoff","Christina Bonfanti"],"date":"2021-09-27","year":2021,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-21-0096.1","openalex":"W3202041678"},"links":{"paper":"https://doi.org/10.1175/mwr-d-21-0096.1"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"U-Nets forecast convection coverage from Himawari-8 brightness temperatures up to 120 minutes, beating persistence at lead times of 60 minutes and beyond.","significance":4,"cited_by":56,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.12269","title":"Integrating Recurrent Neural Networks with Data Assimilation for Scalable Data-Driven State Estimation","authors":["Stephen G. Penny","Timothy A. Smith","Tse-Chun Chen","Jason A. Platt","Hsin-Yi Lin","Michael Goodliff","Henry D. I. Abarbanel"],"date":"2021-09-25","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2109.12269","doi":"10.1029/2021ms002843","openalex":"W4212948582"},"links":{"paper":"https://doi.org/10.1029/2021ms002843","pdf":"https://arxiv.org/pdf/2109.12269"},"orgs":["noaa"],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"RNNs replace the forecast model, error covariance and adjoint in the DA cycle, with DA updating hidden states; the approach scales via localization and parallelization.","significance":4,"cited_by":56,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.12029","title":"Identifying Distributional Differences in Convective Evolution Prior to Rapid Intensification in Tropical Cyclones","authors":["Trey McNeely","Galen Vincent","Rafael Izbicki","Kimberly M. Wood","Ann B. Lee"],"date":"2021-09-24","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.12029","openalex":"W3202025347"},"links":{"paper":"https://arxiv.org/abs/2109.12029","pdf":"https://arxiv.org/pdf/2109.12029"},"orgs":[],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"application","method":["other"],"timescale":["short"],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"AI sequence models with statistical inference reveal interpretable convective structure patterns preceding tropical cyclone rapid intensification, aiding forecaster insight.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.10593","title":"Emulating Aerosol Microphysics with Machine Learning","authors":["Paula Harder","Duncan Watson-Parris","Dominik Strassel","Nicolas Gauger","Philip Stier","Janis Keuper"],"date":"2021-09-22","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.10593","openalex":"W3201234765"},"links":{"paper":"https://arxiv.org/abs/2109.10593","pdf":"https://arxiv.org/pdf/2109.10593"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural network emulates the M7 aerosol microphysics scheme in ECHAM-HAM, reaching R² of 89% and a 120x GPU speed-up for climate model runs.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3110180","title":"Developing Deep Learning Models for Storm Nowcasting","authors":["Joaquin Cuomo","V. Chandrasekar"],"date":"2021-09-21","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3110180","openalex":"W3200655876"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3110180"},"orgs":["colorado-state-university"],"topic":"nowcasting","topics":[],"type":"model","method":[],"timescale":["nowcast"],"spatial":[],"data":["radar"],"status":"research","summary":"Systematic study of deep learning storm nowcasting design choices (history length, loss, predicted frames) from radar data, yielding models that outperform existing implementations.","significance":4,"cited_by":15,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl094737","title":"Deep Learning‐Based Super‐Resolution Climate Simulator‐Emulator Framework for Urban Heat Studies","authors":["Yuankai Wu","Bernardo Teufel","Laxmi Sushama","Stéphane Bélair","Lijun Sun"],"date":"2021-09-21","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl094737","openalex":"W3201655326"},"links":{"paper":"https://doi.org/10.1029/2021gl094737"},"orgs":["eccc"],"topic":"downscaling","topics":["climate-emulation"],"type":"model","method":["cnn","gan-vae"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Adversarial sub-pixel CNN super-resolves 2.5 km regional climate simulations of Montreal to 250 m, improving urban temperature errors and heat-stress indicators.","significance":3,"cited_by":33,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.10399","title":"SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking","authors":["Soukayna Mouatadid","Paulo Orenstein","Genevieve Flaspohler","Miruna Oprescu","Judah Cohen","Franklyn Wang","Sean Knight","Maria Geogdzhayeva","Sam Levang","Ernest Fraenkel","Lester Mackey"],"date":"2021-09-21","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.10399","openalex":"W3201404958"},"links":{"paper":"https://arxiv.org/abs/2109.10399","pdf":"https://arxiv.org/pdf/2109.10399","code":"https://github.com/microsoft/subseasonal_data"},"orgs":[],"topic":"benchmarks-data-eval","topics":["s2s-seasonal"],"type":"benchmark","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"SubseasonalClimateUSA is a curated dataset and benchmark for 2-6 week US forecasts, comparing dynamical models with ten ML and deep learning methods.","significance":4,"cited_by":1,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.09791","title":"Prediction of severe thunderstorm events with ensemble deep learning and radar data","authors":["Sabrina Guastavino","Michele Piana","Marco Tizzi","Federico Cassola","Antonio Iengo","Davide Sacchetti","Enrico Solazzo","Federico Benvenuto"],"date":"2021-09-20","year":2021,"venue":"Scientific Reports","venue_type":"journal","ids":{"arxiv":"2109.09791","doi":"10.21203/rs.3.rs-1928945/v1","openalex":"W4286969663"},"links":{"paper":"https://doi.org/10.1038/s41598-022-23306-6","pdf":"https://arxiv.org/pdf/2109.09791"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"pre-operational","summary":"Deep ensemble learning on radar reflectivity videos issues severe thunderstorm warnings for Liguria, Italy, with a value-weighted skill score for probabilistic-to-binary alerts.","significance":3,"cited_by":51,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.09289","title":"TempNet -- Temporal Super Resolution of Radar Rainfall Products with Residual CNNs","authors":["Muhammed Sit","Bong-Chul Seo","Ibrahim Demir"],"date":"2021-09-20","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.09289","openalex":"W3200721478"},"links":{"paper":"https://arxiv.org/abs/2109.09289","pdf":"https://arxiv.org/pdf/2109.09289"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"TempNet uses residual CNNs to raise the temporal resolution of radar rainfall maps, outperforming optical-flow interpolation and a CNN baseline.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.09076","title":"Towards Representation Learning for Atmospheric Dynamics","authors":["Sebastian Hoffmann","Christian Lessig"],"date":"2021-09-19","year":2021,"venue":"NEURIPS 2021 workshop on Tackling Climate Change with Machine Learning (poster)","venue_type":"journal","ids":{"arxiv":"2109.09076","openalex":"W3200293619"},"links":{"paper":"https://arxiv.org/abs/2109.09076","pdf":"https://arxiv.org/pdf/2109.09076"},"orgs":[],"topic":"benchmarks-data-eval","topics":["downscaling"],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":[],"data":["era5"],"status":"research","summary":"AtmoDist is a self-supervised learned metric for atmospheric dynamics, trained to predict temporal distance between shuffled wind fields, and it improves GAN super-resolution of vorticity over MSE-based baselines.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-asr-18-145-2021","title":"Addressing up-scaling methodologies for convection-permitting EPSs using statistical and machine learning tools","authors":["Tiziana Comito","Colm Clancy","Conor Daly","Alan Hally"],"date":"2021-09-17","year":2021,"venue":"Advances in science and research","venue_type":"journal","ids":{"doi":"10.5194/asr-18-145-2021","openalex":"W3200001725"},"links":{"paper":"https://doi.org/10.5194/asr-18-145-2021","pdf":"https://asr.copernicus.org/articles/18/145/2021/asr-18-145-2021.pdf"},"orgs":[],"topic":"post-processing","topics":["regional-km-scale"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Two machine-learning and statistical up-scaling methods for convection-permitting ensemble rainfall forecasts reduce the double-penalty problem and improve severe-weather forecast skill.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.08770","title":"WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data","authors":["Rupa Kurinchi-Vendhan","Björn Lütjens","Ritwik Gupta","Lucien Werner","Dava Newman"],"date":"2021-09-17","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.08770","openalex":"W3199319659"},"links":{"paper":"https://arxiv.org/abs/2109.08770","pdf":"https://arxiv.org/pdf/2109.08770"},"orgs":["mit","caltech","uc-berkeley"],"topic":"downscaling","topics":[],"type":"benchmark","method":["cnn","gan-vae"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Benchmarks ESRGAN, EDSR and PhIREGAN for super-resolving NWP wind and solar fields, and releases an ML-ready dataset for renewable forecasting.","significance":4,"cited_by":6,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ejrh.2021.100921","title":"Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN","authors":["Tongbi Tu","Kei Ishida","Ali Ercan","Masato Kiyama","Motoki Amagasaki","Tongtiegang Zhao"],"date":"2021-09-16","year":2021,"venue":"Journal of Hydrology Regional Studies","venue_type":"journal","ids":{"doi":"10.1016/j.ejrh.2021.100921","openalex":"W3198951408"},"links":{"paper":"https://doi.org/10.1016/j.ejrh.2021.100921","pdf":"https://www.sciencedirect.com/science/article/pii/S2214581821001506/pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","nwp-analysis","km-scale-sim"],"status":"research","summary":"Hybrid WRF and CNN downscaling produces 6-km daily precipitation from ERA-Interim over a Japanese watershed, cutting cost versus pure dynamical downscaling.","significance":3,"cited_by":31,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0036.1","title":"Evaluating Foehn Occurrence in a Changing Climate Based on Reanalysis and Climate Model Data Using Machine Learning","authors":["Christoph Mony","Lukas Jansing","Michael Armand Sprenger"],"date":"2021-09-15","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0036.1","openalex":"W3199945613"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0036.1"},"orgs":["eth-zurich"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["era5","cmip"],"status":"research","summary":"XGBoost predicts Swiss foehn from synoptic fields in reanalysis and CESM simulations, projecting more spring south-foehn in Altdorf and summer north-foehn in Lugano under warming.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12667-021-00480-6","title":"Spatio-temporal deep learning for day-ahead wind speed forecasting relying on WRF predictions","authors":["Emmanouil Christoforou","Ioannis Z. Emiris","Apostolos Florakis","D. Rizou","S. Zaharia"],"date":"2021-09-15","year":2021,"venue":"Energy Systems","venue_type":"journal","ids":{"doi":"10.1007/s12667-021-00480-6","openalex":"W3201527902"},"links":{"paper":"https://doi.org/10.1007/s12667-021-00480-6","pdf":"https://hal.science/hal-03523828/document"},"orgs":["inria"],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["transformer","rnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Spatio-temporal deep learning corrects day-ahead wind speed forecasts built on WRF predictions for energy use; abstract missing, judged from title.","significance":2,"cited_by":15,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.07250","title":"Adding Uncertainty to Neural Network Regression Tasks in the Geosciences","authors":["Elizabeth A. Barnes","Randal J. Barnes","Nicolas Gordillo"],"date":"2021-09-15","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.07250"},"links":{"paper":"https://arxiv.org/abs/2109.07250","pdf":"https://arxiv.org/pdf/2109.07250"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Neural network regression outputs a general probability distribution for heteroscedastic, asymmetric uncertainty, demonstrated on synthetic climate data.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-frsen.2021.716951","title":"Planetary Boundary Layer Height Estimates From ICESat-2 and CATS Backscatter Measurements","authors":["Stephen P. Palm","Patrick A. Selmer","John E. Yorks","S. Nicholls","E. P. Nowottnick"],"date":"2021-09-13","year":2021,"venue":"Frontiers in Remote Sensing","venue_type":"journal","ids":{"doi":"10.3389/frsen.2021.716951","openalex":"W3200335109"},"links":{"paper":"https://doi.org/10.3389/frsen.2021.716951"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Global planetary boundary layer height retrieved from ICESat-2 and CATS lidar using a threshold method and a CNN, validated against MERRA-2 with good spatial agreement.","significance":3,"cited_by":40,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13183627","title":"RAIN-F+: The Data-Driven Precipitation Prediction Model for Integrated Weather Observations","authors":["Yeji Choi","Keumgang Cha","Minyoung Back","Hyunguk Choi","Taegyun Jeon"],"date":"2021-09-11","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13183627","openalex":"W3200528587"},"links":{"paper":"https://doi.org/10.3390/rs13183627","pdf":"https://www.mdpi.com/2072-4292/13/18/3627/pdf?version=1631933486"},"orgs":[],"topic":"benchmarks-data-eval","topics":["nowcasting"],"type":"benchmark","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite","stations"],"status":"research","summary":"RAIN-F+ fuses radar, station and satellite data over Korea and provides U-Net benchmarks, showing fusion beats radar-only precipitation nowcasts.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.04619","title":"Projection Of Temperature And Precipitation For 2020-2100 For Tehran Region Using Post-processing Of General Circulation Models Output And Artificial Neural Network Approach","authors":["Ehsan Mosadegh","Iman Babaeian"],"date":"2021-09-10","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.04619","openalex":"W3200132792"},"links":{"paper":"https://arxiv.org/abs/2109.04619","pdf":"https://arxiv.org/pdf/2109.04619"},"orgs":[],"topic":"post-processing","topics":["climate-emulation"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Neural network combination of 15 GCMs for Tehran temperature and precipitation outperforms the best single model and multi-model mean in present-day simulations and future projections.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.02953","title":"Combining data assimilation and machine learning to estimate parameters of a convective-scale model","authors":["Stefanie Legler","Tijana Janjic"],"date":"2021-09-07","year":2021,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"arxiv":"2109.02953","doi":"10.1002/qj.4235","openalex":"W3198157224"},"links":{"paper":"https://doi.org/10.1002/qj.4235","pdf":"https://arxiv.org/pdf/2109.02953"},"orgs":[],"topic":"data-assimilation","topics":["hybrid-parameterization"],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Bayesian neural networks estimate convective-scale model parameters from observations within data assimilation in a 1D shallow-water perfect-model setup, reducing initial state errors.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3109259","title":"ATMConvGRU for Weather Forecasting","authors":["Tingzhao Yu","Qiuming Kuang","Ruyi Yang"],"date":"2021-09-06","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3109259","openalex":"W3198258664"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3109259"},"orgs":["cma"],"topic":"nowcasting","topics":["global-medium-range"],"type":"model","method":["rnn","transformer"],"timescale":["nowcast"],"spatial":[],"data":["radar","other"],"status":"research","summary":"ATMConvGRU adds axial attention memory to ConvGRU for sequential weather prediction of temperature, humidity, wind and radar echo, outperforming state-of-the-art methods.","significance":3,"cited_by":27,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.scitotenv.2021.150130","title":"An urban energy balance-guided machine learning approach for synthetic nocturnal surface Urban Heat Island prediction: A heatwave event in Naples","authors":["Ana Oliveira","António Manuel Saraiva Lopes","Samuel Niza","Amílcar Soares"],"date":"2021-09-06","year":2021,"venue":"The Science of The Total Environment","venue_type":"journal","ids":{"doi":"10.1016/j.scitotenv.2021.150130","openalex":"W3198740282"},"links":{"paper":"https://doi.org/10.1016/j.scitotenv.2021.150130"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Urban energy balance-guided machine learning predicts nocturnal surface urban heat island during a Naples heatwave; abstract missing, judged from title.","significance":2,"cited_by":63,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.02013","title":"Simple El Niño prediction scheme using the signature of climate time series","authors":["Nozomi Sugiura","Shinya Kouketsu"],"date":"2021-09-05","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.02013"},"links":{"paper":"https://arxiv.org/abs/2109.02013","pdf":"https://arxiv.org/pdf/2109.02013"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Path-signature machine learning model using climate indices predicts El Niño NINO3.4 SST six months ahead with MSE of 0.596 and identifies North Pacific precursors.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1093-ije-dyab168.323","title":"475Machine learning approach: identifying the impact of heatwaves and air quality on children’s health","authors":["Dimpalben Patel","Le Jian","Jianguo Xiao","Janis Jansz","Grace Yun","Ting Lin","Gavin F Pereira","Andrew Robertson"],"date":"2021-09-01","year":2021,"venue":"International Journal of Epidemiology","venue_type":"journal","ids":{"doi":"10.1093/ije/dyab168.323","openalex":"W3196744274"},"links":{"paper":"https://doi.org/10.1093/ije/dyab168.323","pdf":"https://academic.oup.com/ije/article-pdf/50/Supplement_1/dyab168.323/40212709/dyab168.323.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Random forest models predict children's emergency department attendances in Western Australia from heatwaves, fire burns and air pollutants, with R² up to 0.95.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.heliyon.2021.e07959","title":"Wind and solar resource assessment and prediction using Artificial Neural Network and semi-empirical model: case study of the Colombian Caribbean region","authors":["Oscar Churio Silvera","Marley Cecilia Vanegas Chamorro","Guillermo Eliecer Valencia Ochoa"],"date":"2021-09-01","year":2021,"venue":"Heliyon","venue_type":"journal","ids":{"doi":"10.1016/j.heliyon.2021.e07959","openalex":"W3198140101"},"links":{"paper":"https://doi.org/10.1016/j.heliyon.2021.e07959"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Wind and solar resource assessment for Colombia's Caribbean islands pairs semi-empirical models with a neural network that predicts irradiance with RMSE 0.87.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.2032","title":"Deep learning‐based precipitation bias correction approach for Yin–He global spectral model","authors":["Yi‐Fan Hu","Fukang Yin","Weimin Zhang"],"date":"2021-09-01","year":2021,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.2032","openalex":"W3207197663"},"links":{"paper":"https://doi.org/10.1002/met.2032"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"U-Net-based bias correction of Yin-He global model 3-hour precipitation re-forecasts over China improves threat scores, especially for heavy rain and rainstorms.","significance":3,"cited_by":40,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11177931","title":"Improving Forecast Accuracy with an Auto Machine Learning Post-Correction Technique in Northern Xinjiang","authors":["Junjian Liu","Hailiang Zhang","Huoqing Li","Ali Mamtimin"],"date":"2021-08-27","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11177931","openalex":"W3196323974"},"links":{"paper":"https://doi.org/10.3390/app11177931","pdf":"https://www.mdpi.com/2076-3417/11/17/7931/pdf?version=1630069182"},"orgs":["cma"],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"AutoML post-correction of WRF forecasts at 13 Xinjiang stations cuts temperature RMSE from 3.24 to 2.34 °C and humidity RMSE from 19.54% to 11.54%.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.12132","title":"Machine learning-based aerosol characterization using OCO-2 O2 A-band observations","authors":["Sihe Chen","Vijay Natraj","Zhao-Cheng Zeng","Yuk-ling Yung"],"date":"2021-08-27","year":2021,"venue_type":"preprint","ids":{"arxiv":"2108.12132","doi":"10.1016/j.jqsrt.2021.108049"},"links":{"paper":"https://arxiv.org/abs/2108.12132","pdf":"https://arxiv.org/pdf/2108.12132"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A two-step neural network retrieves aerosol parameters from OCO-2 O2 A-band spectra, improving XCO2 retrievals relative to the Level-2 standard product.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.5220711","title":"Neural Network Radiation Emulator (KMA/NIMS)","authors":["Hwan‐Jin Song","Soonyoung Roh","Park, Hyesook"],"date":"2021-08-26","year":2021,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.5220711","openalex":"W4287020216"},"links":{"paper":"https://doi.org/10.5281/zenodo.5220711"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"Releases code and training data for a neural network radiation emulator in an NWP model, tied to improved forecast accuracy.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-aerospace8090236","title":"Unscented Kalman Filter-Aided Long Short-Term Memory Approach for Wind Nowcasting","authors":["Junghyun Kim","Kyuman Lee"],"date":"2021-08-26","year":2021,"venue":"Aerospace","venue_type":"journal","ids":{"doi":"10.3390/aerospace8090236","openalex":"W3193827085"},"links":{"paper":"https://doi.org/10.3390/aerospace8090236","pdf":"https://www.mdpi.com/2226-4310/8/9/236/pdf?version=1629973755"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn","classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"UKF-aided LSTM improves short-term aviation wind nowcasts over plain LSTM and quantifies uncertainty with Monte Carlo simulation.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3105438","title":"Deep Learning for Bias Correction of Satellite Retrievals of Orographic Precipitation","authors":["Haonan Chen","Luyao Sun","Robert C. Cifelli","Pingping Xie"],"date":"2021-08-26","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3105438","openalex":"W3200436801"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3105438","pdf":"http://repository.library.noaa.gov/view/noaa/65991/noaa_65991_DS1.pdf"},"orgs":["noaa","colorado-state-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"CNN bias correction of CMORPH satellite precipitation over US coastal mountains raises correlation from 0.55 to 0.88 against Stage IV gauge-radar data.","significance":3,"cited_by":53,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11069-021-05002-2","title":"Surrogate modeling of time-dependent metocean conditions during hurricanes","authors":["Chi Qiao","Andrew T. Myers"],"date":"2021-08-26","year":2021,"venue":"Natural Hazards","venue_type":"journal","ids":{"doi":"10.1007/s11069-021-05002-2","openalex":"W4250893363"},"links":{"paper":"https://doi.org/10.1007/s11069-021-05002-2","pdf":"https://www.researchsquare.com/article/rs-234266/latest.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Surrogate model for time-dependent metocean conditions during hurricanes. No abstract is available, so this classification is low-confidence.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10507827.1","title":"Deep Learning for Improving Numerical Weather Prediction of Rainfall Extremes","authors":["Philipp Hess","Niklas Boers"],"date":"2021-08-25","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1002/essoar.10507827.1","openalex":"W3196443665"},"links":{"paper":"https://doi.org/10.1029/2021ms002765","pdf":"https://www.authorea.com/doi/pdf/10.1002/essoar.10507827.1"},"orgs":["pik","tum"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Deep networks trained on an NWP ensemble with a frequency-weighted loss correct rainfall, improving extreme-event forecast skill by factors of two to above six.","significance":4,"cited_by":113,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.10747","title":"Model calibration using ESEm v1.0.0 -- an open, scalable Earth System Emulator","authors":["Duncan Watson-Parris","Andrew Williams","Lucia Deaconu","Philip Stier"],"date":"2021-08-24","year":2021,"venue":"Geosci. Model Dev. 14 (2021) 7659-7672","venue_type":"journal","ids":{"arxiv":"2108.10747","doi":"10.5194/gmd-14-7659-2021","openalex":"W3195287738"},"links":{"paper":"https://arxiv.org/abs/2108.10747","pdf":"https://arxiv.org/pdf/2108.10747"},"orgs":["university-of-oxford"],"topic":"climate-emulation","topics":["infra-software"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"ESEm, an open-source Gaussian-process emulation and calibration toolkit, reduces parametric uncertainty in a GCM and explores CMIP6 scenario uncertainty.","significance":4,"cited_by":61,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13163330","title":"Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations","authors":["Mingshan Duan","Jiangjiang Xia","Zhongwei Yan","Lei Han","Lejian Zhang","Hanmeng Xia","Shuang Yu"],"date":"2021-08-23","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13163330","openalex":"W3195543658"},"links":{"paper":"https://doi.org/10.3390/rs13163330","pdf":"https://www.mdpi.com/2072-4292/13/16/3330/pdf"},"orgs":["iap-cas","cma"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"U-Net-style CNN reconstructs 35 dBZ radar reflectivity from Himawari-8 infrared channels over North China, a proxy product for regions without radar.","significance":3,"cited_by":37,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13163324","title":"High Wind Speed Inversion Model of CYGNSS Sea Surface Data Based on Machine Learning","authors":["Yun Zhang","Jiwei Yin","Shuhu Yang","Wanting Meng","Yanling Han","Ziyu Yan"],"date":"2021-08-23","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13163324","openalex":"W3196003997"},"links":{"paper":"https://doi.org/10.3390/rs13163324","pdf":"https://www.mdpi.com/2072-4292/13/16/3324/pdf?version=1630306663"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"SVR, PCA-SVR and CNN models invert high sea-surface winds from CYGNSS GNSS-R data; the CNN reaches 2.71 m/s MAE for winds above 25 m/s.","significance":3,"cited_by":27,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13163273","title":"Rainrate Estimation from FY-4A Cloud Top Temperature for Mesoscale Convective Systems by Using Machine Learning Algorithm","authors":["Ping Lao","Qi Liu","Yuhao Ding","Yu Wang","Yuan Li","Meng Li"],"date":"2021-08-19","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13163273","openalex":"W3194480665"},"links":{"paper":"https://doi.org/10.3390/rs13163273","pdf":"https://www.mdpi.com/2072-4292/13/16/3273/pdf?version=1629351324"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A random forest hybrid estimates mesoscale convective system rainrate from FY-4A cloud-top temperature features, outperforming the operational FY-4A precipitation product.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fmars.2021.717184","title":"Multi-Year ENSO Forecasts Using Parallel Convolutional Neural Networks With Heterogeneous Architecture","authors":["Min Ye","Jie Nie","An-An Liu","Zhigang Wang","Lei Huang","Hao Tian","Dehai Song","Zhiqiang Wei"],"date":"2021-08-19","year":2021,"venue":"Frontiers in Marine Science","venue_type":"journal","ids":{"doi":"10.3389/fmars.2021.717184","openalex":"W3194009275"},"links":{"paper":"https://doi.org/10.3389/fmars.2021.717184","pdf":"https://www.frontiersin.org/articles/10.3389/fmars.2021.717184/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Parallel CNNs with lead-time-specific architectures extend ENSO forecasts multiple years ahead with better skill than prior deep learning baselines.","significance":4,"cited_by":25,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002521","title":"Building Tangent‐Linear and Adjoint Models for Data Assimilation With Neural Networks","authors":["Sam Hatfield","Matthew Chantry","Peter Dominik Dueben","Philippe Lopez","Alan Geer","T. N. Palmer"],"date":"2021-08-19","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002521","openalex":"W3194469141"},"links":{"paper":"https://doi.org/10.1029/2021ms002521","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021MS002521"},"orgs":["ecmwf","university-of-oxford"],"topic":"data-assimilation","topics":["hybrid-parameterization"],"type":"model","method":["differentiable"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Neural network emulator of gravity wave drag yields tangent-linear and adjoint models that succeed in 4D-Var assimilation, easing code maintenance.","significance":4,"cited_by":97,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.engappai.2021.104423","title":"Data-driven method for the improving forecasts of local weather dynamics","authors":["Tadej Krivec","Juš Kocijan","Matija Perne","Boštjan Grašič","Marija Zlata Božnar","Primož Mlakar"],"date":"2021-08-19","year":2021,"venue":"Engineering Applications of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1016/j.engappai.2021.104423","openalex":"W3194951001"},"links":{"paper":"https://doi.org/10.1016/j.engappai.2021.104423","pdf":"https://www.sciencedirect.com/science/article/pii/S0952197621002712/pdf"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Gaussian process model fuses station observations with NWP forecasts to improve local short- and long-term weather forecasts for dispersion modelling.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-cpe.6559","title":"On the provenance extraction techniques from large scale log files","authors":["Alper Tufek","Mehmet S. Aktaş"],"date":"2021-08-19","year":2021,"venue":"Concurrency and Computation Practice and Experience","venue_type":"journal","ids":{"doi":"10.1002/cpe.6559","openalex":"W3186907865"},"links":{"paper":"https://doi.org/10.1002/cpe.6559"},"orgs":[],"topic":"infra-software","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"ML-based log parser extracts provenance from WRF model runs to build provenance graphs that trace faults in numerical weather forecast workflows.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.13262","title":"Calibration and Uncertainty Quantification of Convective Parameters in an Idealized GCM","authors":["Oliver R. A. Dunbar","Tapio Schneider","Andrew M. Stuart","Alfredo Garbuno-Iñigo"],"date":"2021-08-19","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2012.13262","doi":"10.1029/2020ms002454","openalex":"W3113646778"},"links":{"paper":"https://doi.org/10.1029/2020ms002454","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002454"},"orgs":["caltech"],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Calibrate-emulate-sample with Gaussian process emulators and ensemble Kalman inversion quantifies convective parameter uncertainty in an idealized GCM at a fraction of MCMC cost.","significance":3,"cited_by":88,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1177-10943420211039818","title":"Data-driven global weather predictions at high resolutions","authors":["John Taylor","Pablo Larraondo","Bronis R. de Supinski"],"date":"2021-08-18","year":2021,"venue":"The International Journal of High Performance Computing Applications","venue_type":"journal","ids":{"doi":"10.1177/10943420211039818","openalex":"W4255668578"},"links":{"paper":"https://doi.org/10.1177/10943420211039818","pdf":"https://www.researchsquare.com/article/rs-310930/latest.pdf"},"orgs":[],"topic":"global-medium-range","topics":["infra-software"],"type":"model","method":["transformer","neural-operator"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Data-driven global model forecasts atmospheric state and 0.25-degree precipitation without physics, with training scaled to 1024 GPUs for rapid iteration.","significance":6,"cited_by":10,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11069-021-04955-8","title":"Modeling the economic impact of incoming tropical cyclones using machine learning","authors":["Vera Wendler-Bosco","Charles Nicholson"],"date":"2021-08-17","year":2021,"venue":"Natural Hazards","venue_type":"journal","ids":{"doi":"10.1007/s11069-021-04955-8","openalex":"W3195589458"},"links":{"paper":"https://doi.org/10.1007/s11069-021-04955-8"},"orgs":["university-of-oklahoma"],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Uses machine learning to model the economic impact of incoming tropical cyclones. The abstract is missing, so this classification is low-confidence.","significance":2,"cited_by":12,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.07063","title":"Multistream Graph Attention Networks for Wind Speed Forecasting","authors":["Dogan Aykas","Siamak Mehrkanoon"],"date":"2021-08-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2108.07063"},"links":{"paper":"https://arxiv.org/abs/2108.07063","pdf":"https://arxiv.org/pdf/2108.07063"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["gnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Graph attention network with a learnable adjacency and per-variable attention, combined with LSTM, forecasts wind speed at several Danish and Dutch cities from multivariate weather data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ea001490","title":"A Benchmark to Test Generalization Capabilities of Deep Learning Methods to Classify Severe Convective Storms in a Changing Climate","authors":["María J. Molina","David John Gagne","Andreas Franz Prein"],"date":"2021-08-14","year":2021,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2020ea001490","openalex":"W3173201562"},"links":{"paper":"https://doi.org/10.1029/2020ea001490","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020EA001490"},"orgs":["ncar"],"topic":"extremes-hazards","topics":["climate-analysis-attribution","benchmarks-data-eval"],"type":"benchmark","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["km-scale-sim","cmip"],"status":"research","summary":"CNN trained on present-day WRF storms classifies strongly rotating thunderstorms in end-of-century climate simulations with skill, and explanations reveal learned physical features.","significance":3,"cited_by":49,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.06195","title":"Two-Dimensional Convective Boundary Layer: Numerical Analysis and Echo State Network model","authors":["Florian Heyder","Juan Pedro Mellado","Jörg Schumacher"],"date":"2021-08-13","year":2021,"venue_type":"preprint","ids":{"arxiv":"2108.06195","openalex":"W3195378709"},"links":{"paper":"http://arxiv.org/pdf/2108.06195.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Echo state network trained on direct numerical simulations reproduces convective boundary-layer buoyancy flux statistics and generalizes to unseen flux ratios without solving the equations of motion.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-14-4977-2021","title":"Latent Linear Adjustment Autoencoder v1.0: a novel method for estimating and emulating dynamic precipitation at high resolution","authors":["Christina Heinze‐Deml","Sebastian Sippel","Angeline Greene Pendergrass","Flavio Lehner","Nicolai Meinshausen"],"date":"2021-08-12","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-14-4977-2021","openalex":"W3095433008"},"links":{"paper":"https://doi.org/10.5194/gmd-14-4977-2021","pdf":"https://gmd.copernicus.org/articles/14/4977/2021/gmd-14-4977-2021.pdf"},"orgs":["ncar","eth-zurich"],"topic":"climate-analysis-attribution","topics":["downscaling"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A variational autoencoder with a linear latent penalty separates circulation-driven daily precipitation at 12 km over Europe, enabling dynamical adjustment of high-resolution fields.","significance":3,"cited_by":20,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-20-0222.1","title":"Bias Correction, Anonymization, and Analysis of Smartphone Pressure Observations Using Machine Learning and Multiresolution Kriging","authors":["Callie McNicholas","Clifford F. Mass"],"date":"2021-08-12","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-20-0222.1","openalex":"W3196148980"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0222.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/36/5/WAF-D-20-0222.1.pdf"},"orgs":["university-of-washington"],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"pre-operational","summary":"Machine learning bias correction of billions of smartphone pressure observations cuts errors 43-57% and yields analyses 21-31% better than MADIS networks.","significance":4,"cited_by":14,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ac1d0c","title":"Machine learning to optimize climate projection over China with multi-model ensemble simulations","authors":["Tong Li","Zhihong Jiang","Hervé Le Treut","Laurent Li","Lilong Zhao","Lingling Ge"],"date":"2021-08-12","year":2021,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ac1d0c","openalex":"W3194252960"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ac1d0c","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ac1d0c/pdf"},"orgs":["nuist"],"topic":"post-processing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Random forest combines CMIP6 multi-model ensembles over China, projecting less warming and wetter conditions with better spatial skill than the arithmetic mean.","significance":3,"cited_by":49,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13163157","title":"Deep Learning for Polarimetric Radar Quantitative Precipitation Estimation during Landfalling Typhoons in South China","authors":["Yonghua Zhang","Shuoben Bi","Liping Liu","Haonan Chen","Yi Zhang","Shen Ping","Fan Nils Yang","Yaqiang Wang","Yang Zhang","Shun Yao"],"date":"2021-08-10","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13163157","openalex":"W3191285888"},"links":{"paper":"https://doi.org/10.3390/rs13163157","pdf":"https://www.mdpi.com/2072-4292/13/16/3157/pdf?version=1628582477"},"orgs":["nuist","colorado-state-university","cma"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"QPENet deep learning on dual-polarization radar, trained on 11 typhoons, beats DSD-based parametric QPE for rainfall estimation in South China.","significance":3,"cited_by":28,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s43247-021-00225-4","title":"Training machine learning models on climate model output yields skillful interpretable seasonal precipitation forecasts","authors":["Peter B. Gibson","William E. Chapman","Alphan Altinok","Luca Delle Monache","Michael J. DeFlorio","Duane E. Waliser"],"date":"2021-08-10","year":2021,"venue":"Communications Earth &amp; Environment","venue_type":"journal","ids":{"doi":"10.1038/s43247-021-00225-4","openalex":"W3193123863"},"links":{"paper":"https://doi.org/10.1038/s43247-021-00225-4"},"orgs":["caltech","nasa"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"ML trained on a large climate model ensemble yields seasonal precipitation forecasts over the western US competitive with NMME dynamical models.","significance":4,"cited_by":161,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s00382-021-05916-4","title":"Using deep learning for precipitation forecasting based on spatio-temporal information: a case study","authors":["Weide Li","Xi Gao","Zihan Hao","Rong Xia Sun"],"date":"2021-08-07","year":2021,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-021-05916-4","openalex":"W3188612754"},"links":{"paper":"https://doi.org/10.1007/s00382-021-05916-4"},"orgs":[],"topic":"nowcasting","topics":[],"type":"application","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":[],"status":"research","summary":"Deep learning precipitation forecasts from spatio-temporal inputs in a regional case study; no abstract available, so details are limited.","significance":2,"cited_by":56,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13163112","title":"The New Volcanic Ash Satellite Retrieval VACOS Using MSG/SEVIRI and Artificial Neural Networks: 1. Development","authors":["Dennis Piontek","Luca Bugliaro","Marius Schmidl","Daniel K. Zhou","Christiane Voigt"],"date":"2021-08-06","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13163112","openalex":"W3189604703"},"links":{"paper":"https://doi.org/10.3390/rs13163112","pdf":"https://www.mdpi.com/2072-4292/13/16/3112/pdf?version=1628251950"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Neural-network retrieval VACOS uses MSG/SEVIRI thermal channels and ECMWF profiles to detect volcanic ash and retrieve cloud-top height and particle radius, day and night.","significance":3,"cited_by":13,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-cli9080127","title":"Identification of Weather Influences on Flight Punctuality Using Machine Learning Approach","authors":["Sakdirat Kaewunruen","Jessada Sresakoolchai","Yue Xiang"],"date":"2021-08-06","year":2021,"venue":"Climate","venue_type":"journal","ids":{"doi":"10.3390/cli9080127","openalex":"W3191174179"},"links":{"paper":"https://doi.org/10.3390/cli9080127","pdf":"https://www.mdpi.com/2225-1154/9/8/127/pdf?version=1628768112"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Random forest and neural networks link weather to flight punctuality at Birmingham Airport, reaching R² of 0.80 for punctuality rates.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3100847","title":"Convective Precipitation Nowcasting Using U-Net Model","authors":["Lei Han","Liang He","Haonan Chen","Wei Zhang","Yurong Ge"],"date":"2021-08-06","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3100847","openalex":"W3199775909"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3100847"},"orgs":["colorado-state-university"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"U-Net on five radar frames predicts convective reflectivity, matching TrajGRU and outperforming TREC with a simpler CNN.","significance":3,"cited_by":152,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl092449","title":"First Application of Artificial Neural Networks to Estimate 21st Century Greenland Ice Sheet Surface Melt","authors":["Raymond Sellevold","Miren Vizcaíno"],"date":"2021-08-06","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl092449","openalex":"W3187337830"},"links":{"paper":"https://doi.org/10.1029/2021gl092449","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021GL092449"},"orgs":[],"topic":"climate-emulation","topics":["hybrid-parameterization"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Neural networks trained on CESM2 output emulate 21st-century Greenland ice sheet surface melt across CMIP6 models, avoiding costly regional climate model runs.","significance":4,"cited_by":24,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13163101","title":"Cereal Yield Forecasting with Satellite Drought-Based Indices, Weather Data and Regional Climate Indices Using Machine Learning in Morocco","authors":["El Houssaine Bouras","Lionel Jarlan","Salah Er‐Raki","Riad Balaghi","Abdelhakim Amazirh","Bastien Richard","Saïd Khabba"],"date":"2021-08-05","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13163101","openalex":"W3196327550"},"links":{"paper":"https://doi.org/10.3390/rs13163101","pdf":"https://www.mdpi.com/2072-4292/13/16/3101/pdf?version=1628211600"},"orgs":[],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"Machine learning models with satellite drought indices, weather and NAO predict Moroccan cereal yields up to 4 months before harvest, outperforming single-source models.","significance":2,"cited_by":86,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-forecast3030034","title":"Influence of the Characteristics of Weather Information in a Thunderstorm-Related Power Outage Prediction System","authors":["Peter L. Watson","Marika Koukoula","Emmanouil N. Anagnostou"],"date":"2021-08-05","year":2021,"venue":"Forecasting","venue_type":"journal","ids":{"doi":"10.3390/forecast3030034","openalex":"W3188404705"},"links":{"paper":"https://doi.org/10.3390/forecast3030034","pdf":"https://www.mdpi.com/2571-9394/3/3/34/pdf?version=1628493281"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"evaluation","method":[],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Compares two NWP systems with different data assimilation as inputs to a thunderstorm power-outage model, showing simulation errors propagate quantifiably into outage predictions.","significance":2,"cited_by":24,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3100899","title":"Prediction of Synoptic-Scale Sea Level Pressure Over the Indian Monsoon Region Using Deep Learning","authors":["Aryaman Sinha","Mayuna Gupta","K. S. S. Sai Srujan","Hariprasad Kodamana","S. Sandeep"],"date":"2021-08-05","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3100899","openalex":"W3157896282"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3100899","pdf":"https://www.techrxiv.org/articles/preprint/Prediction_of_synoptic-scale_sea_level_pressure_over_the_Indian_monsoon_region_using_deep_learning/14377298/files/27463490.pdf"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"ConvLSTM predicts daily Indian monsoon sea level pressure anomalies at 7-day lead, with better synoptic skill than a conventional NWP model.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54302-mausam.v71i4.54","title":"Spatio-temporal variations of land surface temperature and precipitation due to climate change in the Jhelum river basin, India","authors":["Dar Himayoun","Thendiyath Roshni","MOHSIN FAROOQ"],"date":"2021-08-04","year":2021,"venue":"MAUSAM","venue_type":"journal","ids":{"doi":"10.54302/mausam.v71i4.54","openalex":"W3142441569"},"links":{"paper":"https://doi.org/10.54302/mausam.v71i4.54","pdf":"https://mausamjournal.imd.gov.in/index.php/MAUSAM/article/download/54/54"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Wavelet-ANN statistical downscaling of CanESM2 under RCP8.5 projects 17-25% wetter and 2-3 °C warmer conditions in the Jhelum basin by 2100.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-electronics10161872","title":"A Regularization-Based Big Data Framework for Winter Precipitation Forecasting on Streaming Data","authors":["Andreas Kanavos","Μαρία Τρίγκα","Elias Dritsas","Gerasimos Vonitsanos","Phivos Mylonas B"],"date":"2021-08-04","year":2021,"venue":"Electronics","venue_type":"journal","ids":{"doi":"10.3390/electronics10161872","openalex":"W3189393624"},"links":{"paper":"https://doi.org/10.3390/electronics10161872","pdf":"https://www.mdpi.com/2079-9292/10/16/1872/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Regularized classifiers in a Spark streaming pipeline predict winter precipitation type (rain, freezing rain, snow) from ASOS station data.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10507695.1","title":"A machine learning bias correction method for precipitation corresponding to weather conditions using simple input data","authors":["Takao Yoshikane","Kei Yoshimura"],"date":"2021-08-04","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10507695.1","openalex":"W3191773775"},"links":{"paper":"https://doi.org/10.1002/essoar.10507695.1"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A simple machine learning bias correction conditioned on weather regimes improves precipitation frequency and local distributions in forecasts beyond 24 hours.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2021.697423","title":"Week 3–4 Prediction of Wintertime CONUS Temperature Using Machine Learning Techniques","authors":["Paul Buchmann","Timothy DelSole"],"date":"2021-08-03","year":2021,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2021.697423","openalex":"W3208736825"},"links":{"paper":"https://doi.org/10.3389/fclim.2021.697423","pdf":"https://www.frontiersin.org/articles/10.3389/fclim.2021.697423/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["cmip","nwp-analysis"],"status":"research","summary":"Ridge and lasso models using Niño3.4 give modest week 3-4 skill for US winter temperature, only slightly beating CFSv2 and climatology-based baselines.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3100485","title":"Transformer for EI Niño-Southern Oscillation Prediction","authors":["Feng Ye","Jie Hu","Tianqiang Huang","Lijun You","Bin Weng","Jianyun Gao"],"date":"2021-08-03","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3100485","openalex":"W3192029423"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3100485"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["transformer"],"timescale":["seasonal","s2s"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"An ENSO Transformer (ENSOTR) predicts the Niño3.4 index skillfully up to 18 months ahead and outperforms CNN baselines, including the 1997–98 El Niño.","significance":4,"cited_by":32,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2109.07468","title":"Computationally-Efficient Climate Predictions using Multi-Fidelity Surrogate Modelling","authors":["Ben Hudson","Frederik Nijweide","Isaac Sebenius"],"date":"2021-08-03","year":2021,"venue_type":"preprint","ids":{"arxiv":"2109.07468"},"links":{"paper":"https://arxiv.org/abs/2109.07468","pdf":"https://arxiv.org/pdf/2109.07468"},"orgs":[],"topic":"downscaling","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Multi-fidelity Gaussian processes fuse a coarse GCM and a regional climate model to predict Peruvian temperatures, evaluating only 6% of the high-fidelity region.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21155234","title":"Forecasting of Typhoon-Induced Wind-Wave by Using Convolutional Deep Learning on Fused Data of Remote Sensing and Ground Measurements","authors":["Chih‐Chiang Wei","Hao-Chun Chang"],"date":"2021-08-02","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21155234","openalex":"W3188214958"},"links":{"paper":"https://doi.org/10.3390/s21155234","pdf":"https://www.mdpi.com/1424-8220/21/15/5234/pdf?version=1627907176"},"orgs":[],"topic":"local-forecasting","topics":["nowcasting"],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"GRU-CNN models forecast typhoon winds and wave heights 1 to 6 h ahead at Taiwan buoys using station data and radar reflectivity images.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.00806","title":"Super-Resolution of Near-Surface Temperature Utilizing Physical Quantities for Real-Time Prediction of Urban Micrometeorology","authors":["Yuki Yasuda","Ryo Onishi","Yuichi Hirokawa","Dmitry Kolomenskiy","Daisuke Sugiyama"],"date":"2021-08-02","year":2021,"venue_type":"preprint","ids":{"arxiv":"2108.00806"},"links":{"paper":"https://arxiv.org/abs/2108.00806","pdf":"https://arxiv.org/pdf/2108.00806"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"A CNN super-resolution model with attention upscales urban near-surface temperature from 20 m to 5 m, beating bicubic interpolation and enabling fast real-time inference.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ea001458","title":"Advanced Grid Model of Weighted Mean Temperature Based on Feedforward Neural Network Over China","authors":["Mingchen Zhu","Wusheng Hu","Wei Sun"],"date":"2021-07-31","year":2021,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2020ea001458","openalex":"W3192122071"},"links":{"paper":"https://doi.org/10.1029/2020ea001458","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020EA001458"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"A feedforward neural network grid model of GNSS weighted mean temperature over China improves on GPT2w-Tm by about 8.6–10.9% in validation.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.00164","title":"Strengthening of Indian Ocean teleconnections permits predictions of springtime rainfall in SE Australia","authors":["Stjepan Marcelja"],"date":"2021-07-31","year":2021,"venue_type":"preprint","ids":{"arxiv":"2108.00164"},"links":{"paper":"https://arxiv.org/abs/2108.00164","pdf":"https://arxiv.org/pdf/2108.00164"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"pre-operational","summary":"Deep learning using Indian Ocean sea surface temperatures and forecast ENSO hindcasts predicts spring rainfall in SE Australia, with skill for September/October from end of June.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl093787","title":"Using Machine Learning to Analyze Physical Causes of Climate Change: A Case Study of U.S. Midwest Extreme Precipitation","authors":["Frances V. Davenport","Noah S. Diffenbaugh"],"date":"2021-07-30","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl093787","openalex":"W3183706855"},"links":{"paper":"https://doi.org/10.1029/2021gl093787"},"orgs":["stanford"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"A CNN identifies 91% of Midwest extreme precipitation events from circulation patterns and finds increasing frequency of the associated patterns over two decades.","significance":4,"cited_by":151,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2108.00048","title":"Controlling Weather Field Synthesis Using Variational Autoencoders","authors":["Dario Augusto Borges Oliveira","Jorge Guevara Diaz","Bianca Zadrozny","Campbell Watson"],"date":"2021-07-30","year":2021,"venue_type":"preprint","ids":{"arxiv":"2108.00048"},"links":{"paper":"https://arxiv.org/abs/2108.00048","pdf":"https://arxiv.org/pdf/2108.00048"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A VAE maps monsoon precipitation fields to a known distribution, enabling controlled synthesis of more extreme rainfall scenarios over southwest India.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3183632597","title":"Weather Forecasting using Advanced Techniques","authors":["Nitish Deolia","Mohit Kumar","Rahul Rajawat"],"date":"2021-07-29","year":2021,"venue_type":"other","ids":{"openalex":"W3183632597"},"links":{"paper":"https://thedesignengineering.com/index.php/DE/article/view/3005"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Generic overview of data mining and machine learning for weather prediction; it claims simpler models can match physical methods but gives no quantitative results.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.13875","title":"Spatio-temporal graph neural networks for multi-site PV power forecasting","authors":["Jelena Simeunović","Baptiste Schubnel","Pierre-Jean Alet","Rafael E. Carrillo"],"date":"2021-07-29","year":2021,"venue":"IEEE Transactions on Sustainable Energy","venue_type":"journal","ids":{"arxiv":"2107.13875","doi":"10.1109/tste.2021.3125200","openalex":"W3183572711"},"links":{"paper":"https://doi.org/10.1109/tste.2021.3125200","pdf":"https://arxiv.org/pdf/2107.13875"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["gnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Graph neural networks forecast multi-site PV power over Switzerland using PV systems as virtual weather stations, beating single-site NWP methods up to 4 hours ahead.","significance":3,"cited_by":272,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-21-0007.1","title":"Using deep learning to emulate and accelerate a radiative-transfer model","authors":["Ryan Lagerquist","David D. Turner","Imme Ebert‐Uphoff","Jebb Q. Stewart","Venita Hagerty"],"date":"2021-07-28","year":2021,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-21-0007.1","openalex":"W3186737891"},"links":{"paper":"https://doi.org/10.1175/jtech-d-21-0007.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atot/38/10/JTECH-D-21-0007.1.pdf"},"orgs":["noaa","colorado-state-university"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"pre-operational","summary":"Knowledge-guided U-Net++ emulates the RRTM shortwave radiation scheme for NWP, running about 10^4 times faster with good tropical generalization.","significance":4,"cited_by":69,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.10855","title":"Quantum Artificial Intelligence for the Science of Climate Change","authors":["Manmeet Singh","Chirag Dhara","Adarsh Kumar","Sukhpal Singh Gill","Steve Uhlig"],"date":"2021-07-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2108.10855"},"links":{"paper":"https://arxiv.org/abs/2108.10855","pdf":"https://arxiv.org/pdf/2108.10855"},"orgs":[],"topic":"infra-software","topics":[],"type":"position","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Opinion piece arguing quantum artificial intelligence algorithms could provide breakthroughs for weather and climate forecasting and climate change science.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12080953","title":"Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models","authors":["Nipun Gunawardena","Giuliana Pallotta","Matthew D. Simpson","Donald D. Lucas"],"date":"2021-07-24","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12080953","openalex":"W3184659341"},"links":{"paper":"https://doi.org/10.3390/atmos12080953","pdf":"https://www.mdpi.com/2073-4433/12/8/953/pdf?version=1627372149"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Linear and logistic regression emulate spatial deposition from a multi-physics atmospheric dispersion ensemble, about 10,000 times faster per run but 24 times faster overall.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-ws.2021.237","title":"Precipitation forecast based on CEEMD–LSTM coupled model","authors":["Xianqi Zhang","Xilong Wu","Shaoyu He","Dong Bao Zhao"],"date":"2021-07-23","year":2021,"venue":"Water Science & Technology Water Supply","venue_type":"journal","ids":{"doi":"10.2166/ws.2021.237","openalex":"W3186826224"},"links":{"paper":"https://doi.org/10.2166/ws.2021.237"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A CEEMD-LSTM hybrid predicts monthly precipitation in Zhengzhou with NSE 0.95, beating LSTM and BP-based baselines on station data.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2021.07.047","title":"Improving prediction of surface solar irradiance variability by integrating observed cloud characteristics and machine learning","authors":["Laura Riihimaki","Xinya Li","Zhangshuan Hou","Larry K. Berg"],"date":"2021-07-23","year":2021,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2021.07.047","openalex":"W3185987761"},"links":{"paper":"https://doi.org/10.1016/j.solener.2021.07.047"},"orgs":["noaa"],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Integrates observed cloud characteristics with machine learning to improve prediction of surface solar irradiance variability at a site.","significance":2,"cited_by":23,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12517-021-07579-1","title":"RETRACTED ARTICLE: Rainfall forecast and computer data algorithm optimization in coastal areas based on improved neural network","authors":["Jingzhu Wu","Xiuzhi Xing"],"date":"2021-07-23","year":2021,"venue":"Arabian Journal of Geosciences","venue_type":"journal","ids":{"doi":"10.1007/s12517-021-07579-1","openalex":"W3186679947"},"links":{"paper":"https://doi.org/10.1007/s12517-021-07579-1"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Retracted article proposing an improved neural network for coastal rainfall forecasting; no abstract is available and the reported results cannot be relied on.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.11114","title":"A comparison of combined data assimilation and machine learning methods for offline and online model error correction","authors":["Alban Farchi","Marc Bocquet","Patrick Laloyaux","Massimo Bonavita","Quentin Malartic"],"date":"2021-07-23","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.11114"},"links":{"paper":"https://arxiv.org/abs/2107.11114","pdf":"https://arxiv.org/pdf/2107.11114"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["differentiable","other"],"timescale":["medium"],"spatial":[],"data":["other"],"status":"research","summary":"Compares resolvent and tendency ML error corrections within data assimilation on a two-scale Lorenz model; tendency correction wins in assimilation and enables online learning.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.11046","title":"Learning the structure of wind: A data-driven nonlocal turbulence model for the atmospheric boundary layer","authors":["Brendan Keith","Ustim Khristenko","Barbara Wohlmuth"],"date":"2021-07-23","year":2021,"venue":"Physics of Fluids 33, 095110 (2021)","venue_type":"journal","ids":{"arxiv":"2107.11046","doi":"10.1063/5.0064394","openalex":"W3186717317"},"links":{"paper":"https://arxiv.org/abs/2107.11046","pdf":"https://arxiv.org/pdf/2107.11046"},"orgs":["tum"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Data-driven nonlocal turbulence model whose covariance kernel is partly a neural network, calibrated to 1968 Kansas field data and more accurate than the IEC standard.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.11042","title":"Deep Learning Based Reconstruction of Total Solar Irradiance","authors":["Yasser Abduallah","Jason T. L. Wang","Yucong Shen","Khalid A. Alobaid","Serena Criscuoli","Haimin Wang"],"date":"2021-07-23","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.11042"},"links":{"paper":"https://arxiv.org/abs/2107.11042","pdf":"https://arxiv.org/pdf/2107.11042"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":[],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"TSInet deep learning reconstructs total solar irradiance over more than 9,000 years, matching physics-based models where data overlap.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w13151997","title":"Examining the Applicability of Wavelet Packet Decomposition on Different Forecasting Models in Annual Rainfall Prediction","authors":["Hua Wang","Wenchuan Wang","Yujin Du","Dongmei Xu"],"date":"2021-07-21","year":2021,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w13151997","openalex":"W3184218263"},"links":{"paper":"https://doi.org/10.3390/w13151997","pdf":"https://www.mdpi.com/2073-4441/13/15/1997/pdf?version=1626924956"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A wavelet packet decomposition plus extreme learning machine hybrid (WPD-ELM) forecasts annual rainfall better than ARIMA and BPNN baselines, though the study is regional and modest in scope.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-21-0026.1","title":"Forecasting excessive rainfall with random forests and a deterministic convection-allowing model","authors":["Aaron J. Hill","Russ S. Schumacher"],"date":"2021-07-21","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-21-0026.1","openalex":"W3187052348"},"links":{"paper":"https://doi.org/10.1175/waf-d-21-0026.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/36/5/WAF-D-21-0026.1.pdf"},"orgs":["colorado-state-university"],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar","stations"],"status":"research","summary":"Random forests trained on convection-allowing WRF output probabilistically forecast excessive rainfall over CONUS, but they consistently underperform WPC's day-1 Excessive Rainfall Outlooks.","significance":4,"cited_by":36,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ea001621","title":"Application of a Radar Echo Extrapolation‐Based Deep Learning Method in Strong Convection Nowcasting","authors":["Jian Yin","Zhiqiu Gao","Wei Han"],"date":"2021-07-21","year":2021,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2020ea001621","openalex":"W3186404120"},"links":{"paper":"https://doi.org/10.1029/2020ea001621","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020EA001621"},"orgs":["nuist","iap-cas","cma"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Trains ConvGRU radar echo extrapolation with SSIM and MS-SSIM losses to reduce blurring; MS-SSIM gives the most realistic strong-echo forecasts out to 2 hours.","significance":4,"cited_by":31,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2108.04330","title":"Creating synthetic night-time visible-light meteorological satellite images using the GAN method","authors":["Wencong Cheng"],"date":"2021-07-21","year":2021,"venue":"Remote Sensing Letters","venue_type":"journal","ids":{"arxiv":"2108.04330","doi":"10.1080/2150704x.2022.2079016","openalex":"W4281772014"},"links":{"paper":"https://doi.org/10.1080/2150704x.2022.2079016","pdf":"https://arxiv.org/pdf/2108.04330"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"GAN with channel attention synthesizes night-time visible satellite images from infrared data and ECMWF NWP fields, using FY-4A observations.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-informatics8030047","title":"Bagging Machine Learning Algorithms: A Generic Computing Framework Based on Machine-Learning Methods for Regional Rainfall Forecasting in Upstate New York","authors":["Ning Yu","Timothy Haskins"],"date":"2021-07-20","year":2021,"venue":"Informatics","venue_type":"journal","ids":{"doi":"10.3390/informatics8030047","openalex":"W3184100052"},"links":{"paper":"https://doi.org/10.3390/informatics8030047","pdf":"https://www.mdpi.com/2227-9709/8/3/47/pdf?version=1626834500"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml","rnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"A bagging framework combining KNN, SVM, DNN and LSTM engines forecasts regional rainfall in Upstate New York, with SVM and KNN best for classification.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-20-0264.1","title":"Feature engineering for subseasonal-to-seasonal warm-season precipitation forecasts in the Midwestern US: towards a unifying hypothesis of anomalous warm-season hydroclimatic circulation","authors":["Elizabeth K. Carter","Dimitris A. Herrera","Scott Steinschneider"],"date":"2021-07-20","year":2021,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-20-0264.1","openalex":"W3185464719"},"links":{"paper":"https://doi.org/10.1175/jcli-d-20-0264.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/clim/34/20/JCLI-D-20-0264.1.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Interpretable machine learning ranks 24 predictive indices for March–September Midwest US S2S precipitation and links them to three moisture and circulation mechanisms.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2021.105774","title":"Improving precipitation nowcasting using a three-dimensional convolutional neural network model from Multi Parameter Phased Array Weather Radar observations","authors":["Dongkyun Kim","Taku Suezawa","Tomoaki Mega","Hiroshi Kikuchi","Eiichi Yoshikawa","Philippe Baron","Tomoo Ushio"],"date":"2021-07-20","year":2021,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2021.105774","openalex":"W3183644698"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2021.105774"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"A 3D convolutional neural network applied to multi-parameter phased-array weather radar volumes improves short-term precipitation nowcasting.","significance":3,"cited_by":52,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.13052-jwe1540-9589.2057","title":"Comparisons of Machine Learning Methods of Statistical Downscaling Method: Case Studies of Daily Climate Anomalies in Thailand","authors":["Kanawut Chattrairat","Waranyu Wongseree","Adisorn Leelasantitham"],"date":"2021-07-19","year":2021,"venue":"Journal of Web Engineering","venue_type":"journal","ids":{"doi":"10.13052/jwe1540-9589.2057","openalex":"W3183438132"},"links":{"paper":"https://doi.org/10.13052/jwe1540-9589.2057"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"evaluation","method":["classical-ml","other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Compares linear regression, Gaussian process, SVM and deep learning for statistical downscaling of Thai temperature and precipitation, with deep learning performing best.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7303","title":"Statistical downscaling of daily precipitation over southeastern South America: Assessing the performance in extreme events","authors":["Matias Ezequiel Olmo","María Laura Bettolli"],"date":"2021-07-18","year":2021,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7303","openalex":"W3183806273"},"links":{"paper":"https://doi.org/10.1002/joc.7303"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Compares analogue, neural network and GLM statistical downscaling of daily precipitation extremes over southeastern South America; no single method performs best across all aspects.","significance":3,"cited_by":30,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.dsm.2021.07.002","title":"Comparative study of three stochastic future weather forecast approaches: a case study","authors":["Vinay Kellengere Shankarnarayan","Hombaliah Ramakrishna"],"date":"2021-07-17","year":2021,"venue":"Data Science and Management","venue_type":"journal","ids":{"doi":"10.1016/j.dsm.2021.07.002","openalex":"W3186512974"},"links":{"paper":"https://doi.org/10.1016/j.dsm.2021.07.002","pdf":"https://www.sciencedirect.com/science/article/pii/S2666764921000254/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares KNN, SWAT and RCP weather generators for station temperature, precipitation and wind; KNN is more robust to noisy data.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.08074","title":"A comparative study of stochastic and deep generative models for multisite precipitation synthesis","authors":["Jorge Guevara","Dario Borges","Campbell Watson","Bianca Zadrozny"],"date":"2021-07-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.08074"},"links":{"paper":"https://arxiv.org/abs/2107.08074","pdf":"https://arxiv.org/pdf/2107.08074"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"evaluation","method":["gan-vae"],"timescale":["climate"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Compares GAN and VAE deep generative models against classical weather generators for multisite precipitation synthesis, offering guidance for future climate scenario generation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.07687","title":"Auto-differentiable Ensemble Kalman Filters","authors":["Yuming Chen","Daniel Sanz-Alonso","Rebecca Willett"],"date":"2021-07-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.07687"},"links":{"paper":"https://arxiv.org/abs/2107.07687","pdf":"https://arxiv.org/pdf/2107.07687"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["differentiable","other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Auto-differentiable ensemble Kalman filters jointly learn surrogate dynamics and assimilate states, outperforming EM and particle-filter baselines on Lorenz-96.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl092555","title":"Correcting Weather and Climate Models by Machine Learning Nudged Historical Simulations","authors":["Oliver Watt‐Meyer","Noah Brenowitz","Spencer Koncius Clark","Brian Henn","Anna Kwa","Jeremy McGibbon","W. A. Perkins","Christopher S. Bretherton"],"date":"2021-07-15","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl092555","openalex":"W3150028748"},"links":{"paper":"https://doi.org/10.1029/2021gl092555","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021GL092555"},"orgs":["ai2","noaa","university-of-washington","princeton-university"],"topic":"hybrid-parameterization","topics":["global-medium-range"],"type":"model","method":["classical-ml"],"timescale":["short","climate"],"spatial":["global"],"data":["nwp-analysis","era5"],"status":"research","summary":"A random forest learns nudging tendencies and is coupled to FV3GFS, reducing 500 hPa height forecast error and annual-mean precipitation RMSE by about 20% in year-long runs.","significance":5,"cited_by":135,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-01431161.2021.1933243","title":"Lightning flash rate nowcasting based on polarimetric radar data and machine learning","authors":["Yunish Shrestha","Yan Rockee Zhang","Richard J. Doviak","Pak Wai Chan"],"date":"2021-07-14","year":2021,"venue":"International Journal of Remote Sensing","venue_type":"journal","ids":{"doi":"10.1080/01431161.2021.1933243","openalex":"W3185117548"},"links":{"paper":"https://doi.org/10.1080/01431161.2021.1933243"},"orgs":["noaa","university-of-oklahoma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"Machine learning on polarimetric S-band radar storm cells predicts lightning flash rates up to 30 minutes ahead, with polarimetric gains mainly for short datasets.","significance":3,"cited_by":7,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.06846","title":"Extreme Precipitation Seasonal Forecast Using a Transformer Neural Network","authors":["Daniel Salles Civitarese","Daniela Szwarcman","Bianca Zadrozny","Campbell Watson"],"date":"2021-07-14","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.06846","openalex":"W3178227234"},"links":{"paper":"https://arxiv.org/abs/2107.06846","pdf":"https://arxiv.org/pdf/2107.06846"},"orgs":["ibm-research"],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["transformer"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Temporal Fusion Transformer forecasts weekly extreme precipitation quantiles up to six months ahead, beating calibrated SEAS5 at six-month lead and modestly beating climatology.","significance":4,"cited_by":25,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-wcd-2-581-2021","title":"An unsupervised learning approach to identifying blocking events: the case of European summer","authors":["Carl Thomas","Apostolos Voulgarakis","Gerald Lim","Joanna D. Haigh","Peer Johannes Nowack"],"date":"2021-07-12","year":2021,"venue":"Weather and Climate Dynamics","venue_type":"journal","ids":{"doi":"10.5194/wcd-2-581-2021","openalex":"W3160024790"},"links":{"paper":"https://doi.org/10.5194/wcd-2-581-2021"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A self-organizing-map blocking index detects European blocking more accurately than existing indices, with higher precision and recall against an expert-labelled ground truth.","significance":4,"cited_by":23,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-21-0012.1","title":"Use of Deep Learning for Weather Radar Nowcasting","authors":["Joaquin Cuomo","V. Chandrasekar"],"date":"2021-07-12","year":2021,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-21-0012.1","openalex":"W3180010583"},"links":{"paper":"https://doi.org/10.1175/jtech-d-21-0012.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atot/38/9/JTECH-D-21-0012.1.pdf"},"orgs":["colorado-state-university"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Residual convolutional encoder-decoder models for radar echo nowcasting match or beat operational systems and transfer across regions without performance decay.","significance":4,"cited_by":28,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-021-0215-y","title":"A Deep Learning Method for Bias Correction of ECMWF 24–240 h Forecasts","authors":["Lei Han","Mingxuan Chen","Kangkai Chen","Haonan Chen","Yanbiao Zhang","Bing Lu","Linye Song","Rui Qin"],"date":"2021-07-10","year":2021,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-021-0215-y","openalex":"W3171394698"},"links":{"paper":"https://doi.org/10.1007/s00376-021-0215-y","pdf":"https://link.springer.com/content/pdf/10.1007/s00376-021-0215-y.pdf"},"orgs":["colorado-state-university","cma"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"CU-net, a CNN, corrects gridded ECMWF-IFS 24–240 h forecasts of four surface variables over North China, beating the ANO correction at all lead times.","significance":4,"cited_by":165,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.04631","title":"Ill-posed Surface Emissivity Retrieval from Multi-Geometry Hyperspectral Images using a Hybrid Deep Neural Network","authors":["Fangcao Xu","Jian Sun","Guido Cervone","Mark Salvador"],"date":"2021-07-09","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.04631"},"links":{"paper":"https://arxiv.org/abs/2107.04631","pdf":"https://arxiv.org/pdf/2107.04631"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","other"],"timescale":[],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Hybrid neural network for hyperspectral atmospheric correction that infers atmospheric state without auxiliary met data, achieving MAE under 0.02 for emissivity across 29 materials.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.04270","title":"Deep Learning Based Forecasting of Indian Summer Monsoon Rainfall","authors":["Bipin Kumar","Namit Abhishek","Rajib Chattopadhyay","Sandeep George","Bhupendra Bahadur Singh","Arya Samanta","B. S. V. Patnaik","Sukhpal Singh Gill","Ravi S. Nanjundiah","Manmeet Singh"],"date":"2021-07-09","year":2021,"venue":"Geocarto International, 2022","venue_type":"journal","ids":{"arxiv":"2107.04270","doi":"10.1080/10106049.2022.2136262","openalex":"W4306873746"},"links":{"paper":"https://arxiv.org/abs/2107.04270","pdf":"https://arxiv.org/pdf/2107.04270"},"orgs":[],"topic":"regional-km-scale","topics":["nowcasting"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"ConvLSTM precipitation forecasts over India at 25 km reach correlation 0.67 at lead day 1 and 0.42 at lead day 2.","significance":3,"cited_by":31,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21144673","title":"Application of the Deep Neural Network in Retrieving the Atmospheric Temperature and Humidity Profiles from the Microwave Humidity and Temperature Sounder Onboard the Feng-Yun-3 Satellite","authors":["Qiurui He","Zhenzhan Wang","Jiaoyang Li"],"date":"2021-07-08","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21144673","openalex":"W3182296058"},"links":{"paper":"https://doi.org/10.3390/s21144673","pdf":"https://www.mdpi.com/1424-8220/21/14/4673/pdf?version=1625729798"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Deep neural networks retrieve temperature and humidity profiles from FY-3 MWHTS microwave sounder and bias-correct its observations, outperforming shallow networks in accuracy and stability.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-pr9071187","title":"A Hybrid LSTM-Based Genetic Programming Approach for Short-Term Prediction of Global Solar Radiation Using Weather Data","authors":["Rami Al-Hajj","Ali Assi","Mohamad M. Fouad","Emad Mabrouk"],"date":"2021-07-08","year":2021,"venue":"Processes","venue_type":"journal","ids":{"doi":"10.3390/pr9071187","openalex":"W3181608074"},"links":{"paper":"https://doi.org/10.3390/pr9071187","pdf":"https://www.mdpi.com/2227-9717/9/7/1187/pdf?version=1626418570"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid LSTM and genetic programming model forecasts short-term global solar radiation from weather station data, with improved accuracy over stacking baselines.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.51201-jusst-21-07149","title":"A Cloud Native Machine Learning based Approach for Detection and Impact of Cyclone and Hurricanes on Coastal Areas of Pacific and Atlantic Ocean","authors":["Drumil Joshi","Fawzan Sayed","Harsh Jain","Jai Beri","Yukti Bandi","Sunil Karamchandani"],"date":"2021-07-07","year":2021,"venue":"Journal of University of Shanghai for Science and Technology","venue_type":"journal","ids":{"doi":"10.51201/jusst/21/07149","openalex":"W3183020475"},"links":{"paper":"https://doi.org/10.51201/jusst/21/07149","pdf":"https://jusst.org/wp-content/uploads/2021/07/A-Cloud-Native-Machine-Learning-based-Approach-for-Detection-and-Impact-of-Cyclone-and-Hurricanes-on-Coastal-Areas-of-Pacific-and-Atlantic-Ocean.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Cloud-deployed machine learning compares classifiers for predicting hurricane and cyclone occurrence over Pacific and Atlantic coasts, with map visualization; the methodological novelty is limited.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2021.126664","title":"Medium-range forecasting of daily reference evapotranspiration across China using numerical weather prediction outputs downscaled by extreme gradient boosting","authors":["Junliang Fan","Lifeng Wu","Jing Zheng","Fucang Zhang"],"date":"2021-07-07","year":2021,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2021.126664","openalex":"W3181049857"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2021.126664"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"XGBoost downscales NWP outputs to medium-range daily reference evapotranspiration across China, a weather-derived quantity for water and agriculture planning.","significance":3,"cited_by":70,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.05573","title":"Tropical cyclone intensity estimations over the Indian ocean using Machine Learning","authors":["Koushik Biswas","Sandeep Kumar","Ashish Kumar Pandey"],"date":"2021-07-07","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.05573","openalex":"W3181089446"},"links":{"paper":"https://arxiv.org/abs/2107.05573","pdf":"https://arxiv.org/pdf/2107.05573"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Classical ML models estimate North Indian Ocean cyclone grade (88% accuracy) and maximum sustained winds (RMSE 2.3) from 28 years of best-track data.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.03432","title":"IowaRain: A Statewide Rain Event Dataset Based on Weather Radars and Quantitative Precipitation Estimation","authors":["Muhammed Sit","Bong-Chul Seo","Ibrahim Demir"],"date":"2021-07-07","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.03432"},"links":{"paper":"https://arxiv.org/abs/2107.03432","pdf":"https://arxiv.org/pdf/2107.03432"},"orgs":[],"topic":"benchmarks-data-eval","topics":["observations-remote-sensing"],"type":"benchmark","method":[],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Releases a 2016-2019 statewide Iowa rainfall event dataset built from NEXRAD radar with quantitative precipitation estimation, intended for ML and physical modeling.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13142653","title":"Estimating the Key Parameter of a Tropical Cyclone Wind Field Model over the Northwest Pacific Ocean: A Comparison between Neural Networks and Statistical Models","authors":["Ziyao Sun","Biao Zhang","Jie Tang"],"date":"2021-07-06","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13142653","openalex":"W3178100259"},"links":{"paper":"https://doi.org/10.3390/rs13142653","pdf":"https://www.mdpi.com/2072-4292/13/14/2653/pdf?version=1625567252"},"orgs":["nuist","cma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Backpropagation neural network estimates the Holland B wind-field parameter for Northwest Pacific typhoons from pressure difference, improving super-typhoon wind speed estimates over statistical models.","significance":2,"cited_by":8,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41467-021-24262-x","title":"Anthropogenic influence on extreme precipitation over global land areas seen in multiple observational datasets","authors":["Gavin D. Madakumbura","Chad W. Thackeray","Jesse Norris","Naomi Goldenson","Alex D. Hall"],"date":"2021-07-06","year":2021,"venue":"Nature Communications","venue_type":"journal","ids":{"doi":"10.1038/s41467-021-24262-x","openalex":"W3127896862"},"links":{"paper":"https://doi.org/10.1038/s41467-021-24262-x","pdf":"https://www.nature.com/articles/s41467-021-24262-x.pdf"},"orgs":["ucla"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip","stations","other"],"status":"research","summary":"Machine learning that accounts for model uncertainty detects a physically interpretable anthropogenic signal in extreme precipitation across all global observational datasets.","significance":6,"cited_by":162,"score":64,"highlight":true,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.06182","title":"Predictive models for wind speed using artificial intelligence and copula","authors":["Md Amimul Ehsan"],"date":"2021-07-06","year":2021,"venue_type":"preprint","ids":{"arxiv":"2107.06182"},"links":{"paper":"https://arxiv.org/abs/2107.06182","pdf":"https://arxiv.org/pdf/2107.06182"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Twelve AI models predict wind speed from meteorological data, with LSTM best at 97.8% accuracy, and copulas model joint wind speed dependence across sites.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.02517","title":"An Evaluation of Machine Learning and Deep Learning Models for Drought Prediction using Weather Data","authors":["Weiwei Jiang","Jiayun Luo"],"date":"2021-07-06","year":2021,"venue":"Journal of Intelligent & Fuzzy Systems, 2022","venue_type":"journal","ids":{"arxiv":"2107.02517","doi":"10.3233/jifs-212748"},"links":{"paper":"https://arxiv.org/abs/2107.02517","pdf":"https://arxiv.org/pdf/2107.02517","code":"https://github.com/jwwthu/DL4Climate"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Benchmarks 16 classical and 16 deep learning models predicting drought levels from 90 days of 18 meteorological indicators, with no single model best across metrics.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21134606","title":"A Rail-Temperature-Prediction Model Based on Machine Learning: Warning of Train-Speed Restrictions Using Weather Forecasting","authors":["Sunguk Hong","Cheoljeong Park","Seong Jin Cho"],"date":"2021-07-05","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21134606","openalex":"W3181580017"},"links":{"paper":"https://doi.org/10.3390/s21134606","pdf":"https://www.mdpi.com/1424-8220/21/13/4606/pdf?version=1625636637"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Machine learning predicts railway rail temperature from weather forecast and solar features, driving a train-speed-limit alarm map for track safety.","significance":2,"cited_by":42,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-forecast3030031","title":"The Effect of Lead-Time Weather Forecast Uncertainty on Outage Prediction Modeling","authors":["Feifei Yang","Diego Cerrai","Emmanouil N. Anagnostou"],"date":"2021-07-05","year":2021,"venue":"Forecasting","venue_type":"journal","ids":{"doi":"10.3390/forecast3030031","openalex":"W3182168536"},"links":{"paper":"https://doi.org/10.3390/forecast3030031","pdf":"https://www.mdpi.com/2571-9394/3/3/31/pdf?version=1625553061"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Propagates 1–5 day weather forecast uncertainty into a machine-learning storm outage model for the northeastern US, with precipitation and gusts dominating error.","significance":3,"cited_by":28,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11136208","title":"DR-Transformer: A Multi-Features Fusion Framework for Tropical Cyclones Intensity Estimation","authors":["Yicheng Luo","Yajing Xu","Si Li","Qifeng Qian","Bo Xiao"],"date":"2021-07-05","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11136208","openalex":"W3194052222"},"links":{"paper":"https://doi.org/10.3390/app11136208","pdf":"https://www.mdpi.com/2076-3417/11/13/6208/pdf?version=1625467215"},"orgs":["cma"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["transformer","cnn"],"timescale":["nowcast"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"DR-Transformer estimates tropical cyclone intensity from satellite images with rotation and distance-consistency features, reaching 7.76-knot RMSE on the TCIR dataset.","significance":3,"cited_by":6,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30534-ijeter-2021-24972021","title":"A Survey of Weather Forecasting based on Machine Learning and Deep Learning Techniques","authors":[],"date":"2021-07-05","year":2021,"venue":"International Journal of Emerging Trends in Engineering Research","venue_type":"journal","ids":{"doi":"10.30534/ijeter/2021/24972021","openalex":"W4246027504"},"links":{"paper":"https://doi.org/10.30534/ijeter/2021/24972021","pdf":"https://doi.org/10.30534/ijeter/2021/24972021"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Survey of machine learning and deep learning methods for weather forecasting, covering applications, types and problems; no new model.","significance":1,"cited_by":22,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2021.126638","title":"Integrated meteorological drought monitoring framework using multi-sensor and multi-temporal earth observation datasets and machine learning algorithms: A case study of central India","authors":["Neeti Neeti","C.M. Arun Murali","Vemuri Muthayya Chowdary","N.H. Rao","Mohit Kesarwani"],"date":"2021-07-04","year":2021,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2021.126638","openalex":"W3178761164"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2021.126638"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Integrates multi-sensor Earth observation data and machine learning to monitor meteorological drought in central India; the abstract is missing.","significance":2,"cited_by":58,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3185374492","title":"Rainfall Rate Prediction Based on Artificial Neural Networks","authors":["A GowriManohara","yuvalakshmi","N Kavyashree"],"date":"2021-07-01","year":2021,"venue":"Journal of Emerging Technologies and Innovative Research","venue_type":"journal","ids":{"openalex":"W3185374492"},"links":{"paper":"https://www.jetir.org/papers/JETIR2107445.pdf"},"orgs":[],"topic":"local-forecasting","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Artificial neural network predicts rainfall rate 30 seconds ahead at Durban from three prior measurements, for link-quality planning; the abstract is garbled and the study is small.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3183264035","title":"Real time Weather Forecast model for Disaster Management using Machine Learning Algorithms","authors":["Hafeeza Samreen","Tugu Bhanu Prakash","S. Vasavi","Duddugunta Bhargav Reddy","Gulla Venkata Nikhil","C. Harikiran"],"date":"2021-07-01","year":2021,"venue":"Turkish Online Journal of Qualitative Inquiry","venue_type":"journal","ids":{"openalex":"W3183264035"},"links":{"paper":"https://tojqi.net/index.php/journal/article/view/1817"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Smartphone app predicts five-day rainfall with ANN and Gaussian process regression using disaster-authority data; limited methodological novelty.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3179869585","title":"Rainfall Prediction Using LASSO Regression","authors":["P Jinashree","D R Pooja","M. Meghana","G. P. Aishwarya","B K Siddharth"],"date":"2021-07-01","year":2021,"venue":"Journal of Emerging Technologies and Innovative Research","venue_type":"journal","ids":{"openalex":"W3179869585"},"links":{"paper":"https://www.jetir.org/papers/JETIR2107156.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares LASSO, backpropagation and linear regression for Indian rainfall prediction using past rainfall records, with metrics but no novel method.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.4134","title":"Classifying precipitation from GEO satellite observations: Prognostic model","authors":["Shruti Ashok Upadhyaya","Pierre‐Emmanuel Kirstetter","Robert J. Kuligowski","Jonathan J. Gourley","Heather M. Grams"],"date":"2021-07-01","year":2021,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.4134","openalex":"W4213315021"},"links":{"paper":"https://doi.org/10.1002/qj.4134"},"orgs":["noaa","university-of-oklahoma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","radar","nwp-analysis"],"status":"research","summary":"A machine-learning classifier on GOES-16 ABI channels with NWP inputs identifies precipitation occurrence with 97% accuracy and convective types at 76%.","significance":3,"cited_by":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.71465-ajainn277","title":"Artificial Intelligence for Climate Resilience: Neural Networks and Big Data","authors":["Dr. David Green"],"date":"2021-06-30","year":2021,"venue":"American Journal of Artificial Intelligence and Neural Networks","venue_type":"journal","ids":{"doi":"10.71465/ajainn277","openalex":"W7143870763"},"links":{"paper":"https://doi.org/10.71465/ajainn277","pdf":"https://australiansciencejournals.com/ajainn/article/download/277/2299"},"orgs":["uc-berkeley"],"topic":"applications-impacts","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Generic overview of neural networks and big data for climate resilience, covering modeling, disaster response and resource management, with no new technical results.","significance":1,"cited_by":0,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14383-cri.2021.16.2.147","title":"Assessment of the Predictability of Heatwave Index Using ASOS and ERA5 Data with Machine Learning: Case Study of South Korea, 1979-2020","authors":["부경대학교 지구환경시스템과학부 공간정보공학전공","Geunah Kim","Jonggu Kang","Yemin Jeong","Seo-Yeon Kim","Subin Cho","Kyung‐Ja Ha","Yangwon Lee"],"date":"2021-06-30","year":2021,"venue":"Journal of Climate Research","venue_type":"journal","ids":{"doi":"10.14383/cri.2021.16.2.147","openalex":"W3191195662"},"links":{"paper":"https://doi.org/10.14383/cri.2021.16.2.147"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"A random forest trained on ERA5 variables reproduces a station-based heatwave index for South Korea (1979-2020) with MAE 0.365 and CC 0.873, and yields gridded maps.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-14-4019-2021","title":"MSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data","authors":["Dawei Li","Yudi Liu","Chaohui Chen"],"date":"2021-06-29","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-14-4019-2021","openalex":"W3119319039"},"links":{"paper":"https://doi.org/10.5194/gmd-14-4019-2021","pdf":"https://gmd.copernicus.org/articles/14/4019/2021/gmd-14-4019-2021.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite","stations"],"status":"research","summary":"MSDM combines optical flow, random forest and CNN to nowcast East China precipitation at 30 to 120 minutes from radar and satellite data.","significance":4,"cited_by":40,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12070834","title":"K-Means and C4.5 Decision Tree Based Prediction of Long-Term Precipitation Variability in the Poyang Lake Basin, China","authors":["Dan Lou","Mengxi Yang","Dawei Shi","Guojie Wang","Waheed Ullah","Yuanfang Chai","Yutian Chen"],"date":"2021-06-28","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12070834","openalex":"W3177257602"},"links":{"paper":"https://doi.org/10.3390/atmos12070834","pdf":"https://www.mdpi.com/2073-4433/12/7/834/pdf?version=1625019977"},"orgs":["nuist"],"topic":"climate-analysis-attribution","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"K-means clustering and C4.5 decision trees link Poyang Lake basin precipitation clusters to preceding spring large-scale circulation indices.","significance":2,"cited_by":16,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.14742","title":"TENT: Tensorized Encoder Transformer for Temperature Forecasting","authors":["Onur Bilgin","Paweł Mąka","Thomas Vergutz","Siamak Mehrkanoon"],"date":"2021-06-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.14742","openalex":"W3177344253"},"links":{"paper":"https://arxiv.org/abs/2106.14742","pdf":"https://arxiv.org/pdf/2106.14742"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["transformer"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Tensorized transformer forecasts temperature from weather station records in USA, Canada and Europe, outperforming CNN, LSTM and ConvLSTM baselines.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7271","title":"Evaluation of statistical downscaling methods for climate change projections over Spain: Present conditions with perfect predictors","authors":["Alfonso Hernanz","Juan Andrés García Valero","Marta Domínguez","Petra Ramos Calzado","María Asunción Pastor Saavedra","Ernesto Rodríguez Camino"],"date":"2021-06-27","year":2021,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7271","openalex":"W3174076701"},"links":{"paper":"https://doi.org/10.1002/joc.7271","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.7271"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Compares analog, regression, ANN, SVM and kernel ridge downscaling over Spain with perfect predictors, finding nonlinear methods add value for temperature.","significance":3,"cited_by":53,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.14110","title":"Stochastic Parameterization using Compressed Sensing: Application to the Lorenz-96 Atmospheric Model","authors":["Amartya Mukherjee","Yusuf Aydogdu","Thambirajah Ravichandran","Navaratnam Sri Namachchivaya"],"date":"2021-06-26","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.14110"},"links":{"paper":"https://arxiv.org/abs/2106.14110","pdf":"https://arxiv.org/pdf/2106.14110"},"orgs":[],"topic":"hybrid-parameterization","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Compressed sensing learns a stochastic parameterization of fine-scale processes in the Lorenz-96 atmospheric model, combined with ensemble Kalman filtering and compared with polynomial regression.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-14-3769-2021","title":"Development of a large-eddy simulation subgrid model based on artificial neural networks: a case study of turbulent channel flow","authors":["Robin Stoffer","Caspar M. van Leeuwen","Damian Podareanu","Valeriu Codreanu","Menno Veerman","Martin Janssens","Oscar Hartogensis","Chiel C. van Heerwaarden"],"date":"2021-06-24","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-14-3769-2021","openalex":"W3099395817"},"links":{"paper":"https://doi.org/10.5194/gmd-14-3769-2021","pdf":"https://gmd.copernicus.org/articles/14/3769/2021/gmd-14-3769-2021.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Develops an ANN subgrid-scale model for LES of atmospheric-type wall turbulence, tested on channel flow, but finds instability when coupled into simulations.","significance":3,"cited_by":25,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13132468","title":"Machine Learning for Climate Precipitation Prediction Modeling over South America","authors":["Juliana Aparecida Anochi","Vinícius Albuquerque de Almeida","Haroldo Fraga de Campos Velho"],"date":"2021-06-24","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13132468","openalex":"W3173345453"},"links":{"paper":"https://doi.org/10.3390/rs13132468","pdf":"https://www.mdpi.com/2072-4292/13/13/2468/pdf?version=1624534657"},"orgs":[],"topic":"regional-km-scale","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"pre-operational","summary":"Machine learning precipitation forecasts over South America reduce errors to under 2 mm versus INPE's operational model, outperforming it in some regions.","significance":3,"cited_by":58,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12070815","title":"Relationship between Early-Stage Features and Lifetime Maximum Intensity of Tropical Cyclones over the Western North Pacific","authors":["Ren Lu","Xiaodong Tang"],"date":"2021-06-24","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12070815","openalex":"W3177144518"},"links":{"paper":"https://doi.org/10.3390/atmos12070815","pdf":"https://www.mdpi.com/2073-4433/12/7/815/pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"AdaBoost models using early-stage vortex and environment features classify western North Pacific storms as weak or strong at genesis (about 75% accuracy) and estimate lifetime maximum intensity (R2 0.30).","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33075-2220-5861-2021-2-16-28","title":"Neural network method for climate forecasting water content of the Chernorechensk reservoir","authors":["А.S. Lubkov","E. N. Voskresenskaya"],"date":"2021-06-24","year":2021,"venue":"Monitoring systems of environment","venue_type":"journal","ids":{"doi":"10.33075/2220-5861-2021-2-16-28","openalex":"W3188249585"},"links":{"paper":"https://doi.org/10.33075/2220-5861-2021-2-16-28","pdf":"https://msoe.ru/wp-content/uploads/2021/07/44-02.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["era5","other"],"status":"research","summary":"Neural network uses SST and SLP indices to forecast monthly precipitation for the Ai-Petri region up to 6 months ahead, with about 23–28% mean absolute deviation.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12070810","title":"Spatiotemporal Model Based on Deep Learning for ENSO Forecasts","authors":["Huantong Geng","Tianlei Wang"],"date":"2021-06-23","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12070810","openalex":"W3177225616"},"links":{"paper":"https://doi.org/10.3390/atmos12070810","pdf":"https://www.mdpi.com/2073-4433/12/7/810/pdf?version=1624520684"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["seasonal","s2s"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"DC-LSTM, a dense-convolution LSTM, forecasts ENSO Nino3.4 up to 20 months ahead with higher skill than a dynamical model over 1994-2010.","significance":4,"cited_by":30,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12060793","title":"Automatic Regional Interpretation and Forecasting System Supported by Machine Learning","authors":["Chao Yan","Jing Feng","Kaiwen Xia","Chaofan Duan"],"date":"2021-06-21","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12060793","openalex":"W3175591587"},"links":{"paper":"https://doi.org/10.3390/atmos12060793","pdf":"https://www.mdpi.com/2073-4433/12/6/793/pdf?version=1624259281"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"ML-enhanced Model Output Statistics post-processes NWP output to predict 24-hour temperature and wind speed at four Chinese cities, beating neural network and SVM baselines.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15233-gfz.2021.38.4","title":"Forecasting the hydroelectric power generation of GCMs using machine learning techniques and deep learning (Almus Dam, Turkey)","authors":["Hesham Alrayess","Aslı ÜLKE KESKİN"],"date":"2021-06-21","year":2021,"venue":"Geofizika","venue_type":"journal","ids":{"doi":"10.15233/gfz.2021.38.4","openalex":"W3173181861"},"links":{"paper":"https://doi.org/10.15233/gfz.2021.38.4","pdf":"https://hrcak.srce.hr/ojs/index.php/geofizika/article/download/16932/volume38_1"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Compares decision trees, deep learning, GLM, gradient boosting and random forests to forecast Almus Dam hydropower from GCM projections; gradient boosting best with r=0.717.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-021-92286-w","title":"Domain knowledge integration into deep learning for typhoon intensity classification","authors":["Maiki Higa","Shinya Tanahara","Yoshitaka Adachi","Natsumi Ishiki","Shin Nakama","Hiroyuki Yamada","Kosuke Ito","Asanobu Kitamoto","Ryota Miyata"],"date":"2021-06-21","year":2021,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-021-92286-w","openalex":"W3175244707"},"links":{"paper":"https://doi.org/10.1038/s41598-021-92286-w","pdf":"https://www.nature.com/articles/s41598-021-92286-w.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"VGG-16 with fisheye preprocessing classifies typhoon intensity from single satellite images more accurately than prior work, with Grad-CAM showing physically relevant eye features.","significance":3,"cited_by":45,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.seta.2021.101354","title":"Solar power generation prediction based on deep Learning","authors":["Rui Chang","Lei Bai","Ching‐Hsien Hsu"],"date":"2021-06-21","year":2021,"venue":"Sustainable Energy Technologies and Assessments","venue_type":"journal","ids":{"doi":"10.1016/j.seta.2021.101354","openalex":"W3174537966"},"links":{"paper":"https://doi.org/10.1016/j.seta.2021.101354"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Deep learning forecasts of solar power generation; the abstract is missing, so the weather-input role and horizon are unverified.","significance":1,"cited_by":61,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.cageo.2021.104868","title":"HPC cluster-based user-defined data integration platform for deep learning in geoscience applications","authors":["Guohua Li","Yeji Choi"],"date":"2021-06-21","year":2021,"venue":"Computers & Geosciences","venue_type":"journal","ids":{"doi":"10.1016/j.cageo.2021.104868","openalex":"W3174294247"},"links":{"paper":"https://doi.org/10.1016/j.cageo.2021.104868","pdf":"https://www.sciencedirect.com/science/article/pii/S009830042100162X/pdf"},"orgs":[],"topic":"infra-software","topics":["nowcasting"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"GeoDIP, an HPC data-integration platform, merges satellite and reanalysis inputs and raises 2-hour precipitation prediction F1 by 9% with a 97% speedup.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.13924","title":"Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural Networks for Earth System Models","authors":["Tobias Sebastian Finn"],"date":"2021-06-21","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.13924","openalex":"W3175485343"},"links":{"paper":"https://arxiv.org/abs/2106.13924","pdf":"https://arxiv.org/pdf/2106.13924","code":"https://github.com/tobifinn/ensemble_transformer"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["transformer"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis","era5"],"status":"research","summary":"A self-attentive ensemble transformer post-processes ECMWF ensemble members member-by-member, calibrating spread and producing spatially coherent 2m temperature ensembles.","significance":4,"cited_by":8,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s00382-021-05847-0","title":"On the suitability of deep convolutional neural networks for continental-wide downscaling of climate change projections","authors":["Jorge Baño‐Medina","Rodrigo Manzanas","José Manuel Gutiérrez"],"date":"2021-06-20","year":2021,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-021-05847-0","openalex":"W3176066814"},"links":{"paper":"https://doi.org/10.1007/s00382-021-05847-0","pdf":"https://link.springer.com/content/pdf/10.1007/s00382-021-05847-0.pdf"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"evaluation","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Assesses whether deep CNN downscaling of GCM projections over Europe yields plausible end-of-century changes, finding smaller departures from raw GCM signals than GLMs.","significance":3,"cited_by":79,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.12045","title":"Deep learning for improved global precipitation in numerical weather prediction systems","authors":["Manmeet Singh","Bipin Kumar","Suryachandra Rao","Sukhpal Singh Gill","Rajib Chattopadhyay","Ravi S Nanjundiah","Dev Niyogi"],"date":"2021-06-20","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.12045","openalex":"W3174473821"},"links":{"paper":"https://arxiv.org/abs/2106.12045","pdf":"https://arxiv.org/pdf/2106.12045"},"orgs":[],"topic":"hybrid-parameterization","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"pre-operational","summary":"A residual U-Net trained on reanalysis, with cubed-sphere inputs, learns global precipitation that doubles grid-point skill versus the operational IMD NWP model, as a proof of concept.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21124200","title":"Modular Neural Networks with Fully Convolutional Networks for Typhoon-Induced Short-Term Rainfall Predictions","authors":["Chih‐Chiang Wei","Tzu-Heng Huang"],"date":"2021-06-18","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21124200","openalex":"W3175538958"},"links":{"paper":"https://doi.org/10.3390/s21124200","pdf":"https://www.mdpi.com/1424-8220/21/12/4200/pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Modular fully convolutional networks use radar echoes to forecast hourly typhoon rainfall 1 to 6 h ahead in southern Taiwan, outperforming an MLP baseline.","significance":3,"cited_by":16,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-20-0208.1","title":"Towards a climatology of fog frequency in the Atacama Desert via multi-spectral satellite data and machine learning techniques","authors":["Christoph Böhm","Jan H. Schween","Mark Reyers","Benedikt Maier","Ulrich Löhnert","Susanne Crewell"],"date":"2021-06-18","year":2021,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-20-0208.1","openalex":"W3176287638"},"links":{"paper":"https://doi.org/10.1175/jamc-d-20-0208.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/apme/60/8/JAMC-D-20-0208.1.pdf"},"orgs":["mit"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"A neural network on MODIS brightness temperatures detects Atacama Desert fog better than a cloud-height method (Heidke skill 0.56 vs 0.49), enabling a fog frequency climatology.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-459258-v1","title":"On the Cluster Validity Test (s) in Unsupervised Machine Learning TDA Approach for Atmospheric River Patterns on Flood Detection in Nigeria","authors":["Felix Obi Ohanuba","Mohd Tahir Ismail","Majid Khan Majahar Ali","Ekele Alih","P. N. Ezra"],"date":"2021-06-17","year":2021,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-459258/v1","openalex":"W3167341067"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-459258/v1","pdf":"https://www.researchsquare.com/article/rs-459258/latest.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Unsupervised topological data analysis is used to identify atmospheric river patterns linked to flooding in Nigeria; no abstract is available.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1142-s0219649221500295","title":"An Improved Multivariate Weather Prediction Model Using Deep Neural Networks and Particle Swarm Optimisation","authors":["K U Jaseena","Binsu C. Kovoor"],"date":"2021-06-17","year":2021,"venue":"Journal of Information & Knowledge Management","venue_type":"journal","ids":{"doi":"10.1142/s0219649221500295","openalex":"W3175339056"},"links":{"paper":"https://doi.org/10.1142/s0219649221500295"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Deep neural network with particle swarm feature selection predicts daily minimum and maximum temperature from local weather variables.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.09757","title":"CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1","authors":["Imme Ebert-Uphoff","Ryan Lagerquist","Kyle Hilburn","Yoonjin Lee","Katherine Haynes","Jason Stock","Christina Kumler","Jebb Q. Stewart"],"date":"2021-06-17","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.09757"},"links":{"paper":"https://arxiv.org/abs/2106.09757","pdf":"https://arxiv.org/pdf/2106.09757"},"orgs":[],"topic":"benchmarks-data-eval","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"A practical guide to writing custom loss functions for environmental and meteorological neural networks, including spatial verification scores like the fractions skill score and physical constraints.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.09512","title":"Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparison","authors":["Benedikt Schulz","Sebastian Lerch"],"date":"2021-06-17","year":2021,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"arxiv":"2106.09512","doi":"10.1175/mwr-d-21-0150.1","openalex":"W3172290062"},"links":{"paper":"https://arxiv.org/abs/2106.09512","pdf":"https://arxiv.org/pdf/2106.09512"},"orgs":["kit"],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Systematic comparison of eight statistical and ML wind gust ensemble postprocessing methods on German convection-permitting ensembles; locally adaptive neural networks perform best.","significance":4,"cited_by":113,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1109-tcyb.2021.3072483","title":"SSAS: Spatiotemporal Scale Adaptive Selection for Improving Bias Correction on Precipitation","authors":["Yiqun Liu","Junping Zhang","Lei Chen","Hai Chu","James Z. Wang","Leiming Ma"],"date":"2021-06-16","year":2021,"venue":"IEEE Transactions on Cybernetics","venue_type":"journal","ids":{"doi":"10.1109/tcyb.2021.3072483","openalex":"W3172563922"},"links":{"paper":"https://doi.org/10.1109/tcyb.2021.3072483","pdf":"https://scholarsphere.psu.edu/resources/3d4ffe51-0735-4f3a-8168-928d8e8a8924/downloads/19879"},"orgs":["fudan-university"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["cnn","transformer"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"An end-to-end spatiotemporal scale-selection model improves ECMWF precipitation bias correction, especially for heavy rain, beating 11 published methods on two benchmarks.","significance":3,"cited_by":9,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.26905-jasiek.v3i1.6204","title":"Prediksi Curah Hujan Wilayah Provinsi Yogyakarta dengan Algoritma Neural Network","authors":["Rubangi Rubangi","Arief Hermawan","Donny Avianto"],"date":"2021-06-14","year":2021,"venue":"JASIEK (Jurnal Aplikasi Sains Informasi Elektronika dan Komputer)","venue_type":"journal","ids":{"doi":"10.26905/jasiek.v3i1.6204","openalex":"W4312959149"},"links":{"paper":"https://doi.org/10.26905/jasiek.v3i1.6204","pdf":"https://jurnal.unmer.ac.id/index.php/jasiek/article/download/6204/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A basic neural network predicts daily rainfall for Yogyakarta Province from 2016–2021 BMKG station data; the study is small and regional.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021ms002464","title":"Detecting Climate Signals Using Explainable AI With Single‐Forcing Large Ensembles","authors":["Zachary M. Labe","Elizabeth A. Barnes"],"date":"2021-06-14","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2021ms002464","openalex":"W3118474455"},"links":{"paper":"https://doi.org/10.1029/2021ms002464"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"evaluation","method":["cnn","other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Layer-wise relevance propagation attributes regional temperature signals to aerosol versus greenhouse forcing in single-forcing large ensembles.","significance":4,"cited_by":78,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2106.06885","title":"Online Learning with Optimism and Delay","authors":["Genevieve Flaspohler","Francesco Orabona","Judah Cohen","Soukayna Mouatadid","Miruna Oprescu","Paulo Orenstein","Lester Mackey"],"date":"2021-06-13","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.06885"},"links":{"paper":"https://arxiv.org/abs/2106.06885","pdf":"https://arxiv.org/pdf/2106.06885"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["other"],"status":"research","summary":"Parameter-free optimistic online learning with delay, motivated by climate forecasting, achieving low regret on four subseasonal forecasting tasks.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13122310","title":"Multi-Task Collaboration Deep Learning Framework for Infrared Precipitation Estimation","authors":["Xuying Yang","Peng Sun","Feng Zhang","Zhenhong Du","Renyi Liu"],"date":"2021-06-12","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13122310","openalex":"W3171688233"},"links":{"paper":"https://doi.org/10.3390/rs13122310","pdf":"https://www.mdpi.com/2072-4292/13/12/2310/pdf?version=1623732650"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A multi-task CNN framework with consistency constraints and cross-branch attention improves Himawari-8 infrared precipitation estimation by 3–5% F1 across intensities.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.envres.2021.111477","title":"A 1-km hourly air-temperature model for 13 northeastern U.S. states using remotely sensed and ground-based measurements","authors":["Daniel Carrión","Kodi B. Arfer","Johnathan Rush","Michael Dorman","Sebastian Thonet Rowland","Marianthi‐Anna Kioumourtzoglou","Itai Kloog","Allan C. Just"],"date":"2021-06-12","year":2021,"venue":"Environmental Research","venue_type":"journal","ids":{"doi":"10.1016/j.envres.2021.111477","openalex":"W3171784908"},"links":{"paper":"https://doi.org/10.1016/j.envres.2021.111477"},"orgs":["columbia-leap"],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"XGBoost model estimates hourly 1-km air temperature across 13 northeastern US states, with RMSE about 1.6 K versus 2.5 K for NLDAS-2.","significance":3,"cited_by":55,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.06868","title":"Short-term forecasting of global solar irradiance with incomplete data","authors":["Laura S. Hoyos-Gómez","Jose F. Ruiz-Muñoz","Belizza J. Ruiz-Mendoza"],"date":"2021-06-12","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.06868"},"links":{"paper":"https://arxiv.org/abs/2106.06868","pdf":"https://arxiv.org/pdf/2106.06868"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares ARIMA, feedforward nets and LSTM for one-day-ahead solar irradiance forecasts from 12 weather stations, with imputation for missing data; LSTM is best under clouds.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-mis.2021.3088543","title":"Robust Precipitation Bias Correction Through an Ordinal Distribution Autoencoder","authors":["Youcheng Luo","Xiaoyang Xu","Yiqun Liu","Hanqing Chao","Hai Chu","Lei Chen","Junping Zhang","Leiming Ma","James Z. Wang"],"date":"2021-06-11","year":2021,"venue":"IEEE Intelligent Systems","venue_type":"journal","ids":{"doi":"10.1109/mis.2021.3088543","openalex":"W3171163466"},"links":{"paper":"https://doi.org/10.1109/mis.2021.3088543","pdf":"https://scholarsphere.psu.edu/resources/57569697-999e-4ffe-9469-6b5d11ef6b4c/downloads/19884"},"orgs":["fudan-university"],"topic":"post-processing","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"An ordinal distribution autoencoder corrects ECMWF and SMS-WARMS precipitation forecast bias and outperforms classical ML and deep baselines.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2106.12041","title":"Analysis of the Evolution of Parametric Drivers of High-End Sea-Level Hazards","authors":["Alana Hough","Tony E. Wong"],"date":"2021-06-11","year":2021,"venue_type":"preprint","ids":{"arxiv":"2106.12041","doi":"10.5194/ascmo-8-117-2022"},"links":{"paper":"https://arxiv.org/abs/2106.12041","pdf":"https://arxiv.org/pdf/2106.12041"},"orgs":[],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Random forests show that climate sensitivity and aerosol forcing scaling dominate parametric uncertainty in 2020-2150 sea-level risk, with thermal expansion driving near-term hazards.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-08839514.2021.1935590","title":"Near Real-time Map Building with Multi-class Image Set Labeling and Classification of Road Conditions Using Convolutional Neural Networks","authors":["Sheela Ramanna","Cenker Sengoz","Scott D. Kehler","Dat Pham"],"date":"2021-06-10","year":2021,"venue":"Applied Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1080/08839514.2021.1935590","openalex":"W3172032788"},"links":{"paper":"https://doi.org/10.1080/08839514.2021.1935590","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/08839514.2021.1935590?needAccess=true"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"EfficientNet classifies road surface conditions from street and highway camera images into five classes at 90.6% validation accuracy, complementing station-based road weather data.","significance":2,"cited_by":24,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-ese3.928","title":"Multivariable neural network to postprocess short‐term, hub‐height wind forecasts","authors":["Andrés A. Salazar","Yuzhang Che","Jiafeng Zheng","Feng Xiao"],"date":"2021-06-10","year":2021,"venue":"Energy Science & Engineering","venue_type":"journal","ids":{"doi":"10.1002/ese3.928","openalex":"W3169581811"},"links":{"paper":"https://doi.org/10.1002/ese3.928"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml","other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A multivariable denoising-autoencoder network corrects hub-height wind speed NWP forecasts at 15 Japanese wind farm sites, cutting RMSE using extra atmospheric variables.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-19-0207.1","title":"Deep Learning for Typhoon Intensity Classification Using Satellite Cloud Images","authors":["Zongsheng Zheng","Chenyu Hu","Zhaorong Liu","Jianbo Hao","Qian Hou","Xiaoyi Jiang"],"date":"2021-06-09","year":2021,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-19-0207.1","openalex":"W3172000859"},"links":{"paper":"https://doi.org/10.1175/jtech-d-19-0207.1"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Typhoon-CNNs classifies typhoon intensity from more than 10,000 satellite cloud images with 88.74% accuracy, beating ResNet50, InceptionV3 and VGG16.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.mlwa.2021.100053","title":"Convection indicator for pre-tactical air traffic flow management using neural networks","authors":["Aniel Jardines","Manuel Soler","Alejandro Cervantes","Javier García‐Heras","Juan Pablo Simarro"],"date":"2021-06-09","year":2021,"venue":"Machine Learning with Applications","venue_type":"journal","ids":{"doi":"10.1016/j.mlwa.2021.100053","openalex":"W3171326223"},"links":{"paper":"https://doi.org/10.1016/j.mlwa.2021.100053","pdf":"https://www.sciencedirect.com/science/article/pii/S2666827021000256/pdf"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"pre-operational","summary":"Neural network uses satellite storm observations and ensemble NWP to predict convection 36 h ahead, yielding a probabilistic indicator that beats existing air traffic convection indicators.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-21-0113.1","title":"Seasonal Forecast of Non-monsoonal Winter Precipitation over the Eurasian Continent using Machine Learning Models","authors":["Qifeng Qian","Xiaojing Jia","Hai Lin","Ruizhi Zhang"],"date":"2021-06-08","year":2021,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-21-0113.1","openalex":"W3168227557"},"links":{"paper":"https://doi.org/10.1175/jcli-d-21-0113.1"},"orgs":["eccc"],"topic":"s2s-seasonal","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","era5"],"status":"research","summary":"Gradient-boosting and related ML models forecast Eurasian winter precipitation seasonally, outperforming linear regression and matching or beating dynamical models; Arctic autumn sea ice is a key predictor.","significance":3,"cited_by":48,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021gl093842","title":"Assessing Decadal Predictability in an Earth‐System Model Using Explainable Neural Networks","authors":["Benjamin A. Toms","Elizabeth A. Barnes","James Wilson Hurrell"],"date":"2021-06-08","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2021gl093842","openalex":"W3167768106"},"links":{"paper":"https://doi.org/10.1029/2021gl093842","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2021GL093842"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["decadal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Explainable neural networks with layerwise relevance propagation identify North Atlantic and North Pacific SST regions that drive decadal predictability of continental temperature in an Earth-system model.","significance":4,"cited_by":39,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13112229","title":"Deep Learning-Based Radar Composite Reflectivity Factor Estimations from Fengyun-4A Geostationary Satellite Observations","authors":["Fenglin Sun","Bo Li","Min Min","Danyu Qin"],"date":"2021-06-07","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13112229","openalex":"W3170277727"},"links":{"paper":"https://doi.org/10.3390/rs13112229","pdf":"https://www.mdpi.com/2072-4292/13/11/2229/pdf?version=1623216324"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"A deep learning regression retrieves radar composite reflectivity maps from Fengyun-4A geostationary satellite data, with R² of 0.88-0.96 and MAE of 0.3-0.6 dBZ.","significance":3,"cited_by":28,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.9734-ajrcos-2021-v9i330222","title":"Predicting Weather Forecasting State Based on Data Mining Classification Algorithms","authors":["Fairoz Q. Kareem","Adnan Mohsin Abdulazeez","Dathar Abas Hasan"],"date":"2021-06-05","year":2021,"venue":"Asian Journal of Research in Computer Science","venue_type":"journal","ids":{"doi":"10.9734/ajrcos/2021/v9i330222","openalex":"W3169925376"},"links":{"paper":"https://doi.org/10.9734/ajrcos/2021/v9i330222"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares neural networks, Naive Bayes, random forest and KNN for classifying weather states from a Kaggle synoptic dataset; random forest reaches 89%.","significance":1,"cited_by":15,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13112211","title":"A Random Forest-Based Data Fusion Method for Obtaining All-Weather Land Surface Temperature with High Spatial Resolution","authors":["Shuo Xu","Jie Cheng","Quan Zhang"],"date":"2021-06-05","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13112211","openalex":"W3168301201"},"links":{"paper":"https://doi.org/10.3390/rs13112211"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random forest fuses thermal and passive microwave data to produce 0.01° all-weather land surface temperature over China, RMSE 2-5 K against in situ data.","significance":2,"cited_by":44,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-021-05833-6","title":"Modeling high-resolution precipitation by coupling a regional climate model with a machine learning model: an application to Sai Gon–Dong Nai Rivers Basin in Vietnam","authors":["Toan Trinh","N. Do","Van Thinh Nguyen","Kara J. Carr"],"date":"2021-06-05","year":2021,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-021-05833-6","openalex":"W3172880256"},"links":{"paper":"https://doi.org/10.1007/s00382-021-05833-6"},"orgs":[],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Couples a regional climate model with a machine learning model to produce high-resolution precipitation for the Sai Gon–Dong Nai basin in Vietnam; abstract unavailable, classified from title.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3081920","title":"A Machine Learning Algorithm for Retrieving Cloud Top Height With Passive Microwave Radiometry","authors":["Jean‐François Rysman","Chantal Claud","Stavros Dafis"],"date":"2021-06-03","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3081920","openalex":"W3166882621"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3081920"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A neural network and gradient boosting combination retrieves cloud top height from passive microwave radiometers, with MAE 2.1 km and correlation 0.8 against radar truth.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en14113245","title":"Regional Solar Irradiance Forecast for Kanto Region by Support Vector Regression Using Forecast of Meso-Ensemble Prediction System","authors":["Takahiro Takamatsu","Hideaki Ohtake","Takashi Oozeki","Tosiyuki Nakaegawa","Yuki Honda","Masahiro Kazumori"],"date":"2021-06-02","year":2021,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en14113245","openalex":"W3171477952"},"links":{"paper":"https://doi.org/10.3390/en14113245","pdf":"https://www.mdpi.com/1996-1073/14/11/3245/pdf?version=1622627556"},"orgs":["jma"],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Support vector regression using JMA mesoscale ensemble forecasts improves day-ahead Kanto solar irradiance prediction and reduces the maximum error.","significance":2,"cited_by":14,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-20-0104.1","title":"Deep Learning Experiments for Tropical Cyclone Intensity Forecasts","authors":["Xu Wenwei","Karthik Balaguru","August Andrew","Nicholas Lalo","Nathan O. Hodas","Mark DeMaria","David R. Judi"],"date":"2021-06-02","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-20-0104.1","openalex":"W3165941698"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0104.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/36/4/WAF-D-20-0104.1.pdf"},"orgs":["colorado-state-university"],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"An MLP using SHIPS predictors beats operational statistical-dynamical models by 5-22% for Atlantic tropical cyclone intensity in 2019-2020 real-time tests.","significance":4,"cited_by":74,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jcp.2021.110484","title":"A data-driven framework for the stochastic reconstruction of small-scale features with application to climate data sets","authors":["Zhong Yi Wan","Boyko Dodov","Christian Lessig","Henk A. Dijkstra","Themistoklis P. Sapsis"],"date":"2021-06-02","year":2021,"venue":"Journal of Computational Physics","venue_type":"journal","ids":{"doi":"10.1016/j.jcp.2021.110484","openalex":"W3167344324"},"links":{"paper":"https://doi.org/10.1016/j.jcp.2021.110484","pdf":"https://www.sciencedirect.com/science/article/pii/S002199912100379X"},"orgs":["mit"],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A data-driven stochastic framework reconstructs small-scale features in climate data sets; no abstract was provided, so impact is hard to assess.","significance":2,"cited_by":11,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46488-nept.2021.v20i02.043","title":"Statistical Downscaling of Rainfall Under Climate Change in Krishna River Sub-basin of Andhra Pradesh, India Using Artificial Neural Network (ANN)","authors":["K. V. R. Satya Sai","Sankranthi Krishnaiah","Akshay Manjunath"],"date":"2021-06-01","year":2021,"venue":"Nature Environment and Pollution Technology","venue_type":"journal","ids":{"doi":"10.46488/nept.2021.v20i02.043","openalex":"W3165975092"},"links":{"paper":"https://doi.org/10.46488/nept.2021.v20i02.043","pdf":"https://doi.org/10.46488/nept.2021.v20i02.043"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5"],"status":"research","summary":"Applies ANN with PCA to downscale CanESM2 rainfall projections for three Krishna sub-basin districts under three RCP scenarios, validated by R² and RMSE.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-e23060691","title":"Quantification of the Direct Solar Impact on Some Components of the Hydro-Climatic System","authors":["Constantin Mares","Ileana Mares","Venera Dobrică","Crişan Demetrescu"],"date":"2021-05-31","year":2021,"venue":"Entropy","venue_type":"journal","ids":{"doi":"10.3390/e23060691","openalex":"W3165355221"},"links":{"paper":"https://doi.org/10.3390/e23060691","pdf":"https://www.mdpi.com/1099-4300/23/6/691/pdf?version=1622631821"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Information-theoretic causal analysis with neural networks quantifies direct solar influences on hydro-climatic variables at specific frequencies and lags.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-14-3067-2021","title":"Physically regularized machine learning emulators of aerosol activation","authors":["Sam James Silva","Po‐Lun Ma","Joseph Clinton Hardin","Daniel Rothenberg"],"date":"2021-05-28","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-14-3067-2021","openalex":"W3125935968"},"links":{"paper":"https://doi.org/10.5194/gmd-14-3067-2021","pdf":"https://gmd.copernicus.org/articles/14/3067/2021/gmd-14-3067-2021.pdf"},"orgs":["tomorrow-io"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Physically regularized ML emulators of aerosol activation outperform many existing parameterizations, enabling hybrid models for Earth system models.","significance":4,"cited_by":37,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-21-0137.1","title":"Predictability of U.S. Regional Extreme Precipitation Occurrence Based on Large-Scale Meteorological Patterns (LSMPs)","authors":["Xiang Gao","Shray Mathur"],"date":"2021-05-27","year":2021,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-21-0137.1","openalex":"W3165364839"},"links":{"paper":"https://doi.org/10.1175/jcli-d-21-0137.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/clim/34/17/JCLI-D-21-0137.1.pdf"},"orgs":["mit"],"topic":"extremes-hazards","topics":[],"type":"evaluation","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Compares CNNs with analogue methods for predicting US regional extreme precipitation from large-scale patterns, finding CNNs more skillful and integrated vapor transport the most predictive variable.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2105.12909","title":"Deconditional Downscaling with Gaussian Processes","authors":["Siu Lun Chau","Shahine Bouabid","Dino Sejdinovic"],"date":"2021-05-27","year":2021,"venue_type":"preprint","ids":{"arxiv":"2105.12909"},"links":{"paper":"https://arxiv.org/abs/2105.12909","pdf":"https://arxiv.org/pdf/2105.12909"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Bayesian Gaussian-process deconditioning method for statistical downscaling of atmospheric fields, with a proven minimax-optimal rate and gains over existing methods.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41467-021-23406-3","title":"Deep learning for bias correction of MJO prediction","authors":["Hyemi Kim","Yoo‐Geun Ham","Young-Sik Joo","Seok‐Woo Son"],"date":"2021-05-25","year":2021,"venue":"Nature Communications","venue_type":"journal","ids":{"doi":"10.1038/s41467-021-23406-3","openalex":"W3165227342"},"links":{"paper":"https://doi.org/10.1038/s41467-021-23406-3","pdf":"https://www.nature.com/articles/s41467-021-23406-3.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["other"],"timescale":["s2s"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Deep learning bias correction of multi-model dynamical forecasts cuts MJO amplitude error by about 90% and phase error by 77% over four-week forecasts.","significance":5,"cited_by":91,"score":40,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-sym13060931","title":"Ensemble Empirical Mode Decomposition with Adaptive Noise with Convolution Based Gated Recurrent Neural Network: A New Deep Learning Model for South Asian High Intensity Forecasting","authors":["Kecheng Peng","Xiaoqun Cao","Bainian Liu","Yanan Guo","Wenlong Tian"],"date":"2021-05-24","year":2021,"venue":"Symmetry","venue_type":"journal","ids":{"doi":"10.3390/sym13060931","openalex":"W3164310397"},"links":{"paper":"https://doi.org/10.3390/sym13060931","pdf":"https://www.mdpi.com/2073-8994/13/6/931/pdf?version=1621852010"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","other"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Combines CEEMDAN decomposition, permutation entropy and ConvGRU to forecast daily South Asian High intensity from NCEP geopotential height, reporting higher accuracy than classical deep learning baselines.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-20-0186.1","title":"From Random Forests to Flood Forecasts: A Research to Operations Success Story","authors":["Russ S. Schumacher","Aaron J. Hill","Mark Klein","James A. Nelson","Michael J. Erickson","Sarah M. Trojniak","Gregory R. Herman"],"date":"2021-05-24","year":2021,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-20-0186.1","openalex":"W3164895358"},"links":{"paper":"https://doi.org/10.1175/bams-d-20-0186.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/bams/102/9/BAMS-D-20-0186.1.pdf"},"orgs":["noaa","colorado-state-university"],"topic":"extremes-hazards","topics":["post-processing"],"type":"operational","method":["classical-ml"],"timescale":["short","medium"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"operational","summary":"CSU-MLP random-forest excessive rainfall forecasts, built from ensemble reforecasts, were transitioned into operational use at NOAA's Weather Prediction Center.","significance":4,"cited_by":42,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2105.10880","title":"RtFPS: An Interactive Map that Visualizes and Predicts Wildfires in the US","authors":["Yang Li","Hermawan Mulyono","Ying Chen","Zhiyin Lu","Desmond Chan"],"date":"2021-05-23","year":2021,"venue_type":"preprint","ids":{"arxiv":"2105.10880"},"links":{"paper":"https://arxiv.org/abs/2105.10880","pdf":"https://arxiv.org/pdf/2105.10880","code":"https://github.com/yangland/rtfps"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Interactive map system that uses a machine learning model to show real-time US wildfire risk from environmental data and historical fire events.","significance":2,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11114757","title":"An ANN Model Trained on Regional Data in the Prediction of Particular Weather Conditions","authors":["Aleksandra Bączkiewicz","Jarosław Wątróbski","Wojciech Sałabun","Joanna Kołodziejczyk"],"date":"2021-05-22","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11114757","openalex":"W3164677999"},"links":{"paper":"https://doi.org/10.3390/app11114757","pdf":"https://www.mdpi.com/2076-3417/11/11/4757/pdf?version=1621953874"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An MLP predicts next-day minimum and maximum temperature and pressure for Szczecin, Poland, with 96% accuracy for temperature.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13112040","title":"A Downscaling–Merging Scheme for Improving Daily Spatial Precipitation Estimates Based on Random Forest and Cokriging","authors":["Xin Yan","Hua Chen","Bingru Tian","Sheng Sheng","Jinxing Wang","Jong‐Suk Kim"],"date":"2021-05-21","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13112040","openalex":"W3164028296"},"links":{"paper":"https://doi.org/10.3390/rs13112040","pdf":"https://www.mdpi.com/2072-4292/13/11/2040/pdf?version=1621997634"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random forest downscales GPM satellite daily precipitation to 0.01° and cokriging merges it with gauges, retaining accuracy while improving spatial detail.","significance":2,"cited_by":86,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13112039","title":"Estimation of Precipitation Area Using S-Band Dual-Polarization Radar Measurements","authors":["Joon Jin Song","Melissa Innerst","Kyuhee Shin","Bo-Young Ye","Minho Kim","Daejin Yeom","GyuWon Lee"],"date":"2021-05-21","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13112039","openalex":"W3164783197"},"links":{"paper":"https://doi.org/10.3390/rs13112039","pdf":"https://www.mdpi.com/2072-4292/13/11/2039/pdf?version=1621845914"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"Compares logistic regression, LDA, trees, SVM and random forests for precipitation-area classification from S-band radar, with spatial features helping.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12060661","title":"Survey on the Application of Deep Learning in Extreme Weather Prediction","authors":["Wei Fang","Qiongying Xue","Liang Chi Shen","Victor S. Sheng"],"date":"2021-05-21","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12060661","openalex":"W3160662458"},"links":{"paper":"https://doi.org/10.3390/atmos12060661","pdf":"https://www.mdpi.com/2073-4433/12/6/661/pdf?version=1621997503"},"orgs":["nuist","cma"],"topic":"extremes-hazards","topics":[],"type":"review","method":["rnn","cnn"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Survey of deep learning methods, including RNNs and CNNs, for predicting extreme weather events.","significance":3,"cited_by":53,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2021.062","title":"Potential of Deep Learning in drought assessment by extracting information from hydrometeorological precursors","authors":["Rajib Maity","Mohd Imran Khan","Subharthi Sarkar","Riya Dutta","Subhra Sekhar Maity","Manali Pal","Kironmala Chanda"],"date":"2021-05-21","year":2021,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2021.062","openalex":"W3164697149"},"links":{"paper":"https://doi.org/10.2166/wcc.2021.062"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A 1D CNN uses hydrometeorological precursors to assess basin-scale meteorological drought, with over 70% accuracy across seven drought categories.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ea001402","title":"Enhance Low Level Temperature and Moisture Profiles Through Combining NUCAPS, ABI Observations, and RTMA Analysis","authors":["Zheng Ma","Zhenglong Li","Jun Li","Timothy J. Schmit","Lídia Cucurull","Robert M. Atlas","Bomin Sun"],"date":"2021-05-20","year":2021,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2020ea001402","openalex":"W3165428335"},"links":{"paper":"https://doi.org/10.1029/2020ea001402","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020EA001402"},"orgs":["noaa","iap-cas"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","nwp-analysis","era5"],"status":"pre-operational","summary":"A deep neural network fuses NUCAPS, ABI and RTMA data to cut low-level temperature and moisture profile RMSE by over 30% versus ERA5.","significance":3,"cited_by":15,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11042-021-11059-9","title":"DSSAE-BBOA: deep learning-based weather big data analysis and visualization","authors":["Madhukar Rao G","Dharavath Ramesh"],"date":"2021-05-20","year":2021,"venue":"Multimedia Tools and Applications","venue_type":"journal","ids":{"doi":"10.1007/s11042-021-11059-9","openalex":"W3164794618"},"links":{"paper":"https://doi.org/10.1007/s11042-021-11059-9"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Deep learning framework (DSSAE-BBOA) for weather big-data analysis and visualization; no abstract is available, so the contribution is unclear.","significance":1,"cited_by":9,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3177298235","title":"Prediction in The Solar Power Generation Based on Weather Forecasts Using Machine Learning","authors":["Visvanathan Kalaiah"],"date":"2021-05-18","year":2021,"venue_type":"other","ids":{"openalex":"W3177298235"},"links":{"paper":"http://www.thedesignengineering.com/index.php/DE/article/view/1608"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"SVM forecasts solar PV output from weather forecasts to support grid balancing; the ML target is power generation rather than the atmosphere.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21103507","title":"Can Local Geographically Restricted Measurements Be Used to Recover Missing Geo-Spatial Data?","authors":["Hrvoje Kalinić","Zvonimir Bilokapić","Frano Matić"],"date":"2021-05-18","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21103507","openalex":"W3160695189"},"links":{"paper":"https://doi.org/10.3390/s21103507","pdf":"https://www.mdpi.com/1424-8220/21/10/3507/pdf?version=1621850797"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Compares linear regression, KNN, trees and neural networks to reconstruct ERA5 wind fields from 1% of points, with k-means sensor placement improving accuracy.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1086-714877","title":"Can Machines Learn How Clouds Work? The Epistemic Implications of Machine Learning Methods in Climate Science","authors":["Suzanne Kawamleh"],"date":"2021-05-18","year":2021,"venue":"Philosophy of Science","venue_type":"journal","ids":{"doi":"10.1086/714877","openalex":"W3163834479"},"links":{"paper":"https://doi.org/10.1086/714877"},"orgs":[],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"position","method":["other"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Philosophical argument that neural-network cloud parameterizations lacking physical process representation undermine the reliability of climate model predictions.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fenrg.2021.639346","title":"Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System","authors":["Moritz Stüber","Felix Scherhag","Matthieu Deru","Alassane Ndiaye","Muhammad Moiz Sakha","Boris Brandherm","Jörg Baus","Georg Frey"],"date":"2021-05-17","year":2021,"venue":"Frontiers in Energy Research","venue_type":"journal","ids":{"doi":"10.3389/fenrg.2021.639346","openalex":"W3161468613"},"links":{"paper":"https://doi.org/10.3389/fenrg.2021.639346","pdf":"https://www.frontiersin.org/articles/10.3389/fenrg.2021.639346/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Compares physics-based and data-driven day-ahead PV power forecasts built on NWP inputs at one site; all ML methods perform comparably.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2105.07043","title":"Post-processing Multi-Model Medium-Term Precipitation Forecasts Using Convolutional Neural Networks","authors":["Bob de Ruiter"],"date":"2021-05-14","year":2021,"venue_type":"preprint","ids":{"arxiv":"2105.07043","openalex":"W3163043998"},"links":{"paper":"https://arxiv.org/abs/2105.07043","pdf":"https://arxiv.org/pdf/2105.07043"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["regional","global"],"data":["nwp-analysis"],"status":"research","summary":"Fully convolutional networks post-process multi-model precipitation forecasts; they did not beat regularized logistic regression, but combining global and regional NWP inputs improved skill.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36227-techrxiv.14540343","title":"Precipitation Nowcasting using Data-driven Reduced-order Model","authors":["Divya S Vidyadharan","Aaron Xavier","Blossom Treesa Bastian","Ajay Ragh","Naveen Chittilapilly"],"date":"2021-05-13","year":2021,"venue_type":"other","ids":{"doi":"10.36227/techrxiv.14540343","openalex":"W4256585467"},"links":{"paper":"https://doi.org/10.36227/techrxiv.14540343","pdf":"https://www.techrxiv.org/articles/preprint/Precipitation_Nowcasting_using_Data-driven_Reduced-order_Model/14540343/1/files/27895341.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Radar nowcasting combines TVL1 optical flow with SINDy sparse dynamics to produce ensemble precipitation forecasts that beat benchmarks on typhoon and squall-line cases.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21103405","title":"FOCUSED–Short-Term Wind Speed Forecast Correction Algorithm Based on Successive NWP Forecasts for Use in Traffic Control Decision Support Systems","authors":["Zdravko Kunić","Bernard Ženko","Biljana Mileva Boshkoska"],"date":"2021-05-13","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21103405","openalex":"W3162174150"},"links":{"paper":"https://doi.org/10.3390/s21103405","pdf":"https://www.mdpi.com/1424-8220/21/10/3405/pdf?version=1621528700"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"FOCUSED corrects short-term NWP wind speed forecasts for dangerous bora gusts on the Croatian Krk bridge, outperforming ANN, random forest and SVM baselines.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl092092","title":"Subseasonal Forecasts of Opportunity Identified by an Explainable Neural Network","authors":["Kirsten J. Mayer","Elizabeth A. Barnes"],"date":"2021-05-13","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl092092","openalex":"W3160924831"},"links":{"paper":"https://doi.org/10.1029/2020gl092092"},"orgs":["colorado-state-university"],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Neural network identifies subseasonal forecasts of opportunity over the North Atlantic at 22-day lead, with layer-wise relevance propagation revealing tropical predictors.","significance":3,"cited_by":101,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3389-feart.2021.659310","title":"Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach","authors":["Cen Wang","Zhaoying Jia","Zhaohui Yin","Fei Liu","Gaopeng Lu","Jianqiu Zheng"],"date":"2021-05-12","year":2021,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2021.659310","openalex":"W3161392142"},"links":{"paper":"https://doi.org/10.3389/feart.2021.659310","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2021.659310/pdf"},"orgs":["nuist","iap-cas","baidu"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Multitask local linear regression predicts China precipitation 2–6 weeks ahead with skill 0.11, rising to 0.13 when the Arctic Oscillation index is added.","significance":3,"cited_by":24,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13101884","title":"Temperature and Relative Humidity Profile Retrieval from Fengyun-3D/HIRAS in the Arctic Region","authors":["Jingjing Hu","Yansong Bao","Jian Liu","Hui Liu","George P. Petropoulos","Petros Katsafados","Liuhua Zhu","Xi Cai"],"date":"2021-05-11","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13101884","openalex":"W3163717131"},"links":{"paper":"https://doi.org/10.3390/rs13101884","pdf":"https://www.mdpi.com/2072-4292/13/10/1884/pdf?version=1621414046"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Neural networks retrieve Arctic temperature and humidity profiles from FY-3D HIRAS under clear skies, closer to ERA5 than AIRS products.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-hydro.2021.176","title":"Deterministic and probabilistic evaluation of raw and post-processing monthly precipitation forecasts: a case study of China","authors":["Yujie Li","Bin Xu","Dong Wang","Quan Jun Wang","Xiongwei Zheng","Jiliang Xu","Fen Zhou","Huaping Huang","Yue‐Ping Xu"],"date":"2021-05-11","year":2021,"venue":"Journal of Hydroinformatics","venue_type":"journal","ids":{"doi":"10.2166/hydro.2021.176","openalex":"W3161807708"},"links":{"paper":"https://doi.org/10.2166/hydro.2021.176","pdf":"https://iwaponline.com/jh/article-pdf/23/4/914/910174/jh0230914.pdf"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"evaluation","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Bayesian joint probability calibration of ML and GCM monthly precipitation forecasts over China yields reliable ensembles, though ML outputs lack skill beyond climatology.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21203-rs.3.rs-410239-v1","title":"Bias adjustment of Cordex database based on a nonlinear artificial neural network method to simulate summer precipitation in the southeast Iran","authors":["Mohammad Reza Salari Fanoodi","Mahmood Khosravi","Taghi Tavousi","Mohsen Hamidianpour"],"date":"2021-05-11","year":2021,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-410239/v1","openalex":"W3160208802"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-410239/v1","pdf":"https://www.researchsquare.com/article/rs-410239/latest.pdf"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Nonlinear neural network bias adjustment of CORDEX regional projections for summer precipitation in southeast Iran. No abstract was provided.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3174999126","title":"A Novel Deep Learning Framework For Rainfall Prediction In Weather Forecasting","authors":["Dr.S. Soundararajan"],"date":"2021-05-10","year":2021,"venue":"Turkish Journal of Computer and Mathematics Education (TURCOMAT)","venue_type":"journal","ids":{"openalex":"W3174999126"},"links":{"paper":"https://turcomat.org/index.php/turkbilmat/article/view/6291"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN-based system predicts rainfall from climatological variables such as temperature and humidity; the abstract gives no quantitative results.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.17762-turcomat.v12i11.5965","title":"Deep Learning For Improved Heat Index Using Iot-Based Data","authors":["Et. al. Dr. C. Jayaprakash"],"date":"2021-05-10","year":2021,"venue":"Türk bilgisayar ve matematik eğitimi dergisi","venue_type":"journal","ids":{"doi":"10.17762/turcomat.v12i11.5965","openalex":"W3176405908"},"links":{"paper":"https://doi.org/10.17762/turcomat.v12i11.5965","pdf":"https://turcomat.org/index.php/turkbilmat/article/download/5965/4965"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Deep learning (LSTM-style) predicts heat index from IoT temperature sensor time series and is compared with generalized linear regression; the study is low-rigour.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-abfeed","title":"Does statistical model perform at par with computationally expensive general circulation model for decadal prediction?","authors":["Rishi Sahastrabuddhe","Subimal Ghosh"],"date":"2021-05-08","year":2021,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/abfeed","openalex":"W3162606147"},"links":{"paper":"https://doi.org/10.1088/1748-9326/abfeed","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/abfeed/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Data-driven MSSA matches CMIP5 GCM skill for SST and Indian summer monsoon rainfall decadal hindcasts, improving ISMR skill over GCMs.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.mlwa.2021.100038","title":"FogNet: A multiscale 3D CNN with double-branch dense block and attention mechanism for fog prediction","authors":["Hamid Kamangir","Waylon G. Collins","Philippe E. Tissot","Scott A. King","Hue Thi Hong Dinh","Niall Durham","James Rizzo"],"date":"2021-05-08","year":2021,"venue":"Machine Learning with Applications","venue_type":"journal","ids":{"doi":"10.1016/j.mlwa.2021.100038","openalex":"W3161760456"},"links":{"paper":"https://doi.org/10.1016/j.mlwa.2021.100038","pdf":"https://www.sciencedirect.com/science/article/pii/S2666827021000190/pdf"},"orgs":["noaa"],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["cnn","transformer"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","other"],"status":"research","summary":"FogNet, a 3D CNN with attention, post-processes NAM forecasts to predict fog visibility at a US airport, outperforming HREF on eight metrics.","significance":3,"cited_by":37,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2021.654763","title":"A Comparative Study on the Skill of CMIP6 Models to Preserve Daily Spatial Patterns of Monsoon Rainfall Over India","authors":["Adway Mitra"],"date":"2021-05-07","year":2021,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2021.654763","openalex":"W3162962282"},"links":{"paper":"https://doi.org/10.3389/fclim.2021.654763","pdf":"https://www.frontiersin.org/articles/10.3389/fclim.2021.654763/pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"A probabilistic graphical model evaluates how well CMIP6 models reproduce daily spatial monsoon rainfall patterns and clusters over India.","significance":2,"cited_by":50,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2105.02585","title":"FDNet: A Deep Learning Approach with Two Parallel Cross Encoding Pathways for Precipitation Nowcasting","authors":["Bi-Ying Yan","Chao Yang","Feng Chen","Kohei Takeda","Changjun Wang"],"date":"2021-05-06","year":2021,"venue":"Journal of Computer Science and Technology","venue_type":"journal","ids":{"arxiv":"2105.02585","doi":"10.1007/s11390-021-1103-8","openalex":"W4389341455"},"links":{"paper":"https://doi.org/10.1007/s11390-021-1103-8","pdf":"https://arxiv.org/pdf/2105.02585"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"FDNet separates radar echo motion into optical flow and morphological deformation via two parallel encoders, achieving state-of-the-art precipitation nowcasting on two radar datasets.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.energy.2021.120842","title":"An investigation on deep learning and wavelet transform to nowcast wind power and wind power ramp: A case study in Brazil and Uruguay","authors":["Pedro Júnior Zucatelli","Erick Giovani Sperandio Nascimento","Alex Álisson Bandeira Santos","A.M.G. Arce","Davidson Martins Moreira"],"date":"2021-05-05","year":2021,"venue":"Energy","venue_type":"journal","ids":{"doi":"10.1016/j.energy.2021.120842","openalex":"W3157443038"},"links":{"paper":"https://doi.org/10.1016/j.energy.2021.120842"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"application","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Deep learning with wavelet transforms nowcasts wind power and wind power ramps in Brazil and Uruguay; no abstract was available, so this is judged from the title.","significance":2,"cited_by":55,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10506957.1","title":"A Neural Network Model for Shortwave Radiative Feedback Quantification","authors":["Aliia Shakirova","Yi Huang"],"date":"2021-05-04","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10506957.1","openalex":"W3159804008"},"links":{"paper":"https://doi.org/10.1002/essoar.10506957.1"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Neural network emulates shortwave radiative fluxes trained on ERA5 to diagnose Arctic albedo, water vapour and cloud feedbacks, capturing albedo nonlinearity that linear kernels miss.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2107.06991","title":"Physics-informed generative neural network: an application to troposphere temperature prediction","authors":["Zhihao Chen","Jie Gao","Weikai Wang","Zheng Yan"],"date":"2021-05-04","year":2021,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"arxiv":"2107.06991","doi":"10.1088/1748-9326/abfde9","openalex":"W3165675070"},"links":{"paper":"https://doi.org/10.1088/1748-9326/abfde9","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/abfde9/pdf"},"orgs":["shanghai-ai-lab"],"topic":"global-medium-range","topics":[],"type":"model","method":["physics-constrained","other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"PGnet is a physics-informed two-stage generative network that uses a mask to refine ERA5 500 hPa temperature predictions and reduce error accumulation in time-series rollouts.","significance":3,"cited_by":28,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asr.2021.04.039","title":"Deep learning model for predicting daily IGS zenith tropospheric delays in West Africa using TensorFlow and Keras","authors":["Samuel Osah","Akwasi Afrifa Acheampong","Collins Fosu","Isaac Dadzie"],"date":"2021-05-03","year":2021,"venue":"Advances in Space Research","venue_type":"journal","ids":{"doi":"10.1016/j.asr.2021.04.039","openalex":"W3159861791"},"links":{"paper":"https://doi.org/10.1016/j.asr.2021.04.039","pdf":"https://www.sciencedirect.com/science/article/pii/S0273117721003380/pdf"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Deep learning model (DLztd) predicts daily GNSS zenith tropospheric delay at four West African stations from surface meteorology, filling data gaps.","significance":2,"cited_by":37,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32628-cseit217318","title":"Weather Forecast through Data Mining","authors":["Swati Pandey","Shruti Sharma","S. Anantha Kumar","Kanchan Bhatt","Rakesh Kumar Arora"],"date":"2021-05-02","year":2021,"venue":"International Journal of Scientific Research in Computer Science Engineering and Information Technology","venue_type":"journal","ids":{"doi":"10.32628/cseit217318","openalex":"W3163893062"},"links":{"paper":"https://doi.org/10.32628/cseit217318","pdf":"https://doi.org/10.32628/cseit217318"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":[],"data":["stations"],"status":"research","summary":"Compares neural networks, random forest, SVM and kNN for weather prediction from government data, with a chatbot front end; the abstract reports no results.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijeecs.v22.i2.pp1208-1215","title":"Weather prediction using random forest machine learning model","authors":["Rajasekaran Meenal","Prawin Angel Michael","D. Pamela","Rajasekaran Ekambaram"],"date":"2021-05-01","year":2021,"venue":"Indonesian Journal of Electrical Engineering and Computer Science","venue_type":"journal","ids":{"doi":"10.11591/ijeecs.v22.i2.pp1208-1215","openalex":"W3152611657"},"links":{"paper":"https://doi.org/10.11591/ijeecs.v22.i2.pp1208-1215","pdf":"http://ijeecs.iaescore.com/index.php/IJEECS/article/download/24172/15022"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random forest predicts daily solar radiation and wind speed for Tamil Nadu from station data, reaching R2 0.97 and beating regression and SVM baselines.","significance":1,"cited_by":90,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002365","title":"Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning","authors":["Tao Zhang","Wuyin Lin","Andrew M. Vogelmann","Minghua Zhang","Shaocheng Xie","Yi Qin","Jean‐Christophe Golaz"],"date":"2021-05-01","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002365","openalex":"W3159792112"},"links":{"paper":"https://doi.org/10.1029/2020ms002365","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002365"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"XGBoost-based convection trigger for GCM deep convection schemes beats CAPE triggers, reaching 91-93% F1 and curbing overpredicted convection occurrence.","significance":4,"cited_by":69,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.48175-ijarsct-1075","title":"Personalized Weather Station With Machine Learning Based Rainfall Predictor","authors":["A Agathiyan","Naresh Kumar K. M","Mr. K. Immanuel"],"date":"2021-04-30","year":2021,"venue":"International Journal of Advanced Research in Science Communication and Technology","venue_type":"journal","ids":{"doi":"10.48175/ijarsct-1075","openalex":"W3162205745"},"links":{"paper":"https://doi.org/10.48175/ijarsct-1075"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Low-cost sensor weather station feeds machine learning to predict local rainfall from temperature, pressure, humidity and wind data.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11094129","title":"A Novel Deep Learning Based Model for Tropical Intensity Estimation and Post-Disaster Management of Hurricanes","authors":["Jayanthi Devaraj","Sumathi Ganesan","Rajvikram Madurai Elavarasan","Umashankar Subramaniam"],"date":"2021-04-30","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11094129","openalex":"W3160409764"},"links":{"paper":"https://doi.org/10.3390/app11094129","pdf":"https://www.mdpi.com/2076-3417/11/9/4129/pdf?version=1619776632"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Improved CNN estimates hurricane intensity from infrared satellite imagery with 7.6-knot RMSE and adds VGG19-based post-disaster damage assessment.","significance":3,"cited_by":39,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13091720","title":"Fusing Precipitable Water Vapor Data in CHINA at Different Timescales Using an Artificial Neural Network","authors":["Zhaohui Xiong","Bao Zhang","Jizhang Sang","Xiaogong Sun","Xiaoming Wei"],"date":"2021-04-29","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13091720","openalex":"W3158482849"},"links":{"paper":"https://doi.org/10.3390/rs13091720","pdf":"https://www.mdpi.com/2072-4292/13/9/1720/pdf?version=1619752792"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Generalized regression neural network calibrates MODIS and ERA5 precipitable water vapor against GNSS over China, improving accuracy most at monthly timescales.","significance":2,"cited_by":13,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2105.06386","title":"Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks","authors":["Alexis Ayala","Christopher Drazic","Brian Hutchinson","Ben Kravitz","Claudia Tebaldi"],"date":"2021-04-29","year":2021,"venue_type":"preprint","ids":{"arxiv":"2105.06386","openalex":"W3194008214"},"links":{"paper":"https://arxiv.org/abs/2105.06386","pdf":"https://arxiv.org/pdf/2105.06386"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Two loosely conditioned GANs emulate 32-day global daily precipitation from a coupled Earth system model, matching dry-day statistics at a fraction of the compute.","significance":4,"cited_by":5,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10506907.1","title":"A Hybrid Deep Learning Model for Improved Wind and Wave Forecasts","authors":["Yuval Yevnin","Yaron Toledo"],"date":"2021-04-28","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10506907.1","openalex":"W3210202320"},"links":{"paper":"https://doi.org/10.1002/essoar.10506907.1"},"orgs":[],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"pre-operational","summary":"Deep learning improves wind forecasts from reanalysis, which then force a wave model, giving about 10% gains in wind and wave height over the Mediterranean and over 35% in the Aegean.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2105.02959","title":"A review on physical and data-driven based nowcasting methods using sky images","authors":["Ekanki Sharma","Wilfried Elmenreich"],"date":"2021-04-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2105.02959"},"links":{"paper":"https://arxiv.org/abs/2105.02959","pdf":"https://arxiv.org/pdf/2105.02959"},"orgs":[],"topic":"nowcasting","topics":[],"type":"review","method":[],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Review of physical and data-driven sky-image methods for intra-hour solar irradiance nowcasting, identifying which image features matter most.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.13958","title":"Defined the predictors of the lightning over India by using artificial neural network","authors":["Pradip Kumar Gautam","Deweshvar Singh"],"date":"2021-04-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.13958"},"links":{"paper":"https://arxiv.org/abs/2104.13958","pdf":"https://arxiv.org/pdf/2104.13958"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"An artificial neural network identifies K-index, AOD and CAPE as key predictors of lightning over India using daily and monthly data.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.12469","title":"Generative modeling of spatio-temporal weather patterns with extreme event conditioning","authors":["Konstantin Klemmer","Sudipan Saha","Matthias Kahl","Tianlin Xu","Xiao Xiang Zhu"],"date":"2021-04-26","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.12469"},"links":{"paper":"https://arxiv.org/abs/2104.12469","pdf":"https://arxiv.org/pdf/2104.12469"},"orgs":[],"topic":"extremes-hazards","topics":["probabilistic-ensembles"],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":[],"data":["era5"],"status":"research","summary":"GAN generates spatio-temporal weather fields conditioned on extreme-event segmentation masks, tested on surface radiation and zonal wind data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13091669","title":"Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems","authors":["Zhiang Chen","Melissa A. Wagner","Jnaneshwar Das","Robert K. Doe","Randall S. Cerveny"],"date":"2021-04-25","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13091669","openalex":"W3161130621"},"links":{"paper":"https://doi.org/10.3390/rs13091669","pdf":"https://www.mdpi.com/2072-4292/13/9/1669/pdf?version=1620632433"},"orgs":["university-of-oklahoma"],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"application","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Deep neural networks on UAS orthomosaics detect and classify tornado damage, producing georeferenced damage heatmaps for post-event assessment after the 2018 Eureka tornado.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.11467","title":"Probabilistic Rainfall Estimation from Automotive Lidar","authors":["Robin Karlsson","David Robert Wong","Kazunari Kawabata","Simon Thompson","Naoki Sakai"],"date":"2021-04-23","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.11467"},"links":{"paper":"https://arxiv.org/abs/2104.11467","pdf":"https://arxiv.org/pdf/2104.11467"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Hierarchical mixture-of-experts model estimates rainfall rate from automotive lidar point clouds, reaching RMSE 2.42 mm/h after filtering uncertain predictions.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-20-0188.1","title":"A Calibrated and Consistent Combination of Probabilistic Forecasts for the Exceedance of Several Precipitation Thresholds Using Neural Networks","authors":["P. Schaumann","Reinhold Hess","Martin Rempel","Ulrich Blahak","Volker Schmidt"],"date":"2021-04-22","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-20-0188.1","openalex":"W3159768227"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0188.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/36/3/WAF-D-20-0188.1.pdf"},"orgs":["dwd"],"topic":"nowcasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"Neural network combines RadVOR radar nowcasts with postprocessed COSMO-DE-EPS ensembles, giving calibrated precipitation threshold probabilities that beat both inputs for 1 to 6 h.","significance":4,"cited_by":7,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-ascmo-7-35-2021","title":"A generalized Spatio-Temporal Threshold Clustering method for identification of extreme event patterns","authors":["Vitaly Kholodovsky","Xin‐Zhong Liang"],"date":"2021-04-21","year":2021,"venue":"Advances in statistical climatology, meteorology and oceanography","venue_type":"journal","ids":{"doi":"10.5194/ascmo-7-35-2021","openalex":"W3153937518"},"links":{"paper":"https://doi.org/10.5194/ascmo-7-35-2021","pdf":"https://ascmo.copernicus.org/articles/7/35/2021/ascmo-7-35-2021.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Spatio-temporal threshold clustering uses pattern recognition and clustering to define consistent extreme precipitation episodes over the contiguous US from gauge data.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.rse.2021.112454","title":"Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural network","authors":["Xiaohui Li","Dongkai Yang","Jingsong Yang","Gang Zheng","Guoqi Han","Yang Nan","Weiqiang Li"],"date":"2021-04-21","year":2021,"venue":"Remote Sensing of Environment","venue_type":"journal","ids":{"doi":"10.1016/j.rse.2021.112454","openalex":"W3156567400"},"links":{"paper":"https://doi.org/10.1016/j.rse.2021.112454"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Applies an artificial neural network to CYGNSS GNSS-reflectometry data to retrieve coastal surface wind speed.","significance":3,"cited_by":96,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3846-jcem.2021.14649","title":"COLLAPSE WARNING SYSTEM USING LSTM NEURAL NETWORKS FOR CONSTRUCTION DISASTER PREVENTION IN EXTREME WIND WEATHER","authors":["Chih‐Chiang Wei"],"date":"2021-04-20","year":2021,"venue":"Journal of Civil Engineering and Management","venue_type":"journal","ids":{"doi":"10.3846/jcem.2021.14649","openalex":"W3154881072"},"links":{"paper":"https://doi.org/10.3846/jcem.2021.14649","pdf":"https://journals.vilniustech.lt/index.php/JCEM/article/download/14649/10501"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["rnn","classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM and other ML wind forecasts drive a scaffold collapse warning system, giving 1–6 hour advance alerts for typhoon winds at Taichung stations.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12040522","title":"A Machine Learning Based Ensemble Forecasting Optimization Algorithm for Preseason Prediction of Atlantic Hurricane Activity","authors":["Xia Sun","Lian Xie","Shahil Umeshkumar Shah","Xipeng Shen"],"date":"2021-04-20","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12040522","openalex":"W3153291388"},"links":{"paper":"https://doi.org/10.3390/atmos12040522","pdf":"https://www.mdpi.com/2073-4433/12/4/522/pdf?version=1618990469"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"ML-optimized ensemble selection and weighting improves preseason Atlantic hurricane forecasts over simple averaging for major hurricane counts.","significance":2,"cited_by":22,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13081577","title":"Evaporation Duct Height Nowcasting in China’s Yellow Sea Based on Deep Learning","authors":["Jie Han","Jiaji Wu","Qinglin Zhu","Hongguang Wang","Yufeng Zhou","Mingbo Jiang","Shoubao Zhang","Bo Wang"],"date":"2021-04-19","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13081577","openalex":"W3153218935"},"links":{"paper":"https://doi.org/10.3390/rs13081577","pdf":"https://www.mdpi.com/2072-4292/13/8/1577/pdf?version=1618828238"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Deep learning nowcasts evaporation duct height in the Yellow Sea at 5-minute resolution for 0–2 h, outperforming traditional time-series methods.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.10066","title":"EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task","authors":["Christian Requena-Mesa","Vitus Benson","Markus Reichstein","Jakob Runge","Joachim Denzler"],"date":"2021-04-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.10066"},"links":{"paper":"https://arxiv.org/abs/2104.10066","pdf":"https://arxiv.org/pdf/2104.10066"},"orgs":[],"topic":"benchmarks-data-eval","topics":["applications-impacts"],"type":"benchmark","method":["cnn","transformer"],"timescale":["short"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"EarthNet2021 dataset and challenge forecasts Sentinel-2 surface imagery conditioned on mesoscale future weather, enabling model intercomparison at 20 m resolution.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.08281","title":"Controlled abstention neural networks for identifying skillful predictions for classification problems","authors":["Elizabeth A. Barnes","Randal J. Barnes"],"date":"2021-04-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.08281","doi":"10.1029/2021ms002573"},"links":{"paper":"https://arxiv.org/abs/2104.08281","pdf":"https://arxiv.org/pdf/2104.08281"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"The NotWrong loss adds an abstention class so classifiers learn from confident samples, outperforming existing losses on several climate prediction tasks.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.08236","title":"Controlled abstention neural networks for identifying skillful predictions for regression problems","authors":["Elizabeth A. Barnes","Randal J. Barnes"],"date":"2021-04-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.08236","doi":"10.1029/2021ms002575"},"links":{"paper":"https://arxiv.org/abs/2104.08236","pdf":"https://arxiv.org/pdf/2104.08236"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"An abstention loss lets regression networks flag low-confidence samples during training, outperforming a standard uncertainty baseline on synthetic climate tasks.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-021-87520-4","title":"Crop response to El Niño-Southern Oscillation related weather variation to help farmers manage their crops","authors":["Ross Chapman","James H. Cock","Marianne I. Samson","Noel Janetski","Kate Janetski","Dadang Gusyana","Sudarshan Kumar Dutta","Thomas Oberthür"],"date":"2021-04-15","year":2021,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-021-87520-4","openalex":"W3156136628"},"links":{"paper":"https://doi.org/10.1038/s41598-021-87520-4","pdf":"https://www.nature.com/articles/s41598-021-87520-4.pdf"},"orgs":[],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["other"],"status":"research","summary":"Machine learning links cacao yields in Sulawesi to ENSO patterns 8–24 months ahead, explaining 75% of yield variation and timing fertilizer use.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-dac.4805","title":"Retracted: Weather forecasting and prediction using hybrid C5.0 machine learning algorithm","authors":["Sudhan M.B","Anitha Thavasimuthu","Aruna Murugesan","G. Charlyn Pushpa Latha","A. Vijay","Laxmi Raja","Rajendran Thavasimuthu"],"date":"2021-04-15","year":2021,"venue":"International Journal of Communication Systems","venue_type":"journal","ids":{"doi":"10.1002/dac.4805","openalex":"W3155716677"},"links":{"paper":"https://doi.org/10.1002/dac.4805"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["era5"],"status":"research","summary":"Retracted paper proposing a C5.0 decision tree with K-means for short-range weather prediction on MERRA data, claiming 90.18% accuracy.","significance":0,"cited_by":146,"score":10,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-fclim.2021.656479","title":"Spatio-Temporal Downscaling of Climate Data Using Convolutional and Error-Predicting Neural Networks","authors":["Agon Serifi","Tobias Günther","Nikolina Ban"],"date":"2021-04-12","year":2021,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"doi":"10.3389/fclim.2021.656479","openalex":"W3154123501"},"links":{"paper":"https://doi.org/10.3389/fclim.2021.656479","pdf":"https://www.frontiersin.org/articles/10.3389/fclim.2021.656479/pdf"},"orgs":["eth-zurich"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","cmip","km-scale-sim"],"status":"research","summary":"Deep convolutional networks reconstruct high-resolution weather and climate fields from low-resolution simulations, and generalize to observed data for precipitation and other variables.","significance":4,"cited_by":80,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.05540","title":"El Niño Modoki thus far can be mostly predicted more than 10 years ahead of time","authors":["X. San Liang","Fen Xu","Yineng Rong"],"date":"2021-04-12","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.05540"},"links":{"paper":"https://arxiv.org/abs/2104.05540","pdf":"https://arxiv.org/pdf/2104.05540"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["decadal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Information-flow causality links sunspot numbers to El Niño Modoki, and a causal deep learning model reproduces events 12 years ahead, according to the authors.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.05107","title":"Towards a Collective Agenda on AI for Earth Science Data Analysis","authors":["Devis Tuia","Ribana Roscher","Jan Dirk Wegner","Nathan Jacobs","Xiao Xiang Zhu","Gustau Camps-Valls"],"date":"2021-04-11","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.05107","doi":"10.1109/mgrs.2020.3043504"},"links":{"paper":"https://arxiv.org/abs/2104.05107","pdf":"https://arxiv.org/pdf/2104.05107"},"orgs":[],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"position","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"Position paper proposing research agendas for AI in Earth science and remote sensing to move beyond disciplinary comfort zones.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.05089","title":"The World as a Graph: Improving El Niño Forecasts with Graph Neural Networks","authors":["Salva Rühling Cachay","Emma Erickson","Arthur Fender C. Bucker","Ernest Pokropek","Willa Potosnak","Suyash Bire","Salomey Osei","Björn Lütjens"],"date":"2021-04-11","year":2021,"venue_type":"preprint","ids":{"arxiv":"2104.05089","openalex":"W3156396258"},"links":{"paper":"https://arxiv.org/abs/2104.05089","pdf":"https://arxiv.org/pdf/2104.05089"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["gnn"],"timescale":["seasonal"],"spatial":["global"],"data":[],"status":"research","summary":"Graphino, a graph neural network with a learned connectivity module, outperforms prior deep learning models for ENSO forecasts up to six months ahead and yields interpretable connections.","significance":5,"cited_by":14,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.21559358","title":"Using Deep Learning Technique to Predict the Weather Forecasting","authors":["Dr. A. C. Subhajini"],"date":"2021-04-10","year":2021,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.21559358","openalex":"W7171209381"},"links":{"paper":"https://doi.org/10.5281/zenodo.21559358"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares backpropagation, RBF, GRNN and deep networks on ten years of Kanyakumari district data, finding deep learning most accurate.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.19696977","title":"Machine Learning Models for Climate Prediction and Adaptation Planning","authors":["Karim Benjelloun","Amira El Mansouri"],"date":"2021-04-10","year":2021,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.19696977","openalex":"W7155215563"},"links":{"paper":"https://doi.org/10.5281/zenodo.19696977"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"review","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":[],"status":"research","summary":"Systematic literature review of machine learning for climate prediction and adaptation planning, with a Morocco focus; offers no new model or result.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3069217","title":"Predicting Tropical Cyclogenesis Using a Deep Learning Method From Gridded Satellite and ERA5 Reanalysis Data in the Western North Pacific Basin","authors":["Rui Zhang","Qingshan Liu","Renlong Hang","Guangcan Liu"],"date":"2021-04-09","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3069217","openalex":"W3155849328"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3069217"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"CNN-based fusion of satellite and ERA5 predictors detects 97.1% of developing tropical cyclones in the western North Pacific at a 20.3% false alarm rate.","significance":3,"cited_by":20,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-14-2699-2021","title":"Applying machine learning methods to detect convection using Geostationary Operational Environmental Satellite-16 (GOES-16) advanced baseline imager (ABI) data","authors":["Yoonjin Lee","Christian D. Kummerow","Imme Ebert‐Uphoff"],"date":"2021-04-08","year":2021,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-14-2699-2021","openalex":"W3147008637"},"links":{"paper":"https://doi.org/10.5194/amt-14-2699-2021","pdf":"https://amt.copernicus.org/articles/14/2699/2021/amt-14-2699-2021.pdf"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"A convolutional network on one-minute GOES-16 visible and infrared imagery detects convection, trained against MRMS radar precipitation types as a proof of concept.","significance":3,"cited_by":50,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ea001604","title":"Classification of Weather Phenomenon From Images by Using Deep Convolutional Neural Network","authors":["Haixia Xiao","Feng Zhang","Zhongping Shen","Kun Wu","Jinglin Zhang"],"date":"2021-04-08","year":2021,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2020ea001604","openalex":"W3153343195"},"links":{"paper":"https://doi.org/10.1029/2020ea001604","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020EA001604"},"orgs":["fudan-university","nuist"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"MeteCNN classifies 11 weather phenomena in a new 6,877-image dataset, reaching about 92% test accuracy.","significance":2,"cited_by":78,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-x50k7x","title":"Long-term hydrometeorological time-series analysis over the central highlands of West Papua","authors":["Sandy Herho"],"date":"2021-04-06","year":2021,"venue_type":"other","ids":{"doi":"10.31223/x50k7x","openalex":"W3150692956"},"links":{"paper":"https://doi.org/10.31223/x50k7x"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"A NARX neural network predicts the 12-month drought index SPI-12 in West Papua from the MEI ENSO index, capturing ENSO-linked rainfall patterns.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl092133","title":"A Toy Model to Investigate Stability of AI‐Based Dynamical Systems","authors":["Blanka Balogh","David Saint‐Martin","Aurélien Ribes"],"date":"2021-04-06","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl092133","openalex":"W3138927827"},"links":{"paper":"https://doi.org/10.1029/2020gl092133","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020GL092133"},"orgs":["meteo-france"],"topic":"xai-uq-physics","topics":["hybrid-parameterization"],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"An extended Lorenz-63 toy model reveals feedforward network instability, which training on Latin Hypercube samples removes, showing sampling design matters for stability.","significance":4,"cited_by":11,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12040455","title":"Atlantic Hurricane Activity Prediction: A Machine Learning Approach","authors":["Tanmay Asthana","Hamid Krim","Xia Sun","Siddharth Roheda","Lian Xie"],"date":"2021-04-03","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12040455","openalex":"W3152101540"},"links":{"paper":"https://doi.org/10.3390/atmos12040455","pdf":"https://www.mdpi.com/2073-4433/12/4/455/pdf?version=1617966473"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"CNN feature fusion of sea-level pressure, SST and wind predicts preseason Atlantic hurricane activity with skill up to 18 months ahead.","significance":3,"cited_by":17,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.01435","title":"A Bayesian Machine Learning Algorithm for Predicting ENSO Using Short Observational Time Series","authors":["Nan Chen","Faheem Gilani","John Harlim"],"date":"2021-04-03","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"arxiv":"2104.01435","doi":"10.1029/2021gl093704","openalex":"W3144899584"},"links":{"paper":"https://doi.org/10.1029/2021gl093704","pdf":"https://arxiv.org/pdf/2104.01435"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A Bayesian neural network trained on only 20 years of data predicts Niño 3 SST skillfully for 9.5 months, overcoming the spring predictability barrier.","significance":4,"cited_by":14,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.18629902","title":"Rainfall Forecasting in Sub-Sahara Africa-Ghana using LSTM Deep Learning Approach","authors":["Charity Oseiwah Adjei","Wei Tian","Bernard-Marie Onzo","Shiwei Chen","Emmanuel Adu Gyamfi Kedjanyi","Oscar Famous Darteh"],"date":"2021-04-02","year":2021,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.18629902","openalex":"W3155532891"},"links":{"paper":"https://doi.org/10.5281/zenodo.18629902"},"orgs":["nuist"],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"LSTM with correlation-based feature selection predicts hourly rainfall at Axim, Ghana, using ECMWF and station data, with MSE of 0.002.","significance":1,"cited_by":4,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.00954","title":"Skillful Precipitation Nowcasting using Deep Generative Models of Radar","authors":["Suman Ravuri","Karel Lenc","Matthew Willson","Dmitry Kangin","Remi Lam","Piotr Mirowski","Megan Fitzsimons","Maria Athanassiadou","Sheleem Kashem","Sam Madge","Rachel Prudden","Amol Mandhane","Aidan Clark","Andrew Brock","Karen Simonyan","Raia Hadsell","Niall Robinson","Ellen Clancy","Alberto Arribas","Shakir Mohamed"],"date":"2021-04-02","year":2021,"venue":"Nature","venue_type":"journal","ids":{"arxiv":"2104.00954","doi":"10.1038/s41586-021-03854-z","openalex":"W3202525453"},"links":{"paper":"https://arxiv.org/abs/2104.00954","pdf":"https://arxiv.org/pdf/2104.00954"},"orgs":["google-deepmind","met-office","university-of-reading"],"topic":"nowcasting","topics":["probabilistic-ensembles"],"type":"model","method":["gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"operational","summary":"DGMR, a deep generative model of radar, produces skillful 5-90 minute precipitation nowcasts that Met Office experts ranked first in 88% of cases.","significance":8,"cited_by":1015,"score":100,"highlight":true,"highlight_reason":"DGMR, a landmark Nature paper on generative radar nowcasting validated by Met Office forecasters; became the reference baseline for probabilistic nowcasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.47236-2594-7036.2021.v5.i2.131-146p","title":"A Precipitation forecasting in central ecotone region in Brazil using artificial neural networks and public climatic data","authors":["Tiago da Silva Almeida","Hudson Pena Magalhães"],"date":"2021-04-01","year":2021,"venue":"Revista Sítio Novo","venue_type":"journal","ids":{"doi":"10.47236/2594-7036.2021.v5.i2.131-146p","openalex":"W3146487173"},"links":{"paper":"https://doi.org/10.47236/2594-7036.2021.v5.i2.131-146p","pdf":"https://sitionovo.ifto.edu.br/index.php/sitionovo/article/download/919/308"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Multilayer perceptrons with ENSO indices forecast weekly precipitation at six Tocantins, Brazil stations, with 33.38 mm/week test RMSE.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-20-0219.1","title":"Statistical Postprocessing of Wind Speed Forecasts Using Convolutional Neural Networks","authors":["Simon Veldkamp","Kirien Whan","Sjoerd Dirksen","Maurice Schmeits"],"date":"2021-04-01","year":2021,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"arxiv":"2007.04005","doi":"10.1175/mwr-d-20-0219.1","openalex":"W3042212860"},"links":{"paper":"https://doi.org/10.1175/mwr-d-20-0219.1"},"orgs":["knmi"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"CNNs postprocess HARMONIE-AROME wind speed forecasts over the Netherlands using full spatial patterns, improving CRPS and Brier skill over fully connected networks and quantile regression forests at 48 h.","significance":3,"cited_by":62,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2020wr029308","title":"Deep Learning for Daily Precipitation and Temperature Downscaling","authors":["Fang Wang","Di Tian","Lisa L. Lowe","Latif Kalin","John C. Lehrter"],"date":"2021-04-01","year":2021,"venue":"Water Resources Research","venue_type":"journal","ids":{"doi":"10.1029/2020wr029308","openalex":"W3154650405"},"links":{"paper":"https://doi.org/10.1029/2020wr029308","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020WR029308"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"SRDRN residual CNN downscales daily precipitation and temperature from 100 km to 4 km, reproduces extremes, and transfers across regions.","significance":4,"cited_by":231,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12517-021-06997-5","title":"Tropical cyclone intensity classification from infrared images of clouds over Bay of Bengal and Arabian Sea using machine learning classifiers","authors":["Chinmoy Kar","Sreeparna Banerjee"],"date":"2021-04-01","year":2021,"venue":"Arabian Journal of Geosciences","venue_type":"journal","ids":{"doi":"10.1007/s12517-021-06997-5","openalex":"W3152764939"},"links":{"paper":"https://doi.org/10.1007/s12517-021-06997-5"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Machine learning classifiers categorize tropical cyclone intensity from infrared cloud images over the Bay of Bengal and Arabian Sea.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.02573","title":"Prediction of Solar Radiation Using Artificial Neural Network","authors":["Shahriar Rahman","Shazzadur Rahman","A K M Bahalul Haque"],"date":"2021-04-01","year":2021,"venue":"Journal of Physics: Conference Series , 2021","venue_type":"journal","ids":{"arxiv":"2104.02573","doi":"10.1088/1742-6596/1767/1/012041"},"links":{"paper":"https://arxiv.org/abs/2104.02573","pdf":"https://arxiv.org/pdf/2104.02573"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An artificial neural network predicts hourly solar radiation from station weather variables such as temperature, humidity, wind and pressure, reporting MAE and MSE.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.00615","title":"Physics-informed neural networks for the shallow-water equations on the sphere","authors":["Alex Bihlo","Roman O. Popovych"],"date":"2021-04-01","year":2021,"venue":"J. Comp. Phys. 456 (2022), 111024","venue_type":"journal","ids":{"arxiv":"2104.00615","doi":"10.1016/j.jcp.2022.111024"},"links":{"paper":"https://arxiv.org/abs/2104.00615","pdf":"https://arxiv.org/pdf/2104.00615"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Physics-informed neural networks solve shallow-water equations on the sphere using a sequence of time-window networks and a boundary-encoding layer, tested on Williamson cases.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.00430","title":"Latent Space Data Assimilation by using Deep Learning","authors":["Mathis Peyron","Anthony Fillion","Selime Gürol","Victor Marchais","Serge Gratton","Pierre Boudier","Gael Goret"],"date":"2021-04-01","year":2021,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"arxiv":"2104.00430","doi":"10.1002/qj.4153","openalex":"W3144434902"},"links":{"paper":"https://doi.org/10.1002/qj.4153","pdf":"https://arxiv.org/pdf/2104.00430"},"orgs":["nvidia"],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"An autoencoder latent-space ensemble Kalman filter with a neural surrogate reduces data assimilation cost and beats ETKF-Q on an augmented Lorenz 96 system.","significance":3,"cited_by":68,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2021.3068069","title":"Gap-Filling Satellite Land Surface Temperature Over Heatwave Periods With Machine Learning","authors":["Isaac Buo","Valentina Sagris","Jaak Jaagus"],"date":"2021-03-31","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2021.3068069","openalex":"W3150849752"},"links":{"paper":"https://doi.org/10.1109/lgrs.2021.3068069"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Random forest fills cloud-caused gaps in satellite land surface temperature during heatwaves using land cover, elevation and vegetation indices.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2021-6664413","title":"Prediction of Short-Time Rainfall Based on Deep Learning","authors":["Dechao Sun","Jiali Wu","Hong Huang","Renfang Wang","Feng Liang","Hong Xinhua"],"date":"2021-03-30","year":2021,"venue":"Mathematical Problems in Engineering","venue_type":"journal","ids":{"doi":"10.1155/2021/6664413","openalex":"W3146080885"},"links":{"paper":"https://doi.org/10.1155/2021/6664413","pdf":"https://downloads.hindawi.com/journals/mpe/2021/6664413.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Conv3D-GRU encodes radar echo sequences to predict rainfall intensity 1–2 hours ahead, improving short-term heavy rainfall accuracy over baselines.","significance":3,"cited_by":51,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.advwatres.2021.103907","title":"A novel hybrid artificial neural network - Parametric scheme for postprocessing medium-range precipitation forecasts","authors":["Mohammadvaghef Ghazvinian","Yu Zhang","Dong‐Jun Seo","Minxue He","Nelun Fernando"],"date":"2021-03-30","year":2021,"venue":"Advances in Water Resources","venue_type":"journal","ids":{"doi":"10.1016/j.advwatres.2021.103907","openalex":"W3140878669"},"links":{"paper":"https://doi.org/10.1016/j.advwatres.2021.103907","pdf":"https://www.sciencedirect.com/science/article/am/pii/S0309170821000622?via%3Dihub"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Hybrid neural network and parametric scheme for post-processing medium-range precipitation forecasts; abstract unavailable, so classification rests on the title.","significance":3,"cited_by":54,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.16180","title":"Prediction of Landfall Intensity, Location, and Time of a Tropical Cyclone","authors":["Sandeep Kumar","Koushik Biswas","Ashish Kumar Pandey"],"date":"2021-03-30","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.16180"},"links":{"paper":"https://arxiv.org/abs/2103.16180","pdf":"https://arxiv.org/pdf/2103.16180"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"LSTM on best-track data predicts North Indian Ocean landfall intensity, location and time; 24-hour input gives 4.24-knot and 51.7 km errors.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.16108","title":"Predicting Landfall's Location and Time of a Tropical Cyclone Using Reanalysis Data","authors":["Sandeep Kumar","Koushik Biswas","Ashish Kumar Pandey"],"date":"2021-03-30","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.16108"},"links":{"paper":"https://arxiv.org/abs/2103.16108","pdf":"https://arxiv.org/pdf/2103.16108"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["global"],"data":["era5"],"status":"research","summary":"CNN-LSTM predicts tropical cyclone landfall location and time from 9–21 hours of ERA5 data, with location errors of 66–159 km across six basins.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1098-rsta.2020.0071","title":"The importance of uncertainty quantification in model reproducibility","authors":["Victoria Volodina","Peter Challenor"],"date":"2021-03-29","year":2021,"venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","venue_type":"journal","ids":{"doi":"10.1098/rsta.2020.0071","openalex":"W3148450921"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0071"},"orgs":["alan-turing-institute"],"topic":"xai-uq-physics","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Applies Gaussian process emulators and history matching to global parameter search in a climate model, framing uncertainty quantification as essential for model reproducibility.","significance":3,"cited_by":54,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.cam.2021.113451","title":"Machine learning feature analysis illuminates disparity between E3SM climate models and observed climate change","authors":["J. Jake Nichol","Matthew Gregor Peterson","Kara Peterson","G. Matthew Fricke","Melanie E. Moses"],"date":"2021-03-29","year":2021,"venue":"Journal of Computational and Applied Mathematics","venue_type":"journal","ids":{"doi":"10.1016/j.cam.2021.113451","openalex":"W3147885337"},"links":{"paper":"https://doi.org/10.1016/j.cam.2021.113451"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Applies machine learning feature analysis to E3SM climate model output to explain its disparity with observed climate change; abstract unavailable.","significance":2,"cited_by":35,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.15235","title":"KNN, An Underestimated Model for Regional Rainfall Forecasting","authors":["Ning Yu","Timothy Haskins"],"date":"2021-03-28","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.15235"},"links":{"paper":"https://arxiv.org/abs/2103.15235","pdf":"https://arxiv.org/pdf/2103.15235"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Compares classical and deep learning models for regional rainfall forecasting in Upstate New York catchments; KNN best at handling precipitation uncertainty.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.engappai.2021.104233","title":"Interpretable tropical cyclone intensity estimation using Dvorak-inspired machine learning techniques","authors":["Yu‐Ju Lee","David Hall","Quan Liu","Wen-Wei Liao","Ming-Chun Huang"],"date":"2021-03-27","year":2021,"venue":"Engineering Applications of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1016/j.engappai.2021.104233","openalex":"W3142405176"},"links":{"paper":"https://doi.org/10.1016/j.engappai.2021.104233"},"orgs":["noaa"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":[],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Interpretable machine learning methods inspired by the Dvorak technique estimate tropical cyclone intensity from satellite imagery; the abstract is unavailable, so details are limited.","significance":3,"cited_by":28,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3066299","title":"Tropical Cyclone Intensity Estimation From Geostationary Satellite Imagery Using Deep Convolutional Neural Networks","authors":["Chong Wang","Gang Zheng","Xiaofeng Li","Qing Xu","Bin Liu","Jun A. Zhang"],"date":"2021-03-26","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3066299","openalex":"W3143274035"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3066299"},"orgs":["noaa"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"CNNs estimate western North Pacific tropical cyclone intensity from Himawari-8 infrared images, reaching 88.9% accuracy and 4.62 m/s RMSE with focal loss and binary framing.","significance":4,"cited_by":104,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jclepro.2021.126776","title":"Weather radar echo prediction method based on convolution neural network and Long Short-Term memory networks for sustainable e-agriculture","authors":["Lei Zhang","Zhenyue Huang","Wei Liu","Zhongli Guo","Zhe Zhang"],"date":"2021-03-26","year":2021,"venue":"Journal of Cleaner Production","venue_type":"journal","ids":{"doi":"10.1016/j.jclepro.2021.126776","openalex":"W3140593863"},"links":{"paper":"https://doi.org/10.1016/j.jclepro.2021.126776"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"CNN-LSTM model predicts weather radar echoes for agricultural applications; nowcasting from radar sequences is the core contribution.","significance":2,"cited_by":76,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.14430","title":"Combining distribution-based neural networks to predict weather forecast probabilities","authors":["Mariana Clare","Omar Jamil","Cyril Morcrette"],"date":"2021-03-26","year":2021,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"arxiv":"2103.14430","doi":"10.1002/qj.4180","openalex":"W3143333732"},"links":{"paper":"https://doi.org/10.1002/qj.4180","pdf":"https://arxiv.org/pdf/2103.14430","code":"https://github.com/mc4117/ResNet_Weather"},"orgs":["met-office"],"topic":"probabilistic-ensembles","topics":["global-medium-range"],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Neural networks predict full probability density functions for WeatherBench geopotential and temperature at 3 and 5 days, stacked into a combined forecast that beats some NWP models.","significance":3,"cited_by":52,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2021.02.033","title":"A deep learning model for intra-day forecasting of solar irradiance using satellite-based estimations in the vicinity of a PV power plant","authors":["Emilio Pérez","J. M. Alonso Pérez","Jorge Segarra-Tamarit","Héctor Beltrán"],"date":"2021-03-25","year":2021,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2021.02.033","openalex":"W3147053664"},"links":{"paper":"https://doi.org/10.1016/j.solener.2021.02.033"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Deep learning forecasts intra-day solar irradiance from satellite-derived estimates near a PV plant, a short-horizon nowcasting application.","significance":2,"cited_by":59,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-x5q893","title":"Prediction of rapid intensification of tropical cyclones with deep learning","authors":["Sambatra Andrianomena","Mika H. Rafieferantsoa","Holifidy Rapanoel","Rondrotiana Barimalala"],"date":"2021-03-23","year":2021,"venue_type":"other","ids":{"doi":"10.31223/x5q893","openalex":"W3139453002"},"links":{"paper":"https://doi.org/10.31223/x5q893","pdf":"http://eartharxiv.org/repository/object/2195/download/4546/"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"CNN classifiers (VGG, ResNet, Xception) on satellite imagery detect tropical cyclone rapid intensification, with Xception reaching ROC-AUC 0.911 and FAR 0.182.","significance":4,"cited_by":0,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2020.3041760","title":"DeepDT: Generative Adversarial Network for High-Resolution Climate Prediction","authors":["Jianxin Cheng","Jin Liu","Qiuming Kuang","Zhou Xu","Chenkai Shen","Wang Liu","Kang Zhou"],"date":"2021-03-23","year":2021,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2020.3041760","openalex":"W3138469499"},"links":{"paper":"https://doi.org/10.1109/lgrs.2020.3041760"},"orgs":["cma"],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"DeepDT trains a GAN with separate generator and discriminator steps to reduce artifacts in CNN-based climate downscaling, outperforming most CNN baselines.","significance":2,"cited_by":20,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.uclim.2021.100820","title":"Investigation of urban climates and built environment relations by using machine learning","authors":["Mustafa Koc","Aktan Acar"],"date":"2021-03-23","year":2021,"venue":"Urban Climate","venue_type":"journal","ids":{"doi":"10.1016/j.uclim.2021.100820","openalex":"W3137708158"},"links":{"paper":"https://doi.org/10.1016/j.uclim.2021.100820"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Uses machine learning to relate urban climate to built environment features; abstract unavailable, so scope is inferred from the title.","significance":2,"cited_by":27,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7113","title":"Identification and inter‐comparison of appropriate long‐term precipitation datasets using decision tree model and statistical matrix over China","authors":["Muhammad Abrar Faiz","Yongqiang Zhang","Faisal Baig","Dariusz Wrzesiński","Farah Naz"],"date":"2021-03-23","year":2021,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7113","openalex":"W3137981130"},"links":{"paper":"https://doi.org/10.1002/joc.7113"},"orgs":[],"topic":"benchmarks-data-eval","topics":["observations-remote-sensing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"A fast-frugal decision tree ranks seven long-term precipitation datasets against 813 China gauge grids, placing APHRODITE first; machine learning is a light evaluation tool.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.12434","title":"Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery","authors":["Manu Tom","Tianyu Wu","Emmanuel Baltsavias","Konrad Schindler"],"date":"2021-03-23","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.12434"},"links":{"paper":"https://arxiv.org/abs/2103.12434","pdf":"https://arxiv.org/pdf/2103.12434"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"Supervised classifier on 20 years of MODIS imagery maps Swiss mountain lake ice, finding freeze duration falling about 0.8 days per year.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-20-0169.1","title":"Monthly rainfall forecasting using temperature and climate indices through a hybrid method in Queensland, Australia","authors":["Meysam Ghamariadyan","Monzur Alam Imteaz"],"date":"2021-03-22","year":2021,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-20-0169.1","openalex":"W3138821319"},"links":{"paper":"https://doi.org/10.1175/jhm-d-20-0169.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/hydr/22/5/JHM-D-20-0169.1.pdf"},"orgs":[],"topic":"local-forecasting","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Wavelet neural networks forecast monthly rainfall at Queensland stations up to 12 months ahead, reducing three-month RMSE to 38.6 mm versus 72.2 mm for plain ANN.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2021jd034604","title":"Evaluating Variations in Tropical Cyclone Precipitation in Eastern Mexico Using Machine Learning Techniques","authors":["Laiyin Zhu","Pascual Aguilera"],"date":"2021-03-20","year":2021,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2021jd034604","openalex":"W3121620620"},"links":{"paper":"https://doi.org/10.1029/2021jd034604"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Random forest over a 99-year climatology identifies drivers of tropical cyclone precipitation in eastern Mexico, with distance to track the strongest predictor for events.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.neucom.2021.02.072","title":"SCENT: A new precipitation nowcasting method based on sparse correspondence and deep neural network","authors":["Wei Fang","Feihong Zhang","Victor S. Sheng","Yewen Ding"],"date":"2021-03-19","year":2021,"venue":"Neurocomputing","venue_type":"journal","ids":{"doi":"10.1016/j.neucom.2021.02.072","openalex":"W3137229174"},"links":{"paper":"https://doi.org/10.1016/j.neucom.2021.02.072"},"orgs":["nuist"],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"SCENT pairs sparse correspondence tracking with a deep network for precipitation nowcasting; abstract unavailable, so the classification rests on the title.","significance":2,"cited_by":20,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jastp.2021.105614","title":"Novel statistical downscaling emulator for precipitation projections using deep Convolutional Autoencoder over Northern Africa","authors":["Hassen Babaousmail","Rongtao Hou","Gnim Tchalim Gnitou","Brian Odhiambo Ayugi"],"date":"2021-03-19","year":2021,"venue":"Journal of Atmospheric and Solar-Terrestrial Physics","venue_type":"journal","ids":{"doi":"10.1016/j.jastp.2021.105614","openalex":"W3137285346"},"links":{"paper":"https://doi.org/10.1016/j.jastp.2021.105614"},"orgs":["nuist"],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Deep convolutional autoencoder emulates statistical downscaling of precipitation projections over Northern Africa; abstract unavailable.","significance":2,"cited_by":22,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002423","title":"Process‐Based Climate Model Development Harnessing Machine Learning: III. The Representation of Cumulus Geometry and Their 3D Radiative Effects","authors":["Najda Villefranque","Danny Williamson","Fleur Couvreux","F. Hourdin","Jacques Gautrais A","Richard Fournier","Robin James Hogan","Stéphane Blanco","Victoria Volodina"],"date":"2021-03-18","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002423","openalex":"W3108134949"},"links":{"paper":"https://doi.org/10.1029/2020ms002423","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002423"},"orgs":["ecmwf","meteo-france","alan-turing-institute"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Calibrates cloud geometry parameters for 3D radiation using ML surrogate emulators, reducing top-of-atmosphere and surface flux errors from about 10 to 5 W/m2.","significance":3,"cited_by":21,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10506533.1","title":"Machine learning prediction of the Madden-Julian Oscillation","authors":["Riccardo Silini","Marcelo Barreiro","Cristina Masoller"],"date":"2021-03-18","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10506533.1","openalex":"W4252790117"},"links":{"paper":"https://doi.org/10.1002/essoar.10506533.1"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["other"],"status":"research","summary":"Artificial neural networks predict the Madden-Julian Oscillation with about 26-27 days average skill, reaching 60+ days for some initial phases, competitive with dynamical models.","significance":4,"cited_by":1,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.10005","title":"Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset","authors":["Antonios Mamalakis","Imme Ebert-Uphoff","Elizabeth A. Barnes"],"date":"2021-03-18","year":2021,"venue":"Environmental Data Science, 1, E8 (2022)","venue_type":"journal","ids":{"arxiv":"2103.10005","doi":"10.1017/eds.2022.7","openalex":"W3138147141"},"links":{"paper":"https://arxiv.org/abs/2103.10005","pdf":"https://arxiv.org/pdf/2103.10005"},"orgs":["colorado-state-university"],"topic":"xai-uq-physics","topics":[],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Synthetic attribution benchmark for XAI in generic geoscience regression problems; not specifically about weather or climate.","significance":2,"cited_by":101,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.21203-rs.3.rs-317538-v1","title":"Improving annual precipitation prediction using extreme learning machine with wavelet packet decomposition","authors":["Hua Wang","Wenchuan Wang","Yujin Du","Dongmei Xu","Yiduo Zhang"],"date":"2021-03-17","year":2021,"venue":"Research Square","venue_type":"preprint","ids":{"doi":"10.21203/rs.3.rs-317538/v1","openalex":"W3153174798"},"links":{"paper":"https://doi.org/10.21203/rs.3.rs-317538/v1","pdf":"https://www.researchsquare.com/article/rs-317538/latest.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["other"],"status":"research","summary":"Improves annual precipitation prediction by combining wavelet packet decomposition with extreme learning machines; abstract unavailable, so details are limited.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.7100","title":"Development and evaluation of pre and post integration techniques for enhancing drought predictions over India","authors":["Venkatesh Kolluru","Srinivas Kolluru"],"date":"2021-03-17","year":2021,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.7100","openalex":"W3138624676"},"links":{"paper":"https://doi.org/10.1002/joc.7100"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","era5","stations"],"status":"research","summary":"Tests 13 machine learning algorithms with pre- and post-integration of satellite precipitation products for drought indices over India; Bayesian-regularized neural networks perform best.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.09743","title":"Deep Learning-based Extreme Heatwave Forecast","authors":["Valérian Jacques-Dumas","Francesco Ragone","Pierre Borgnat","Patrice Abry","Freddy Bouchet"],"date":"2021-03-17","year":2021,"venue":"Frontiers in Climate","venue_type":"journal","ids":{"arxiv":"2103.09743","doi":"10.3389/fclim.2022.789641","openalex":"W3137094912"},"links":{"paper":"https://arxiv.org/abs/2103.09743","pdf":"https://arxiv.org/pdf/2103.09743"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"CNN trained on climate model output forecasts long-lasting extreme heatwaves up to 15 days ahead, using class-imbalance undersampling and transfer learning.","significance":3,"cited_by":90,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2020gl091912","title":"Using Video Recognition to Identify Tropical Cyclone Positions","authors":["Mohan Smith","Ralf Toumi"],"date":"2021-03-16","year":2021,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl091912","openalex":"W3137998335"},"links":{"paper":"https://doi.org/10.1029/2020gl091912","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020GL091912"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Video-based CNN with ConvLSTM locates tropical cyclone centers from hourly geostationary infrared sequences, giving a 19.3 km median error and 42% lower error than baseline.","significance":4,"cited_by":13,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.09360","title":"Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers","authors":["Ashesh Chattopadhyay","Mustafa Mustafa","Pedram Hassanzadeh","Eviatar Bach","Karthik Kashinath"],"date":"2021-03-16","year":2021,"venue":"Geoscientific Model Development, 15(5), 2022, 2221-2237","venue_type":"journal","ids":{"arxiv":"2103.09360","doi":"10.5194/gmd-15-2221-2022","openalex":"W4220664202"},"links":{"paper":"https://arxiv.org/abs/2103.09360","pdf":"https://arxiv.org/pdf/2103.09360"},"orgs":["lbnl-nersc"],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["cnn","other"],"timescale":["short"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Equivariance-preserving U-STN networks improve data-driven Z500 forecasts by 45% over U-Nets, and coupling them with ensemble Kalman data assimilation gives stable cycles under high observation noise.","significance":4,"cited_by":58,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.08761","title":"Modeling Weather-induced Home Insurance Risks with Support Vector Machine Regression","authors":["Asim K. Dey","Vyacheslav Lyubchich","Yulia R. Gel"],"date":"2021-03-15","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.08761"},"links":{"paper":"https://arxiv.org/abs/2103.08761","pdf":"https://arxiv.org/pdf/2103.08761"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Applies support vector regression to model precipitation-driven home insurance claims in a Canadian city; low-significance sector application.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.scib.2021.03.009","title":"Unified deep learning model for El Niño/Southern Oscillation forecasts by incorporating seasonality in climate data","authors":["Yoo‐Geun Ham","Jeong-Hwan Kim","Eun-Sol Kim","Kyoung-Woon On"],"date":"2021-03-14","year":2021,"venue":"中国科学通报：英文版","venue_type":"journal","ids":{"doi":"10.1016/j.scib.2021.03.009","openalex":"W3138422838"},"links":{"paper":"https://doi.org/10.1016/j.scib.2021.03.009","pdf":"https://www.sciencedirect.com/science/article/pii/S2095927321002243/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["s2s","seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"An all-season CNN for ENSO forecasts improves boreal spring skill and keeps predictions consistent across seasons and lead times.","significance":4,"cited_by":87,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020jc016988","title":"Tropical Cyclone Wind Speed Estimation From Satellite Altimeter‐Derived Ocean Parameters","authors":["Syarawi M. H. Sharoni","Mohd Nadzri Md Reba","Mohammad Shawkat Hossain"],"date":"2021-03-13","year":2021,"venue":"Journal of Geophysical Research Oceans","venue_type":"journal","ids":{"doi":"10.1029/2020jc016988","openalex":"W3138262265"},"links":{"paper":"https://doi.org/10.1029/2020jc016988"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Regression and neural network models using Jason altimeter ocean parameters estimate tropical cyclone 10 m winds up to 35 m/s with 1 m/s accuracy.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w13060776","title":"Improving Radar-Based Rainfall Forecasts by Long Short-Term Memory Network in Urban Basins","authors":["Duc Hai Nguyen","Jeong‐Bae Kim","Deg‐Hyo Bae"],"date":"2021-03-12","year":2021,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w13060776","openalex":"W3138337159"},"links":{"paper":"https://doi.org/10.3390/w13060776","pdf":"https://www.mdpi.com/2073-4441/13/6/776/pdf?version=1616041992"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"LSTM post-processes MAPLE radar nowcasts for 180-minute rainfall at 13 urban stations in South Korea, outperforming MLR, MARS, MLP and basic RNN baselines.","significance":3,"cited_by":21,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2021.223","title":"Statistical downscaling using principal component regression for climate change impact assessment at the Cauvery river basin","authors":["P. Loganathan","Amit Baburao Mahindrakar"],"date":"2021-03-12","year":2021,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2021.223","openalex":"W3137146693"},"links":{"paper":"https://doi.org/10.2166/wcc.2021.223","pdf":"https://iwaponline.com/jwcc/article-pdf/12/6/2314/934475/jwc0122314.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Applies principal component regression to downscale 26 CMIP5 models over the Cauvery basin and ranks them by precipitation skill; modest machine learning novelty.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.07028","title":"Stable Emulation of an Entire Suite of Model Physics in a State-of-the-Art GCM using a Neural Network","authors":["Alexei Belochitski","Vladimir Krasnopolsky"],"date":"2021-03-12","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.07028","openalex":"W4287273057"},"links":{"paper":"https://arxiv.org/abs/2103.07028","pdf":"https://arxiv.org/pdf/2103.07028"},"orgs":[],"topic":"hybrid-parameterization","topics":["global-medium-range","climate-emulation"],"type":"model","method":["other"],"timescale":["medium","climate"],"spatial":["global"],"data":["nwp-analysis","other"],"status":"research","summary":"A single shallow neural network emulates the full atmospheric physics suite in NCEP GFS, remaining stable for medium-range forecasts and a year-long AMIP run with realistic output and speedup.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.07024","title":"Robustness of Neural Network Emulations of Radiative Transfer Parameterizations in a State-of-the-Art General Circulation Model","authors":["Alexei Belochitski","Vladimir Krasnopolsky"],"date":"2021-03-12","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"2103.07024","doi":"10.5194/gmd-14-7425-2021","openalex":"W3137215208"},"links":{"paper":"https://doi.org/10.5194/gmd-14-7425-2021","pdf":"https://arxiv.org/pdf/2103.07024"},"orgs":["noaa"],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"evaluation","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Shows shallow-network emulators of radiative transfer, built for an older GCM, stay stable and realistic when transplanted into a newer state-of-the-art GCM under AMIP-like runs.","significance":4,"cited_by":36,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21061981","title":"RN-Net: A Deep Learning Approach to 0–2 Hour Rainfall Nowcasting Based on Radar and Automatic Weather Station Data","authors":["Fuhan Zhang","Xiaodong Wang","Jiping Guan","Meihan Wu","Lina Guo"],"date":"2021-03-11","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21061981","openalex":"W3134265440"},"links":{"paper":"https://doi.org/10.3390/s21061981","pdf":"https://www.mdpi.com/1424-8220/21/6/1981/pdf?version=1615954716"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Dual-encoder RNN fuses radar mosaics and station rainfall for 0–2 hour grid nowcasts, reaching 0.523 threat score at 0.5 h, about 3–4 times WRF.","significance":3,"cited_by":42,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32629-jai.v4i1.483","title":"Principle of Machine Learning and Its Potential Application in Cli-mate Prediction","authors":["Shengping He","Huijun Wang","Hua Li","Jiazhen Zhao"],"date":"2021-03-11","year":2021,"venue":"Journal of Autonomous Intelligence","venue_type":"journal","ids":{"doi":"10.32629/jai.v4i1.483","openalex":"W4285481359"},"links":{"paper":"https://doi.org/10.32629/jai.v4i1.483"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"review","method":["cnn","classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Tutorial on machine learning basics, with a CNN applied to East Asian winter monthly temperature and compared against a dynamical model; no headline numeric result.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7220757615","title":"Prediksi Cuaca Kota Denpasar menggunakan Algoritma ELM dengan Optimasi Quantum Delta Particle Swarm Optimization","authors":["Adam Sulthoni Akbar","Candra Dewi Dewi","Randy Cahya Wihandika"],"date":"2021-03-09","year":2021,"venue":"Jurnal Pengembangan Teknologi dan Ilmu Komputer","venue_type":"journal","ids":{"openalex":"W7220757615"},"links":{"paper":"https://j-ptiik.ub.ac.id/index.php/index/article/view/8746"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Uses Extreme Learning Machine with quantum delta PSO to predict Denpasar weather; reports 100% accuracy on a small, unvalidated dataset.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-14-1941-2021","title":"Using machine learning to model uncertainty for water vapor atmospheric motion vectors","authors":["Joaquim Teixeira","Hai Nguyen","Derek J. Posselt","Hui Su","Longtao Wu"],"date":"2021-03-09","year":2021,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-14-1941-2021","openalex":"W3135147573"},"links":{"paper":"https://doi.org/10.5194/amt-14-1941-2021","pdf":"https://amt.copernicus.org/articles/14/1941/2021/amt-14-1941-2021.pdf"},"orgs":["nasa","caltech"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"Random forest combined with Gaussian mixture clustering characterizes bias and standard error of water vapour atmospheric motion vectors, addressing a known gap in uncertainty estimation.","significance":3,"cited_by":15,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-19-0274.1","title":"Random Forest Model to Assess Predictor Importance and Nowcast Severe Storms using High-Resolution Radar–GOES Satellite–Lightning Observations","authors":["John R. Mecikalski","Thea N. Sandmæl","Elisa M. Murillo","Cameron R. Homeyer","Kristopher M. Bedka","Jason M. Apke","Christopher P. Jewett"],"date":"2021-03-08","year":2021,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-19-0274.1","openalex":"W3135212186"},"links":{"paper":"https://doi.org/10.1175/mwr-d-19-0274.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/149/6/MWR-D-19-0274.1.pdf"},"orgs":["nasa","colorado-state-university","university-of-oklahoma"],"topic":"nowcasting","topics":["observations-remote-sensing","extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Random forests combining GOES-16 satellite, lightning and radar fields improve severe storm warning prediction over radar alone, identifying cloud-top divergence as most informative.","significance":3,"cited_by":35,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.04885","title":"Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder","authors":["Takuya Kurihana","Elisabeth Moyer","Rebecca Willett","Davis Gilton","Ian Foster"],"date":"2021-03-08","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing, 2021","venue_type":"journal","ids":{"arxiv":"2103.04885","doi":"10.1109/tgrs.2021.3098008","openalex":"W3133596514"},"links":{"paper":"https://arxiv.org/abs/2103.04885","pdf":"https://arxiv.org/pdf/2103.04885"},"orgs":["university-of-chicago"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Rotation-invariant autoencoder (RICC) clusters satellite cloud imagery without predefined classes, with evaluation showing physically meaningful, spatially coherent and orientation-invariant cloud clusters.","significance":4,"cited_by":27,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.04530","title":"Weather Analogs with a Machine Learning Similarity Metric for Renewable Resource Forecasting","authors":["Weiming Hu","Guido Cervone","George Young","Luca Delle Monache"],"date":"2021-03-08","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.04530"},"links":{"paper":"https://arxiv.org/abs/2103.04530","pdf":"https://arxiv.org/pdf/2103.04530"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis"],"status":"research","summary":"A neural-network similarity metric replaces hand-tuned distances in analog ensembles, improving wind speed and solar irradiance forecasts over Euclidean-distance analogs.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13051004","title":"Regional Zenith Tropospheric Delay Modeling Based on Least Squares Support Vector Machine Using GNSS and ERA5 Data","authors":["Song Li","Tianhe Xu","Nan Jiang","Honglei Yang","Shuaimin Wang","Zhen Zhang"],"date":"2021-03-06","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13051004","openalex":"W3134030007"},"links":{"paper":"https://doi.org/10.3390/rs13051004","pdf":"https://www.mdpi.com/2072-4292/13/5/1004/pdf?version=1615351364"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Builds least-squares SVM regional zenith tropospheric delay models over Europe from GNSS and ERA5, with the best scheme reaching 9 mm RMSE.","significance":3,"cited_by":33,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12030343","title":"A Novel Convective Storm Location Prediction Model Based on Machine Learning Methods","authors":["Hansoo Lee","Jonggeun Kim","Eun Kyeong Kim","Sungshin Kim"],"date":"2021-03-06","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12030343","openalex":"W3135377703"},"links":{"paper":"https://doi.org/10.3390/atmos12030343","pdf":"https://www.mdpi.com/2073-4433/12/3/343/pdf?version=1615887381"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Machine learning models trained on temporal properties of radar convective storms predict their future locations, showing usable nowcasts with slight error.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10596-021-10037-2","title":"Trajectory prediction based on long short-term memory network and Kalman filter using hurricanes as an example","authors":["Wanting Qin","Jun Tang","Cong Da Lu","Songyang Lao"],"date":"2021-03-05","year":2021,"venue":"Computational Geosciences","venue_type":"journal","ids":{"doi":"10.1007/s10596-021-10037-2","openalex":"W3135808047"},"links":{"paper":"https://doi.org/10.1007/s10596-021-10037-2","pdf":"https://link.springer.com/content/pdf/10.1007/s10596-021-10037-2.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short","medium"],"spatial":["regional"],"data":["other"],"status":"research","summary":"An LSTM with Kalman filter smoothing predicts Atlantic hurricane tracks from 1851–2016 historical data with the lowest error among compared LSTM variants.","significance":3,"cited_by":27,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-a14030083","title":"Typhoon Intensity Forecasting Based on LSTM Using the Rolling Forecast Method","authors":["Shijin Yuan","Cheng Wang","Bin Mu","Feifan Zhou","Wansuo Duan"],"date":"2021-03-04","year":2021,"venue":"Algorithms","venue_type":"journal","ids":{"doi":"10.3390/a14030083","openalex":"W3134967300"},"links":{"paper":"https://doi.org/10.3390/a14030083","pdf":"https://www.mdpi.com/1999-4893/14/3/83/pdf?version=1615882533"},"orgs":["iap-cas"],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["medium"],"spatial":["regional"],"data":["other"],"status":"research","summary":"An LSTM with rolling forecasts predicts typhoon intensity up to 120 h from historical data and outperforms a feed-forward network on 2015 typhoons.","significance":3,"cited_by":57,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.02157","title":"A Deep and Wide Neural Network-based Model for Rajasthan Summer Monsoon Rainfall (RSMR) Prediction","authors":["Vikas Bajpai","Anukriti Bansal"],"date":"2021-03-03","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.02157"},"links":{"paper":"https://arxiv.org/abs/2103.02157","pdf":"https://arxiv.org/pdf/2103.02157"},"orgs":[],"topic":"s2s-seasonal","topics":["local-forecasting"],"type":"evaluation","method":["cnn","classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other","stations"],"status":"research","summary":"Compares 1D CNN, MLP and Wide-Deep networks for summer monsoon rainfall in Rajasthan using IMD gridded and gauge data; the Wide-Deep model performs best.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21070-pssh.v1i.22","title":"Weather Forecast using Learning Vector Quantization Methods","authors":["Siska Andriani","Kotim Subandi"],"date":"2021-03-02","year":2021,"venue":"Procedia of Social Sciences and Humanities","venue_type":"journal","ids":{"doi":"10.21070/pssh.v1i.22","openalex":"W3167352788"},"links":{"paper":"https://doi.org/10.21070/pssh.v1i.22","pdf":"https://pssh.umsida.ac.id/index.php/pssh/article/download/22/17"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Learning vector quantization neural network for weather forecasting reaches 72% accuracy; a small, locally scoped study with limited novelty.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.01479","title":"Statistical Post-Processing for Gridded Temperature Prediction Using Encoder-Decoder-Based Deep Convolutional Neural Networks","authors":["Atsushi Kudo"],"date":"2021-03-02","year":2021,"venue":"Journal of the Meteorological Society of Japan Ser II","venue_type":"journal","ids":{"arxiv":"2103.01479","doi":"10.2151/jmsj.2022-011","openalex":"W3133620062"},"links":{"paper":"https://doi.org/10.2151/jmsj.2022-011","pdf":"https://arxiv.org/pdf/2103.01479"},"orgs":["jma"],"topic":"post-processing","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"An encoder-decoder CNN post-processes NWP output to produce gridded surface temperatures over Kanto, correcting front position errors and extreme temperatures better than the operational Kalman-filter guidance.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5902-2179460x43258","title":"Application of RBF artificial neural networks to precipitation and temperature forecasting in Paraná, Brazil","authors":["Carla Milléo","Ricardo Carvalho de Almeida"],"date":"2021-03-01","year":2021,"venue":"Ciência e Natura","venue_type":"journal","ids":{"doi":"10.5902/2179460x43258","openalex":"W4293165932"},"links":{"paper":"https://doi.org/10.5902/2179460x43258","pdf":"https://periodicos.ufsm.br/cienciaenatura/article/download/43258/46009"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["local"],"data":["stations"],"status":"research","summary":"RBF neural networks forecast monthly temperature and precipitation for Paraná, Brazil, with best skill for temperature and 3-month smoothed series.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-5.0038429","title":"Comparative study of data-driven short-term wind power forecasting approaches for the Norwegian Arctic region","authors":["Hao Chen","Yngve Birkelund","Stian Normann Anfinsen","Fuqing Yuan"],"date":"2021-03-01","year":2021,"venue":"Journal of Renewable and Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1063/5.0038429","openalex":"W3159458251"},"links":{"paper":"https://doi.org/10.1063/5.0038429"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Comparison of nine machine learning methods for short-term wind power forecasting at five Arctic farms; NWP wind inputs give an edge over univariate models for 1 to 6 hours.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.1986","title":"Predicting origins of coherent air mass trajectories using a neural network—the case of dry intrusions","authors":["Vered Silverman","Stav Nahum","Shira Raveh‐Rubin"],"date":"2021-03-01","year":2021,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.1986","openalex":"W3157050139"},"links":{"paper":"https://doi.org/10.1002/met.1986","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.1986"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Segmentation neural network identifies dry intrusion origins from ERA-Interim geopotential height alone, enabling detection in climate datasets lacking wind fields.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.1978","title":"Estimation of precipitation induced by tropical cyclones based on machine‐learning‐enhanced analogue identification of numerical prediction","authors":["Yuanyuan Liu","Lei Li","Yesen Liu","Pak Wai Chan","Wen‐Hai Zhang","Li Zhang"],"date":"2021-03-01","year":2021,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.1978","openalex":"W3133929378"},"links":{"paper":"https://doi.org/10.1002/met.1978","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.1978"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"ML-enhanced analogue method using LLE reduces NWP precipitation error for tropical cyclones at Shenzhen, improving on raw NWP and traditional analogue approaches.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10506356.1","title":"Predicting the MJO using interpretable machine-learning models","authors":["Zane Martin","Elizabeth A. Barnes","Eric Daniel Maloney"],"date":"2021-03-01","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10506356.1","openalex":"W3136570554"},"links":{"paper":"https://doi.org/10.1002/essoar.10506356.1"},"orgs":["colorado-state-university"],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":[],"timescale":["s2s"],"spatial":["global"],"data":["other"],"status":"research","summary":"Interpretable neural networks forecast MJO convection several weeks ahead, using layer-wise relevance propagation to explain sources of predictability compared with dynamical models.","significance":4,"cited_by":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.00318","title":"Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation","authors":["Lucia Minah Yang","Ian Grooms"],"date":"2021-02-27","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.00318","doi":"10.1016/j.jcp.2021.110532"},"links":{"paper":"https://arxiv.org/abs/2103.00318","pdf":"https://arxiv.org/pdf/2103.00318"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Patched autoencoder-based constructed analog ensembles outperform unpatched versions on a 1D toy model, offering a route to scale to global domains.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10506334.1","title":"Semantic Segmentation with Deep Convolutional Neural Networks for Automated Dust Detection in Goes-R Satellite Imagery","authors":["Talha Ali Khan","Nicholas J. Elmer","Muthukumaran Ramasubramanian","Emily B. Berndt","Iksha Gurung","Aaron S. Kaulfus","Manil Maskey","Rahul Ramachandran"],"date":"2021-02-26","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10506334.1","openalex":"W3137978387"},"links":{"paper":"https://doi.org/10.1002/essoar.10506334.1"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A UNet segments airborne dust at night from GOES-16 infrared bands, aiming to support dust storm warnings for forecasters.","significance":2,"cited_by":1,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.13025","title":"Multifidelity Ensemble Kalman Filtering Using Surrogate Models Defined by Physics-Informed Autoencoders","authors":["Andrey A Popov","Adrian Sandu"],"date":"2021-02-25","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.13025"},"links":{"paper":"https://arxiv.org/abs/2102.13025","pdf":"https://arxiv.org/pdf/2102.13025"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Nonlinear physics-informed autoencoder surrogates extend multifidelity ensemble Kalman filtering, outperforming linear surrogates on Lorenz 96 data assimilation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.11192","title":"Variational Data Assimilation with a Learned Inverse Observation Operator","authors":["Thomas Frerix","Dmitrii Kochkov","Jamie A. Smith","Daniel Cremers","Michael P. Brenner","Stephan Hoyer"],"date":"2021-02-22","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.11192"},"links":{"paper":"https://arxiv.org/abs/2102.11192","pdf":"https://arxiv.org/pdf/2102.11192"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"A learned observation-to-state mapping improves variational data assimilation, tested on Lorenz96 and 2D turbulence with better forecast quality.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w13040550","title":"Stepwise Identification of Influencing Factors and Prediction of Typhoon Precipitation in Anhui Province Based on the Back Propagation Neural Network Model","authors":["Yuliang Zhou","Yang Li","Juliang Jin","Ping Zhou","Dong Zhang","Shaowei Ning","Yi Cui"],"date":"2021-02-21","year":2021,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w13040550","openalex":"W3130989615"},"links":{"paper":"https://doi.org/10.3390/w13040550","pdf":"https://www.mdpi.com/2073-4441/13/4/550/pdf?version=1613906065"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Backpropagation neural network with iteratively selected predictors forecasts typhoon precipitation occurrence in Anhui with 100% hindcast and 90% validation accuracy.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.asr.2021.01.054","title":"High temporal resolution global PWV dataset of 2005–2016 by using a neural network approach to determine the mean temperature of the atmosphere","authors":["Pengfei Yang","Qingzhi Zhao","Zufeng Li","Wanqiang Yao","Yibin Yao"],"date":"2021-02-21","year":2021,"venue":"Advances in Space Research","venue_type":"journal","ids":{"doi":"10.1016/j.asr.2021.01.054","openalex":"W3133373236"},"links":{"paper":"https://doi.org/10.1016/j.asr.2021.01.054"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"benchmark","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Builds a global 2005–2016 high-temporal-resolution precipitable water vapour dataset using a neural network to estimate atmospheric mean temperature.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.10570","title":"Symbolic regression for scientific discovery: an application to wind speed forecasting","authors":["Ismail Alaoui Abdellaoui","Siamak Mehrkanoon"],"date":"2021-02-21","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.10570"},"links":{"paper":"https://arxiv.org/abs/2102.10570","pdf":"https://arxiv.org/pdf/2102.10570"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies the equation learner symbolic regression to derive an interpretable analytical formula for short-term wind speed forecasting using few features.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3354-cr01642","title":"Intercomparison of statistical downscaling models: a case study of a large-scale river basin","authors":["P. Loganathan","Amit Baburao Mahindrakar"],"date":"2021-02-19","year":2021,"venue":"Climate Research","venue_type":"journal","ids":{"doi":"10.3354/cr01642","openalex":"W3131989680"},"links":{"paper":"https://doi.org/10.3354/cr01642"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Proposes XGBoost-based statistical downscaling of ACCESS1.0 GCM output for Indian river basin, with bias near zero and NSE 0.75-0.85 against 35 stations.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21041421","title":"Real-Time Rainfall Forecasts Based on Radar Reflectivity during Typhoons: Case Study in Southeastern Taiwan","authors":["Chih‐Chiang Wei","Chen-Chia Hsu"],"date":"2021-02-18","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21041421","openalex":"W3130553882"},"links":{"paper":"https://doi.org/10.3390/s21041421","pdf":"https://www.mdpi.com/1424-8220/21/4/1421/pdf?version=1613970466"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"GRU models using radar reflectivity and station data forecast typhoon rainfall 1, 3 and 6 hours ahead in southeastern Taiwan, outperforming XGBoost and linear regression benchmarks.","significance":3,"cited_by":9,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00703-021-00777-2","title":"Artificial intelligence in forecasting central pressure drop and maximum sustained wind speed of cyclonic systems over Arabian Sea: skill comparison with conventional models","authors":["Ishita Sarkar","Sutapa Chaudhuri","Jayanti Pal"],"date":"2021-02-18","year":2021,"venue":"Meteorology and Atmospheric Physics","venue_type":"journal","ids":{"doi":"10.1007/s00703-021-00777-2","openalex":"W3131997100"},"links":{"paper":"https://doi.org/10.1007/s00703-021-00777-2"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Compares AI models with conventional methods for forecasting central pressure drop and maximum wind speed of Arabian Sea cyclones.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12020261","title":"Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step","authors":["Chang-Hoo Jeong","Wonsu Kim","Won-Kyun Joo","Dongmin Jang","Mun Yong Yi"],"date":"2021-02-16","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12020261","openalex":"W3129862240"},"links":{"paper":"https://doi.org/10.3390/atmos12020261","pdf":"https://www.mdpi.com/2073-4433/12/2/261/pdf?version=1613657888"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Weighted broadcasting in an encoding-forecasting radar model emphasizes the latest frames, improving MAE by 1.74% and heavy-rain (30 mm/h+) skill by over 30%.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-20-0127.1","title":"Response of U.S. West Coast Mountain Snowpack to Local Sea Surface Temperature Perturbations: Insights from Numerical Modeling and Machine Learning","authors":["Xiaodong Chen","Lai-Yung Ruby Leung","Yang Gao","Ying Liu"],"date":"2021-02-16","year":2021,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-20-0127.1","openalex":"W3131050860"},"links":{"paper":"https://doi.org/10.1175/jhm-d-20-0127.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/hydr/22/4/JHM-D-20-0127.1.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["applications-impacts"],"type":"application","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip","km-scale-sim"],"status":"research","summary":"6-km regional simulations show local SST warming shifts US West Coast snowpack, with neural networks attributing the response to precipitation amount and temperature.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2021.3056470","title":"Advancing Radar Nowcasting Through Deep Transfer Learning","authors":["Lei Han","Yangyang Zhao","Haonan Chen","V. Chandrasekar"],"date":"2021-02-16","year":2021,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2021.3056470","openalex":"W3133088081"},"links":{"paper":"https://doi.org/10.1109/tgrs.2021.3056470"},"orgs":["colorado-state-university"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Transfers a CNN radar nowcaster trained near Beijing to Guangzhou via fine-tuning and MMD, improving skill with only small target-domain datasets.","significance":4,"cited_by":72,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11069-021-04620-0","title":"A deep learning model for predicting climate-induced disasters","authors":["May Haggag","Ahmad S. Siam","Wael W. El-Dakhakhni","Paulin Coulibaly","Elkafi Hassini"],"date":"2021-02-16","year":2021,"venue":"Natural Hazards","venue_type":"journal","ids":{"doi":"10.1007/s11069-021-04620-0","openalex":"W3130065289"},"links":{"paper":"https://doi.org/10.1007/s11069-021-04620-0"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":[],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Deep learning model for predicting climate-induced natural disasters; abstract unavailable, so the approach and results are unverified.","significance":2,"cited_by":45,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2402.09846","title":"A Deep Learning Approach to Radar‐Based QPE","authors":["Ting‐Shuo Yo","Shih‐Hao Su","Jung‐Lien Chu","Chiao‐Wei Chang","Hung‐Chi Kuo"],"date":"2021-02-16","year":2021,"venue":"Earth and Space Science","venue_type":"journal","ids":{"arxiv":"2402.09846","doi":"10.1029/2020ea001340","openalex":"W3130265949"},"links":{"paper":"https://doi.org/10.1029/2020ea001340","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020EA001340"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Volume-to-point machine learning maps gridded QPESUMS radar sequences to Taiwan station rainfall, performing comparably to the operational scheme and excelling in heavy-rain detection.","significance":3,"cited_by":30,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.08175","title":"Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination","authors":["Ashesh","Buo-Fu Chen","Treng-Shi Huang","Boyo Chen","Chia-Tung Chang","Hsuan-Tien Lin"],"date":"2021-02-16","year":2021,"venue":"Artificial Intelligence for the Earth Systems","venue_type":"journal","ids":{"arxiv":"2102.08175","doi":"10.1175/aies-d-21-0005.1","openalex":"W3130868088"},"links":{"paper":"https://doi.org/10.1175/aies-d-21-0005.1","pdf":"https://arxiv.org/pdf/2102.08175"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Nowcasting model adds a discriminator for realistic rain maps and consecutive attention extending lead time to three hours, with a new radar benchmark.","significance":4,"cited_by":15,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30534-ijatcse-2021-361012021","title":"Univariate Time Series Prediction of Wind speed with a case study of Yanbu, Saudi Arabia","authors":[],"date":"2021-02-15","year":2021,"venue":"International Journal of Advanced Trends in Computer Science and Engineering","venue_type":"journal","ids":{"doi":"10.30534/ijatcse/2021/361012021","openalex":"W4253434930"},"links":{"paper":"https://doi.org/10.30534/ijatcse/2021/361012021","pdf":"https://doi.org/10.30534/ijatcse/2021/361012021"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares kNN, random forest, SVR, Holt-Winters and ARIMA for univariate hourly wind speed forecasting at Yanbu, Saudi Arabia.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1098-rsta.2020.0246","title":"Domain-driven models yield better predictions at lower cost than reservoir computers in Lorenz systems","authors":["Ryan Pyle","Nikola Jovanovic","Devika Subramanian","Krishna V. Palem","Ankit Patel"],"date":"2021-02-15","year":2021,"venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","venue_type":"journal","ids":{"doi":"10.1098/rsta.2020.0246","openalex":"W3129474221"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0246"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Shows echo state networks reduce to a polynomial regression (D2R2), a SINDy generalization that outperforms reservoir computers on Lorenz 63 and 96.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1098-rsta.2020.0097","title":"Can deep learning beat numerical weather prediction?","authors":["M. G. Schultz","C. Betancourt","B. Gong","F. Kleinert","M. Langguth","L. H. Leufen","A. Mozaffari","S. Stadtler"],"date":"2021-02-15","year":2021,"venue":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2020.0097","doi":"10.1098/rsta.2020.0097","openalex":"W3132280960"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0097"},"orgs":["juelich"],"topic":"global-medium-range","topics":["data-assimilation"],"type":"position","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Discusses whether deep learning could fully replace numerical weather models and data assimilation, reviewing ML concepts and their fit for weather data.","significance":3,"cited_by":564,"score":42,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1098-rsta.2020.0093","title":"Physics-informed machine learning: case studies for weather and climate modelling","authors":["K. Kashinath","M. Mustafa","A. Albert","J-L. Wu","C. Jiang","S. Esmaeilzadeh","K. Azizzadenesheli","R. Wang","A. Chattopadhyay","A. Singh","A. Manepalli","D. Chirila","R. Yu","R. Walters","B. White","H. Xiao","H. A. Tchelepi","P. Marcus","A. Anandkumar","P. Hassanzadeh","Prabhat"],"date":"2021-02-15","year":2021,"venue":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2020.0093","doi":"10.1098/rsta.2020.0093","openalex":"W3133294546"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0093"},"orgs":["caltech","lbnl-nersc","nvidia","stanford","uc-berkeley"],"topic":"xai-uq-physics","topics":["climate-emulation"],"type":"review","method":["physics-constrained"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Surveys physics-informed ML approaches with ten case studies for emulating, downscaling and forecasting weather and climate, reporting greater consistency and data efficiency.","significance":4,"cited_by":668,"score":71,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1098-rsta.2020.0091","title":"Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop","authors":["Sue Ellen Haupt","William Chapman","Samantha V. Adams","Charlie Kirkwood","J. Scott Hosking","Niall H. Robinson","Sebastian Lerch","Aneesh C. Subramanian"],"date":"2021-02-15","year":2021,"venue":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2020.0091","doi":"10.1098/rsta.2020.0091","openalex":"W3130099148"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0091"},"orgs":["alan-turing-institute","kit","met-office","ncar"],"topic":"post-processing","topics":["benchmarks-data-eval"],"type":"position","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Oxford workshop position on AI post-processing for weather and climate, releasing five archived ML-ready datasets with baseline notebooks to encourage trustworthy, FAIR and physically informed methods.","significance":3,"cited_by":103,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1098-rsta.2020.0089","title":"Learning earth system models from observations: machine learning or data assimilation?","authors":["A. J. Geer"],"date":"2021-02-15","year":2021,"venue":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2020.0089","doi":"10.1098/rsta.2020.0089","openalex":"W3131584643"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0089"},"orgs":["ecmwf"],"topic":"data-assimilation","topics":["foundation-models"],"type":"position","method":["rnn","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Perspective framing data assimilation and machine learning as equivalent inverse methods in a Bayesian network, e.g. linking 4D-Var to recurrent neural networks, to learn earth system models from observations.","significance":4,"cited_by":229,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s12145-021-00583-9","title":"Air temperature forecasting using artificial neural network for Ararat valley","authors":["Hrachya V. Astsatryan","Hayk Grigoryan","Aghasi Poghosyan","Rita Abrahamyan","Shushanik Asmaryan","Vahagn S. Muradyan","Garegin Tepanosyan","Yaniss Guigoz","Grégory Giuliani"],"date":"2021-02-14","year":2021,"venue":"Earth Science Informatics","venue_type":"journal","ids":{"doi":"10.1007/s12145-021-00583-9","openalex":"W3132590595"},"links":{"paper":"https://doi.org/10.1007/s12145-021-00583-9"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies an artificial neural network to forecast air temperature in the Ararat valley from station observations.","significance":2,"cited_by":64,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.10935","title":"Data-driven geophysical forecasting: Simple, low-cost, and accurate baselines with kernel methods","authors":["Boumediene Hamzi","Romit Maulik","Houman Owhadi"],"date":"2021-02-13","year":2021,"venue_type":"preprint","ids":{"arxiv":"2103.10935"},"links":{"paper":"https://arxiv.org/abs/2103.10935","pdf":"https://arxiv.org/pdf/2103.10935"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional","global"],"data":["era5","other"],"status":"research","summary":"Learned-kernel kernel-flow emulators forecast weekly sea-surface temperature and daily North American temperature, beating LSTMs and classical baselines in accuracy and cost.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.06442","title":"Broad-UNet: Multi-scale feature learning for nowcasting tasks","authors":["Jesus Garcia Fernandez","Siamak Mehrkanoon"],"date":"2021-02-12","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.06442","doi":"10.1016/j.neunet.2021.08.036"},"links":{"paper":"https://arxiv.org/abs/2102.06442","pdf":"https://arxiv.org/pdf/2102.06442"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Broad-UNet with asymmetric convolutions and ASPP predicts satellite-based precipitation and cloud cover maps more accurately than standard UNet with fewer parameters.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.uclim.2021.100797","title":"Utilizing world urban database and access portal tools (WUDAPT) and machine learning to facilitate spatial estimation of heatwave patterns","authors":["Yuan Shi","Chao Ren","Ming Luo","Jason K. S. Ching","Xinwei Li","Muhammad Bilal","Xiaoyi Fang","Zhihua Ren"],"date":"2021-02-10","year":2021,"venue":"Urban Climate","venue_type":"journal","ids":{"doi":"10.1016/j.uclim.2021.100797","openalex":"W3128817464"},"links":{"paper":"https://doi.org/10.1016/j.uclim.2021.100797"},"orgs":["nuist","cma"],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Combines WUDAPT urban morphology data with machine learning to spatially estimate heatwave patterns; the abstract is unavailable, so the details are limited.","significance":2,"cited_by":28,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12145-021-00577-7","title":"Bias correction of global ensemble precipitation forecasts by Random Forest method","authors":["Morteza Zarei","Mohsen Najarchi","Reza Mastouri"],"date":"2021-02-09","year":2021,"venue":"Earth Science Informatics","venue_type":"journal","ids":{"doi":"10.1007/s12145-021-00577-7","openalex":"W3127395088"},"links":{"paper":"https://doi.org/10.1007/s12145-021-00577-7"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Random forest bias-corrects global ensemble precipitation forecasts; the abstract is missing, so this rests on the title alone.","significance":3,"cited_by":45,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10506141.1","title":"Machine Learning to Characterize Hydro-Climate Impacts and Thresholds to Rainfed Agricultural Productivity","authors":["Steven John Burian","Carlos Anthony Oroza","J. Marshall Shepherd","Daniyal Hassan","Vengus Panhwar","Ryan Johnson"],"date":"2021-02-09","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10506141.1","openalex":"W4240558689"},"links":{"paper":"https://doi.org/10.1002/essoar.10506141.1"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["satellite","era5"],"status":"research","summary":"Random forest and MARS models link TRMM, GPM and GLDAS hydro-climate drivers to Pakistani wheat yield, identifying six phenological phases with strong responses.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10506139.1","title":"Exploring Bayesian deep learning for weather forecasting with the Lorenz 84 system","authors":["Yang Liu","Jisk Jakob Attema","Wilco Hazeleger"],"date":"2021-02-09","year":2021,"venue_type":"other","ids":{"doi":"10.1002/essoar.10506139.1","openalex":"W4234882251"},"links":{"paper":"https://doi.org/10.1002/essoar.10506139.1"},"orgs":[],"topic":"probabilistic-ensembles","topics":[],"type":"model","method":["rnn"],"timescale":["medium"],"spatial":[],"data":["other"],"status":"research","summary":"Bayesian LSTMs give reliable probabilistic forecasts of the Lorenz 84 atmospheric analogue, staying near the attractor and beating VAR and persistence.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.05107","title":"Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models","authors":["Jonathan A. Weyn","Dale R. Durran","Rich Caruana","Nathaniel Cresswell-Clay"],"date":"2021-02-09","year":2021,"venue":"Sub-Seasonal Forecasting With a Large Ensemble of Deep-Learning Weather Prediction Models. Journal of Advances in Modeling Earth Systems, 2021","venue_type":"journal","ids":{"arxiv":"2102.05107","doi":"10.1029/2021ms002502","openalex":"W3128630349"},"links":{"paper":"https://arxiv.org/abs/2102.05107","pdf":"https://arxiv.org/pdf/2102.05107"},"orgs":["microsoft-research","university-of-washington"],"topic":"s2s-seasonal","topics":["probabilistic-ensembles"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"A CNN-based cubed-sphere ensemble of 32 deep-learning weather models gives 2-6 week forecasts that are only modestly worse than the ECMWF S2S ensemble over land.","significance":6,"cited_by":227,"score":69,"highlight":true,"highlight_reason":"Large DLWP ensemble on a cubed sphere gives cheap S2S forecasts, near ECMWF-level skill at long leads; an important early step for ML-based S2S prediction.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1002-qj.3997","title":"Statistical approaches to assimilate ASCAT soil moisture information—I. Methodologies and first assessment","authors":["Filipe Aires","Peter Weston","Patricia de Rosnay","David Fairbairn"],"date":"2021-02-08","year":2021,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.3997","openalex":"W3127615175"},"links":{"paper":"https://doi.org/10.1002/qj.3997"},"orgs":["ecmwf"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Compares CDF-matching and neural network retrievals of ASCAT soil moisture for NWP assimilation, finding inversion better suited than forward modelling.","significance":3,"cited_by":38,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11041491","title":"Reconstruction of Missing Data in Weather Radar Image Sequences Using Deep Neuron Networks","authors":["Lihao Gao","Yu Zheng","Yaqiang Wang","Jiangjiang Xia","Xunlai Chen","Bin Li","Ming Luo","Yuchen Guo"],"date":"2021-02-06","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11041491","openalex":"W3127989953"},"links":{"paper":"https://doi.org/10.3390/app11041491","pdf":"https://www.mdpi.com/2076-3417/11/4/1491/pdf?version=1614153708"},"orgs":["iap-cas","cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["rnn","cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A CNN-BiConvLSTM reconstructs missing weather radar frames, outperforming interpolation, optical flow and ConvLSTM baselines across missing patterns.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31033-ijemr.11.1.11","title":"An Investigation of Weather Forecasting using Machine Learning Techniques","authors":["M. Vanitha","J.Haritha"],"date":"2021-02-05","year":2021,"venue":"International Journal of Engineering and Management Research","venue_type":"journal","ids":{"doi":"10.31033/ijemr.11.1.11","openalex":"W3127502339"},"links":{"paper":"https://doi.org/10.31033/ijemr.11.1.11"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Basic AI models trained on multi-station historical observations forecast near-term weather; neighbouring-region data is found to improve accuracy.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2103.06206","title":"Reservoir Computing as a Tool for Climate Predictability Studies","authors":["B. T. Nadiga"],"date":"2021-02-05","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2103.06206","doi":"10.1029/2020ms002290","openalex":"W3128402393"},"links":{"paper":"https://arxiv.org/abs/2103.06206","pdf":"https://arxiv.org/pdf/2103.06206"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-emulation"],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Reservoir computing predicts North Atlantic SST in a CESM control run, beating linear inverse models with limited data and suggesting emulator potential.","significance":4,"cited_by":52,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.04534","title":"A modular framework for extreme weather generation","authors":["Bianca Zadrozny","Campbell D. Watson","Daniela Szwarcman","Daniel Civitarese","Dario Oliveira","Eduardo Rodrigues","Jorge Guevara"],"date":"2021-02-05","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.04534"},"links":{"paper":"https://arxiv.org/abs/2102.04534","pdf":"https://arxiv.org/pdf/2102.04534"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A modular framework generates extreme precipitation scenarios from interchangeable ML components to support climate resilience planning, with initial comparisons of two approaches.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.03206","title":"A Survey on Mathematical Aspects of Machine Learning in GeoPhysics: The Cases of Weather Forecast, Wind Energy, Wave Energy, Oil and Gas Exploration","authors":["Miroslav Kosanic","Veljko Milutinovic"],"date":"2021-02-05","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.03206"},"links":{"paper":"https://arxiv.org/abs/2102.03206","pdf":"https://arxiv.org/pdf/2102.03206"},"orgs":[],"topic":"applications-impacts","topics":["global-medium-range"],"type":"review","method":["other"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Surveys machine learning in geophysics across weather forecasting, wind and wave energy, and oil and gas exploration, with notes on dataflow acceleration.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7220562121","title":"Climate Science and AI: Transforming Environmental Big Data Analysis","authors":["Adam Nick Alia Johnson"],"date":"2021-02-04","year":2021,"venue":"International Journal of New Media Studies","venue_type":"journal","ids":{"openalex":"W7220562121"},"links":{"paper":"https://ijnms.com/index.php/ijnms/article/view/195","pdf":"https://ijnms.com/index.php/ijnms/article/download/195/159"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"General overview of AI and big data methods for analysing climate and environmental datasets; it is a broad survey with no new method or quantitative result.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-14-785-2021","title":"Smartphone pressure data: quality control and impact on atmospheric analysis","authors":["Rumeng Li","Qinghong Zhang","Juanzhen Sun","Yun Chen","Lili Ding","Tian Wang"],"date":"2021-02-02","year":2021,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-14-785-2021","openalex":"W3088971752"},"links":{"paper":"https://doi.org/10.5194/amt-14-785-2021","pdf":"https://amt.copernicus.org/articles/14/785/2021/amt-14-785-2021.pdf"},"orgs":["ncar","cma"],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Machine-learning bias correction of 2016 smartphone pressure data reduces bias, and dense analysis resolves convective structure in a Beijing hailstorm better than station data.","significance":3,"cited_by":14,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W4399035348","title":"An Interdisciplinary Machine Learning Approach for Wind Speed Forecasting","authors":["Pedro Júnior Zucatelli","Erick Giovani Sperandio Nascimento","Alejandro Mauricio Gutiérrez Arce","Davidson Martins Moreira"],"date":"2021-02-01","year":2021,"venue":"DOAJ (DOAJ: Directory of Open Access Journals)","venue_type":"preprint","ids":{"openalex":"W4399035348"},"links":{"paper":"https://doaj.org/article/82b9cd77610f4beea1a7c084324e8f15"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Supervised machine learning applied to wind speed forecasting at one site in Uruguay to support grid energy management; the abstract gives no quantitative results.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33383-2020-075","title":"Discrete Ordinate Radiative Transfer Model With the Neural Network Based Eigenvalue Solver: proof Of Concept","authors":["Dmitry Efremenko"],"date":"2021-02-01","year":2021,"venue":"Light & Engineering","venue_type":"journal","ids":{"doi":"10.33383/2020-075","openalex":"W3136794531"},"links":{"paper":"https://doi.org/10.33383/2020-075"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural network replaces the eigenvalue solver in a discrete-ordinate radiative transfer model, with only a 3x speedup and generality retained; a proof-of-concept.","significance":1,"cited_by":6,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002268","title":"Machine Learning the Warm Rain Process","authors":["Andrew Gettelman","David John Gagne","Chih‐Chieh Chen","Matthew W. Christensen","Zachary J. Lebo","Hugh Morrison","Gabrielle Gantos"],"date":"2021-02-01","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002268","openalex":"W3047163080"},"links":{"paper":"https://doi.org/10.1029/2020ms002268","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002268"},"orgs":["ncar","university-of-oxford"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Neural-network emulators replace bin-microphysics warm-rain processes in a GCM, reproducing its climate behaviour at the control run's computational cost.","significance":4,"cited_by":130,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.00696","title":"Numerical Weather Forecasting using Convolutional-LSTM with Attention and Context Matcher Mechanisms","authors":["Selim Furkan Tekin","Oğuzhan Karaahmetoğlu","Fatih İlhan","Ismail Balaban","Süleyman S. Kozat"],"date":"2021-02-01","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.00696","openalex":"W3126234886"},"links":{"paper":"https://arxiv.org/abs/2102.00696","pdf":"https://arxiv.org/pdf/2102.00696"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["rnn","cnn","transformer"],"timescale":["short","medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A ConvLSTM encoder-decoder with CNN, attention and context matcher outperforms ConvLSTM, TrajGRU and U-Net on ERA5 and WeatherBench forecasts.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s21030941","title":"Temperature Prediction Based on Bidirectional Long Short-Term Memory and Convolutional Neural Network Combining Observed and Numerical Forecast Data","authors":["Seongyoep Jeong","Inyoung Park","Hyun Soo Kim","Chul Han Song","Hong Kook Kim"],"date":"2021-01-31","year":2021,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s21030941","openalex":"W3127230973"},"links":{"paper":"https://doi.org/10.3390/s21030941","pdf":"https://www.mdpi.com/1424-8220/21/3/941/pdf?version=1612186587"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["rnn","cnn"],"timescale":["medium"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"BLSTM and CNN fuse station observations with RDAPS model images to predict Korean temperatures up to 14 days ahead, beating single-source models.","significance":3,"cited_by":34,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11898-1001-7313.20210101","title":"Application of Artificial Intelligence Technology to Numerical Weather Prediction","authors":["Sun Jian","Zhuo Cao","Heng Li","Qian Simeng","Xin Wang","Limin Yan","Xue Wei"],"date":"2021-01-31","year":2021,"venue":"DOAJ (DOAJ: Directory of Open Access Journals)","venue_type":"preprint","ids":{"doi":"10.11898/1001-7313.20210101","openalex":"W3133000293"},"links":{"paper":"https://doi.org/10.11898/1001-7313.20210101"},"orgs":[],"topic":"global-medium-range","topics":["data-assimilation","post-processing"],"type":"review","method":[],"timescale":["short","medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Reviews how artificial intelligence is applied across numerical weather prediction, including data assimilation, error correction, and end-to-end neural forecasting models.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1111-gcb.15531","title":"Greening of the earth does not compensate for rising soil heterotrophic respiration under climate change","authors":["Dilip G. T. Naidu","Sumanta Bagchi"],"date":"2021-01-29","year":2021,"venue":"Global Change Biology","venue_type":"journal","ids":{"doi":"10.1111/gcb.15531","openalex":"W3121222644"},"links":{"paper":"https://doi.org/10.1111/gcb.15531"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Machine learning on 2001-2019 global NPP, heterotrophic respiration and climate data finds soil carbon losses likely as precipitation drives warming-related vulnerability.","significance":3,"cited_by":35,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.00085","title":"Long-Range Seasonal Forecasting of 2m-Temperature with Machine Learning","authors":["Etienne E. Vos","Ashley Gritzman","Sibusisiwe Makhanya","Thabang Mashinini","Campbell D. Watson"],"date":"2021-01-29","year":2021,"venue_type":"preprint","ids":{"arxiv":"2102.00085","openalex":"W3127138007"},"links":{"paper":"https://arxiv.org/abs/2102.00085","pdf":"https://arxiv.org/pdf/2102.00085"},"orgs":["ibm-research"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["seasonal"],"spatial":["local"],"data":[],"status":"research","summary":"CNN and RNN models forecast 2 m temperature out to 52 weeks at six locations, beating climatology up to 30 weeks for correlation, but only at select sites.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos12020173","title":"Tropical Overshooting Cloud-Top Height Retrieval from Himawari-8 Imagery Based on Random Forest Model","authors":["Gaoyun Wang","Hongqing Wang","Yizhou Zhuang","Qiong Wu","Siyue Chen","Haokai Kang"],"date":"2021-01-28","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12020173","openalex":"W3121591485"},"links":{"paper":"https://doi.org/10.3390/atmos12020173","pdf":"https://www.mdpi.com/2073-4433/12/2/173/pdf?version=1612165576"},"orgs":["ucla"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Random forest retrieves tropical overshooting cloud-top height from Himawari-8 infrared channels against CloudSat, reaching r=0.92 and RMSE 222 m versus 1305 m for interpolation.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-acp-21-1015-2021","title":"3D radiative heating of tropical upper tropospheric cloud systems derived from synergistic A-Train observations and machine learning","authors":["Claudia J. Stubenrauch","Giacomo Caria","Sofia E. Protopapadaki","Friederike Hemmer"],"date":"2021-01-26","year":2021,"venue":"Atmospheric chemistry and physics","venue_type":"journal","ids":{"doi":"10.5194/acp-21-1015-2021","openalex":"W3092643984"},"links":{"paper":"https://doi.org/10.5194/acp-21-1015-2021","pdf":"https://acp.copernicus.org/articles/21/1015/2021/acp-21-1015-2021.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","other"],"status":"research","summary":"Neural networks trained on satellite lidar, radar and reanalysis data map 3D radiative heating of tropical upper clouds, finding about 0.3 K/day net heating that enhances latent heating by 25%.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11031100","title":"A Hybrid Wind Power Forecasting Model with XGBoost, Data Preprocessing Considering Different NWPs","authors":["Quoc‐Thang Phan","Yuan‐Kang Wu","Quốc Dũng Phan"],"date":"2021-01-25","year":2021,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11031100","openalex":"W3125211436"},"links":{"paper":"https://doi.org/10.3390/app11031100","pdf":"https://www.mdpi.com/2076-3417/11/3/1100/pdf?version=1611716430"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"XGBoost wind power forecaster uses autoencoder-compressed 20-member NWP ensembles from Taiwan CWB, improving short-term deterministic and probabilistic accuracy.","significance":2,"cited_by":67,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.10041","title":"Deep Graph Convolutional Networks for Wind Speed Prediction","authors":["Tomasz Stańczyk","Siamak Mehrkanoon"],"date":"2021-01-25","year":2021,"venue_type":"preprint","ids":{"arxiv":"2101.10041"},"links":{"paper":"https://arxiv.org/abs/2101.10041","pdf":"https://arxiv.org/pdf/2101.10041"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["gnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Spatio-temporal graph convolution with a learnable adjacency matrix forecasts wind speed across weather stations in Denmark and the Netherlands, outperforming baselines.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jag.2021.102295","title":"Creating 1-km long-term (1980–2014) daily average air temperatures over the Tibetan Plateau by integrating eight types of reanalysis and land data assimilation products downscaled with MODIS-estimated temperature lapse rates based on machine learning","authors":["Hongbo Zhang","Walter Willem Immerzeel","Fan Zhang","Remco J. de Kok","Sally J. Gorrie","Ming Ye"],"date":"2021-01-22","year":2021,"venue":"International Journal of Applied Earth Observation and Geoinformation","venue_type":"journal","ids":{"doi":"10.1016/j.jag.2021.102295","openalex":"W3125777535"},"links":{"paper":"https://doi.org/10.1016/j.jag.2021.102295"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations","satellite"],"status":"research","summary":"Gradient boosting fuses eight reanalyses with MODIS-based lapse rates to produce a 1-km daily air temperature dataset over the Tibetan Plateau for 1980-2014.","significance":3,"cited_by":39,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.09126","title":"Will Artificial Intelligence supersede Earth System and Climate Models?","authors":["Christopher Irrgang","Niklas Boers","Maike Sonnewald","Elizabeth A. Barnes","Christopher Kadow","Joanna Staneva","Jan Saynisch-Wagner"],"date":"2021-01-22","year":2021,"venue":"Nature Machine Intelligence","venue_type":"journal","ids":{"arxiv":"2101.09126","doi":"10.1038/s42256-021-00374-3","openalex":"W3194456427"},"links":{"paper":"https://arxiv.org/abs/2101.09126","pdf":"https://arxiv.org/pdf/2101.09126"},"orgs":["colorado-state-university","noaa","pik","princeton-university","university-of-washington"],"topic":"hybrid-parameterization","topics":[],"type":"position","method":[],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Perspective proposing Neural Earth System Modelling, which fuses deep networks and Earth system models into interpretable hybrids that might eventually replace them.","significance":4,"cited_by":306,"score":81,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos12020128","title":"Valley Winds at the Local Scale: Correcting Routine Weather Forecast Using Artificial Neural Networks","authors":["Florian Dupuy","Gert‐Jan Duine","Pierre Durand","Thierry Hedde","Eric R. Pardyjak","Pierre Roubin"],"date":"2021-01-20","year":2021,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos12020128","openalex":"W3123173177"},"links":{"paper":"https://doi.org/10.3390/atmos12020128","pdf":"https://www.mdpi.com/2073-4433/12/2/128/pdf?version=1612776919"},"orgs":[],"topic":"post-processing","topics":["regional-km-scale"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A neural network corrects 3 km WRF forecasts of valley winds in complex terrain, significantly improving low-level wind speed and direction.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-20-0014.1","title":"Using Artificial Neural Networks to Improve CFS Week-3–4 Precipitation and 2-m Air Temperature Forecasts","authors":["Yun Long Fan","Vladimir M. Krasnopolsky","Huug van den Dool","Chung-Yu Wu","Jon Gottschalck"],"date":"2021-01-20","year":2021,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-20-0014.1","openalex":"W3122954327"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0014.1"},"orgs":["noaa"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Neural networks post-process NCEP CFS week-3–4 precipitation and 2-m temperature forecasts, improving skill over multiple linear regression correction.","significance":3,"cited_by":17,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.08195","title":"Machine learning emulation of gravity wave drag in numerical weather forecasting","authors":["Matthew Chantry","Sam Hatfield","Peter Duben","Inna Polichtchouk","Tim Palmer"],"date":"2021-01-20","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2101.08195","doi":"10.1029/2021ms002477","openalex":"W3123510158"},"links":{"paper":"https://arxiv.org/abs/2101.08195","pdf":"https://arxiv.org/pdf/2101.08195"},"orgs":["ecmwf","university-of-oxford"],"topic":"hybrid-parameterization","topics":["global-medium-range"],"type":"model","method":["other"],"timescale":["medium","seasonal"],"spatial":["global"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Neural emulators of the non-orographic gravity wave drag scheme run stably to seasonal timescales, improve medium-range forecasts and run ten times faster on GPUs than the CPU scheme.","significance":5,"cited_by":79,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-w13020231","title":"Evaluation and Correction of IMERG Late Run Precipitation Product in Rainstorm over the Southern Basin of China","authors":["Yu Chen","Jianchun Zheng","Deyong Hu","Yufei Di","Xiuhua Zhang","Manqing Liu"],"date":"2021-01-19","year":2021,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w13020231","openalex":"W3121950764"},"links":{"paper":"https://doi.org/10.3390/w13020231","pdf":"https://www.mdpi.com/2073-4441/13/2/231/pdf?version=1611064471"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Regression, ANN and GWR corrections of IMERG late-run rainstorm precipitation in southern China slightly improve accuracy, with the best method varying by region.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-03610918.2020.1854302","title":"Employing long short-term memory and Facebook prophet model in air temperature forecasting","authors":["Toni Toharudin","Resa Septiani Pontoh","Rezzy Eko Caraka","Solichatus Zahroh","Youngjo Lee","Rung-Ching Chen"],"date":"2021-01-19","year":2021,"venue":"Communications in Statistics - Simulation and Computation","venue_type":"journal","ids":{"doi":"10.1080/03610918.2020.1854302","openalex":"W3124899688"},"links":{"paper":"https://doi.org/10.1080/03610918.2020.1854302"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares LSTM and Facebook Prophet on five years of daily air temperature in Bandung; each performs better on different variables, with small RMSE differences.","significance":2,"cited_by":137,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-esd-12-69-2021","title":"Characterisation of Atlantic meridional overturning hysteresis using Langevin dynamics","authors":["Jelle van den Berk","Sybren Drijfhout","Wilco Hazeleger"],"date":"2021-01-18","year":2021,"venue":"Earth System Dynamics","venue_type":"journal","ids":{"doi":"10.5194/esd-12-69-2021","openalex":"W3121534514"},"links":{"paper":"https://doi.org/10.5194/esd-12-69-2021","pdf":"https://esd.copernicus.org/articles/12/69/2021/esd-12-69-2021.pdf"},"orgs":["knmi"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A machine learning fit of a six-parameter Langevin model reproduces AMOC collapse trajectories from intermediate-complexity climate models under freshwater forcing.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020jd033682","title":"Climatology and Evolution of the Antarctic Peninsula Föhn Wind‐Induced Melt Regime From 1979–2018","authors":["Matthew K. Laffin","Charles Sutton Zender","Sameer Singh","Jan Melchior van Wessem","Smeets Cjpp","Carleen H. Reijmer"],"date":"2021-01-18","year":2021,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2020jd033682","openalex":"W3093398400"},"links":{"paper":"https://doi.org/10.1029/2020jd033682","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020JD033682"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["era5","stations","km-scale-sim"],"status":"research","summary":"A machine learning föhn detection algorithm trained on automatic weather stations maps 1979-2018 föhn-driven Antarctic Peninsula melt, finding 3.1% of total melt.","significance":3,"cited_by":41,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.06813","title":"Fast and accurate learned multiresolution dynamical downscaling for precipitation","authors":["Jiali Wang","Zhengchun Liu","Ian Foster","Won Chang","Rajkumar Kettimuthu","Rao Kotamarthi"],"date":"2021-01-18","year":2021,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"2101.06813","doi":"10.5194/gmd-14-6355-2021","openalex":"W3123393465"},"links":{"paper":"https://doi.org/10.5194/gmd-14-6355-2021","pdf":"https://arxiv.org/pdf/2101.06813"},"orgs":["argonne"],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["cnn","gan-vae"],"timescale":["climate"],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"CNNs trained with MSE and conditional GANs emulate 12 km precipitation from 50 km simulations, running 30 years in 14 minutes versus one month.","significance":4,"cited_by":72,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002200","title":"Reconstructing Past Global Vegetation With Random Forest Machine Learning, Sacrificing the Dynamic Response for Robust Results","authors":["Amelie Lindgren","Zhengyao Lu","Qiong Zhang","Gustaf Hugelius"],"date":"2021-01-17","year":2021,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002200","openalex":"W3114009147"},"links":{"paper":"https://doi.org/10.1029/2020ms002200","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002200"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Random forest reconstructs global biome vegetation from pollen for past climates, giving robust preindustrial and mid-Holocene patterns but failing at the Last Glacial Maximum.","significance":3,"cited_by":43,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.09356","title":"Dynamical prediction of two meteorological factors using the deep neural network and the long short term memory $(1)$","authors":["Ki Hong Shin","Jae Won Jung","Sung Kyu Seo","Cheol Hwan You","Dong In Lee","Jisun Lee","Ki Ho Chang","Woon Seon Jung","Kyungsik Kim"],"date":"2021-01-16","year":2021,"venue_type":"preprint","ids":{"arxiv":"2101.09356","doi":"10.1007/s40042-022-00472-4"},"links":{"paper":"https://arxiv.org/abs/2101.09356","pdf":"https://arxiv.org/pdf/2101.09356"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares ANN, DNN, ELM, LSTM and LSTM with peephole connections for temperature and humidity at ten South Korean cities; LSTM gives the lowest errors.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2020.592667","title":"Using Machine Learning to Make Computationally Inexpensive Projections of 21st Century Stratospheric Column Ozone Changes in the Tropics","authors":["James Keeble","Yu Yeung Scott Yiu","Alexander Thomas Archibald","Fiona M. O’Connor","Alistair Sellar","Jeremy P. R. B. Walton","John Adrian Pyle"],"date":"2021-01-14","year":2021,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2020.592667","openalex":"W3118991685"},"links":{"paper":"https://doi.org/10.3389/feart.2020.592667","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2020.592667/pdf"},"orgs":["met-office","university-of-cambridge"],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Ridge, Lasso, random forest and extra trees emulate UKESM1 tropical stratospheric ozone projections under SSPs, matching the model when trained on future simulations.","significance":3,"cited_by":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10546-020-00586-x","title":"Using Machine-Learning Methods to Improve Surface Wind Speed from the Outputs of a Numerical Weather Prediction Model","authors":["Naveen Goutham","Bastien Alonzo","Aurore Dupré","Riwal Plougonven","Rebeca Doctors","Lishan Liao","Mathilde Mougeot","Aurélie Fischer","Philippe J Drobinski"],"date":"2021-01-14","year":2021,"venue":"Boundary-Layer Meteorology","venue_type":"journal","ids":{"doi":"10.1007/s10546-020-00586-x","openalex":"W3118842719"},"links":{"paper":"https://doi.org/10.1007/s10546-020-00586-x"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Applies machine learning to correct surface wind speed forecasts from a numerical weather prediction model using observations.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.05616","title":"Road Surface Translation Under Snow-covered and Semantic Segmentation for Snow Hazard Index","authors":["Takato Yasuno","Junichiro Fujii","Hiroaki Sugawara","Masazumi Amakata"],"date":"2021-01-14","year":2021,"venue_type":"preprint","ids":{"arxiv":"2101.05616"},"links":{"paper":"https://arxiv.org/abs/2101.05616","pdf":"https://arxiv.org/pdf/2101.05616"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["cnn","gan-vae"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Applies pix2pix GAN and DeepLabv3+ segmentation to live road images to compute a snow-cover hazard index for Japanese highways.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.buildenv.2021.107601","title":"Using recurrent neural networks for localized weather prediction with combined use of public airport data and on-site measurements","authors":["Jung Min Han","Yu Qian Ang","Ali M Malkawi","Holly Wasilowski Samuelson"],"date":"2021-01-13","year":2021,"venue":"Building and Environment","venue_type":"journal","ids":{"doi":"10.1016/j.buildenv.2021.107601","openalex":"W3120887079"},"links":{"paper":"https://doi.org/10.1016/j.buildenv.2021.107601","pdf":"https://www.sciencedirect.com/science/article/pii/S0360132321000160/pdf"},"orgs":["mit"],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Recurrent neural networks generate localized synthetic weather data from airport and on-site measurements, improving test accuracy over standard weather files by over 100%.","significance":3,"cited_by":92,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jocs.2020.101295","title":"Machine learning based algorithms for uncertainty quantification in numerical weather prediction models","authors":["Azam Moosavi","Vishwas Rao","Adrian Sandu"],"date":"2021-01-12","year":2021,"venue":"Journal of Computational Science","venue_type":"journal","ids":{"doi":"10.1016/j.jocs.2020.101295","openalex":"W3120662190"},"links":{"paper":"https://doi.org/10.1016/j.jocs.2020.101295","pdf":"https://www.sciencedirect.com/science/article/am/pii/S1877750320305895"},"orgs":["argonne"],"topic":"xai-uq-physics","topics":["probabilistic-ensembles"],"type":"model","method":[],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Proposes machine learning algorithms for uncertainty quantification in numerical weather prediction models; no abstract is available to confirm details.","significance":2,"cited_by":71,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.09509","title":"Short-term daily precipitation forecasting with seasonally-integrated autoencoder","authors":["Donlapark Ponnoprat"],"date":"2021-01-12","year":2021,"venue":"Applied Soft Computing, 102, 107083 (2021)","venue_type":"journal","ids":{"arxiv":"2101.09509","doi":"10.1016/j.asoc.2021.107083","openalex":"W3119644826"},"links":{"paper":"https://arxiv.org/abs/2101.09509","pdf":"https://arxiv.org/pdf/2101.09509"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Seasonally-integrated LSTM autoencoder forecasts daily precipitation, raising horizon-3 forecast-observation correlation by 37 points over baselines.","significance":3,"cited_by":28,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20546-ijcmas.2021.1001.349","title":"Medium Range Forecast of Maximum Temperature of Coimbatore using ANN","authors":["D Abinayarajam","Sanjay Govind Patil","Ga Dheebakaran","S. P. Ramanathan"],"date":"2021-01-10","year":2021,"venue":"International Journal of Current Microbiology and Applied Sciences","venue_type":"journal","ids":{"doi":"10.20546/ijcmas.2021.1001.349","openalex":"W3146312791"},"links":{"paper":"https://doi.org/10.20546/ijcmas.2021.1001.349","pdf":"https://www.ijcmas.com/10-1-2021/D. Abinayarajam, et al.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural network autoregression forecasts daily maximum temperature in Coimbatore from 1991-2017 station records at medium range.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en14020338","title":"Numerical Weather Prediction and Artificial Neural Network Coupling for Wind Energy Forecast","authors":["Lorenzo Donadio","Jiannong Fang","Fernando Porté‐Agel"],"date":"2021-01-09","year":2021,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en14020338","openalex":"W3118645195"},"links":{"paper":"https://doi.org/10.3390/en14020338","pdf":"https://www.mdpi.com/1996-1073/14/2/338/pdf?version=1611051230"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Hybrid NWP and ANN models forecast wind farm power over complex terrain beyond 6 hours, with the direct power model reaching 8.76% normalized MAE.","significance":3,"cited_by":88,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-14-107-2021","title":"ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather","authors":["","Karthik Kashinath","Mayur Mudigonda","Sol Kim","Lukas Kapp-Schwoerer","Andre Graubner","Ege Karaismailoglu","Leo von Kleist","Thorsten Kurth","Annette Greiner","Ankur Mahesh","Kevin Yang","Colby Lewis","Jiayi Chen","Andrew Lou","Sathyavat Chandran","Ben Toms","Will Chapman","Katherine Dagon","Christine A. Shields","Travis O'Brien","Michael Wehner","William Collins"],"date":"2021-01-08","year":2021,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-14-107-2021","openalex":"W3015232219"},"links":{"paper":"https://doi.org/10.5194/gmd-14-107-2021"},"orgs":["colorado-state-university","eth-zurich","lbnl-nersc","ncar","nvidia","uc-berkeley"],"topic":"extremes-hazards","topics":[],"type":"benchmark","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"ClimateNet releases an expert-labeled dataset of tropical cyclones and atmospheric rivers in CAM5.1 output, and a deep learning segmentation model that enables pixel-level extreme event analysis.","significance":5,"cited_by":111,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2101.03247","title":"Glacier Calving Front Segmentation Using Attention U-Net","authors":["Michael Holzmann","Amirabbas Davari","Thorsten Seehaus","Matthias Braun","Andreas Maier","Vincent Christlein"],"date":"2021-01-08","year":2021,"venue_type":"preprint","ids":{"arxiv":"2101.03247"},"links":{"paper":"https://arxiv.org/abs/2101.03247","pdf":"https://arxiv.org/pdf/2101.03247"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","transformer"],"timescale":[],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Attention U-Net segments tidewater glacier calving fronts from SAR imagery end-to-end, matching U-Net with a 1.5% better Dice score and attention maps for tuning.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10707-020-00426-7","title":"From reanalysis to satellite observations: gap-filling with imbalanced learning","authors":["Jingze Lu","Kaijun Ren","Xiaoyong Li","Yanlai Zhao","Zichen Xu","Xiaoli Ren"],"date":"2021-01-07","year":2021,"venue":"GeoInformatica","venue_type":"journal","ids":{"doi":"10.1007/s10707-020-00426-7","openalex":"W3119799331"},"links":{"paper":"https://doi.org/10.1007/s10707-020-00426-7"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["era5","satellite"],"status":"research","summary":"Gap-filling of satellite observations from reanalysis using imbalanced learning; no abstract was provided, so scope and results are inferred from the title only.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs13020164","title":"A Novel LSTM Model with Interaction Dual Attention for Radar Echo Extrapolation","authors":["Chuyao Luo","Xutao Li","Yongliang Wen","Yunming Ye","Xiaofeng Zhang"],"date":"2021-01-06","year":2021,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs13020164","openalex":"W3118349806"},"links":{"paper":"https://doi.org/10.3390/rs13020164","pdf":"https://www.mdpi.com/2072-4292/13/2/164/pdf?version=1609926921"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"IDA-LSTM adds coupled convolutions and channel-position dual attention to ConvLSTM to reduce underestimation of high radar echoes in extrapolation on CIKM 2017 data.","significance":3,"cited_by":76,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en14020273","title":"Estimating Downward Shortwave Solar Radiation on Clear-Sky Days in Heterogeneous Surface Using LM-BP Neural Network","authors":["Weizhen Wang","Jiaojiao Feng","Feinan Xu"],"date":"2021-01-06","year":2021,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en14020273","openalex":"W3120753011"},"links":{"paper":"https://doi.org/10.3390/en14020273","pdf":"https://www.mdpi.com/1996-1073/14/2/273/pdf?version=1610088866"},"orgs":[],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"LM-BP neural network estimates clear-sky surface shortwave radiation from ASTER imagery with RMSE 27.34 W/m2 against site measurements.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.01975","title":"Predicting Forest Fire Using Remote Sensing Data And Machine Learning","authors":["Suwei Yang","Massimo Lupascu","Kuldeep S. Meel"],"date":"2021-01-06","year":2021,"venue_type":"preprint","ids":{"arxiv":"2101.01975"},"links":{"paper":"https://arxiv.org/abs/2101.01975","pdf":"https://arxiv.org/pdf/2101.01975"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A machine learning model built on remote sensing data predicts forest fires in Indonesia with AUC above 0.81, beating a 0.70 baseline.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2101.01000","title":"Conditional Local Convolution for Spatio-temporal Meteorological Forecasting","authors":["Haitao Lin","Zhangyang Gao","Yongjie Xu","Lirong Wu","Ling Li","Stan. Z. Li"],"date":"2021-01-04","year":2021,"venue_type":"preprint","ids":{"arxiv":"2101.01000"},"links":{"paper":"https://arxiv.org/abs/2101.01000","pdf":"https://arxiv.org/pdf/2101.01000"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["gnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"CLCRN, a graph-based recurrent network with local conditional convolutions, forecasts meteorological sensor time series and reports state-of-the-art results on weather benchmarks.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-020-01963-1","title":"Prediction of heat waves over Pakistan using support vector machine algorithm in the context of climate change","authors":["Najeebullah Khan","Shamsuddin Shahid","Tarmizi Ismail","Farida Behlil"],"date":"2021-01-03","year":2021,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-020-01963-1","openalex":"W3119802920"},"links":{"paper":"https://doi.org/10.1007/s00477-020-01963-1"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Support vector machine model predicts heat waves over Pakistan under climate change; the abstract is unavailable, so details are limited.","significance":2,"cited_by":59,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-21664250.2020.1868736","title":"Application of recurrent neural network for prediction of the time-varying storm surge","authors":["Yusuke Igarashi","Yoshimitsu TAJIMA"],"date":"2021-01-02","year":2021,"venue":"Coastal Engineering Journal","venue_type":"journal","ids":{"doi":"10.1080/21664250.2020.1868736","openalex":"W3124382064"},"links":{"paper":"https://doi.org/10.1080/21664250.2020.1868736"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"RNN outperforms DNN for fast prediction of typhoon-driven storm surge time series at ten Tokyo Bay points, trained on 151 simulated typhoons.","significance":3,"cited_by":32,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3175667698","title":"On the efficiency of machine learning algorithms for imputation in spatiotemporal meteorological data","authors":["Andrey Konstantinovich Gorshenin","Svetlana Lukina"],"date":"2021-01-01","year":2021,"venue":"Advances in intelligent systems and computing","venue_type":"other","ids":{"openalex":"W3175667698"},"links":{"paper":"https://istina.msu.ru/publications/article/346755291/"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["stations"],"status":"research","summary":"Compares random forests, XGBoost, SVM and EM for imputing up to 40% missing precipitation at over a hundred stations; XGBoost combinations reach nRMSE 0.01–0.07.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54216-fpa.060204","title":"Weather Forecasting for Batu Pahat Using Neural Network","authors":["Chan Weng","Rozaida Binti Ghazali","Salama A. Mustafa","Ali Noori Kareem","Bashar Ahmed Khalaf"],"date":"2021-01-01","year":2021,"venue":"Fusion Practice and Applications","venue_type":"journal","ids":{"doi":"10.54216/fpa.060204","openalex":"W3202344275"},"links":{"paper":"https://doi.org/10.54216/fpa.060204"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies a multilayer perceptron trained on Malaysian Meteorological Department station data to forecast daily weather conditions for Batu Pahat.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.5478925","title":"A machine learning approach to generate daily synthetic NDVI and LST products for urban scale SUHI and heatwaves assessment","authors":["Isaac Buo","Valentina Sagris","Jaak Jaagus"],"date":"2021-01-01","year":2021,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.5478925","openalex":"W4286984965"},"links":{"paper":"https://doi.org/10.5281/zenodo.5478925"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Random forests generate gap-free daily 100 m and 500 m NDVI and land surface temperature products to support urban heatwave and heat-island assessment.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-npg-2021-6","title":"Producing realistic climate data with generative adversarial networks GANs","authors":["Camille Besombes","Olivier Pannekoucke","Corentin Lapeyre","Benjamin Mark Sanderson","Olivier Thual"],"date":"2021-01-01","year":2021,"venue":"Nonlinear processes in geophysics","venue_type":"journal","ids":{"doi":"10.5194/npg-2021-6","openalex":"W4205420528"},"links":{"paper":"https://doi.org/10.5194/npg-28-347-2021"},"orgs":["meteo-france"],"topic":"climate-emulation","topics":["probabilistic-ensembles"],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Wasserstein GAN with a CNN generator learns a 64-dimensional latent space of synthetic PLASIM climate states, reproducing leading EOF statistics and geostrophic balance.","significance":3,"cited_by":34,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3929-ethz-b-000488935","title":"On the similarities between Vision Transformers and Residual Networks for Weather Prediction","authors":["Bernhard Walser"],"date":"2021-01-01","year":2021,"venue":"Repository for Publications and Research Data (ETH Zurich)","venue_type":"preprint","ids":{"doi":"10.3929/ethz-b-000488935","openalex":"W3168196654"},"links":{"paper":"https://doi.org/10.3929/ethz-b-000488935"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["transformer","cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Compares Vision Transformers with residual networks for data-driven weather prediction; no abstract is available to confirm the findings.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33545-2707661x.2021.v2.i1a.96","title":"Rainfall forecasting using advanced machine learning models","authors":["Sanjaikanth E Vadakkethil Somanathan Pillai","Kiran Polimetla","Rajiv Avacharmal","Arun Pandiyan Perumal"],"date":"2021-01-01","year":2021,"venue":"International Journal of Communication and Information Technology","venue_type":"journal","ids":{"doi":"10.33545/2707661x.2021.v2.i1a.96","openalex":"W4403308662"},"links":{"paper":"https://doi.org/10.33545/2707661x.2021.v2.i1a.96","pdf":"https://www.computersciencejournals.com/ijcit/archives/2021/vol2issue1/PartA/5-2-11-460.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Compares decision trees, random forests and gradient boosting for rainfall prediction from historical records, reporting better accuracy than traditional statistical methods.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3319-tao.2021.07.23.01","title":"Probabilistic typhoon rainfall forecasting using a modified fuzzy inference model","authors":["Shien‐Tsung Chen"],"date":"2021-01-01","year":2021,"venue":"Terrestrial Atmospheric and Oceanic Sciences","venue_type":"journal","ids":{"doi":"10.3319/tao.2021.07.23.01","openalex":"W4200587490"},"links":{"paper":"https://doi.org/10.3319/tao.2021.07.23.01","pdf":"http://tao.cgu.org.tw/index.php/articles/archive/hydrology/item/download/3702_92adc190aa95f01d00cee39a80b35d5e"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A modified fuzzy inference model gives probabilistic typhoon rainfall forecasts 1–3 hours ahead, with median-based deterministic forecasts performing satisfactorily.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32604-iasc.2021.020010","title":"Method of Bidirectional LSTM Modelling for the Atmospheric Temperature","authors":["Shuo Peng Liang","Dingcheng Wang","Jingrong Wu","Rui Wang","Ruiqi Wang"],"date":"2021-01-01","year":2021,"venue":"Intelligent Automation & Soft Computing","venue_type":"journal","ids":{"doi":"10.32604/iasc.2021.020010","openalex":"W3194669303"},"links":{"paper":"https://doi.org/10.32604/iasc.2021.020010"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"BL-FC, a bidirectional LSTM with fully connected layers, forecasts hourly station temperature in Ireland and beats LSTM, GRU and RNN, especially for abnormal temperatures.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32604-cmes.2021.015528","title":"A Contemporary Review on Drought Modeling Using Machine Learning Approaches","authors":["Karpagam Sundararajan","Lalit Garg","Kathiravan Srinivasan","Ali Kashif Bashir","Jayakumar Kaliappan","Ganapathy Pattukandan Ganapathy","Senthil Kumaran Selvaraj","T. Meena"],"date":"2021-01-01","year":2021,"venue":"Computer Modeling in Engineering & Sciences","venue_type":"journal","ids":{"doi":"10.32604/cmes.2021.015528","openalex":"W3184482175"},"links":{"paper":"https://doi.org/10.32604/cmes.2021.015528","pdf":"https://file.techscience.com/uploads/attached/file/20220218/20220218054131_56815.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Reviews machine learning methods for drought prediction, covering drought indices, datasets and performance metrics, with an India focus.","significance":2,"cited_by":94,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.28974-idojaras.2021.3.8","title":"Downscaling diurnal temperature over west and southwest Iran : A comparison of statistical downscaling approaches","authors":["Mohammad Reza Poodineh"],"date":"2021-01-01","year":2021,"venue":"Időjárás","venue_type":"journal","ids":{"doi":"10.28974/idojaras.2021.3.8","openalex":"W3199424483"},"links":{"paper":"https://doi.org/10.28974/idojaras.2021.3.8","pdf":"https://www.met.hu/downloads.php?fn=/metadmin/newspaper/2021/09/bdbe0a258306972216c055d8011523e4-125-3-8-poodineh.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["stations","nwp-analysis","cmip"],"status":"research","summary":"Compares artificial neural networks with SDSM for downscaling diurnal temperature in western Iran; ANN gives lower errors at mountain stations.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25675-3.04699","title":"Using machine learning to improve vertical profiles of temperature and moisture for severe weather nowcasting","authors":["Jason Stock","Anderson, Charles","Ebert-Uphoff, Imme","Shrideep Pallickara","Kummerow, Christian"],"date":"2021-01-01","year":2021,"venue":"Digital Collections of Colorado (Colorado State University)","venue_type":"preprint","ids":{"doi":"10.25675/3.04699","openalex":"W3197335227"},"links":{"paper":"https://doi.org/10.25675/3.04699","pdf":"https://hdl.handle.net/10217/233704"},"orgs":[],"topic":"post-processing","topics":["nowcasting","extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis","satellite","stations"],"status":"research","summary":"Neural networks combine RAP forecasts, surface analyses and GOES-16 satellite data to correct temperature and moisture profiles for severe weather nowcasting.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.3997702","title":"Wind Power Ramp Characterisation and Forecasting Using Numerical Weather Prediction and Machine Learning Models","authors":["Russell Sharp","Hisham Ihshaish","J. Ignacio Deza"],"date":"2021-01-01","year":2021,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.3997702","openalex":"W7204405469"},"links":{"paper":"https://doi.org/10.2139/ssrn.3997702"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":[],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Combines numerical weather prediction and machine learning to characterise and forecast wind power ramp events; no abstract is available.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.3902660","title":"Prediction of Weather Forecasting by Using Machine Learning","authors":["N. Lakshmi","P. Ajimunnisa .","V. Lakshmi Prasanna","T. YugaSravani .","M. Raviteja"],"date":"2021-01-01","year":2021,"venue":"International Journal of Innovative Research in Computer Science & Technology","venue_type":"journal","ids":{"doi":"10.2139/ssrn.3902660","openalex":"W3197709238"},"links":{"paper":"https://doi.org/10.21276/ijircst.2021.9.4.7"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Generic study of machine learning for weather forecasting; no abstract is available, so methods and results cannot be verified.","significance":1,"cited_by":7,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.17638-03116349","title":"Pattern Recognition for Weather Phenomena in Climate Data","authors":["Grzegorz Muszyński"],"date":"2021-01-01","year":2021,"venue":"University of Liverpool","venue_type":"preprint","ids":{"doi":"10.17638/03116349","openalex":"W3157100220"},"links":{"paper":"https://doi.org/10.17638/03116349"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"Thesis develops learned pattern recognition for atmospheric rivers (topological data analysis plus ML) and blocking (deep CNNs) in climate simulations and reanalysis.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijhst.2021.10037945","title":"Cloud classification: principles and applications","authors":["Bhavin Fataniya","Seema Mahajan"],"date":"2021-01-01","year":2021,"venue":"International Journal of Hydrology Science and Technology","venue_type":"journal","ids":{"doi":"10.1504/ijhst.2021.10037945","openalex":"W3161700771"},"links":{"paper":"https://doi.org/10.1504/ijhst.2021.10037945"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Survey of 2000–2018 satellite cloud classification methods, from thresholds to machine learning, recommending hybrid approaches combining ML, thresholds and physical parameters.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14191-atmos.2021.31.1.073","title":"Development of Surface Weather Forecast Model by using LSTM Machine Learning Method","authors":["Sungjae Hong","Jae Hwan Kim","Dae Sung Choi","Kanghyun Baek"],"date":"2021-01-01","year":2021,"venue_type":"other","ids":{"doi":"10.14191/atmos.2021.31.1.073","openalex":"W3156448609"},"links":{"paper":"https://doi.org/10.14191/atmos.2021.31.1.073"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Builds an LSTM-based surface weather forecast model; no abstract is available to confirm the results.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11648-j.earth.20211003.14","title":"Using Oscillatory Processes in Northern Hemisphere Proxy Temperature Records to Forecast Industrial-era Temperatures","authors":["J. Abbot"],"date":"2021-01-01","year":2021,"venue":"Earth Sciences","venue_type":"journal","ids":{"doi":"10.11648/j.earth.20211003.14","openalex":"W3186869157"},"links":{"paper":"https://doi.org/10.11648/j.earth.20211003.14","pdf":"http://article.sciencepublishinggroup.com/pdf/10.11648.j.earth.20211003.14.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Spectral analysis of proxy temperature records trains a neural network on pre-1880 oscillations to forecast 20th-century warming, estimating natural versus anthropogenic contributions.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2021-7363471","title":"An Application of ANN Ensemble for Estimating of Precipitation Using Regional Climate Models","authors":["Dongwoo Jang"],"date":"2021-01-01","year":2021,"venue":"Advances in Civil Engineering","venue_type":"journal","ids":{"doi":"10.1155/2021/7363471","openalex":"W3133716199"},"links":{"paper":"https://doi.org/10.1155/2021/7363471","pdf":"https://downloads.hindawi.com/journals/ace/2021/7363471.pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"ANN ensemble combines five regional climate models to correct Korean precipitation against observations, improving on individual RCMs, most strongly inland.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2021-5661292","title":"Distributed Typhoon Track Prediction Based on Complex Features and Multitask Learning","authors":["Yongjiao Sun","Yaning Song","Baiyou Qiao","Boyang Li"],"date":"2021-01-01","year":2021,"venue":"Complexity","venue_type":"journal","ids":{"doi":"10.1155/2021/5661292","openalex":"W3182190984"},"links":{"paper":"https://doi.org/10.1155/2021/5661292","pdf":"https://downloads.hindawi.com/journals/complexity/2021/5661292.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A distributed multitask deep network using climatic, geographic and physical features is proposed for typhoon track prediction; the abstract gives no quantitative gain.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2021.3128522","title":"Contextual Sa-Attention Convolutional LSTM for Precipitation Nowcasting: A Spatiotemporal Sequence Forecasting View","authors":["Taisong Xiong","Jianxing He","Hao Wang","Xiaowen Tang","Zhao Shi","Qiangyu Zeng"],"date":"2021-01-01","year":2021,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2021.3128522","openalex":"W3211959704"},"links":{"paper":"https://doi.org/10.1109/jstars.2021.3128522","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/09618869.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn","transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Self-attention ConvLSTM encoder-forecaster for radar-based precipitation nowcasting, evaluated on HKO-7 radar echo sequences with improved visual and quantitative results.","significance":3,"cited_by":41,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2021.3104389","title":"MIIDAPS-AI: An Explainable Machine-Learning Algorithm for Infrared and Microwave Remote Sensing and Data Assimilation Preprocessing - Application to LEO and GEO Sensors","authors":["Eric S. Maddy","Sid‐Ahmed Boukabara"],"date":"2021-01-01","year":2021,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2021.3104389","openalex":"W3194988337"},"links":{"paper":"https://doi.org/10.1109/jstars.2021.3104389","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/09512479.pdf"},"orgs":["noaa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"pre-operational","summary":"MIIDAPS-AI deep-learning retrieval of temperature, moisture and cloud from microwave and infrared sounders runs about 100 times faster with comparable accuracy to operational methods.","significance":4,"cited_by":41,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2021.3083647","title":"Using Conditional Generative Adversarial 3-D Convolutional Neural Network for Precise Radar Extrapolation","authors":["Cong Wang","Ping Wang","Pingping Wang","Bing Xue","Di Wang"],"date":"2021-01-01","year":2021,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2021.3083647","openalex":"W3164939772"},"links":{"paper":"https://doi.org/10.1109/jstars.2021.3083647","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9314330/09440761.pdf"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A 3-D CNN plus conditional GAN postprocessor sharpens radar echo extrapolations, improving intense echo and convective prediction over North China in 2015–2016.","significance":4,"cited_by":39,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2021.3065585","title":"Forecasting El Niño and La Niña Using Spatially and Temporally Structured Predictors and a Convolutional Neural Network","authors":["Mahdi Hashemi"],"date":"2021-01-01","year":2021,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2021.3065585","openalex":"W3136539577"},"links":{"paper":"https://doi.org/10.1109/jstars.2021.3065585","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9314330/09376101.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["era5"],"status":"research","summary":"A CNN using spatially restructured SST, sea-level pressure and wind predictors forecasts El Niño and La Niña types one year ahead with high precision.","significance":4,"cited_by":22,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2021.3050767","title":"Tropical Cyclone Intensity Classification and Estimation Using Infrared Satellite Images With Deep Learning","authors":["Changjiang Zhang","Xiaojie Wang","Leiming Ma","Xiaoqin Lu"],"date":"2021-01-01","year":2021,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2021.3050767","openalex":"W3120451880"},"links":{"paper":"https://doi.org/10.1109/jstars.2021.3050767","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9314330/09320562.pdf"},"orgs":["cma"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A cascaded CNN classifies and estimates northwest Pacific tropical cyclone intensity from infrared satellite images, reaching 8.60 kt RMSE against best-track data.","significance":4,"cited_by":117,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.procir.2021.11.075","title":"Convolutional neural network with dual inputs for time series ice prediction on rotor blades of wind turbines","authors":["Markus Kreutz","Abderrahim Ait Alla","Kamaloddin Varasteh","Jan-Hendrik Ohlendorf","Michael Lütjen","Michael Freitag","Klaus‐Dieter Thoben"],"date":"2021-01-01","year":2021,"venue":"Procedia CIRP","venue_type":"journal","ids":{"doi":"10.1016/j.procir.2021.11.075","openalex":"W3216034464"},"links":{"paper":"https://doi.org/10.1016/j.procir.2021.11.075","pdf":"https://www.sciencedirect.com/science/article/pii/S2212827121009732/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Dual-input 1D CNN predicts wind turbine blade icing 24 hours ahead using turbine data and weather forecasts, reaching 97.9% balanced accuracy across three wind farms.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-pamm.202000112","title":"Machine Learning with Feature Importance Analysis for Tornado Prediction from Environmental Sounding Data","authors":["Brice E. Coffer","Michaela Kubacki","Yixin Wen","Ting Zhang","Carlos Barajas","Matthias K. Gobbert"],"date":"2021-01-01","year":2021,"venue":"PAMM","venue_type":"journal","ids":{"doi":"10.1002/pamm.202000112","openalex":"W3042754474"},"links":{"paper":"https://doi.org/10.1002/pamm.202000112"},"orgs":["noaa","university-of-oklahoma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Random forest on RUC pre-storm sounding data discriminates tornadic from nontornadic storms, with feature analysis showing pressure has little impact.","significance":2,"cited_by":8,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2104.14910","title":"Calibration of wind speed ensemble forecasts for power generation","authors":["Sándor Baran","Ágnes Baran"],"date":"2021-01-01","year":2021,"venue":"Időjárás","venue_type":"journal","ids":{"arxiv":"2104.14910","doi":"10.28974/idojaras.2021.4.4","openalex":"W3157494408"},"links":{"paper":"https://doi.org/10.28974/idojaras.2021.4.4","pdf":"https://www.met.hu/downloads.php?fn=/metadmin/newspaper/2021/12/8d9a70d11ac5d55e6b7213ae67c4438d-125-4-4-baran.pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A flexible machine learning method calibrates 100 m wind speed ensembles into truncated normal distributions, outperforming three EMOS variants and raw ensembles in a Hungarian case study.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2102.02892","title":"Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for Localized Surface Temperature Forecasting in an Urban Environment","authors":["Manzhu Yu","Fangcao Xu","Weiming Hu","Jian Sun","Guido Cervone"],"date":"2021-01-01","year":2021,"venue":"IEEE Access","venue_type":"journal","ids":{"arxiv":"2102.02892","doi":"10.1109/access.2021.3116809","openalex":"W3202925140"},"links":{"paper":"https://doi.org/10.1109/access.2021.3116809","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09552907.pdf"},"orgs":["ncar"],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Stacked LSTM forecasts day-ahead hourly temperature at about 150 m resolution on NYC IoT sensors, beating ARIMA and FNN, with Weather Underground history improving accuracy.","significance":3,"cited_by":70,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.24853-jasat.3.2.45-50","title":"Weather Forcast Optimization Using Learning Vector Quantization Methods with Genetic Algorithms","authors":["Siska Andriani","Kotim Subandi"],"date":"2020-12-31","year":2020,"venue_type":"other","ids":{"doi":"10.24853/jasat.3.2.45-50","openalex":"W3136881394"},"links":{"paper":"https://doi.org/10.24853/jasat.3.2.45-50"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Learning vector quantization tuned by a genetic algorithm reaches 73% accuracy for categorical weather forecasts in Citeko, Indonesia.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3157438366","title":"집중호우 시기 기계학습 및 PM기법을 이용한 수문학적 강우보정에 관한 연구","authors":["고철민","정영윤","지용근","이영미","김병식"],"date":"2020-12-30","year":2020,"venue_type":"other","ids":{"openalex":"W3157438366"},"links":{"paper":"https://db.koreascholar.com/Article?code=405460"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["radar","nwp-analysis","stations"],"status":"research","summary":"XGBoost with probability matching post-processes LENS and Dong-Nae forecasts, improving Korean heavy-rainfall QPF skill (Korean-language version).","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en14010158","title":"Probabilistic Forecasting of Wind Turbine Icing Related Production Losses Using Quantile Regression Forests","authors":["Jennie Molinder","Sebastian Scher","Erik Olof Nilsson","Heiner Körnich","Hans Bergström","Anna Sjöblom"],"date":"2020-12-30","year":2020,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en14010158","openalex":"W3117125377"},"links":{"paper":"https://doi.org/10.3390/en14010158","pdf":"https://www.mdpi.com/1996-1073/14/1/158/pdf?version=1609328626"},"orgs":[],"topic":"applications-impacts","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Quantile regression forests give probabilistic icing-related production-loss forecasts for Swedish wind parks, improved by physical icing model inputs.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14383-cri.2020.15.4.257","title":"A Study on Hydrological Rainfall Adjustment using Machine Learning and Probability Matching Method during Heavy Rainfall Season","authors":["(주)에코브레인 신사업개발팀","Chul-Min Ko","Yeong Yun Jeong","Yong-Keun Ji","Youngmi Lee","Byung Sik Kim"],"date":"2020-12-30","year":2020,"venue":"Journal of Climate Research","venue_type":"journal","ids":{"doi":"10.14383/cri.2020.15.4.257","openalex":"W3134409327"},"links":{"paper":"https://doi.org/10.14383/cri.2020.15.4.257"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar","stations"],"status":"research","summary":"XGBoost with probability matching post-processes LENS and Dong-Nae forecasts, improving Korean heavy-rainfall QPF skill over 14 events.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.15037","title":"Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networks","authors":["Jindong Han","Hao Liu","Hengshu Zhu","Hui Xiong","Dejing Dou"],"date":"2020-12-30","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.15037"},"links":{"paper":"https://arxiv.org/abs/2012.15037","pdf":"https://arxiv.org/pdf/2012.15037"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["gnn","rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"MasterGNN jointly predicts air quality and weather at monitoring stations using heterogeneous recurrent graph networks with multi-adversarial training, beating seven baselines.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6987","title":"Projected changes of typhoon intensity in a regional climate model: Development of a machine learning bias correction scheme","authors":["Jinkai Tan","Sheng Chen","Chia‐Ying Lee","Guangtao Dong","Wenyan Hu","Jun Wang"],"date":"2020-12-28","year":2020,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6987","openalex":"W3117541273"},"links":{"paper":"https://doi.org/10.1002/joc.6987"},"orgs":["columbia-leap"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"A machine-learning bias correction for a 25-km regional climate model raises simulated violent typhoon frequency from zero to match observations and projects increases under warming.","significance":4,"cited_by":8,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.29207-resti.v4i6.2456","title":"Implementation of Convolutional Neural Network and Multilayer Perceptron in Predicting Air Temperature in Padang","authors":["Isman Kurniawan","Lusi Sofiana Silaban","Devi Munandar"],"date":"2020-12-26","year":2020,"venue":"Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)","venue_type":"journal","ids":{"doi":"10.29207/resti.v4i6.2456","openalex":"W3113923396"},"links":{"paper":"https://doi.org/10.29207/resti.v4i6.2456","pdf":"http://jurnal.iaii.or.id/index.php/RESTI/article/download/2456/353"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares CNN, MLP and hybrid CNN-MLP for air temperature prediction at a Padang station; CNN gives the highest R2.","significance":1,"cited_by":9,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app11010125","title":"NowDeepN: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction","authors":["Gabriela Czibula","Andrei Mihai","Eugen Mihuleţ"],"date":"2020-12-24","year":2020,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app11010125","openalex":"W3113711264"},"links":{"paper":"https://doi.org/10.3390/app11010125","pdf":"https://www.mdpi.com/2076-3417/11/1/125/pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"pre-operational","summary":"NowDeepN ensemble of deep neural networks predicts future radar product values from past values, reaching under 4% normalised RMSE on Romanian radar data.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.energy.2020.119692","title":"EALSTM-QR: Interval wind-power prediction model based on numerical weather prediction and deep learning","authors":["Xiaosheng Peng","Hongyu Wang","Jianxun Lang","Wenze Li","Qiyou Xu","Zuowei Zhang","Tao Cai","Shanxu Duan","Fangjie Liu","Chaoshun Li"],"date":"2020-12-24","year":2020,"venue":"Energy","venue_type":"journal","ids":{"doi":"10.1016/j.energy.2020.119692","openalex":"W3117620741"},"links":{"paper":"https://doi.org/10.1016/j.energy.2020.119692"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"EALSTM-QR produces interval wind-power forecasts from numerical weather prediction inputs using deep learning; the title suggests an energy-sector application (no abstract).","significance":2,"cited_by":145,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.6046-gtzyyg.2020.04.19","title":"Research on downscaling of TRMM precipitation products based on deep learning: Exemplified by northeast China","authors":["Fangzhou Du","Yuli Shi","Xia Sheng"],"date":"2020-12-23","year":2020,"venue":"Guotu ziyuan yaogan","venue_type":"journal","ids":{"doi":"10.6046/gtzyyg.2020.04.19","openalex":"W3157775974"},"links":{"paper":"https://doi.org/10.6046/gtzyyg.2020.04.19"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":[],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Deep learning is applied to downscale TRMM satellite precipitation products over northeast China; the abstract is missing, so methods and results are unverified.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3111277298","title":"Storm-scale Ensemble-based Severe Weather Guidance: Development of an Object-based Verification Framework and Applications of Machine Learning","authors":["Montgomery L. Flora"],"date":"2020-12-18","year":2020,"venue":"SHAREOK (University of Oklahoma; Oklahoma State University; Central Oklahoma University)","venue_type":"preprint","ids":{"openalex":"W3111277298"},"links":{"paper":"https://hdl.handle.net/11244/326598"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval","post-processing"],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"Object-based verification of storm-scale mesocyclone probabilities, plus evaluation of ML calibrations of Warn-on-Forecast severe weather guidance.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-nhess-20-3551-2020","title":"Examining the operational use of avalanche problems with decision trees and model-generated weather and snowpack variables","authors":["Simon Horton","Moses Towell","Pascal Haegeli"],"date":"2020-12-18","year":2020,"venue":"Natural hazards and earth system sciences","venue_type":"journal","ids":{"doi":"10.5194/nhess-20-3551-2020","openalex":"W3083962070"},"links":{"paper":"https://doi.org/10.5194/nhess-20-3551-2020","pdf":"https://nhess.copernicus.org/articles/20/3551/2020/nhess-20-3551-2020.pdf"},"orgs":[],"topic":"applications-impacts","topics":["xai-uq-physics"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["nwp-analysis","other"],"status":"research","summary":"Conditional inference trees link modelled weather and snowpack variables to avalanche problem types in Glacier National Park, Canada.","significance":2,"cited_by":22,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10505473.1","title":"A Success Story: Advancing Outage Prediction Modeling Capabilities for Decision Making","authors":["William O. Taylor","Diego Cerrai","Marika Koukoula","Feifei Yang","Guannan Liang","Emmanouil N. Anagnostou"],"date":"2020-12-18","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10505473.1","openalex":"W3127703291"},"links":{"paper":"https://doi.org/10.1002/essoar.10505473.1"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"operational","summary":"Describes an operational ML ensemble that predicts storm-driven customer power outages along the US Eastern Seaboard using weather, land cover and infrastructure proxies.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3151308413","title":"Deep Learning for Climate Science and Extreme Weather Prediction I","authors":["Gemma J. Anderson"],"date":"2020-12-17","year":2020,"venue":"AGU Fall Meeting 2020","venue_type":"journal","ids":{"openalex":"W3151308413"},"links":{"paper":"https://agu.confex.com/agu/fm20/webprogram/Session107145.html"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"AGU 2020 session on deep learning for climate science and extreme weather prediction; a conference session listing with no technical content.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.bdr.2020.100179","title":"A Data-Driven Method for Hybrid Data Assimilation with Multilayer Perceptron","authors":["Lilan Huang","Hongze Leng","Xiaoyong Li","Kaijun Ren","Junqiang Song","Dongzi Wang"],"date":"2020-12-17","year":2020,"venue":"Big Data Research","venue_type":"journal","ids":{"doi":"10.1016/j.bdr.2020.100179","openalex":"W3111668569"},"links":{"paper":"https://doi.org/10.1016/j.bdr.2020.100179"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Multilayer perceptron-based method for hybrid data assimilation of atmospheric states (no abstract; classification based on title).","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.bdr.2020.100178","title":"Deep Learning-Based Weather Prediction: A Survey","authors":["Xiaoli Ren","Xiaoyong Li","Kaijun Ren","Junqiang Song","Zichen Xu","Kefeng Deng","Xiang Wang"],"date":"2020-12-17","year":2020,"venue":"Big Data Research","venue_type":"journal","ids":{"doi":"10.1016/j.bdr.2020.100178","openalex":"W3111294584"},"links":{"paper":"https://doi.org/10.1016/j.bdr.2020.100178"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":["other"],"timescale":["short","medium"],"spatial":["global"],"data":[],"status":"research","summary":"Survey of deep learning approaches to weather prediction across forecast horizons (no abstract available; classification based on title).","significance":3,"cited_by":263,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.09700","title":"RainNet: A Large-Scale Imagery Dataset and Benchmark for Spatial Precipitation Downscaling","authors":["Xuanhong Chen","Kairui Feng","Naiyuan Liu","Yifan Lu","Zhengyan Tong","Bingbing Ni","Ziang Liu","Ning Lin"],"date":"2020-12-17","year":2020,"venue":"Conference on Neural Information Processing Systems (NeurIPS) 2022","venue_type":"journal","ids":{"arxiv":"2012.09700","openalex":"W3112230558"},"links":{"paper":"https://arxiv.org/abs/2012.09700","pdf":"https://arxiv.org/pdf/2012.09700"},"orgs":[],"topic":"benchmarks-data-eval","topics":["downscaling"],"type":"benchmark","method":[],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Releases RainNet, a 62,400-pair precipitation downscaling dataset with 17 years of hourly maps and benchmarks 14 models, including deep learning baselines.","significance":5,"cited_by":2,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.09670","title":"RainBench: Towards Global Precipitation Forecasting from Satellite Imagery","authors":["Christian Schroeder de Witt","Catherine Tong","Valentina Zantedeschi","Daniele De Martini","Freddie Kalaitzis","Matthew Chantry","Duncan Watson-Parris","Piotr Bilinski"],"date":"2020-12-17","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.09670","openalex":"W4287551475"},"links":{"paper":"https://arxiv.org/abs/2012.09670","pdf":"https://arxiv.org/pdf/2012.09670"},"orgs":["university-of-oxford","inria"],"topic":"benchmarks-data-eval","topics":["global-medium-range"],"type":"benchmark","method":[],"timescale":["medium"],"spatial":["global"],"data":["satellite","era5","other"],"status":"research","summary":"RainBench is a multimodal global benchmark combining simulated satellite data, ERA5 and IMERG precipitation, with the PyRain library and medium-range baselines.","significance":5,"cited_by":5,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.09433","title":"Helping Reduce Environmental Impact of Aviation with Machine Learning","authors":["Ashish Kapoor"],"date":"2020-12-17","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.09433"},"links":{"paper":"https://arxiv.org/abs/2012.09433","pdf":"https://arxiv.org/pdf/2012.09433"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":[],"timescale":["short"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Uses machine learning to improve winds-aloft forecasts and an uncertainty-aware routing method, aiming to cut flight time and aviation's climate impact.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3196253607","title":"Deep Learning for Climate Science and Extreme Weather Prediction II Posters","authors":["Gemma J. Anderson"],"date":"2020-12-16","year":2020,"venue":"AGU Fall Meeting 2020","venue_type":"journal","ids":{"openalex":"W3196253607"},"links":{"paper":"https://agu.confex.com/agu/fm20/webprogram/Session104665.html"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"AGU 2020 poster session on deep learning for climate science and extreme weather prediction; a conference listing with no technical content.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.38007-nn.2020.010401","title":"Optimal Analysis of Weather Forecast Supporting Convolutional Neural Networks","authors":[],"date":"2020-12-16","year":2020,"venue":"International Journal of Neural Network","venue_type":"journal","ids":{"doi":"10.38007/nn.2020.010401","openalex":"W4312529626"},"links":{"paper":"https://doi.org/10.38007/nn.2020.010401"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"CNN-based weather forecast analysis, a low-visibility journal paper (no abstract; classification based on title).","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.09037","title":"Copula-based synthetic data augmentation for machine-learning emulators","authors":["David Meyer","Thomas Nagler","Robin J. Hogan"],"date":"2020-12-16","year":2020,"venue":"Geoscientific Model Development, 14(8), 5205--5215 (2021)","venue_type":"journal","ids":{"arxiv":"2012.09037","doi":"10.5194/gmd-14-5205-2021"},"links":{"paper":"https://arxiv.org/abs/2012.09037","pdf":"https://arxiv.org/pdf/2012.09037"},"orgs":[],"topic":"hybrid-parameterization","topics":["benchmarks-data-eval"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Copula-generated synthetic data augments training of a neural emulator of longwave radiation, reducing mean absolute error by up to 62% in a toy setting.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7217705723","title":"Exploration of the earth environment using “Himawari-8” data of meteorological satellite and deep learning","authors":["Ryuta Ando","Shigeto Watanabe","Ken T. Murata","Pichate Kunakornvong"],"date":"2020-12-15","year":2020,"venue":"UTK RESEARCH JOURNAL","venue_type":"journal","ids":{"openalex":"W7217705723"},"links":{"paper":"https://ph02.tci-thaijo.org/index.php/rmutk/article/view/240210","pdf":"https://ph02.tci-thaijo.org/index.php/rmutk/article/download/240210/164539"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A supervised model on 16 Himawari-8 spectral bands classifies typhoon, cloud, sea, land, snow and ice with 96.5% accuracy.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su122410499","title":"Using Deep Learning and Machine Learning Methods to Diagnose Hailstorms in Large-Scale Thermodynamic Environments","authors":["Farha Pulukool","Longzhuang Li","Chuntao Liu"],"date":"2020-12-15","year":2020,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su122410499","openalex":"W3111834364"},"links":{"paper":"https://doi.org/10.3390/su122410499","pdf":"https://www.mdpi.com/2071-1050/12/24/10499/pdf?version=1608195061"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["global"],"data":["era5","satellite"],"status":"research","summary":"Random forest, autoencoder and CNN models diagnose hailstorm occurrence globally from four ERA5 thermodynamic attributes, with random forest performing best.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.07830","title":"Identifying Opportunities for Skillful Weather Prediction with Interpretable Neural Networks","authors":["Elizabeth A. Barnes","Kirsten Mayer","Benjamin Toms","Zane Martin","Emily Gordon"],"date":"2020-12-14","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.07830","openalex":"W3111043129"},"links":{"paper":"https://arxiv.org/abs/2012.07830","pdf":"https://arxiv.org/pdf/2012.07830"},"orgs":["colorado-state-university"],"topic":"xai-uq-physics","topics":["s2s-seasonal"],"type":"model","method":["cnn"],"timescale":["s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Layer-wise relevance propagation applied to neural networks identifies atmospheric states associated with enhanced weather predictability, giving physical insight into predictability mechanisms.","significance":4,"cited_by":12,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.06825","title":"Physics-Informed Machine Learning Simulator for Wildfire Propagation","authors":["Luca Bottero","Francesco Calisto","Giovanni Graziano","Valerio Pagliarino","Martina Scauda","Sara Tiengo","Simone Azeglio"],"date":"2020-12-12","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.06825"},"links":{"paper":"https://arxiv.org/abs/2012.06825","pdf":"https://arxiv.org/pdf/2012.06825"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["physics-constrained"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Feasibility study replacing WRF-SFIRE numerical solvers with physics-informed machine learning in Julia to enable real-time wildfire spread simulation.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3194785918","title":"RainBench: Enabling Data-Driven Precipitation Forecasting on a Global Scale","authors":["Catherine Tong","Christian Schroder de Witt","Valentina Zantedeschi","Daniele De Martini","Freddie Kalaitzis","Matthew Chantry","Duncan Watson‐Parris","Piotr Biliński"],"date":"2020-12-11","year":2020,"venue_type":"other","ids":{"openalex":"W3194785918"},"links":{"paper":"https://www.climatechange.ai/papers/neurips2020/38/paper.pdf"},"orgs":[],"topic":"benchmarks-data-eval","topics":["global-medium-range"],"type":"benchmark","method":[],"timescale":["short"],"spatial":["global"],"data":["era5","satellite"],"status":"research","summary":"RainBench provides a global ML-ready dataset of precipitation and atmospheric variables for data-driven precipitation forecasting (no abstract; based on title).","significance":5,"cited_by":0,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3165529874","title":"Physics-augmented Deep Learning to Improve Tropical Cyclone Intensity and Size Estimation from Satellite Imagery","authors":["Jing‐Yi Zhuo"],"date":"2020-12-11","year":2020,"venue":"AGU Fall Meeting 2020","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-20-0333.1","openalex":"W3165529874"},"links":{"paper":"https://agu.confex.com/agu/fm20/webprogram/Paper690714.html"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["physics-constrained"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Physics-augmented deep learning estimates tropical cyclone intensity and size from satellite imagery; classified from title only, as no abstract was available.","significance":2,"cited_by":75,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-x5w59m","title":"Bias correction of global climate model using machine learning algorithms to determine meteorological variables in different tropical climates of Indonesia","authors":["Juan Nathaniel"],"date":"2020-12-11","year":2020,"venue_type":"other","ids":{"doi":"10.31223/x5w59m","openalex":"W3111867255"},"links":{"paper":"https://doi.org/10.31223/x5w59m","pdf":"http://eartharxiv.org/repository/object/1879/download/3967/"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional","local"],"data":["cmip","era5","stations"],"status":"research","summary":"Tree-based machine learning corrects climate model biases against Indonesian station observations, with ENSO included; savanna regions show the largest corrections, reaching about 36.67% improvement.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl091236","title":"Observational Constraints on Warm Cloud Microphysical Processes Using Machine Learning and Optimization Techniques","authors":["Jui-Yuan Christine Chiu","C. Kevin Yang","Peter Jan van Leeuwen","Graham Feingold","Robert Wood","Yann Blanchard","Fan Mei","Jian Wang"],"date":"2020-12-11","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl091236","openalex":"W3110725524"},"links":{"paper":"https://doi.org/10.1029/2020gl091236","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020GL091236"},"orgs":["noaa","university-of-washington","university-of-reading","colorado-state-university"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Machine-learning-constrained autoconversion and accretion parameterizations, fitted to Azores cloud-probe data, cut uncertainty to about 15% and 5% and reveal drizzle number's role.","significance":4,"cited_by":36,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.06679","title":"Convolutional LSTM Neural Networks for Modeling Wildland Fire Dynamics","authors":["John Burge","Matthew Bonanni","Matthias Ihme","Lily Hu"],"date":"2020-12-11","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.06679"},"links":{"paper":"https://arxiv.org/abs/2012.06679","pdf":"https://arxiv.org/pdf/2012.06679"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Trains a ConvLSTM on simulated data to model wildland fire spread under dynamic wind and terrain, finding it outperforms other architectures in capturing spread rate.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.06246","title":"EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts","authors":["Christian Requena-Mesa","Vitus Benson","Joachim Denzler","Jakob Runge","Markus Reichstein"],"date":"2020-12-11","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.06246","openalex":"W3196456148"},"links":{"paper":"https://arxiv.org/abs/2012.06246","pdf":"https://arxiv.org/pdf/2012.06246"},"orgs":[],"topic":"benchmarks-data-eval","topics":["applications-impacts"],"type":"benchmark","method":[],"timescale":["medium"],"spatial":["regional","local"],"data":["satellite","nwp-analysis","other"],"status":"research","summary":"Introduces EarthNet2021, a 32,000-sample dataset and challenge for forecasting 20 m Sentinel-2 imagery conditioned on 1.28 km weather forecasts, with a new EarthNetScore ranking.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-abd213","title":"Large-scale emulation of spatio-temporal variation in temperature under climate change","authors":["Xiao-Chen Yuan","Nan Zhang","Weizheng Wang","Yi‐Ming Wei"],"date":"2020-12-10","year":2020,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/abd213","openalex":"W3110964805"},"links":{"paper":"https://doi.org/10.1088/1748-9326/abd213","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/abd213/pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Nearest-neighbour Gaussian process and PCA emulators reproduce gridded Earth system model temperature responses to emission scenarios, enabling cheap projections for impact assessment.","significance":4,"cited_by":9,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.05960","title":"3D Scattering Tomography by Deep Learning with Architecture Tailored to Cloud Fields","authors":["Yael Sde-Chen","Yoav Y. Schechner","Vadim Holodovsky","Eshkol Eytan"],"date":"2020-12-10","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.05960"},"links":{"paper":"https://arxiv.org/abs/2012.05960","pdf":"https://arxiv.org/pdf/2012.05960"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"3DeepCT, a neural network tailored to stationary cloud fields, reconstructs 3D cloud volumes from multi-view images with orders-of-magnitude faster inference than physics-based methods.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su122410295","title":"Photovoltaic Power Prediction Using Artificial Neural Networks and Numerical Weather Data","authors":["Javier López Gómez","Ana Ogando-Martínez","Francisco Manuel Troncoso Pastoriza","Lara Febrero-Garrido","Enrique Granada","José A. Orosa"],"date":"2020-12-09","year":2020,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su122410295","openalex":"W3111374748"},"links":{"paper":"https://doi.org/10.3390/su122410295","pdf":"https://www.mdpi.com/2071-1050/12/24/10295/pdf?version=1607702444"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Neural network maps GDAS numerical weather data to photovoltaic power output at an Italian plant with under 10% error, even without local weather measurements.","significance":2,"cited_by":80,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2020.125862","title":"On the use of convolutional Gaussian processes to improve the seasonal forecasting of precipitation and temperature","authors":["Chao Wang","Wei Zhang","Gabriele Villarini"],"date":"2020-12-09","year":2020,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2020.125862","openalex":"W3112880004"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2020.125862"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Convolutional Gaussian processes are applied to improve seasonal forecasts of precipitation and temperature, targeting meteorological rather than hydrological variables.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.10396","title":"Cloud detection machine learning algorithms for PROBA-V","authors":["Luis Gómez-Chova","Gonzalo Mateo-García","Jordi Muñoz-Marí","Gustau Camps-Valls"],"date":"2020-12-09","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.10396","doi":"10.1109/igarss.2017.8127437"},"links":{"paper":"https://arxiv.org/abs/2012.10396","pdf":"https://arxiv.org/pdf/2012.10396"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Statistical machine learning cloud masking for Proba-V satellite scenes provides per-pixel cloud flags to reduce errors in land and sea biophysical retrievals.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.10395","title":"Transfer Learning with Convolutional Networks for Atmospheric Parameter Retrieval","authors":["David Malmgren-Hansen","Allan Aasbjerg Nielsen","Valero Laparra","Gustau Camps- Valls"],"date":"2020-12-09","year":2020,"venue":"2018 IEEE International Geoscience and Remote Sensing Symposium","venue_type":"journal","ids":{"arxiv":"2012.10395","doi":"10.1109/igarss.2018.8518097"},"links":{"paper":"https://arxiv.org/abs/2012.10395","pdf":"https://arxiv.org/pdf/2012.10395"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Transfers CNN features learned for one IASI physical variable to retrieve other atmospheric parameters, cutting retraining cost while matching models trained from scratch.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.10394","title":"Deep Learning for Climate Model Output Statistics","authors":["Michael Steininger","Daniel Abel","Katrin Ziegler","Anna Krause","Heiko Paeth","Andreas Hotho"],"date":"2020-12-09","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.10394"},"links":{"paper":"https://arxiv.org/abs/2012.10394","pdf":"https://arxiv.org/pdf/2012.10394"},"orgs":[],"topic":"post-processing","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"ConvMOS, a CNN for model output statistics, reduces precipitation errors in the REMO regional climate model and outperforms three common MOS approaches.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.10393","title":"A deep network approach to multitemporal cloud detection","authors":["Devis Tuia","Benjamin Kellenberger","Adrian Pérez-Suay","Gustau Camps-Valls"],"date":"2020-12-09","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.10393"},"links":{"paper":"https://arxiv.org/abs/2012.10393","pdf":"https://arxiv.org/pdf/2012.10393"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["rnn","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A recurrent convolutional network with temporal memory detects clouds in MSG SEVIRI image time series day and night with pixel-level confidence maps.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.05015","title":"Fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcasting","authors":["Vincent Bouget","Dominique Béréziat","Julien Brajard","Anastase Charantonis","Arthur Filoche"],"date":"2020-12-09","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"arxiv":"2012.05015","doi":"10.3390/rs13020246","openalex":"W3111510448"},"links":{"paper":"https://doi.org/10.3390/rs13020246","pdf":"https://arxiv.org/pdf/2012.05015"},"orgs":["lbnl-nersc"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"Fusing rain radar images with NWP wind forecasts in a deep network improves 30-minute rain nowcasts, scoring 8% higher F1 than optical flow and 7% higher than radar-only.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3129190311","title":"Hybrid Weather Prediction: A Blend of Machine Learning and Numerical Modeling","authors":["Troy Arcomano"],"date":"2020-12-08","year":2020,"venue":"AGU Fall Meeting 2020","venue_type":"journal","ids":{"openalex":"W3129190311"},"links":{"paper":"https://agu.confex.com/agu/fm20/webprogram/Paper770450.html"},"orgs":[],"topic":"hybrid-parameterization","topics":["global-medium-range"],"type":"position","method":["other"],"timescale":["short"],"spatial":["global"],"data":[],"status":"research","summary":"AGU 2020 presentation on blending machine learning with numerical weather models; a conference abstract with no detailed results.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.uclim.2020.100739","title":"Mapping urban temperature using crowd-sensing data and machine learning","authors":["Marius Zumwald","Benedikt Knüsel","David Niklaus Bresch","Reto Knutti"],"date":"2020-12-08","year":2020,"venue":"Urban Climate","venue_type":"journal","ids":{"doi":"10.1016/j.uclim.2020.100739","openalex":"W3112229965"},"links":{"paper":"https://doi.org/10.1016/j.uclim.2020.100739","pdf":"https://www.sciencedirect.com/science/article/pii/S2212095520301061/pdf"},"orgs":["meteoswiss","eth-zurich"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","satellite"],"status":"research","summary":"Quantile regression forest fuses 691 crowd-sourced citizen weather stations with open data to map Zurich urban temperature at 10 m resolution during a 2019 heatwave.","significance":3,"cited_by":99,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002217","title":"Process‐Based Climate Model Development Harnessing Machine Learning: I. A Calibration Tool for Parameterization Improvement","authors":["Fleur Couvreux","F. Hourdin","Daniel Williamson","Romain Roehrig","Victoria Volodina","Najda Villefranque","Catherine Rio","Olivier Audouin","James M. Salter","Éric Bazile","Florent Brient","Florence Favot","Rachel Honnert","Marie‐Pierre Lefebvre","Jean‐Baptiste Madeleine","Quentin Rodier","Wenzhe Xu"],"date":"2020-12-07","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002217","openalex":"W3049378437"},"links":{"paper":"https://doi.org/10.1029/2020ms002217","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002217"},"orgs":["meteo-france","alan-turing-institute"],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Gaussian process calibration tunes boundary-layer parameterization parameters against large-eddy simulations in single-column mode, before global model tuning.","significance":3,"cited_by":121,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.03630","title":"Randomized kernels for large scale Earth observation applications","authors":["Adrián Pérez-Suay","Julia Amorós-López","Luis Gómez-Chova","Valero Laparra","Jordi Muñoz-Marí","Gustau Camps-Valls"],"date":"2020-12-07","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.03630"},"links":{"paper":"https://arxiv.org/abs/2012.03630","pdf":"https://arxiv.org/pdf/2012.03630"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Random Fourier-feature kernel approximation enables fast retrieval of atmospheric parameters from IASI sounders, PROSAIL emulation and cloud detection on millions of samples.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.03338","title":"Understanding Climate Impacts on Vegetation with Gaussian Processes in Granger Causality","authors":["Miguel Morata-Dolz","Diego Bueso","Maria Piles","Gustau Camps-Valls"],"date":"2020-12-06","year":2020,"venue":"AI for Earth Sciences Workshop at NeurIPS 2020","venue_type":"journal","ids":{"arxiv":"2012.03338"},"links":{"paper":"https://arxiv.org/abs/2012.03338","pdf":"https://arxiv.org/pdf/2012.03338"},"orgs":[],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"A nonlinear Gaussian-process Granger causality method attributes global vegetation greenness to precipitation and soil moisture over 30 years of gridded satellite data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002225","title":"Process‐Based Climate Model Development Harnessing Machine Learning: II. Model Calibration From Single Column to Global","authors":["F. Hourdin","Daniel Williamson","Catherine Rio","Fleur Couvreux","Romain Roehrig","Najda Villefranque","Ionela Musat","F. Binta Diallo","Laurent Fairhead","Victoria Volodina"],"date":"2020-12-04","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002225","openalex":"W3047510468"},"links":{"paper":"https://doi.org/10.1029/2020ms002225"},"orgs":["meteo-france","alan-turing-institute"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml","physics-constrained"],"timescale":[],"spatial":["global"],"data":["km-scale-sim","other"],"status":"research","summary":"Emulator-based calibration of an atmospheric model's parameterizations against large-eddy simulations matches hand-tuned global performance while keeping process-level behaviour physically sound.","significance":4,"cited_by":83,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10505147.1","title":"Climate extremes factor attribution: a small data challenge in ML realm","authors":["Prashant Dave"],"date":"2020-12-03","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10505147.1","openalex":"W4241333000"},"links":{"paper":"https://doi.org/10.1002/essoar.10505147.1"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Random forests with SMOTE oversampling identify geopotential height and sensible heat flux as key drivers of Indian heatwave days, reaching an F1 score of 0.85.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.01598","title":"Graph Neural Networks for Improved El Niño Forecasting","authors":["Salva Rühling Cachay","Emma Erickson","Arthur Fender C. Bucker","Ernest Pokropek","Willa Potosnak","Salomey Osei","Björn Lütjens"],"date":"2020-12-02","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.01598","openalex":"W3107025976"},"links":{"paper":"https://arxiv.org/abs/2012.01598","pdf":"https://arxiv.org/pdf/2012.01598"},"orgs":[],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["gnn"],"timescale":["seasonal","s2s"],"spatial":["global"],"data":[],"status":"research","summary":"Spatiotemporal graph neural networks forecast ENSO at 1 and 3 months lead, outperforming state-of-the-art systems and modeling teleconnections more interpretably.","significance":4,"cited_by":17,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3724-sp.j.1089.2020.18250","title":"Ordinal Relation and Relative Learning for Foggy Image Visibility Detection","authors":["Qi Wu","Xiaowu Wang","Jun Zhang","Yi Xia","Peng Chen","Qing Yan"],"date":"2020-12-01","year":2020,"venue":"Journal of Computer-Aided Design & Computer Graphics","venue_type":"journal","ids":{"doi":"10.3724/sp.j.1089.2020.18250","openalex":"W3182777517"},"links":{"paper":"https://doi.org/10.3724/sp.j.1089.2020.18250"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Triplet-based ordinal deep learning estimates fog visibility from images, outperforming multiclass baselines on synthetic and real dense-fog datasets.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.gloei.2021.01.003","title":"Forecasting method of monthly wind power generation based on climate model and long short-term memory neural network","authors":["Rui Yin","Dengxuan Li","Yifeng Wang","Weidong Chen"],"date":"2020-12-01","year":2020,"venue":"Global Energy Interconnection","venue_type":"journal","ids":{"doi":"10.1016/j.gloei.2021.01.003","openalex":"W3126276509"},"links":{"paper":"https://doi.org/10.1016/j.gloei.2021.01.003","pdf":"https://www.sciencedirect.com/science/article/pii/S2096511721000037/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn"],"timescale":["seasonal"],"spatial":[],"data":["other"],"status":"research","summary":"An LSTM network maps climate-model meteorology to monthly wind power utilisation hours, giving medium- to long-term generation forecasts for power planning; the case study is limited.","significance":2,"cited_by":35,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46501-ijmtst061132","title":"Predicting Weather Conditions from Images","authors":["Shonima Minhas and Shreya Kapoor"],"date":"2020-11-30","year":2020,"venue":"International Journal for Modern Trends in Science and Technology","venue_type":"journal","ids":{"doi":"10.46501/ijmtst061132","openalex":"W3109215886"},"links":{"paper":"https://doi.org/10.46501/ijmtst061132","pdf":"https://doi.org/10.46501/ijmtst061132"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN classifies outdoor photographs into cloudy, rainy, shine and sunrise weather classes, comparing four CNN architectures with different depths.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w12123353","title":"CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles","authors":["Chiranjib Chaudhuri","Colin Robertson"],"date":"2020-11-30","year":2020,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w12123353","openalex":"W3093984799"},"links":{"paper":"https://doi.org/10.3390/w12123353","pdf":"https://www.mdpi.com/2073-4441/12/12/3353/pdf?version=1606721574"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"CliGAN, a Wasserstein GAN with structural similarity loss, downscales multi-model CMIP6 annual maximum precipitation to regional gridded fields.","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15407-vidbir2020.48.072","title":"Image segmentation of clouds based on deep learning","authors":["Bohdan Rusyn","Oleksiy Lutsyk","Rostyslav Kosarevych","Valentyna Korniy"],"date":"2020-11-30","year":2020,"venue":"Information extraction and processing","venue_type":"journal","ids":{"doi":"10.15407/vidbir2020.48.072","openalex":"W3109926590"},"links":{"paper":"https://doi.org/10.15407/vidbir2020.48.072"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"U-Net-based deep learning improves segmentation of atmospheric cloud images from aircraft and satellite sensors, with claimed real-time capability for weather monitoring.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002232","title":"Machine Learning for Model Error Inference and Correction","authors":["Massimo Bonavita","Patrick Laloyaux"],"date":"2020-11-30","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002232","openalex":"W3098905200"},"links":{"paper":"https://doi.org/10.1029/2020ms002232"},"orgs":["ecmwf"],"topic":"data-assimilation","topics":["hybrid-parameterization"],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Neural networks reproduce weak-constraint 4D-Var model error corrections in the operational ECMWF IFS and could extend correction to the whole atmospheric column.","significance":5,"cited_by":161,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3389-frwa.2020.536743","title":"Downscaling Satellite and Reanalysis Precipitation Products Using Attention-Based Deep Convolutional Neural Nets","authors":["Alexander Y. Sun","Guoqiang Tang"],"date":"2020-11-26","year":2020,"venue":"Frontiers in Water","venue_type":"journal","ids":{"doi":"10.3389/frwa.2020.536743","openalex":"W3108040709"},"links":{"paper":"https://doi.org/10.3389/frwa.2020.536743","pdf":"https://www.frontiersin.org/articles/10.3389/frwa.2020.536743/pdf"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","satellite","other"],"status":"research","summary":"Attention-based U-Net downscales ERA5-Land, TRMM and IMERG monthly precipitation to 1 km over Central Texas, using PRISM as target over 2001–2018.","significance":3,"cited_by":61,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2020.3040648","title":"PFST-LSTM: A SpatioTemporal LSTM Model With Pseudoflow Prediction for Precipitation Nowcasting","authors":["Chuyao Luo","Xutao Li","Yunming Ye"],"date":"2020-11-26","year":2020,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2020.3040648","openalex":"W3109184532"},"links":{"paper":"https://doi.org/10.1109/jstars.2020.3040648","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9314330/09272611.pdf","code":"https://github.com/luochuyao/PFST-LSTM"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"PFST-LSTM adds a spatial memory cell and position alignment to ConvLSTM for precipitation nowcasting, outperforming baselines on CIKM 2017 radar data.","significance":3,"cited_by":124,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jiot.2020.3040736","title":"Consensus Forecast of Rainfall Using Hybrid Climate Learning Model","authors":["Neethu Madhukumar","Eric Wang","Yifan Zhang","Wei Xiang"],"date":"2020-11-26","year":2020,"venue":"IEEE Internet of Things Journal","venue_type":"journal","ids":{"doi":"10.1109/jiot.2020.3040736","openalex":"W3107939130"},"links":{"paper":"https://doi.org/10.1109/jiot.2020.3040736"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A hybrid model selects the best climate model forecast with a probabilistic MLP, then uses a deep LSTM to produce next-day rainfall in Australian climate zones.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12233860","title":"Downscaling TRMM Monthly Precipitation Using Google Earth Engine and Google Cloud Computing","authors":["Abdelrazek Elnashar","Hongwei Zeng","Bingfang Wu","Ning Zhang","Fuyou Tian","Miao Zhang","Weiwei Zhu","Nana Yan","Zeqiang Chen","Zhiyu Sun","Xinghua Wu","Yuan Li"],"date":"2020-11-25","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12233860","openalex":"W3106583177"},"links":{"paper":"https://doi.org/10.3390/rs12233860","pdf":"https://www.mdpi.com/2072-4292/12/23/3860/pdf"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Gradient boosting, SVR and ANN downscale TRMM precipitation from 25 km to 1 km using vegetation indices, with the ANN performing best in the Mekong region.","significance":2,"cited_by":66,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020eo149637","title":"Boosting Weather Prediction with Machine Learning","authors":["Sarah Stanley"],"date":"2020-11-25","year":2020,"venue":"Eos","venue_type":"journal","ids":{"doi":"10.1029/2020eo149637","openalex":"W3109880999"},"links":{"paper":"https://doi.org/10.1029/2020eo149637"},"orgs":[],"topic":"benchmarks-data-eval","topics":[],"type":"benchmark","method":[],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Eos article introducing WeatherBench, an ERA5-based benchmark dataset for evaluating data-driven AI weather forecasting against standard baselines.","significance":4,"cited_by":0,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.12353","title":"FireSRnet: Geoscience-Driven Super-Resolution of Future Fire Risk from Climate Change","authors":["Tristan Ballard","Gopal Erinjippurath"],"date":"2020-11-24","year":2020,"venue_type":"preprint","ids":{"arxiv":"2011.12353","openalex":"W3106848048"},"links":{"paper":"https://arxiv.org/abs/2011.12353","pdf":"https://arxiv.org/pdf/2011.12353"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["satellite","cmip"],"status":"research","summary":"A super-resolution CNN enhances fire risk maps from climate models, outperforming interpolation at 4x and 8x and projecting risk for 2040 and 2100.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10504937.1","title":"Assessment of predictability in Downscaling GEFS Precipitation Forecasts","authors":["Smit Chetan Doshi","Tirthankar Roy"],"date":"2020-11-23","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10504937.1","openalex":"W3109044207"},"links":{"paper":"https://doi.org/10.1002/essoar.10504937.1"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Feedforward neural networks statistically downscale GEFS precipitation forecasts, assessing which predictors matter at each lead time up to 16 days.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.11705","title":"DeepClimGAN: A High-Resolution Climate Data Generator","authors":["Alexandra Puchko","Robert P. Link","Brian Hutchinson","Ben Kravitz","Abigail Snyder"],"date":"2020-11-23","year":2020,"venue_type":"preprint","ids":{"arxiv":"2011.11705","openalex":"W3107695222"},"links":{"paper":"http://arxiv.org/abs/2011.11705","pdf":"https://arxiv.org/pdf/2011.11705"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"DeepClimGAN, a conditional GAN, emulates Earth system model daily weather under chosen scenarios to sample extremes far more cheaply than full ESM runs.","significance":4,"cited_by":6,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.11313","title":"Deep-learning based down-scaling of summer monsoon rainfall data over Indian region","authors":["Bipin Kumar","Rajib Chattopadhyay","Manmeet Singh","Niraj Chaudhari","Karthik Kodari","Amit Barve"],"date":"2020-11-23","year":2020,"venue":"Theoretical and Applied Climatology 2021","venue_type":"journal","ids":{"arxiv":"2011.11313","doi":"10.1007/s00704-020-03489-6","openalex":"W3108599172"},"links":{"paper":"https://arxiv.org/abs/2011.11313","pdf":"https://arxiv.org/pdf/2011.11313"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other","era5"],"status":"research","summary":"Compares SRCNN variants and DeepSD for 4x downscaling of Indian summer monsoon rainfall, finding DeepSD gives the best spatial distribution and lowest RMSE.","significance":3,"cited_by":95,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12223825","title":"Applying Deep Learning to Clear-Sky Radiance Simulation for VIIRS with Community Radiative Transfer Model—Part 2: Model Architecture and Assessment","authors":["Xingming Liang","Quanhua Liu"],"date":"2020-11-21","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12223825","openalex":"W3109071147"},"links":{"paper":"https://doi.org/10.3390/rs12223825","pdf":"https://www.mdpi.com/2072-4292/12/22/3825/pdf?version=1611898920"},"orgs":["noaa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis","other"],"status":"research","summary":"A fully connected deep network emulates CRTM clear-sky VIIRS thermal radiances over global oceans, with mean biases near 0.01 K and standard deviations under 0.1 K.","significance":3,"cited_by":20,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10504858.1","title":"Assimilating GOES-R Latent Heating in FV3 using Machine Learning","authors":["Yoonjin Lee","Kyle Hilburn","Milija Županski","Ting‐Chi Wu"],"date":"2020-11-20","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10504858.1","openalex":"W3195057889"},"links":{"paper":"https://doi.org/10.1002/essoar.10504858.1"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"A CNN called GREMLIN fuses GOES-R ABI and GLM data into synthetic radar reflectivity, proposed to feed convective-scale data assimilation and latent heating initialization.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10504854.1","title":"Inferring Airmass Properties from GOES-R ABI Observations","authors":["Kyle Hilburn"],"date":"2020-11-20","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10504854.1","openalex":"W3193434426"},"links":{"paper":"https://doi.org/10.1002/essoar.10504854.1"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"CNNs infer airmass properties such as moisture and instability from GOES-R ABI imagery, offering an automated alternative to sparse radiosondes for NWP and forecasters.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41612-020-00148-5","title":"Predicting global patterns of long-term climate change from short-term simulations using machine learning","authors":["L. A. Mansfield","P. J. Nowack","M. Kasoar","R. G. Everitt","W. J. Collins","A. Voulgarakis"],"date":"2020-11-19","year":2020,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"doi":"10.1038/s41612-020-00148-5","openalex":"W3098916164"},"links":{"paper":"https://doi.org/10.1038/s41612-020-00148-5"},"orgs":["university-of-reading"],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Machine learning maps short-term climate model responses to long-term temperature change under forcing scenarios, enabling cheaper climate projections.","significance":4,"cited_by":114,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2011.09733","title":"Preparing Weather Data for Real-Time Building Energy Simulation","authors":["Maryam MeshkinKiya","Riccardo Paolini"],"date":"2020-11-19","year":2020,"venue_type":"preprint","ids":{"arxiv":"2011.09733"},"links":{"paper":"https://arxiv.org/abs/2011.09733","pdf":"https://arxiv.org/pdf/2011.09733"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural network imputation of missing and anomalous station temperature and humidity data outperforms interpolation and other supervised methods for building simulation inputs.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35762-aer.2021.43.1.1","title":"Change in Rainfall Patterns in the Hilly Region of Uttarakhand due to the Impact of Climate Change","authors":["Dilip Kumar","Rajib Kumar Bhattacharjya"],"date":"2020-11-18","year":2020,"venue":"Applied Environmental Research","venue_type":"journal","ids":{"doi":"10.35762/aer.2021.43.1.1","openalex":"W3107819176"},"links":{"paper":"https://doi.org/10.35762/aer.2021.43.1.1"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"An ANN with PCA statistically downscales CanESM2 projections to Uttarakhand districts, projecting monsoon rainfall changes of up to 200% under RCP8.5.","significance":2,"cited_by":15,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-20-0058.1","title":"Deep-Learning-Based Gridded Downscaling of Surface Meteorological Variables in Complex Terrain. Part II: Daily Precipitation","authors":["Yingkai Sha","David John Gagne","Gregory West","Roland B. Stull"],"date":"2020-11-16","year":2020,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-20-0058.1","openalex":"W3099309371"},"links":{"paper":"https://doi.org/10.1175/jamc-d-20-0058.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/apme/59/12/jamc-d-20-0058.1.pdf"},"orgs":["ncar"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Nest-UNet, a UNet variant with nested skip connections, downscales daily precipitation from 0.25° to 4 km over western North America, outperforming bias-correction baselines.","significance":3,"cited_by":129,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-20-0057.1","title":"Deep-Learning-Based Gridded Downscaling of Surface Meteorological Variables in Complex Terrain. Part I: Daily Maximum and Minimum 2-m Temperature","authors":["Yingkai Sha","David John Gagne","Gregory West","Roland B. Stull"],"date":"2020-11-16","year":2020,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-20-0057.1","openalex":"W3105660549"},"links":{"paper":"https://doi.org/10.1175/jamc-d-20-0057.1"},"orgs":["ncar"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"UNet-AE adds an elevation autoencoder branch to downscale daily TMAX/TMIN from 0.25° to 4 km, cutting MAE by over 10% in unseen regions.","significance":3,"cited_by":141,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002226","title":"Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization","authors":["Peter Ukkonen","Robert L. Pincus","Robin James Hogan","Kristian Pagh Nielsen","Eigil Kaas"],"date":"2020-11-16","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002226","openalex":"W3100028353"},"links":{"paper":"https://doi.org/10.1029/2020ms002226","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002226"},"orgs":["ecmwf","noaa"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural networks replace gas optics in the RRTMGP radiation scheme, running 1–6 times faster with heating-rate errors below 0.1 K/day, giving 3.5x faster longwave fluxes.","significance":4,"cited_by":80,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-7897824","title":"A Climate Downscaling Deep Learning Model considering the Multiscale Spatial Correlations and Chaos of Meteorological Events","authors":["Bin Mu","Bo Qin","Shijin Yuan","Xiaoyun Qin"],"date":"2020-11-15","year":2020,"venue":"Mathematical Problems in Engineering","venue_type":"journal","ids":{"doi":"10.1155/2020/7897824","openalex":"W3098061809"},"links":{"paper":"https://doi.org/10.1155/2020/7897824","pdf":"https://downloads.hindawi.com/journals/mpe/2020/7897824.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A two-stage deep learning climate downscaling network with stepwise reconstruction and ensemble inference captures multiscale spatial correlations and extremes better than simple SISR analogies.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.00678","title":"Meta-modeling strategy for data-driven forecasting","authors":["Dominic J. Skinner","Romit Maulik"],"date":"2020-11-14","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.00678"},"links":{"paper":"https://arxiv.org/abs/2012.00678","pdf":"https://arxiv.org/pdf/2012.00678"},"orgs":[],"topic":"climate-emulation","topics":["benchmarks-data-eval"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Meta-modeling uses cheap low-fidelity models to skip costly high-fidelity evaluations when predicting temperature fields, giving an adaptive training strategy for geophysical emulation.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2020.536337","title":"Comparison of Different Methods for Spatial Downscaling of GPM IMERG V06B Satellite Precipitation Product Over a Typical Arid to Semi-Arid Area","authors":["Cheng Chen","Qiuwen Chen","Binni Qin","Shuhe Zhao","Zheng Duan"],"date":"2020-11-13","year":2020,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2020.536337","openalex":"W3098062448"},"links":{"paper":"https://doi.org/10.3389/feart.2020.536337","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2020.536337/pdf"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Compares two regression and three ML methods (ANN, SVM, RF) for downscaling IMERG to 1 km over Gansu; ML beats regression against 80 rain gauges.","significance":2,"cited_by":42,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-020-01930-w","title":"Western North Pacific tropical cyclone track forecasts by a machine learning model","authors":["Jinkai Tan","Sheng Chen","Jun Wang"],"date":"2020-11-13","year":2020,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-020-01930-w","openalex":"W3098487652"},"links":{"paper":"https://doi.org/10.1007/s00477-020-01930-w"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning model for western North Pacific tropical cyclone track forecasts; abstract unavailable, so method details and skill cannot be verified.","significance":3,"cited_by":30,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12223712","title":"Partitioning Global Surface Energy and Their Controlling Factors Based on Machine Learning","authors":["Xiuliang Yuan","Friday Uchenna Ochege","Philippe De Maeyer","Alishir Kurban"],"date":"2020-11-12","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12223712","openalex":"W3105369412"},"links":{"paper":"https://doi.org/10.3390/rs12223712","pdf":"https://www.mdpi.com/2072-4292/12/22/3712/pdf?version=1606139321"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["era5","satellite","stations"],"status":"research","summary":"Random forest models using FLUXNET, reanalysis and LAI explain 53–90% of global latent and sensible heat flux variance, linking contrasting flux trends mainly to rising CO2.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.00679","title":"Using Machine Learning to Calibrate Storm-Scale Probabilistic Guidance of Severe Weather Hazards in the Warn-on-Forecast System","authors":["Montgomery Flora","Corey K. Potvin","Patrick S. Skinner","Shawn Handler","Amy McGovern"],"date":"2020-11-12","year":2020,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"arxiv":"2012.00679","doi":"10.1175/mwr-d-20-0194.1","openalex":"W3135540785"},"links":{"paper":"https://doi.org/10.1175/mwr-d-20-0194.1","pdf":"https://arxiv.org/pdf/2012.00679"},"orgs":["noaa","university-of-oklahoma"],"topic":"post-processing","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Random forests, gradient-boosted trees and logistic regression calibrate NOAA Warn-on-Forecast ensemble guidance for tornado, hail and wind, beating updraft-helicity baselines.","significance":4,"cited_by":67,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.06125","title":"Hurricane Forecasting: A Novel Multimodal Machine Learning Framework","authors":["Léonard Boussioux","Cynthia Zeng","Théo Guénais","Dimitris Bertsimas"],"date":"2020-11-11","year":2020,"venue":"2022, Weather and Forecasting, 37(6), 817-831","venue_type":"journal","ids":{"arxiv":"2011.06125","doi":"10.1175/waf-d-21-0091.1","openalex":"W3105826485"},"links":{"paper":"https://arxiv.org/abs/2011.06125","pdf":"https://arxiv.org/pdf/2011.06125"},"orgs":["mit"],"topic":"extremes-hazards","topics":["global-medium-range"],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis","other"],"status":"pre-operational","summary":"Hurricast combines encoder-decoder features with gradient-boosted trees for 24-hour tropical cyclone track and intensity, matching operational skill in seconds and improving NHC consensus.","significance":4,"cited_by":65,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.05586","title":"Strict Enforcement of Conservation Laws and Invertibility in CNN-Based Super Resolution for Scientific Datasets","authors":["Andrew Geiss","Joseph C. Hardin"],"date":"2020-11-11","year":2020,"venue_type":"preprint","ids":{"arxiv":"2011.05586","openalex":"W3210121282"},"links":{"paper":"https://arxiv.org/abs/2011.05586","pdf":"https://arxiv.org/pdf/2011.05586"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["radar","satellite","other"],"status":"research","summary":"Adds a differentiable operator to CNN super-resolution so outputs exactly conserve low-resolution averages, demonstrated on radar, satellite and climate model data.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-8408931","title":"A Precipitation Nowcasting Mechanism for Real-World Data Based on Machine Learning","authors":["Yanfei Xiang","Jianbing Ma","Xi Wu"],"date":"2020-11-10","year":2020,"venue":"Mathematical Problems in Engineering","venue_type":"journal","ids":{"doi":"10.1155/2020/8408931","openalex":"W3103277094"},"links":{"paper":"https://doi.org/10.1155/2020/8408931","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/2020/8408931"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Machine learning precipitation nowcasting from Hubei radar reflectivity handles missing radar data and outperforms optical flow, with a mechanism for single and cumulative altitudes.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.04811","title":"Machine learning methods for the detection of polar lows in satellite mosaics: major issues and their solutions","authors":["Mikhail Krinitskiy","Polina Verezemskaya","Svyatoslav Elizarov","Sergey Gulev"],"date":"2020-11-09","year":2020,"venue_type":"preprint","ids":{"arxiv":"2011.04811"},"links":{"paper":"https://arxiv.org/abs/2011.04811","pdf":"https://arxiv.org/pdf/2011.04811"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Deep CNN approach detects polar mesocyclones and polar lows in satellite mosaics, addressing class imbalance and scale filtering for satellite data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.04452","title":"Comparison between ARIMA and Deep Learning Models for Temperature Forecasting","authors":["Eranga De Saa","Lochandaka Ranathunga"],"date":"2020-11-09","year":2020,"venue_type":"preprint","ids":{"arxiv":"2011.04452","openalex":"W3103881545"},"links":{"paper":"https://arxiv.org/abs/2011.04452","pdf":"https://arxiv.org/pdf/2011.04452"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["cnn","rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares ARIMA with a hybrid 1D-CNN plus LSTM network for hourly temperature forecasting in Szeged, finding the deep model outperforms ARIMA.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app10217915","title":"M2GSNet: Multi-Modal Multi-Task Graph Spatiotemporal Network for Ultra-Short-Term Wind Farm Cluster Power Prediction","authors":["Hang Fan","Xuemin Zhang","Shengwei Mei","Kunjin Chen","Xinyang Chen"],"date":"2020-11-08","year":2020,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app10217915","openalex":"W3098580617"},"links":{"paper":"https://doi.org/10.3390/app10217915","pdf":"https://www.mdpi.com/2076-3417/10/21/7915/pdf?version=1605064028"},"orgs":["tsinghua-university"],"topic":"applications-impacts","topics":[],"type":"model","method":["gnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Graph neural network fuses wind farm power history with NWP inputs and multi-task learning to predict ultra-short-term power for all farms in a cluster.","significance":2,"cited_by":49,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.03303","title":"Deep coastal sea elements forecasting using U-Net based models","authors":["Jesús García Fernández","Ismail Alaoui Abdellaoui","Siamak Mehrkanoon"],"date":"2020-11-06","year":2020,"venue":"Knowledge-Based Systems","venue_type":"journal","ids":{"arxiv":"2011.03303","doi":"10.1016/j.knosys.2022.109445","openalex":"W3100761977"},"links":{"paper":"https://doi.org/10.1016/j.knosys.2022.109445","pdf":"https://arxiv.org/pdf/2011.03303"},"orgs":[],"topic":"regional-km-scale","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"U-Net variants with residual, parallel and asymmetric convolutions forecast multi-step coastal Netherlands sea elements from hourly Copernicus data, with the best model winning on frame prediction.","significance":3,"cited_by":39,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.mlwa.2020.100008","title":"Machine learning based multi-index prediction of aviation turbulence over the Asia-Pacific","authors":["K. K. Hon","Cho Wing Ng","Pak Wai Chan"],"date":"2020-11-05","year":2020,"venue":"Machine Learning with Applications","venue_type":"journal","ids":{"doi":"10.1016/j.mlwa.2020.100008","openalex":"W3097793621"},"links":{"paper":"https://doi.org/10.1016/j.mlwa.2020.100008","pdf":"https://www.sciencedirect.com/science/article/pii/S2666827020300086/pdf"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"XGBoost combines NWP turbulence indices into a multi-index consensus, raising aviation turbulence forecast skill by 3–17% over Asia-Pacific against pilot reports.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2020.105337","title":"CNN-based near-real-time precipitation estimation from Fengyun-2 satellite over Xinjiang, China","authors":["Mei Xue","Renlong Hang","Qingshan Liu","Xiao–Tong Yuan","Xinyu Lu"],"date":"2020-11-05","year":2020,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2020.105337","openalex":"W3096052669"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2020.105337"},"orgs":["nuist","cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"CNN retrieves near-real-time precipitation from FengYun-2 satellite imagery over Xinjiang, China; no abstract was available, so this summary is based on the title.","significance":2,"cited_by":59,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2011.03081","title":"Machine Learning Climate Model Dynamics: Offline versus Online Performance","authors":["Noah D. Brenowitz","Brian Henn","Jeremy McGibbon","Spencer K. Clark","Anna Kwa","W. Andre Perkins","Oliver Watt-Meyer","Christopher S. Bretherton"],"date":"2020-11-05","year":2020,"venue_type":"preprint","ids":{"arxiv":"2011.03081","openalex":"W3101098605"},"links":{"paper":"https://arxiv.org/abs/2011.03081","pdf":"https://arxiv.org/pdf/2011.03081"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"evaluation","method":["classical-ml"],"timescale":["medium","climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Compares random forest and neural network moist-physics parameterizations trained on a 3 km global simulation; NN wins offline but crashes within 7 days when coupled.","significance":4,"cited_by":32,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12213598","title":"Reconstruction and Nowcasting of Rainfall Field by Oblique Earth-Space Links Network: Preliminary Results from Numerical Simulation","authors":["Minghao Xian","Xichuan Liu","Kun Song","Taichang Gao"],"date":"2020-11-02","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12213598","openalex":"W3095770262"},"links":{"paper":"https://doi.org/10.3390/rs12213598"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Simulated oblique Earth-space link network reconstructs rainfall fields (RMSE under 3.46 mm/h) and a deep learning model nowcasts rain cell motion and peak intensity.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3111839714","title":"A Prognostic Approach For Precipitation Forecast Using Naive Bayes Algorithm","authors":["Razeef Mohd","Abeena Mohi-u-din Azad","Anwaar Ahmad Wani","Idrees Ahmad Bhat"],"date":"2020-11-01","year":2020,"venue":"Solid State Technology","venue_type":"journal","ids":{"openalex":"W3111839714"},"links":{"paper":"http://solidstatetechnology.us/index.php/JSST/article/view/4603"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Naive Bayes classifier predicts daily precipitation for Srinagar from five selected weather attributes, reported as accurate against observed station data.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-15502287.2020.1841335","title":"Nowcasting prediction of wind speed using computational intelligence and wavelet in Brazil","authors":["Pedro Júnior Zucatelli","Erick Giovani Sperandio Nascimento","Alex Álisson Bandeira Santos","Davidson Martins Moreira"],"date":"2020-11-01","year":2020,"venue":"International Journal for Computational Methods in Engineering Science and Mechanics","venue_type":"journal","ids":{"doi":"10.1080/15502287.2020.1841335","openalex":"W3096993295"},"links":{"paper":"https://doi.org/10.1080/15502287.2020.1841335"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid wavelet-packet and RNN models nowcast 100–150 m wind speed at three Brazilian tower sites; an RNN with discrete Meyer wavelet performed best.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.71465-ajainn143","title":"Neural Networks for Climate Change Predictions: Opportunities and Challenges","authors":["Dr. Olivia Roberts"],"date":"2020-10-31","year":2020,"venue":"American Journal of Artificial Intelligence and Neural Networks","venue_type":"journal","ids":{"doi":"10.71465/ajainn143","openalex":"W7143742335"},"links":{"paper":"https://doi.org/10.71465/ajainn143","pdf":"https://australiansciencejournals.com/ajainn/article/download/143/140"},"orgs":["university-of-oxford"],"topic":"climate-emulation","topics":[],"type":"review","method":["other"],"timescale":["climate"],"spatial":["global"],"data":[],"status":"research","summary":"Overview of neural networks for climate change prediction, discussing opportunities and challenges without new methods or quantitative results.","significance":1,"cited_by":0,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.21585080","title":"Efficient Weather Prediction Model using Relevant Machine Learning Approach","authors":["Abhishek Pandey","Harsha Khanna"],"date":"2020-10-30","year":2020,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.21585080","openalex":"W3131521663"},"links":{"paper":"https://doi.org/10.5281/zenodo.21585080"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Garbled, low-quality abstract on machine learning for temperature and rainfall prediction; no clear method, data or quantitative result.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20944-preprints202010.0648.v1","title":"Deep Learning for Satellite Rainfall Retrieval Using Himawari-8 Multiple Spectral Channels","authors":["Jenq‐Dar Tsay","Kevin Kao","Chun-Chieh Chao","Yu‐Cheng Chang"],"date":"2020-10-30","year":2020,"venue":"Preprints.org","venue_type":"preprint","ids":{"doi":"10.20944/preprints202010.0648.v1","openalex":"W3095052343"},"links":{"paper":"https://doi.org/10.20944/preprints202010.0648.v1","pdf":"https://www.preprints.org/manuscript/202010.0648/v1/download"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","stations"],"status":"pre-operational","summary":"PERSIANN-CWB uses a deeper convolutional autoencoder CNN on Himawari-8 infrared and water vapor channels, improving rainfall retrieval over Taiwan relative to the prior CNN version.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2020.3032353","title":"Prediction of ENSO Beyond Spring Predictability Barrier Using Deep Convolutional LSTM Networks","authors":["Mayuna Gupta","Hariprasad Kodamana","S. Sandeep"],"date":"2020-10-29","year":2020,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2020.3032353","openalex":"W3097124628"},"links":{"paper":"https://doi.org/10.1109/lgrs.2020.3032353"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"ConvLSTM predicts the Niño3.4 index up to one year ahead, overcoming the spring predictability barrier and capturing strong El Niño events.","significance":3,"cited_by":44,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-020-75508-5","title":"Exploring the long-term changes in the Madden Julian Oscillation using machine learning","authors":["Panini Dasgupta","Abirlal Metya","C. V. Naidu","Manmeet Singh","Mathew Koll Roxy"],"date":"2020-10-29","year":2020,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-020-75508-5","openalex":"W3095637399"},"links":{"paper":"https://doi.org/10.1038/s41598-020-75508-5","pdf":"https://www.nature.com/articles/s41598-020-75508-5.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml","cnn"],"timescale":["s2s"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"Support vector regression and CNN reconstruct the RMM MJO index back to 1905, improving on prior regression by up to 4% and revealing a 22-27% rise in MJO intensity.","significance":3,"cited_by":41,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.15158","title":"CNN Profiler on Polar Coordinate Images for Tropical Cyclone Structure Analysis","authors":["Boyo Chen","Buo-Fu Chen","Chun-Min Hsiao"],"date":"2020-10-28","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.15158"},"links":{"paper":"https://arxiv.org/abs/2010.15158","pdf":"https://arxiv.org/pdf/2010.15158"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing","benchmarks-data-eval"],"type":"benchmark","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"CNN on polar-coordinate satellite images profiles full tropical cyclone structure parameters and wind profiles, with a new labeled benchmark dataset as baseline.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.14977","title":"Real-time Tropical Cyclone Intensity Estimation by Handling Temporally Heterogeneous Satellite Data","authors":["Boyo Chen","Buo-Fu Chen","Yun-Nung Chen"],"date":"2020-10-28","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.14977"},"links":{"paper":"https://arxiv.org/abs/2010.14977","pdf":"https://arxiv.org/pdf/2010.14977"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn","gan-vae"],"timescale":["nowcast"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"GAN-CNN framework trains on visible and passive microwave data and estimates tropical cyclone intensity from IR and water vapor images every 15 minutes, versus 3-hourly before.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11111157","title":"Precipitation Nowcasting with Weather Radar Images and Deep Learning in São Paulo, Brasil","authors":["Suzanna Maria Bonnet","Alexandre G. Evsukoff","Carlos Augusto Morales"],"date":"2020-10-27","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11111157","openalex":"W3097431378"},"links":{"paper":"https://doi.org/10.3390/atmos11111157","pdf":"https://www.mdpi.com/2073-4433/11/11/1157/pdf?version=1603782051"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Applies the PredRNN++ video prediction model to São Paulo radar reflectivity sequences, forecasting up to 1 h ahead as a nowcasting aid.","significance":3,"cited_by":39,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019jg005619","title":"Constraining Uncertainty in Projected Gross Primary Production With Machine Learning","authors":["Manuel Schlund","Veronika Eyring","Gustau Camps‐Valls","Pierre Friedlingstein","Pierre Gentine","Markus Reichstein"],"date":"2020-10-27","year":2020,"venue":"Journal of Geophysical Research Biogeosciences","venue_type":"journal","ids":{"doi":"10.1029/2019jg005619","openalex":"W3097560197"},"links":{"paper":"https://doi.org/10.1029/2019jg005619","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2019JG005619"},"orgs":["columbia-leap","mpi-biogeochemistry"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global","regional"],"data":["cmip"],"status":"research","summary":"Combines an emergent constraint with machine learning to narrow CMIP5 end-of-century GPP to 171 ± 12 Gt C/yr and reduce gridded projection uncertainty.","significance":3,"cited_by":49,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-020-03446-3","title":"Developing drought index–based forecasts for tropical climates using wavelet neural network: an application in Fiji","authors":["Anshuka Anshuka","Alexander Buzacott","W. Vervoort","Floris van Ogtrop"],"date":"2020-10-27","year":2020,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-020-03446-3","openalex":"W3096413988"},"links":{"paper":"https://doi.org/10.1007/s00704-020-03446-3"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Wavelet neural network forecasts drought indices for Fiji tropical stations, applying a hybrid wavelet-ANN approach to seasonal drought prediction; abstract not provided.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.14610","title":"Improving seasonal forecast using probabilistic deep learning","authors":["Baoxiang Pan","Gemma J. Anderson","AndrE Goncalves","Donald D. Lucas","CEline J. W. Bonfils","Jiwoo Lee"],"date":"2020-10-27","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2010.14610","doi":"10.1029/2021ms002766","openalex":"W3097095651"},"links":{"paper":"https://doi.org/10.1029/2021ms002766","pdf":"https://arxiv.org/pdf/2010.14610"},"orgs":[],"topic":"s2s-seasonal","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A probabilistic deep network trained on climate simulations beats a dynamical seasonal system for precipitation and temperature, with saliency analysis of ENSO-driven predictability.","significance":5,"cited_by":49,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.14300","title":"Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams using Machine Learning","authors":["Manu Tom","Rajanie Prabha","Tianyu Wu","Emmanuel Baltsavias","Laura Leal-Taixe","Konrad Schindler"],"date":"2020-10-27","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.14300"},"links":{"paper":"https://arxiv.org/abs/2010.14300","pdf":"https://arxiv.org/pdf/2010.14300"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"Semantic segmentation of VIIRS, MODIS and webcam images maps Swiss lake ice cover and ice-on/off dates, reaching mIoU above 93% for satellites and releasing a webcam benchmark.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.14100","title":"A Multi-task Two-stream Spatiotemporal Convolutional Neural Network for Convective Storm Nowcasting","authors":["W. Zhang","H. Liu","P. Li","L. Han"],"date":"2020-10-27","year":2020,"venue":"2020 IEEE International Conference on Big Data (Big Data), 2020, pp. 3953-3960","venue_type":"journal","ids":{"arxiv":"2010.14100","doi":"10.1109/bigdata50022.2020.9377890"},"links":{"paper":"https://arxiv.org/abs/2010.14100","pdf":"https://arxiv.org/pdf/2010.14100"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"A multi-task two-stream CNN fuses radar and satellite data for convective storm nowcasting, using pixel-wise sampling to handle class imbalance.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11111151","title":"Prediction of Short-Time Cloud Motion Using a Deep-Learning Model","authors":["Xinyue Su","Tiejian Li","Chenge An","Guangqian Wang"],"date":"2020-10-26","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11111151","openalex":"W3096763162"},"links":{"paper":"https://doi.org/10.3390/atmos11111151","pdf":"https://www.mdpi.com/2073-4433/11/11/1151/pdf?version=1603771964"},"orgs":["tsinghua-university"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Multi-GRU-RCN model forecasts intra-hour cloud motion from FengYun-2G infrared imagery, outperforming optical flow, ConvLSTM and GRU baselines.","significance":3,"cited_by":31,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.13903","title":"T$^2$-Net: A Semi-supervised Deep Model for Turbulence Forecasting","authors":["Denghui Zhang","Yanchi Liu","Wei Cheng","Bo Zong","Jingchao Ni","Zhengzhang Chen","Haifeng Chen","Hui Xiong"],"date":"2020-10-26","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.13903"},"links":{"paper":"https://arxiv.org/abs/2010.13903","pdf":"https://arxiv.org/pdf/2010.13903"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"model","method":["cnn","rnn","gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Semi-supervised ConvLSTM encoder-decoder with dual label guessing forecasts aviation air turbulence from weather data, improving accuracy under scarce turbulence labels.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2012.00688","title":"Short term solar energy prediction by machine learning algorithms","authors":["Farah Shahid","Aneela Zameer","Mudasser Afzal","Muhammad Hassan"],"date":"2020-10-25","year":2020,"venue_type":"preprint","ids":{"arxiv":"2012.00688"},"links":{"paper":"https://arxiv.org/abs/2012.00688","pdf":"https://arxiv.org/pdf/2012.00688"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Random forest and ridge regression on GEFS forecast grids predict daily solar energy at 98 stations, with random forest giving the best accuracy.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.12996","title":"Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models with Real-Geography Boundary Conditions","authors":["Griffin Mooers","Mike Pritchard","Tom Beucler","Jordan Ott","Galen Yacalis","Pierre Baldi","Pierre Gentine"],"date":"2020-10-24","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2010.12996","doi":"10.1029/2020ms002385","openalex":"W3094331675"},"links":{"paper":"https://doi.org/10.1029/2020ms002385","pdf":"https://arxiv.org/pdf/2010.12996"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Feed-forward DNNs emulate cloud superparameterization with real geography, explaining over 70% of mid-to-upper tropospheric temporal variance at 15-minute scale.","significance":4,"cited_by":52,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3212152148","title":"Solar Power Forecast Using Artificial Neural Network Techniques","authors":["Talaye Talakoobi"],"date":"2020-10-23","year":2020,"venue_type":"other","ids":{"openalex":"W3212152148"},"links":{"paper":"https://webthesis.biblio.polito.it/15873/"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Compares LSTM, LSTNet and TCN for short-term solar power forecasting; TCN performs best and sunny/cloudy clustering improves accuracy.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.12605","title":"Using machine learning to correct model error in data assimilation and forecast applications","authors":["Alban Farchi","Patrick Laloyaux","Massimo Bonavita","Marc Bocquet"],"date":"2020-10-23","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.12605","doi":"10.1002/qj.4116"},"links":{"paper":"https://arxiv.org/abs/2010.12605","pdf":"https://arxiv.org/pdf/2010.12605"},"orgs":[],"topic":"data-assimilation","topics":["hybrid-parameterization"],"type":"model","method":["cnn","physics-constrained"],"timescale":["medium"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Hybrid model combines a knowledge-based quasi-geostrophic model with deep learning, learned iteratively within 4D-Var, to correct model error and improve short- to mid-range forecasts.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-20-0080.1","title":"Improving Radar-Based Precipitation Nowcasts with Machine Learning Using an Approach Based on Random Forest","authors":["Yiwen Mao","Asgeir Sorteberg"],"date":"2020-10-22","year":2020,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-20-0080.1","openalex":"W3093785987"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0080.1"},"orgs":[],"topic":"nowcasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis","stations"],"status":"research","summary":"Random forest post-processing of radar nowcasts and NWP for hourly precipitation occurrence at 41 Norwegian stations, improving skill and reducing false alarms.","significance":3,"cited_by":39,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.11946","title":"Prediction of Temperature and Rainfall in Bangladesh using Long Short Term Memory Recurrent Neural Networks","authors":["Mohammad Mahmudur Rahman Khan","Md. Abu Bakr Siddique","Shadman Sakib","Anas Aziz","Ihtyaz Kader Tasawar","Ziad Hossain"],"date":"2020-10-22","year":2020,"venue":"2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","venue_type":"journal","ids":{"arxiv":"2010.11946","doi":"10.1109/ismsit50672.2020.9254585"},"links":{"paper":"https://arxiv.org/abs/2010.11946","pdf":"https://arxiv.org/pdf/2010.11946"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM forecasts month-wise temperature and rainfall in Bangladesh using 115 years of station data, with a mean temperature error of -0.38 C over two years.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.11787","title":"Prediction of Rainfall in Rajasthan, India using Deep and Wide Neural Network","authors":["Vikas Bajpai","Anukriti Bansal","Kshitiz Verma","Sanjay Agarwal"],"date":"2020-10-22","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.11787"},"links":{"paper":"https://arxiv.org/abs/2010.11787","pdf":"https://arxiv.org/pdf/2010.11787"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Deep-and-wide network with convolutional features and latitude/longitude inputs predicts rainfall across Rajasthan from historical time series, compared against MLP, LSTM and CNN baselines.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2020.3031244","title":"Learnable Optical Flow Network for Radar Echo Extrapolation","authors":["Chengwei Zhang","Xudong Zhou","Xiaoyong Zhuge","Meng Xu"],"date":"2020-10-21","year":2020,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2020.3031244","openalex":"W3094401231"},"links":{"paper":"https://doi.org/10.1109/jstars.2020.3031244","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/9314330/09234687.pdf"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Fully convolutional learnable optical-flow network extrapolates six years of Guangdong radar mosaics, outperforming optical flow and other deep models for convective nowcasting.","significance":3,"cited_by":22,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-8882279","title":"Application of Offshore Visibility Forecast Based on Temporal Convolutional Network and Transfer Learning","authors":["Zhenyu Lu","Zheng Cheng","Ting-Ya Yang"],"date":"2020-10-20","year":2020,"venue":"Computational Intelligence and Neuroscience","venue_type":"journal","ids":{"doi":"10.1155/2020/8882279","openalex":"W3093852439"},"links":{"paper":"https://doi.org/10.1155/2020/8882279","pdf":"https://downloads.hindawi.com/journals/cin/2020/8882279.pdf"},"orgs":["nuist"],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Applies a temporal convolutional network with transfer learning to forecast offshore visibility at Haikou Station, improving 24 h forecast scores and beating the CUACE model on TS score by 0.16.","significance":2,"cited_by":9,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.10374","title":"Dynamical Landscape and Multistability of a Climate Model","authors":["Georgios Margazoglou","Tobias Grafke","Alessandro Laio","Valerio Lucarini"],"date":"2020-10-20","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.10374","doi":"10.1098/rspa.2021.0019"},"links":{"paper":"https://arxiv.org/abs/2010.10374","pdf":"https://arxiv.org/pdf/2010.10374"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Combines quasipotential landscape theory and manifold learning to locate multistable climate states in an intermediate-complexity model, finding a third stable intermediate state.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.09947","title":"Use of neural networks for stable, accurate and physically consistent parameterization of subgrid atmospheric processes with good performance at reduced precision","authors":["Janni Yuval","Paul A. O'Gorman","Chris N. Hill"],"date":"2020-10-20","year":2020,"venue":"Geophysical Research Letters, 48, e2020GL091363 (2021)","venue_type":"journal","ids":{"arxiv":"2010.09947","doi":"10.1029/2020gl091363","openalex":"W3129165870"},"links":{"paper":"https://arxiv.org/abs/2010.09947","pdf":"https://arxiv.org/pdf/2010.09947"},"orgs":["mit"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Physically constrained neural network subgrid parameterization trained on high-resolution simulations stays stable in coupled runs and tolerates reduced numerical precision.","significance":5,"cited_by":141,"score":40,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-20-0079.1","title":"Graph-Guided Regularized Regression of Pacific Ocean Climate Variables to Increase Predictive Skill of Southwestern U.S. Winter Precipitation","authors":["Abby Stevens","Rebecca M. Willett","Antonios Mamalakis","Efi Foufoula‐Georgiou","Alejandro Tejedor","James T. Randerson","Padhraic Smyth","Stephen J. Wright"],"date":"2020-10-19","year":2020,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-20-0079.1","openalex":"W3108142464"},"links":{"paper":"https://doi.org/10.1175/jcli-d-20-0079.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/clim/34/2/JCLI-D-20-0079.1.pdf"},"orgs":["university-of-chicago"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Graph-guided regularized regression on Pacific sea surface temperatures improves seasonal winter precipitation prediction in the southwestern US over benchmark regularizers and teleconnection models.","significance":3,"cited_by":14,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-07055900.2020.1843393","title":"Neural Network Classification of Ice-Crystal Images Observed by an Airborne Cloud Imaging Probe","authors":["Zepei Wu","Shuo Liu","Delong Zhao","Ling Yang","Zixin Xu","Zhipeng Yang","Wei Zhou","Hui He","Mengyu Huang","Dantong Liu","Ruijie Li","Deping Ding"],"date":"2020-10-19","year":2020,"venue":"ATMOSPHERE-OCEAN","venue_type":"journal","ids":{"doi":"10.1080/07055900.2020.1843393","openalex":"W3110448726"},"links":{"paper":"https://doi.org/10.1080/07055900.2020.1843393"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A transfer-learned EfficientNet-b6 CNN classifies airborne cloud-probe ice-crystal images with 98% average precision, supporting cloud microphysics research.","significance":2,"cited_by":18,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.09694","title":"Data Assimilation Networks","authors":["Pierre Boudier","Anthony Fillion","Serge Gratton","Selime Gürol","Sixin Zhang"],"date":"2020-10-19","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.09694"},"links":{"paper":"https://arxiv.org/abs/2010.09694","pdf":"https://arxiv.org/pdf/2010.09694"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Deep recurrent architecture learns data assimilation with approximate prior and posterior densities, matching EnKF performance on the Lorenz-95 toy system with Gaussian errors.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12203420","title":"Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning","authors":["Alexandra I. Khalyasmaa","Stanislav A. Eroshenko","Valeriy A. Tashchilin","Ramachandran Hariprakash","T. Chakravarthi","Денис Бутусов"],"date":"2020-10-18","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12203420","openalex":"W3093800066"},"links":{"paper":"https://doi.org/10.3390/rs12203420"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Industry day-ahead photovoltaic forecasting system using weather forecast inputs reports over 92% accuracy on sunny days and 83% on cloudy days.","significance":2,"cited_by":23,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.09031","title":"Living in the Physics and Machine Learning Interplay for Earth Observation","authors":["Gustau Camps-Valls","Daniel H. Svendsen","Jordi Cortés-Andrés","Álvaro Moreno-Martínez","Adrián Pérez-Suay","Jose Adsuara","Irene Martín","Maria Piles","Jordi Muñoz-Marí","Luca Martino"],"date":"2020-10-18","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.09031"},"links":{"paper":"https://arxiv.org/abs/2010.09031","pdf":"https://arxiv.org/pdf/2010.09031"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"position","method":["physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Position paper outlining an agenda for combining physics and machine learning in Earth system science, covering equation discovery, physics constraints, parameterizations and emulation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-ws.2020.267","title":"Information gain-based modular fuzzy neural network to forecast rainstorms","authors":["Xiaoyan Huang","Li He","Huasheng Zhao","Ying Huan","Wu Yushuang"],"date":"2020-10-17","year":2020,"venue":"Water Science & Technology Water Supply","venue_type":"journal","ids":{"doi":"10.2166/ws.2020.267","openalex":"W3111972659"},"links":{"paper":"https://doi.org/10.2166/ws.2020.267"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["other","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Modular fuzzy neural network with information-gain predictor selection improves 24 h heavy-rainfall forecasts from ECMWF output over Guangxi stations.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl089444","title":"Evaluation of Neural Network Emulations for Radiation Parameterization in Cloud Resolving Model","authors":["Soonyoung Roh","Hwan‐Jin Song"],"date":"2020-10-17","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl089444","openalex":"W3041848413"},"links":{"paper":"https://doi.org/10.1029/2020gl089444","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020GL089444"},"orgs":["kma"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Neural network radiation emulators in a cloud-resolving model run 20–100 times faster and, run frequently, improve 6 h forecast accuracy over infrequent original radiation calls.","significance":3,"cited_by":50,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2310.17356","title":"Sky Imager-Based Forecast of Solar Irradiance Using Machine Learning","authors":["Anas Al-lahham","Obaidah Theeb","Khaled Elalem","Tariq A. Alshawi","Saleh A. Alshebeili"],"date":"2020-10-16","year":2020,"venue":"Electronics","venue_type":"journal","ids":{"arxiv":"2310.17356","doi":"10.3390/electronics9101700","openalex":"W3093189042"},"links":{"paper":"https://doi.org/10.3390/electronics9101700","pdf":"https://www.mdpi.com/2079-9292/9/10/1700/pdf?version=1603349707"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Estimates short-term solar irradiance from sky images with low computational cost, forecasting up to 4 h ahead on 16 years of data.","significance":3,"cited_by":55,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-0221-15-10-p10014","title":"Calibration method of meteorological sensor based on enhanced BP network","authors":["Y. M. Wang","Kebin Jia","P.Y. Liu","Wei‐bo Zhang","Jiankun Yang"],"date":"2020-10-15","year":2020,"venue":"Journal of Instrumentation","venue_type":"journal","ids":{"doi":"10.1088/1748-0221/15/10/p10014","openalex":"W3121203298"},"links":{"paper":"https://doi.org/10.1088/1748-0221/15/10/p10014","pdf":"https://iopscience.iop.org/article/10.1088/1748-0221/15/10/P10014/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Uses an enhanced back-propagation network with Gaussian activation and Levenberg-Marquardt training to calibrate an atmospheric pressure sensor, cutting MSE from 5.93 to 0.77 on a microcontroller.","significance":1,"cited_by":12,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.07445","title":"Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data","authors":["Fantine Huot","R. Lily Hu","Matthias Ihme","Qing Wang","John Burge","Tianjian Lu","Jason Hickey","Yi-Fan Chen","John Anderson"],"date":"2020-10-15","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.07445"},"links":{"paper":"https://arxiv.org/abs/2010.07445","pdf":"https://arxiv.org/pdf/2010.07445"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Compares four deep learning models on nearly a decade of remote sensing, weather and fire records, reaching 83% AUC for wildfire likelihood.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-20-0074.1","title":"Radar Super Resolution Using a Deep Convolutional Neural Network","authors":["Andrew Geiss","Joseph Clinton Hardin"],"date":"2020-10-12","year":2020,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-20-0074.1","openalex":"W3110128403"},"links":{"paper":"https://doi.org/10.1175/jtech-d-20-0074.1"},"orgs":["university-of-washington"],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"A deep CNN super-resolves NEXRAD radar reflectivity, outperforming interpolation at 4x and 8x resolution increases on objective and perceptual metrics after six months of training data.","significance":3,"cited_by":46,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-20-0177.1","title":"PERSIANN Dynamic Infrared–Rain Rate (PDIR-Now): A Near-Real-Time, Quasi-Global Satellite Precipitation Dataset","authors":["Phu Nguyen","Mohammed Ombadi","Vesta Afzali Gorooh","Eric Jay Shearer","Mojtaba Sadeghi","Soroosh Sorooshian","Kuolin Hsu","David T. Bolvin","Martin F. Ralph"],"date":"2020-10-12","year":2020,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-20-0177.1","openalex":"W3107195989"},"links":{"paper":"https://doi.org/10.1175/jhm-d-20-0177.1","pdf":"https://www.osti.gov/servlets/purl/1850278"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"benchmark","method":["classical-ml"],"timescale":["nowcast"],"spatial":["global"],"data":["satellite","stations"],"status":"operational","summary":"PDIR-Now provides hourly quasi-global infrared-based precipitation at 0.04° with 15-60 min latency, improving the critical success index to 0.53 from 0.47 over PERSIANN-CCS.","significance":3,"cited_by":138,"score":67,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12065-020-00505-6","title":"Analysis on intelligent machine learning enabled with meta-heuristic algorithms for solar irradiance prediction","authors":["T. Vaisakh","R. Jayabarathi"],"date":"2020-10-11","year":2020,"venue":"Evolutionary Intelligence","venue_type":"journal","ids":{"doi":"10.1007/s12065-020-00505-6","openalex":"W3092132485"},"links":{"paper":"https://doi.org/10.1007/s12065-020-00505-6"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Analysis of machine learning with meta-heuristic optimisation for solar irradiance prediction; no abstract is available to confirm results.","significance":1,"cited_by":41,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.enbuild.2020.110543","title":"Generating future weather files under climate change scenarios to support building energy simulation – A machine learning approach","authors":["Mirata Hosseini","Anahita Bigtashi","Bruno Lee"],"date":"2020-10-10","year":2020,"venue":"Energy and Buildings","venue_type":"journal","ids":{"doi":"10.1016/j.enbuild.2020.110543","openalex":"W3091890796"},"links":{"paper":"https://doi.org/10.1016/j.enbuild.2020.110543"},"orgs":[],"topic":"applications-impacts","topics":["downscaling"],"type":"application","method":["other"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Uses a machine learning approach to generate future weather files under climate change scenarios for building energy simulation; no abstract available.","significance":2,"cited_by":82,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11101072","title":"Increasing Neurons or Deepening Layers in Forecasting Maximum Temperature Time Series?","authors":["Trang Thi Kieu Tran","Taesam Lee","Jong‐Suk Kim"],"date":"2020-10-09","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11101072","openalex":"W3092157780"},"links":{"paper":"https://doi.org/10.3390/atmos11101072","pdf":"https://www.mdpi.com/2073-4433/11/10/1072/pdf?version=1602749163"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Studies how ANN parameter count and hidden-layer depth affect one-day-ahead maximum temperature forecasts at South Korean stations, with a five-layer, 49-parameter model giving the lowest RMSE.","significance":2,"cited_by":39,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10504498.1","title":"Deep learning classification of potentially severe convective storms in a changing climate","authors":["María J. Molina","David John Gagne","Andreas Franz Prein"],"date":"2020-10-08","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10504498.1","openalex":"W3097792698"},"links":{"paper":"https://doi.org/10.1002/essoar.10504498.1"},"orgs":["ncar"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","km-scale-sim"],"status":"research","summary":"A CNN trained on current-climate storms skillfully classifies strongly rotating, potentially severe convection in end-of-century climate simulations, generalizing to future conditions.","significance":3,"cited_by":0,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.04051","title":"HECT: High-Dimensional Ensemble Consistency Testing for Climate Models","authors":["Niccolò Dalmasso","Galen Vincent","Dorit Hammerling","Ann B. Lee"],"date":"2020-10-08","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.04051","openalex":"W3214343389"},"links":{"paper":"https://arxiv.org/abs/2010.04051","pdf":"https://arxiv.org/pdf/2010.04051"},"orgs":[],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Uses probabilistic classifiers, including tree-based models and neural networks, for a goodness-of-fit test checking CESM climate simulation ensemble consistency after code changes.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.05783","title":"Structural Forecasting for Tropical Cyclone Intensity Prediction: Providing Insight with Deep Learning","authors":["Trey McNeely","Niccolò Dalmasso","Kimberly M. Wood","Ann B. Lee"],"date":"2020-10-07","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.05783","openalex":"W3092495915"},"links":{"paper":"https://arxiv.org/abs/2010.05783","pdf":"https://arxiv.org/pdf/2010.05783"},"orgs":[],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"model","method":[],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep learning framework monitors physically relevant predictors and their relationships to aid human forecasters in tropical cyclone intensity change prediction.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.03293","title":"Stochastic parameterization with VARX processes","authors":["Nick Verheul","Daan Crommelin"],"date":"2020-10-07","year":2020,"venue":"Commun. Appl. Math. Comput. Sci. 16 (2021) 33-57","venue_type":"journal","ids":{"arxiv":"2010.03293","doi":"10.2140/camcos.2021.16.33"},"links":{"paper":"https://arxiv.org/abs/2010.03293","pdf":"https://arxiv.org/pdf/2010.03293"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A diagonal-structured VARX process parameterizes small-scale Lorenz '96 features, matching unimodal and trimodal invariant distributions with few parameters.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-8887364","title":"Comparison of Machine-Learning Algorithms for Near-Surface Air-Temperature Estimation from FY-4A AGRI Data","authors":["Ke Zhou","Hailei Liu","Xiaobo Deng","Hao Wang","Shenglan Zhang"],"date":"2020-10-06","year":2020,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2020/8887364","openalex":"W3092290657"},"links":{"paper":"https://doi.org/10.1155/2020/8887364","pdf":"https://downloads.hindawi.com/journals/amete/2020/8887364.pdf"},"orgs":["nuist","cma"],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"Compares six ML models for near-surface air temperature from FY-4A satellite data; XGBoost gives R² 0.902 and RMSE 1.946 °C.","significance":3,"cited_by":10,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2020.3026944","title":"Estimating Retrieval Errors From Neural Network Inversion Schemes—Application to the Retrieval of Temperature Profiles From IASI","authors":["Filipe Aires","Victor Pellet"],"date":"2020-10-06","year":2020,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2020.3026944","openalex":"W3092116406"},"links":{"paper":"https://doi.org/10.1109/tgrs.2020.3026944"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Input-space clustering scheme estimates retrieval uncertainty for neural-network IASI temperature profile retrievals, useful for NWP assimilation.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.02866","title":"Machine-Learned Preconditioners for Linear Solvers in Geophysical Fluid Flows","authors":["Jan Ackmann","Peter D. Düben","Tim N. Palmer","Piotr K. Smolarkiewicz"],"date":"2020-10-06","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.02866"},"links":{"paper":"https://arxiv.org/abs/2010.02866","pdf":"https://arxiv.org/pdf/2010.02866"},"orgs":["ecmwf","ncar","university-of-oxford"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Machine-learned preconditioners for the semi-implicit linear solver in a shallow-water model are competitive with conventional preconditioners and generalize beyond the training range.","significance":3,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.34257-gjsfrhvol20is4pg5","title":"Estimation of Hurricane Intensity from ATMS-Derived Temperature Anomaly using Machine Learning","authors":["Lin Lin"],"date":"2020-10-05","year":2020,"venue":"Global Journal of Human Social Science","venue_type":"journal","ids":{"doi":"10.34257/gjsfrhvol20is4pg5","openalex":"W3092616178"},"links":{"paper":"https://doi.org/10.34257/gjsfrhvol20is4pg5"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Support vector regression on ATMS satellite warm-core temperature anomalies estimates Atlantic hurricane intensity, with Pmin error of 7.23 hPa when day of year is included.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.02275","title":"Short-term prediction of photovoltaic power generation using Gaussian process regression","authors":["Yahya Al Lawati","Jack Kelly","Dan Stowell"],"date":"2020-10-05","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.02275"},"links":{"paper":"https://arxiv.org/abs/2010.02275","pdf":"https://arxiv.org/pdf/2010.02275"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Gaussian process regression forecasts 48-hour and 4-hour photovoltaic output in the UK, using sky cloud coverage as a predictor.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2010.01282","title":"TCLNet: Learning to Locate Typhoon Center Using Deep Neural Network","authors":["Chao Tan"],"date":"2020-10-03","year":2020,"venue_type":"preprint","ids":{"arxiv":"2010.01282"},"links":{"paper":"https://arxiv.org/abs/2010.01282","pdf":"https://arxiv.org/pdf/2010.01282"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"TCLNet, a lightweight fully convolutional network with a new typhoon center dataset, locates typhoon centers with 14.4% higher accuracy and 92.7% fewer parameters.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4018-ijwsr.2020100102","title":"Real-Time Weather Analytics","authors":["Lavanya K V","Sathyan Venkatanarayanan","Anay Anand Bhoraskar"],"date":"2020-10-01","year":2020,"venue":"International Journal of Web Services Research","venue_type":"journal","ids":{"doi":"10.4018/ijwsr.2020100102","openalex":"W3091965409"},"links":{"paper":"https://doi.org/10.4018/ijwsr.2020100102"},"orgs":[],"topic":"local-forecasting","topics":["infra-software"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Proposes a streaming pipeline in which an LSTM continuously learns from live OpenWeatherMap feeds via Kafka to forecast temperature and precipitation for agriculture; no quantitative results reported.","significance":1,"cited_by":7,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app10196878","title":"Application of Machine Learning Techniques to Delineate Homogeneous Climate Zones in River Basins of Pakistan for Hydro-Climatic Change Impact Studies","authors":["Ammara Nusrat","Hamza Farooq Gabriel","Sajjad Haider","Shakil Ahmad","Muhammad Shahid","Saad Ahmed Jamal"],"date":"2020-10-01","year":2020,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app10196878","openalex":"W3090569372"},"links":{"paper":"https://doi.org/10.3390/app10196878","pdf":"https://www.mdpi.com/2076-3417/10/19/6878/pdf?version=1601514968"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Applies machine learning clustering to delineate homogeneous climate zones in Pakistan's Indus sub-basins for selecting GCMs and projecting seasonal precipitation trends to 2099.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33564-ijeast.2020.v05i06.022","title":"WEATHER FORECASTING USING REGRESSION","authors":["Sahil Makhijani","Anurag Dubey","Ankush Makhijani"],"date":"2020-10-01","year":2020,"venue":"International Journal of Engineering Applied Sciences and Technology","venue_type":"journal","ids":{"doi":"10.33564/ijeast.2020.v05i06.022","openalex":"W3133504073"},"links":{"paper":"https://doi.org/10.33564/ijeast.2020.v05i06.022","pdf":"https://doi.org/10.33564/ijeast.2020.v05i06.022"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Explores a generic regression model for weather forecasting over long periods; the abstract reports it is outperformed by professional services.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22115-scce.2020.242813.1251","title":"Simulation of Monthly Precipitation in Semnan City Using ANN Artificial Intelligence Model","authors":["Hamidreza Ghazvinian","Hossein Bahrami","Hossein Ghazvinian","Salim Heddam"],"date":"2020-10-01","year":2020,"venue":"DOAJ (DOAJ: Directory of Open Access Journals)","venue_type":"preprint","ids":{"doi":"10.22115/scce.2020.242813.1251","openalex":"W3087367702"},"links":{"paper":"https://doi.org/10.22115/scce.2020.242813.1251"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies an ANN to simulate monthly precipitation in Semnan, Iran from temperature, humidity, wind and pressure inputs, with the best scenario reaching R² of 0.86.","significance":1,"cited_by":16,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-4018042","title":"Multimodal Semisupervised Deep Graph Learning for Automatic Precipitation Nowcasting","authors":["Kaichao Miao","Wei Wang","Rui Hu","Lei Zhang","Yali Zhang","Xiang Wang","Fudong Nian"],"date":"2020-10-01","year":2020,"venue":"Mathematical Problems in Engineering","venue_type":"journal","ids":{"doi":"10.1155/2020/4018042","openalex":"W3091524508"},"links":{"paper":"https://doi.org/10.1155/2020/4018042","pdf":"https://downloads.hindawi.com/journals/mpe/2020/4018042.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Multimodal semisupervised graph convolutional framework fuses meteorological and non-meteorological data to nowcast precipitation, including areas lacking radar coverage.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl090309","title":"Enabling Smart Dynamical Downscaling of Extreme Precipitation Events With Machine Learning","authors":["Xiaoming Shi"],"date":"2020-09-29","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl090309","openalex":"W3048943496"},"links":{"paper":"https://doi.org/10.1029/2020gl090309"},"orgs":[],"topic":"extremes-hazards","topics":["downscaling"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"CNNs pre-screen GCM circulation data so only a small subset needs kilometre-scale dynamical downscaling, retaining 92–98% of extreme precipitation events.","significance":4,"cited_by":27,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.12931","title":"Classification and understanding of cloud structures via satellite images with EfficientUNet","authors":["Tashin Ahmed","Noor Hossain Nuri Sabab"],"date":"2020-09-27","year":2020,"venue":"SN Computer Science","venue_type":"journal","ids":{"arxiv":"2009.12931","doi":"10.1007/s42979-021-00981-2","openalex":"W4225648146"},"links":{"paper":"https://doi.org/10.1007/s42979-021-00981-2","pdf":"https://arxiv.org/pdf/2009.12931"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"EfficientNet encoder with UNet decoder classifies satellite shallow-cloud organization patterns, scoring a Dice of about 66% on a Kaggle benchmark.","significance":2,"cited_by":71,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12193160","title":"Development of a Machine Learning-Based Radiometric Bias Correction for NOAA’s Microwave Integrated Retrieval System (MiRS)","authors":["Yan Zhou","Christopher Grassotti"],"date":"2020-09-26","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12193160","openalex":"W3090941517"},"links":{"paper":"https://doi.org/10.3390/rs12193160","pdf":"https://www.mdpi.com/2072-4292/12/19/3160/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"A deep neural network dynamic radiometric bias correction for ATMS radiances in MiRS improves temperature and humidity profile retrievals over ocean.","significance":3,"cited_by":17,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w12102685","title":"Tropical Cyclone Intensity Change Prediction Based on Surrounding Environmental Conditions with Deep Learning","authors":["Xin Wang","Wenke Wang","Bing Sheng Yan"],"date":"2020-09-25","year":2020,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w12102685","openalex":"W3088132247"},"links":{"paper":"https://doi.org/10.3390/w12102685","pdf":"https://www.mdpi.com/2073-4441/12/10/2685/pdf?version=1601039716"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"A 3D-CNN on surrounding atmosphere and ocean fields predicts 24 h tropical cyclone intensity change, improving MAE and intensification classification accuracy.","significance":3,"cited_by":47,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2020.105281","title":"Improving ECMWF short-term intensive rainfall forecasts using generative adversarial nets and deep belief networks","authors":["Huosheng Xie","Lidong Wu","Wei Xie","Qing Lin","Ming Liu","Yongjing Lin"],"date":"2020-09-25","year":2020,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2020.105281","openalex":"W3088110263"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2020.105281"},"orgs":["cma"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["gan-vae","other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Applies GANs and deep belief networks to improve ECMWF short-term intense rainfall forecasts; the abstract is missing, so reported gains are unverified.","significance":2,"cited_by":22,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijrte.b3266.099320","title":"Projection of Temperature and Precipitation using Multiple Linear Regression and Artificial Neural Network as a Downscaling Methodology for Upper Bhima Basin","authors":["Dattatray Kisan Rajmane","Milind L. Waikar"],"date":"2020-09-24","year":2020,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.b3266.099320","openalex":"W4213241522"},"links":{"paper":"https://doi.org/10.35940/ijrte.b3266.099320"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional","local"],"data":["cmip","stations"],"status":"research","summary":"An ANN outperforms multiple linear regression for downscaling GCM temperature and precipitation projections over the Upper Bhima basin in India.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-e22101075","title":"Can Short and Partial Observations Reduce Model Error and Facilitate Machine Learning Prediction?","authors":["Nan Chen"],"date":"2020-09-24","year":2020,"venue":"Entropy","venue_type":"journal","ids":{"doi":"10.3390/e22101075","openalex":"W3088522085"},"links":{"paper":"https://doi.org/10.3390/e22101075","pdf":"https://www.mdpi.com/1099-4300/22/10/1075/pdf?version=1603417295"},"orgs":[],"topic":"data-assimilation","topics":["climate-emulation"],"type":"model","method":["other"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"A conditional sampling method uses short partial observations to generate training data that reduces model error and improves machine learning forecasts of turbulent and climate-like systems.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jksuci.2020.09.009","title":"Deterministic weather forecasting models based on intelligent predictors: A survey","authors":["K U Jaseena","Binsu C. Kovoor"],"date":"2020-09-24","year":2020,"venue":"Journal of King Saud University - Computer and Information Sciences","venue_type":"journal","ids":{"doi":"10.1016/j.jksuci.2020.09.009","openalex":"W3088671467"},"links":{"paper":"https://doi.org/10.1016/j.jksuci.2020.09.009","pdf":"https://www.sciencedirect.com/science/article/pii/S1319157820304729/pdf"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":["cnn","rnn","transformer"],"timescale":["short","medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Survey classifying deterministic deep learning weather forecasting models and public datasets, with directions for future research.","significance":3,"cited_by":95,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.11577","title":"Cloud Cover Nowcasting with Deep Learning","authors":["Léa Berthomier","Bruno Pradel","Lior Perez"],"date":"2020-09-24","year":2020,"venue":"Proceedings of the 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE, Paris, France, 9-12 November 2020","venue_type":"journal","ids":{"arxiv":"2009.11577","doi":"10.1109/ipta50016.2020.9286606"},"links":{"paper":"https://arxiv.org/abs/2009.11577","pdf":"https://arxiv.org/pdf/2009.11577"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"CNNs on Meteosat imagery for cloud cover nowcasting; U-Net beats persistence and the AROME physical model on meteorological metrics.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12193111","title":"Global Cyclone and Anticyclone Detection Model Based on Remotely Sensed Wind Field and Deep Learning","authors":["Ming Xie","Ying Li","Kai Cao"],"date":"2020-09-23","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12193111","openalex":"W3088368485"},"links":{"paper":"https://doi.org/10.3390/rs12193111","pdf":"https://www.mdpi.com/2072-4292/12/19/3111/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A Faster R-CNN detects global cyclones and anticyclones from ASCAT scatterometer wind fields, reducing false alarms and tracking Hurricane Irma.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2020.3023950","title":"An Energy-Based Generative Adversarial Forecaster for Radar Echo Map Extrapolation","authors":["Pengfei Xie","Xutao Li","Xiyang Ji","Xunlai Chen","Yuanzhao Chen","Jia Liu","Yunming Ye"],"date":"2020-09-23","year":2020,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2020.3023950","openalex":"W3089203045"},"links":{"paper":"https://doi.org/10.1109/lgrs.2020.3023950"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"An energy-based GAN combined with a convolutional RNN extrapolates radar echo maps with sharper, more stable results than ConvGRU and GA-ConvGRU baselines.","significance":3,"cited_by":59,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2020.3023683","title":"Hyperspectral Infrared Sounder Cloud Detection Using Deep Neural Network Model","authors":["Qian Liu","Hui Xu","Dexuan Sha","Tsengdar J. Lee","Daniel Q. Duffy","Jeff Walter","Chaowei Phil Yang"],"date":"2020-09-23","year":2020,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2020.3023683","openalex":"W3087947032"},"links":{"paper":"https://doi.org/10.1109/lgrs.2020.3023683"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A DNN trained on principal components of CrIS hyperspectral spectra, with VIIRS cloud masks as truth, detects cloudy fields of view with 93% accuracy.","significance":3,"cited_by":16,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00500-020-05199-7","title":"Short-term photovoltaic power generation predicting by input/output structure of weather forecast using deep learning","authors":["Dong-Ha Shin","Eun-Gyu Ha","Taeoh Kim","Chang-Bok Kim"],"date":"2020-09-23","year":2020,"venue":"Soft Computing","venue_type":"journal","ids":{"doi":"10.1007/s00500-020-05199-7","openalex":"W3088122083"},"links":{"paper":"https://doi.org/10.1007/s00500-020-05199-7"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Deep learning predicts short-term photovoltaic power using weather forecast inputs; abstract not available, so classification is low confidence.","significance":2,"cited_by":43,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.11279","title":"Augmented Convolutional LSTMs for Generation of High-Resolution Climate Change Projections","authors":["Nidhin Harilal","Udit Bhatia","Mayank Singh"],"date":"2020-09-23","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"arxiv":"2009.11279","doi":"10.1109/access.2021.3057500","openalex":"W3087936449"},"links":{"paper":"https://doi.org/10.1109/access.2021.3057500","pdf":"https://arxiv.org/pdf/2009.11279"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Auxiliary-variable-informed convolutional LSTM statistically downscales CMIP-style precipitation from 115 km to 25 km over India, with better extreme-event prediction than baselines.","significance":3,"cited_by":40,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.11239","title":"Deep multi-stations weather forecasting: explainable recurrent convolutional neural networks","authors":["Ismail Alaoui Abdellaoui","Siamak Mehrkanoon"],"date":"2020-09-23","year":2020,"venue_type":"preprint","ids":{"arxiv":"2009.11239","openalex":"W3087767645"},"links":{"paper":"https://arxiv.org/abs/2009.11239","pdf":"https://arxiv.org/pdf/2009.11239"},"orgs":[],"topic":"local-forecasting","topics":["xai-uq-physics"],"type":"model","method":["cnn","rnn","transformer"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Recurrent-convolutional networks with self-attention forecast daily weather at 18 European cities, with occlusion analysis explaining which features and cities matter.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2020.105269","title":"A two-moment machine learning parameterization of the autoconversion process","authors":["Léster Alfonso","José María Zamora"],"date":"2020-09-22","year":2020,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2020.105269","openalex":"W3087797646"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2020.105269"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Machine-learning replacement for the autoconversion cloud microphysics process in a two-moment scheme, offered as a faster parameterization for atmospheric models.","significance":3,"cited_by":17,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11229-020-02865-z","title":"Understanding climate change with statistical downscaling and machine learning","authors":["Julie Jebeile","Vincent Lam","Tim Räz"],"date":"2020-09-22","year":2020,"venue":"Synthese","venue_type":"journal","ids":{"doi":"10.1007/s11229-020-02865-z","openalex":"W3088559633"},"links":{"paper":"https://doi.org/10.1007/s11229-020-02865-z","pdf":"https://link.springer.com/content/pdf/10.1007/s11229-020-02865-z.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"position","method":[],"timescale":["climate"],"spatial":[],"data":[],"status":"research","summary":"Philosophical analysis of how statistical downscaling and machine learning contribute to understanding climate change; a perspective piece rather than a new method.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-13-4399-2020","title":"RadNet 1.0: exploring deep learning architectures for longwave radiative transfer","authors":["Ying Liu","Rodrigo Caballero","Joy Merwin Monteiro"],"date":"2020-09-21","year":2020,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-13-4399-2020","openalex":"W3001673168"},"links":{"paper":"https://doi.org/10.5194/gmd-13-4399-2020","pdf":"https://gmd.copernicus.org/articles/13/4399/2020/gmd-13-4399-2020.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural network emulators replace longwave radiative transfer in a climate model, giving up to 370x GPU speedup with under 0.1 K/day heating-rate error.","significance":4,"cited_by":34,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.09823","title":"Latent State Inference in a Spatiotemporal Generative Model","authors":["Matthias Karlbauer","Tobias Menge","Sebastian Otte","Hendrik P. A. Lensch","Thomas Scholten","Volker Wulfmeyer","Martin V. Butz"],"date":"2020-09-21","year":2020,"venue_type":"preprint","ids":{"arxiv":"2009.09823"},"links":{"paper":"https://arxiv.org/abs/2009.09823","pdf":"https://arxiv.org/pdf/2009.09823"},"orgs":[],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["rnn","gnn"],"timescale":[],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"DISTANA with active tuning infers hidden causal factors, recovering Earth's land-sea mask from temperature dynamics alone while improving temperature prediction.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w12092628","title":"Monthly Rainfall Anomalies Forecasting for Southwestern Colombia Using Artificial Neural Networks Approaches","authors":["Teresita Canchala","Wilfredo Alfonso-Morales","Yesid Carvajal Escobar","Wilmar L. Cerón","Eduardo Francisco Caicedo"],"date":"2020-09-20","year":2020,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w12092628","openalex":"W3087204164"},"links":{"paper":"https://doi.org/10.3390/w12092628","pdf":"https://www.mdpi.com/2073-4441/12/9/2628/pdf?version=1600595397"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Neural network models with ENSO indices forecast monthly rainfall anomalies in Southwestern Colombia five months ahead, with the data-driven approach showing suitable skill.","significance":2,"cited_by":33,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-esd-11-835-2020","title":"Reconstructing coupled time series in climate systems using three kinds of machine-learning methods","authors":["Yu Huang","Lichao Yang","Zuntao Fu"],"date":"2020-09-18","year":2020,"venue":"Earth System Dynamics","venue_type":"journal","ids":{"doi":"10.5194/esd-11-835-2020","openalex":"W3087389050"},"links":{"paper":"https://doi.org/10.5194/esd-11-835-2020","pdf":"https://esd.copernicus.org/articles/11/835/2020/esd-11-835-2020.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["rnn","other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Reservoir computing and LSTM learn coupling relations among toy climate variables and reconstruct one series from another; convergent cross mapping guides input selection.","significance":3,"cited_by":30,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.08454","title":"ExGAN: Adversarial Generation of Extreme Samples","authors":["Siddharth Bhatia","Arjit Jain","Bryan Hooi"],"date":"2020-09-17","year":2020,"venue_type":"preprint","ids":{"arxiv":"2009.08454"},"links":{"paper":"https://arxiv.org/abs/2009.08454","pdf":"https://arxiv.org/pdf/2009.08454"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"model","method":["gan-vae","physics-constrained"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"GAN combined with extreme value theory generates realistic extreme samples, evaluated on US precipitation, with constant-time generation at a given extremeness probability.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-13-4271-2020","title":"Can machine learning improve the model representation of turbulent kinetic energy dissipation rate in the boundary layer for complex terrain?","authors":["Nicola Bodini","Julie K. Lundquist","Mike Optis"],"date":"2020-09-16","year":2020,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-13-4271-2020","openalex":"W3087330307"},"links":{"paper":"https://doi.org/10.5194/gmd-13-4271-2020"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Random forests and polynomial regression trained on Perdigão sonic anemometer data remove the MYNN bias in boundary-layer TKE dissipation and cut average error by up to 30%.","significance":3,"cited_by":33,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijisme.j1259.0961020","title":"Short-Term Solar Forecasting Model using Artificial Neural Networks","authors":["Naveen Kumar Dubey","M.P.S. Chawla"],"date":"2020-09-15","year":2020,"venue":"International Journal of Innovative Science and Modern Engineering","venue_type":"journal","ids":{"doi":"10.35940/ijisme.j1259.0961020","openalex":"W3193887808"},"links":{"paper":"https://doi.org/10.35940/ijisme.j1259.0961020","pdf":"https://doi.org/10.35940/ijisme.j1259.0961020"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"NARX neural networks trained with Levenberg-Marquardt and Bayesian regularization forecast short-term solar irradiance and other weather variables from hourly station data.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-20-0050.1","title":"Nowcasting Multicell Short-Term Intense Precipitation Using Graph Models and Random Forests","authors":["Cong Wang","Ping Wang","Di Wang","Jinyi Hou","Bing Xue"],"date":"2020-09-15","year":2020,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-20-0050.1","openalex":"W3095023762"},"links":{"paper":"https://doi.org/10.1175/mwr-d-20-0050.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/148/11/MWR-D-20-0050.1.pdf"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","stations"],"status":"research","summary":"Graph-based multicell features with a random forest predict next-hour short-term intense precipitation in North China with 79.2% POD and 68.3% CSI.","significance":3,"cited_by":18,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2020.3017709","title":"A Novel Tensor Network for Tropical Cyclone Intensity Estimation","authors":["Zhao Chen","Xingxing Yu"],"date":"2020-09-15","year":2020,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2020.3017709","openalex":"W3088335020"},"links":{"paper":"https://doi.org/10.1109/tgrs.2020.3017709"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn","other"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"A tensor-algebra CNN with multitask learning estimates tropical cyclone wind speed and intensity class from FY-4 multispectral imagery, handling invalid bands.","significance":3,"cited_by":53,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-020-71831-z","title":"A mask R-CNN model for reidentifying extratropical cyclones based on quasi-supervised thought","authors":["Chuhan Lu","Yang Kong","Zhaoyong Guan"],"date":"2020-09-14","year":2020,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-020-71831-z","openalex":"W3086362950"},"links":{"paper":"https://doi.org/10.1038/s41598-020-71831-z","pdf":"https://www.nature.com/articles/s41598-020-71831-z.pdf"},"orgs":["nuist"],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"A quasi-supervised Mask R-CNN reidentifies Northern Hemisphere extratropical cyclones, finding 8.29% more cyclones than the traditional automatic method.","significance":3,"cited_by":35,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-2020-214","title":"Deep-learning based climate downscaling using the super-resolution method: a case study over the western US","authors":["Xingying Huang"],"date":"2020-09-11","year":2020,"venue_type":"other","ids":{"doi":"10.5194/gmd-2020-214","openalex":"W3085005768"},"links":{"paper":"https://doi.org/10.5194/gmd-2020-214","pdf":"https://gmd.copernicus.org/preprints/gmd-2020-214/gmd-2020-214.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other","cmip"],"status":"research","summary":"Super-resolution CNN downscales daily temperature and precipitation to 4 km over the western US in about 23 ms per day, competitive with dynamical downscaling.","significance":4,"cited_by":10,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.05665","title":"Spatio-Temporal Functional Neural Networks","authors":["Aniruddha Rajendra Rao","Qiyao Wang","Haiyan Wang","Hamed Khorasgani","Chetan Gupta"],"date":"2020-09-11","year":2020,"venue_type":"preprint","ids":{"arxiv":"2009.05665"},"links":{"paper":"https://arxiv.org/abs/2009.05665","pdf":"https://arxiv.org/pdf/2009.05665"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Two spatio-temporal extensions of functional neural networks are shown in simulations and applied to precipitation prediction, with the meteorological case as the main demonstration.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s20185173","title":"Real-Time Weather Monitoring and Prediction Using City Buses and Machine Learning","authors":["Ziqi Huang","Ying‐Chih Chen","Chih-Yu Wen"],"date":"2020-09-10","year":2020,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s20185173","openalex":"W3083789630"},"links":{"paper":"https://doi.org/10.3390/s20185173","pdf":"https://www.mdpi.com/1424-8220/20/18/5173/pdf?version=1599741478"},"orgs":[],"topic":"local-forecasting","topics":["infra-software"],"type":"application","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"LSTM and MLP models use city-bus sensor data to monitor and forecast temperature, humidity and pressure one day ahead.","significance":2,"cited_by":59,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s20185132","title":"Classification and Prediction of Typhoon Levels by Satellite Cloud Pictures through GC–LSTM Deep Learning Model","authors":["Jianyin Zhou","Jie Xiang","Sixun Huang"],"date":"2020-09-09","year":2020,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s20185132","openalex":"W3084018155"},"links":{"paper":"https://doi.org/10.3390/s20185132","pdf":"https://www.mdpi.com/1424-8220/20/18/5132/pdf?version=1599806950"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["gnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A GCN-LSTM model classifies typhoon levels from Himawari-8 cloud images with 92.35% accuracy, and 95.12% for typhoons and super typhoons.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2020.3016001","title":"Rain-Type Classification From Microwave Satellite Observations Using Deep Neural Network Segmentation","authors":["Yeji Choi","Seongchan Kim"],"date":"2020-09-09","year":2020,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2020.3016001","openalex":"W3085215416"},"links":{"paper":"https://doi.org/10.1109/lgrs.2020.3016001"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"U-Net and fully connected networks classify four rain types from GPM GMI brightness temperatures, reaching 0.95 total accuracy against DPR labels.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.04318","title":"Combining data assimilation and machine learning to infer unresolved scale parametrisation","authors":["Julien Brajard","Alberto Carrassi","Marc Bocquet","Laurent Bertino"],"date":"2020-09-09","year":2020,"venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2009.04318","doi":"10.1098/rsta.2020.0086","openalex":"W3133002925"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0086","pdf":"https://arxiv.org/pdf/2009.04318"},"orgs":["lbnl-nersc","university-of-reading"],"topic":"data-assimilation","topics":["hybrid-parameterization"],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Ensemble Kalman filter estimates model error from sparse noisy observations to train a neural parametrisation, yielding hybrid forecasts with better skill on Lorenz and a coupled ocean-atmosphere model.","significance":3,"cited_by":181,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2009.03977","title":"Modeling Wildfire Perimeter Evolution using Deep Neural Networks","authors":["Maxfield E. Green","Karl Kaiser","Nat Shenton"],"date":"2020-09-08","year":2020,"venue_type":"preprint","ids":{"arxiv":"2009.03977"},"links":{"paper":"https://arxiv.org/abs/2009.03977","pdf":"https://arxiv.org/pdf/2009.03977"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Deep CNN trained on remotely sensed atmospheric and environmental series predicts 24-hour wildfire perimeter evolution in the Sierra Nevada with 78-98% validation accuracy.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1098-rstb.2019.0510","title":"Impact of extreme weather conditions on European crop production in 2018","authors":["Damien Beillouin","Bernhard Schauberger","Ana Bastos","Philippe Ciais","David Makowski"],"date":"2020-09-06","year":2020,"venue":"Philosophical Transactions of the Royal Society B Biological Sciences","venue_type":"journal","ids":{"doi":"10.1098/rstb.2019.0510","openalex":"W3083643364"},"links":{"paper":"https://doi.org/10.1098/rstb.2019.0510","pdf":"https://royalsocietypublishing.org/doi/pdf/10.1098/rstb.2019.0510"},"orgs":["pik"],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning models explain up to 65% of historical crop yield anomalies in 17 European countries, linking 2018 extreme temperature and rainfall to losses.","significance":3,"cited_by":431,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12172859","title":"Neural Network Based Quality Control of CYGNSS Wind Retrieval","authors":["Rajeswari Balasubramaniam","Christopher S. Ruf"],"date":"2020-09-03","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12172859","openalex":"W3083369567"},"links":{"paper":"https://doi.org/10.3390/rs12172859","pdf":"https://www.mdpi.com/2072-4292/12/17/2859/pdf?version=1599136290"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A neural network quality-control filter for CYGNSS ocean wind retrievals reaches over 75% outlier detection with under 20% false alarms for 5–18 m/s winds.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-20-0004.1","title":"Paleoclimate Constraints on the Spatiotemporal Character of Past and Future Droughts","authors":["Sloan Coats","Jason E. Smerdon","Samantha L. Stevenson","John Fasullo","Bette L. Otto‐Bliesner","Toby R. Ault"],"date":"2020-09-03","year":2020,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-20-0004.1","openalex":"W3083573135"},"links":{"paper":"https://doi.org/10.1175/jcli-d-20-0004.1"},"orgs":["ncar","columbia-leap"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Machine learning identifies three-dimensional drought events in tree-ring reconstructions and CMIP simulations, suggesting models underestimate the range of future hydroclimate states.","significance":3,"cited_by":32,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-13-4669-2020","title":"Gradient boosting machine learning to improve satellite-derived column water vapor measurement error","authors":["Allan C. Just","Yang Liu","Meytar Sorek‐Hamer","Johnathan Rush","Michael Dorman","Robert B. Chatfield","Yujie Wang A","Alexei Lyapustin","Itai Kloog"],"date":"2020-09-02","year":2020,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-13-4669-2020","openalex":"W2996781720"},"links":{"paper":"https://doi.org/10.5194/amt-13-4669-2020","pdf":"https://amt.copernicus.org/articles/13/4669/2020/amt-13-4669-2020.pdf"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"XGBoost corrects MAIAC satellite column water vapor errors, cutting RMSE by 26.9% for Terra and 16.5% for Aqua against AERONET sites.","significance":3,"cited_by":33,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3175044352","title":"WIND POWER GENERATION PREDICTION BASED ON WEATHER FORECAST DATA USING DEEP NEURAL NETWORKS","authors":["Minwoo Baek","Min Kyu Sim","Jae-Yoon Jung"],"date":"2020-09-01","year":2020,"venue":"ICIC express letters. Part B, Applications","venue_type":"journal","ids":{"openalex":"W3175044352"},"links":{"paper":"https://ci.nii.ac.jp/naid/40022434335"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Deep neural networks predict wind power generation from weather forecast data; abstract not available, so classification is low confidence.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3082463709","title":"RStudio AI Blog: An introduction to weather forecasting with deep learning","authors":["Sigrid Keydana"],"date":"2020-09-01","year":2020,"venue_type":"other","ids":{"openalex":"W3082463709"},"links":{"paper":"https://blogs.rstudio.com/ai/posts/2020-09-01-weather-prediction/"},"orgs":[],"topic":"local-forecasting","topics":["llms-agents"],"type":"review","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Tutorial introducing deep learning for weather time-series forecasting from station data; abstract not available, so classification is low confidence.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15407-pp2020.02-03.375","title":"Application of machine learning to improving numerical weather prediction","authors":["А.Yu. Doroshenko","Vitalii Shpyg","Roman Kushnirenko"],"date":"2020-09-01","year":2020,"venue":"PROBLEMS IN PROGRAMMING","venue_type":"journal","ids":{"doi":"10.15407/pp2020.02-03.375","openalex":"W3100905835"},"links":{"paper":"https://doi.org/10.15407/pp2020.02-03.375"},"orgs":[],"topic":"post-processing","topics":["global-medium-range"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Neural network predicts and corrects COSMO regional model 2m temperature errors, improving forecasts in about 50% of cases.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40333-020-0097-3","title":"Precipitation forecasting by large-scale climate indices and machine learning techniques","authors":["Mehdi Gholami Rostam","Seyyed Javad Sadatinejad","Arash Malekian"],"date":"2020-09-01","year":2020,"venue":"Journal of Arid Land","venue_type":"journal","ids":{"doi":"10.1007/s40333-020-0097-3","openalex":"W3103163422"},"links":{"paper":"https://doi.org/10.1007/s40333-020-0097-3"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Machine learning models predict precipitation from large-scale climate indices in an arid-land region; abstract not available, so classification is low confidence.","significance":2,"cited_by":28,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.71465-ajdsa884","title":"Big Data Analytics for Climate Change Modeling and Prediction","authors":["Dr. Richard Hughes"],"date":"2020-08-31","year":2020,"venue":"American Journal of Data Science and Analysis","venue_type":"journal","ids":{"doi":"10.71465/ajdsa884","openalex":"W7144320622"},"links":{"paper":"https://doi.org/10.71465/ajdsa884","pdf":"https://australiansciencejournals.com/ajdsa/article/download/884/986"},"orgs":["university-of-oxford"],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","cmip"],"status":"research","summary":"Review of big data and machine learning for climate change modeling using satellite, sensor and climate model data, covering challenges and outlook without new methods.","significance":2,"cited_by":0,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.61841-37nnyn17","title":"WEATHER FORECASTING USING MACHINE LEARNING ALGORITHM","authors":["S. Nagadevi","Varun Ramesh","Helloween James"],"date":"2020-08-31","year":2020,"venue":"International Journal of Psychosocial Rehabilitation","venue_type":"journal","ids":{"doi":"10.61841/37nnyn17","openalex":"W7215697320"},"links":{"paper":"https://doi.org/10.61841/37nnyn17","pdf":"https://psychosocial.com/index.php/ijpr/article/download/6840/6176"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Compares k-NN, decision tree, random forest and linear regression for weather prediction, reporting accuracy with no new method.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-20-0116.1","title":"Aviation Turbulence Forecasting at Upper Levels with Machine Learning Techniques Based on Regression Trees","authors":["Domingo Muñoz‐Esparza","Robert D. Sharman","Wiebke K. Deierling"],"date":"2020-08-31","year":2020,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-20-0116.1","openalex":"W3081677703"},"links":{"paper":"https://doi.org/10.1175/jamc-d-20-0116.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/apme/59/11/JAMC-D-20-0116.1.pdf"},"orgs":["ncar"],"topic":"applications-impacts","topics":["extremes-hazards","post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Random forests and gradient-boosted regression trees using HRRR forecast features improve upper-level aviation turbulence (EDR) forecasts and reduce false alarms versus regression baselines.","significance":3,"cited_by":33,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-20-0097.1","title":"Evaluation, Tuning, and Interpretation of Neural Networks for Working with Images in Meteorological Applications","authors":["Imme Ebert‐Uphoff","Kyle Hilburn"],"date":"2020-08-31","year":2020,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-20-0097.1","openalex":"W3082330840"},"links":{"paper":"https://doi.org/10.1175/bams-d-20-0097.1"},"orgs":["colorado-state-university"],"topic":"xai-uq-physics","topics":["observations-remote-sensing"],"type":"review","method":["cnn","other"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Tutorial-style guidance on evaluating, tuning and interpreting neural networks for meteorological satellite images, covering receptive fields, relevance propagation and image-to-image translation.","significance":4,"cited_by":108,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11069-020-04258-4","title":"Objective approach for rainstorm based on dual-factor feature extraction and generalized regression neural network","authors":["Huang Xiaoyan","Li He","Zhao Huasheng","Ying Hong Huang","Wu Yushuang"],"date":"2020-08-31","year":2020,"venue":"Natural Hazards","venue_type":"journal","ids":{"doi":"10.1007/s11069-020-04258-4","openalex":"W3081677063"},"links":{"paper":"https://doi.org/10.1007/s11069-020-04258-4"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Generalized regression neural network with dual-factor feature extraction for rainstorm prediction; only the title is available, so the abstract-based assessment is limited.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.13524","title":"Physics-inspired adaptions to low-parameter neural network weather forecasts systems","authors":["Sebastian Scher","Gabriele Messori"],"date":"2020-08-31","year":2020,"venue_type":"preprint","ids":{"arxiv":"2008.13524","openalex":"W3082110642"},"links":{"paper":"https://arxiv.org/abs/2008.13524","pdf":"https://arxiv.org/pdf/2008.13524"},"orgs":[],"topic":"global-medium-range","topics":["hybrid-parameterization"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Spherenet convolution and hemisphere-specific network design improve WeatherBench CNN forecasts at 1.4 degrees for 500 hPa height and 850 hPa temperature up to day 10.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4208-cicp.oa-2020-0006","title":"A Data-Driven Random Subfeature Ensemble Learning Algorithm for Weather Forecasting","authors":["Chen Yu","Haochen Li","Jiangjiang Xia","Hanqiuzi Wen Hanqiuzi Wen","Pingwen Zhang"],"date":"2020-08-26","year":2020,"venue":"Communications in Computational Physics","venue_type":"journal","ids":{"doi":"10.4208/cicp.oa-2020-0006","openalex":"W3082642777"},"links":{"paper":"https://doi.org/10.4208/cicp.oa-2020-0006"},"orgs":["iap-cas"],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random Subfeature Ensemble Learning (RSEL) combines random feature subsets and ensembling to improve wind speed and direction forecasts over traditional methods, with claimed robustness.","significance":2,"cited_by":4,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl089102","title":"Applying Satellite Observations of Tropical Cyclone Internal Structures to Rapid Intensification Forecast With Machine Learning","authors":["Hui Su","Longtao Wu","Jonathan H. Jiang","Raksha Pai","Alex X. Liu","Albert J. Zhai","Peyman Tavallali","Mark DeMaria"],"date":"2020-08-25","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl089102","openalex":"W3080794575"},"links":{"paper":"https://doi.org/10.1029/2020gl089102","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020GL089102"},"orgs":["ibm-research","nasa","caltech"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Machine learning using satellite inner-core precipitation and outflow temperature beats the NHC operational rapid-intensification consensus, improving Peirce skill score by 12 to 138%.","significance":4,"cited_by":88,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.10789","title":"Smart Weather Forecasting Using Machine Learning:A Case Study in Tennessee","authors":["A H M Jakaria","Md Mosharaf Hossain","Mohammad Ashiqur Rahman"],"date":"2020-08-25","year":2020,"venue_type":"preprint","ids":{"arxiv":"2008.10789","openalex":"W3081054889"},"links":{"paper":"https://arxiv.org/abs/2008.10789","pdf":"https://arxiv.org/pdf/2008.10789"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Simple ML models trained on multi-station historical data give short-range local weather forecasts in Tennessee, and adding neighboring stations improves accuracy.","significance":2,"cited_by":50,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1911.11089","title":"Unlocking GOES: A Statistical Framework for Quantifying the Evolution of Convective Structure in Tropical Cyclones","authors":["Trey McNeely","Ann B. Lee","Kimberly M. Wood","Dorit Hammerling"],"date":"2020-08-25","year":2020,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"arxiv":"1911.11089","doi":"10.1175/jamc-d-19-0286.1","openalex":"W2990356215"},"links":{"paper":"https://doi.org/10.1175/jamc-d-19-0286.1","pdf":"https://arxiv.org/pdf/1911.11089"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Interpretable satellite-derived convective structure features with logistic lasso classify tropical cyclone rapid intensity change, matching the accuracy of environmental predictors.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12172731","title":"Application of Convolutional Neural Network for Spatiotemporal Bias Correction of Daily Satellite-Based Precipitation","authors":["Xuan-Hien Le","Giha Lee","Kwansue Jung","Hyunuk An","Seungsoo Lee","Younghun Jung"],"date":"2020-08-24","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12172731","openalex":"W3080669681"},"links":{"paper":"https://doi.org/10.3390/rs12172731","pdf":"https://www.mdpi.com/2072-4292/12/17/2731/pdf?version=1598254494"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Convolutional autoencoder corrects pixel-wise bias of PERSIANN-CDR daily satellite precipitation against APHRODITE over the Mekong, outperforming a standard-deviation method.","significance":3,"cited_by":72,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.10679","title":"Machine learning for weather and climate are worlds apart","authors":["Duncan Watson-Parris"],"date":"2020-08-24","year":2020,"venue":"Phil. Trans. R. Soc. A. 379 (2021) 20200098","venue_type":"journal","ids":{"arxiv":"2008.10679","doi":"10.1098/rsta.2020.0098","openalex":"W3081457782"},"links":{"paper":"https://arxiv.org/abs/2008.10679","pdf":"https://arxiv.org/pdf/2008.10679"},"orgs":["university-of-oxford"],"topic":"climate-emulation","topics":[],"type":"position","method":[],"timescale":["climate"],"spatial":["global"],"data":[],"status":"research","summary":"Position review arguing climate emulation with machine learning differs from weather forecasting, since climate is a boundary-condition problem with steady-state emulation opportunities.","significance":3,"cited_by":62,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.shpsa.2020.08.003","title":"Understanding climate phenomena with data-driven models","authors":["Benedikt Knüsel","Christoph Baumberger"],"date":"2020-08-23","year":2020,"venue":"Studies in History and Philosophy of Science Part A","venue_type":"journal","ids":{"doi":"10.1016/j.shpsa.2020.08.003","openalex":"W3080358284"},"links":{"paper":"https://doi.org/10.1016/j.shpsa.2020.08.003","pdf":"https://www.sciencedirect.com/science/article/pii/S0039368120301606?via%3Dihub"},"orgs":["eth-zurich"],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"position","method":["other"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Philosophical framework arguing data-driven machine learning climate models can provide scientific understanding, illustrated with an atmospheric research case study.","significance":2,"cited_by":53,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app10175808","title":"A Model Output Deep Learning Method for Grid Temperature Forecasts in Tianjin Area","authors":["Keran Chen","Ping Wang","Xiaojun Yang","Nan Zhang","Di Wang"],"date":"2020-08-22","year":2020,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app10175808","openalex":"W3081373097"},"links":{"paper":"https://doi.org/10.3390/app10175808","pdf":"https://www.mdpi.com/2076-3417/10/17/5808/pdf?version=1598076628"},"orgs":["cma"],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"End-to-end CNN post-processing (MODL) of TIGGE ECMWF forecasts improves Tianjin 2 m temperature RMSE over ECMWF, MOS and other ML baselines, especially in the first three days.","significance":3,"cited_by":29,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.09090","title":"TRU-NET: A Deep Learning Approach to High Resolution Prediction of Rainfall","authors":["Rilwan Adewoyin","Peter Dueben","Peter Watson","Yulan He","Ritabrata Dutta"],"date":"2020-08-20","year":2020,"venue":"Machine Learning","venue_type":"journal","ids":{"arxiv":"2008.09090","doi":"10.1007/s10994-021-06022-6","openalex":"W3058542386"},"links":{"paper":"https://doi.org/10.1007/s10994-021-06022-6","pdf":"https://arxiv.org/pdf/2008.09090"},"orgs":["ecmwf"],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"TRU-NET, a convolutional-recurrent U-Net with cross attention, predicts high-resolution rainfall from climate model fields with lower RMSE than a dynamical model's rainfall output.","significance":3,"cited_by":9,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.12928-telkomnika.v18i5.14887","title":"Precipitation prediction using recurrent neural networks and long short-term memory","authors":["Mishka Alditya Priatna","Esmeralda C. Djamal"],"date":"2020-08-19","year":2020,"venue":"TELKOMNIKA (Telecommunication Computing Electronics and Control)","venue_type":"journal","ids":{"doi":"10.12928/telkomnika.v18i5.14887","openalex":"W3022223935"},"links":{"paper":"https://doi.org/10.12928/telkomnika.v18i5.14887"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"RNN and LSTM models predict station precipitation, reaching 85.71% accuracy for weekly predictions versus 83.33% for monthly on validation data.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.08626","title":"Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench","authors":["Stephan Rasp","Nils Thuerey"],"date":"2020-08-19","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2008.08626","doi":"10.1029/2020ms002405","openalex":"W3099145603"},"links":{"paper":"https://arxiv.org/abs/2008.08626","pdf":"https://arxiv.org/pdf/2008.08626"},"orgs":["tum"],"topic":"global-medium-range","topics":["benchmarks-data-eval"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"A residual CNN pretrained on climate model output and fine-tuned on reanalysis gives WeatherBench 5-day forecasts that outperform prior submissions and rival a physical baseline.","significance":4,"cited_by":239,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-waf-d-20-0031.1","title":"ENSO Dynamics, Trends, and Prediction Using Machine Learning","authors":["Julian Hernandez","Óscar J. Mesa","Upmanu Lall"],"date":"2020-08-18","year":2020,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-20-0031.1","openalex":"W3070087388"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0031.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/35/5/wafD200031.pdf"},"orgs":["columbia-leap"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal","s2s"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Nonhomogeneous hidden Markov model identifies five ENSO regimes from 1856 to 2019 and gives out-of-sample probabilistic Niño forecasts comparable to existing models.","significance":4,"cited_by":27,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-19-0356.1","title":"Factors Affecting the Weakening Rate of Tropical Cyclones over the Western North Pacific","authors":["Rong Fei","Jing Xin Xu","Yuqing Wang","Chi Yang"],"date":"2020-08-18","year":2020,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-19-0356.1","openalex":"W3076386101"},"links":{"paper":"https://doi.org/10.1175/mwr-d-19-0356.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/148/9/mwrD190356.pdf"},"orgs":["cma"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"XGBoost and statistical analysis of ERA-Interim identify relative intensity, sea-surface temperature drop and wind shear as dominant drivers of western North Pacific typhoon weakening.","significance":3,"cited_by":29,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.12257","title":"A comparative study of convolutional neural network models for wind field downscaling","authors":["Kevin Höhlein","Michael Kern","Timothy Hewson","Rüdiger Westermann"],"date":"2020-08-18","year":2020,"venue":"Meteorol Appl. 2020; 27:e1961","venue_type":"journal","ids":{"arxiv":"2008.12257","doi":"10.1002/met.1961","openalex":"W3080778091"},"links":{"paper":"https://arxiv.org/abs/2008.12257","pdf":"https://arxiv.org/pdf/2008.12257"},"orgs":["ecmwf","tum"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","nwp-analysis"],"status":"research","summary":"Compares CNN architectures and proposes DeepRU, a U-Net variant, to downscale ERA5-driven 100 m wind forecasts from 31 km to 9 km over the Alps.","significance":3,"cited_by":132,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.08062","title":"Compute, Time and Energy Characterization of Encoder-Decoder Networks with Automatic Mixed Precision Training","authors":["Siddharth Samsi","Michael Jones","Mark M. Veillette"],"date":"2020-08-18","year":2020,"venue_type":"preprint","ids":{"arxiv":"2008.08062","doi":"10.1109/hpec43674.2020.9286241"},"links":{"paper":"https://arxiv.org/abs/2008.08062","pdf":"https://arxiv.org/pdf/2008.08062"},"orgs":[],"topic":"infra-software","topics":["nowcasting"],"type":"evaluation","method":["cnn"],"timescale":["nowcast"],"spatial":[],"data":["other"],"status":"research","summary":"Characterizes compute, time and energy costs of training a UNet for precipitation nowcasting, showing mixed-precision and distributed training cut training time without losing accuracy.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11080870","title":"Typhoon Quantitative Rainfall Prediction from Big Data Analytics by Using the Apache Hadoop Spark Parallel Computing Framework","authors":["Chih‐Chiang Wei","Tzu-Hao Chou"],"date":"2020-08-17","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11080870","openalex":"W3049749700"},"links":{"paper":"https://doi.org/10.3390/atmos11080870","pdf":"https://www.mdpi.com/2073-4433/11/8/870/pdf"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses deep neural networks and multiple linear regression on Spark-based big-data infrastructure to predict typhoon rainfall at four Taiwan stations, with faster computation than standalone systems.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.07653","title":"Nonparametric Conditional Density Estimation In A Deep Learning Framework For Short-Term Forecasting","authors":["David B. Huberman","Brian J. Reich","Howard D. Bondell"],"date":"2020-08-17","year":2020,"venue":"Environmental and Ecological Statistics","venue_type":"journal","ids":{"arxiv":"2008.07653","doi":"10.1007/s10651-021-00499-z","openalex":"W3057495178"},"links":{"paper":"https://doi.org/10.1007/s10651-021-00499-z","pdf":"https://arxiv.org/pdf/2008.07653"},"orgs":[],"topic":"extremes-hazards","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Proposes a neural conditional-density estimator with case-control sampling for tropical cyclone intensity forecasting, outperforming other ML conditional-distribution methods in simulations and Atlantic storm data.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11591-ijai.v9.i3.pp456-463","title":"Comparison of daily rainfall forecasting using multilayer perceptron neural network model","authors":["Mazwin Arleena Masngut","Shuhaida Binti Ismail","Aida Mustapha","Suhaila Mohd. Yasin"],"date":"2020-08-16","year":2020,"venue":"IAES International Journal of Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.11591/ijai.v9.i3.pp456-463","openalex":"W3022385021"},"links":{"paper":"https://doi.org/10.11591/ijai.v9.i3.pp456-463","pdf":"http://ijai.iaescore.com/index.php/IJAI/article/download/20485/13036"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A multilayer perceptron outperforms ARIMA for daily rainfall forecasting at a single site, with lower MAE and RMSE and R of 0.94.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.06489","title":"A Deep Convolutional Neural Network Model for improving WRF Forecasts","authors":["Alqamah Sayeed","Yunsoo Choi","Jia Jung","Yannic Lops","Ebrahim Eslami","Ahmed Khan Salman"],"date":"2020-08-14","year":2020,"venue":"IEEE Transactions on Neural Networks and Learning Systems","venue_type":"journal","ids":{"arxiv":"2008.06489","doi":"10.1109/tnnls.2021.3100902","openalex":"W3191088285"},"links":{"paper":"https://doi.org/10.1109/tnnls.2021.3100902","pdf":"https://arxiv.org/pdf/2008.06489"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A CNN post-processes one-day WRF forecasts over South Korea, raising annual index of agreement for wind from 0.67 to 0.85 at 93 stations.","significance":3,"cited_by":75,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.05590","title":"Machine Learning for Robust Identification of Complex Nonlinear Dynamical Systems: Applications to Earth Systems Modeling","authors":["Nishant Yadav","Sai Ravela","Auroop R. Ganguly"],"date":"2020-08-12","year":2020,"venue_type":"preprint","ids":{"arxiv":"2008.05590","openalex":"W3048402863"},"links":{"paper":"https://arxiv.org/abs/2008.05590","pdf":"https://arxiv.org/pdf/2008.05590"},"orgs":["mit"],"topic":"hybrid-parameterization","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Gaussian process parameter estimation for the Lorenz-96 climate benchmark outperforms deep learning and linear regression under small-data constraints, with uncertainty quantification.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.05575","title":"Comprehensive forecasting based analysis using stacked stateless and stateful Gated Recurrent Unit models","authors":["Swayamjit Saha","Niladri Majumder","Devansh Sangani"],"date":"2020-08-12","year":2020,"venue_type":"preprint","ids":{"arxiv":"2008.05575"},"links":{"paper":"https://arxiv.org/abs/2008.05575","pdf":"https://arxiv.org/pdf/2008.05575"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Stacked stateful GRU models forecast solar irradiance at four West Bengal regions, with stateful designs improving prediction accuracy.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.37121-jase.v3i2.98","title":"Application of nonlinear autoregressive neural network to estimation of global solar radiation over Nigeria","authors":["Olusola Samuel Ojo","Babatunde Adeyemi"],"date":"2020-08-11","year":2020,"venue":"Journal of Advances in Science and Engineering","venue_type":"journal","ids":{"doi":"10.37121/jase.v3i2.98","openalex":"W3084600478"},"links":{"paper":"https://doi.org/10.37121/jase.v3i2.98"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A NARX neural network estimates monthly global solar radiation across Nigeria from meteorological variables, reaching an index of agreement of 0.85 versus 0.77 for linear regression.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2008.04679","title":"ClimAlign: Unsupervised statistical downscaling of climate variables via normalizing flows","authors":["Brian Groenke","Luke Madaus","Claire Monteleoni"],"date":"2020-08-11","year":2020,"venue_type":"preprint","ids":{"arxiv":"2008.04679"},"links":{"paper":"https://arxiv.org/abs/2008.04679","pdf":"https://arxiv.org/pdf/2008.04679"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"ClimAlign uses normalizing flows for unsupervised statistical downscaling of daily temperature and precipitation, matching supervised baselines while enabling conditional and unconditional sampling.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020ms002076","title":"A Moist Physics Parameterization Based on Deep Learning","authors":["Yilun Han","Guang Jun Zhang","Xiaomeng Huang","Yong Wang"],"date":"2020-08-08","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2020ms002076","openalex":"W3047833863"},"links":{"paper":"https://doi.org/10.1029/2020ms002076","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2020MS002076"},"orgs":["tsinghua-university"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"ResCu, a residual CNN trained on SPCAM output, parameterizes moist convection and clouds with moist-static-energy conservation, outperforming conventional schemes in single-column tests.","significance":4,"cited_by":156,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jobe.2020.101629","title":"Solar power forecast for a residential smart microgrid based on numerical weather predictions using artificial intelligence methods","authors":["Reza Sabzehgar","Diba Zia Amirhosseini","Mohammad Rasouli"],"date":"2020-08-08","year":2020,"venue":"Journal of Building Engineering","venue_type":"journal","ids":{"doi":"10.1016/j.jobe.2020.101629","openalex":"W3048024710"},"links":{"paper":"https://doi.org/10.1016/j.jobe.2020.101629"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Applies AI methods to numerical weather predictions to forecast residential solar power in a smart microgrid; abstract unavailable, so classification is tentative.","significance":2,"cited_by":77,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12162536","title":"GNSS-Based Machine Learning Storm Nowcasting","authors":["Marcelina Łoś","Kamil Smolak","Guergana Guerova","Witold Rohm"],"date":"2020-08-06","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12162536","openalex":"W3048067806"},"links":{"paper":"https://doi.org/10.3390/rs12162536","pdf":"https://www.mdpi.com/2072-4292/12/16/2536/pdf?version=1596853536"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Combines GNSS integrated water vapour with tomography wet refractivity profiles in an ML model predicting 0–2 h storm occurrence over Poland, above 87% accuracy.","significance":3,"cited_by":46,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11080823","title":"Prediction Skill of Extended Range 2-m Maximum Air Temperature Probabilistic Forecasts Using Machine Learning Post-Processing Methods","authors":["Ting Peng","Xiefei Zhi","Yan Ji","Luying Ji","Ye Tian"],"date":"2020-08-04","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11080823","openalex":"W3047222331"},"links":{"paper":"https://doi.org/10.3390/atmos11080823","pdf":"https://www.mdpi.com/2073-4433/11/8/823/pdf?version=1596543507"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["medium","s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Neural networks and NGBoost post-process SubX GEFS 2-m maximum temperature forecasts, beating EMOS by about 0.2 in CRPS over lead times of 1 to 35 days.","significance":4,"cited_by":66,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.17850643","title":"AI-Driven Environmental Simulation and Climate Pattern Prediction","authors":["Kettunen, Aino","Rantala, Marko","Saaristo, Linnea","Koivuniemi, Ville"],"date":"2020-08-02","year":2020,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.17850643","openalex":"W7110886606"},"links":{"paper":"https://doi.org/10.5281/zenodo.17850643"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Generic overview of AI-driven environmental simulation and climate pattern prediction; accuracy claims lack methodological detail, so significance is minimal.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-20-0096.1","title":"Using Artificial Neural Networks for Generating Probabilistic Subseasonal Precipitation Forecasts over California","authors":["Michael Scheuerer","Matthew B. Switanek","Rochelle P. Worsnop","Thomas M. Hamill"],"date":"2020-08-01","year":2020,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-20-0096.1","openalex":"W3046652087"},"links":{"paper":"https://doi.org/10.1175/mwr-d-20-0096.1"},"orgs":["noaa"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml","cnn"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Neural networks postprocess ECMWF reforecasts into probabilistic 7-day California precipitation outlooks out to week 4, beating a state-of-the-art method, though week 3-4 skill stays low.","significance":4,"cited_by":81,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2020ea001140","title":"Machine Learning Models for the Seasonal Forecast of Winter Surface Air Temperature in North America","authors":["Qifeng Qian","Xiao Jing Jia","Hai Lin"],"date":"2020-08-01","year":2020,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2020ea001140","openalex":"W3046782112"},"links":{"paper":"https://doi.org/10.1029/2020ea001140"},"orgs":["eccc"],"topic":"s2s-seasonal","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"SVR and XGBoost seasonal winter surface air temperature forecasts over North America outperform two dynamical models in 2011–2017 real-time tests.","significance":3,"cited_by":42,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.15404","title":"Regional Rainfall Prediction Using Support Vector Machine Classification of Large-Scale Precipitation Maps","authors":["Eslam A. Hussein","Mehrdad Ghaziasgar","Christopher Thron"],"date":"2020-07-30","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.15404"},"links":{"paper":"https://arxiv.org/abs/2007.15404","pdf":"https://arxiv.org/pdf/2007.15404"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium","s2s"],"spatial":["regional"],"data":["other"],"status":"research","summary":"SVM classifies sequences of daily US rainfall maps to predict regional heavy rain 1 to 30 days ahead; central region beats baseline but corner regions do not.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.14706","title":"Kernel Methods and their derivatives: Concept and perspectives for the Earth system sciences","authors":["J. Emmanuel Johnson","Valero Laparra","Adrián Pérez-Suay","Miguel D. Mahecha","Gustau Camps-Valls"],"date":"2020-07-29","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.14706","doi":"10.1371/journal.pone.0235885"},"links":{"paper":"https://arxiv.org/abs/2007.14706","pdf":"https://arxiv.org/pdf/2007.14706"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Derives analytic derivatives of kernel methods for interpretability and illustrates them on Earth system data cubes, though the core contribution is generic ML.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6769","title":"Statistical downscaling of daily temperature and precipitation over China using deep learning neural models: Localization and comparison with other methods","authors":["Lei Sun","Yufeng Lan"],"date":"2020-07-26","year":2020,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6769","openalex":"W3044232223"},"links":{"paper":"https://doi.org/10.1002/joc.6769"},"orgs":["nuist"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"CNN statistical downscaling of daily temperature and precipitation over China outperforms GLM and BCSD/BCCI for precipitation, though ERA-Interim is better for temporal correlation.","significance":4,"cited_by":117,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.12941","title":"Learning Variational Data Assimilation Models and Solvers","authors":["Ronan Fablet","Bertrand Chapron","Lucas. Drumetz","Etienne Memin","Olivier Pannekoucke","Francois Rousseau"],"date":"2020-07-25","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.12941","doi":"10.1029/2021ms002572"},"links":{"paper":"https://arxiv.org/abs/2007.12941","pdf":"https://arxiv.org/pdf/2007.12941"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["differentiable"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"End-to-end neural variational data assimilation, with learned model and solver, outperforms classical gradient descent on Lorenz-63 and Lorenz-96 reconstructions.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-5462040","title":"Development of Stacked Long Short-Term Memory Neural Networks with Numerical Solutions for Wind Velocity Predictions","authors":["Chih‐Chiang Wei"],"date":"2020-07-23","year":2020,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2020/5462040","openalex":"W3044173857"},"links":{"paper":"https://doi.org/10.1155/2020/5462040","pdf":"https://downloads.hindawi.com/journals/amete/2020/5462040.pdf"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Stacked LSTM and DRNN models using WRF outputs predict typhoon wind speeds in northeastern Taiwan for 1 to 6 hours, outperforming memoryless MLPs.","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl089098","title":"Improving Wind Forecasts in the Lower Stratosphere by Distilling an Analog Ensemble Into a Deep Neural Network","authors":["Salvatore Candido","Aakanksha Singh","Luca Delle Monache"],"date":"2020-07-23","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl089098","openalex":"W3044055657"},"links":{"paper":"https://doi.org/10.1029/2020gl089098"},"orgs":[],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis","stations"],"status":"research","summary":"Distilling an analog ensemble into a deep network postprocesses ECMWF stratospheric wind forecasts, cutting latency to near zero and beating ENS wind-speed error by 20% against balloon data.","significance":4,"cited_by":12,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.11836","title":"A Novel Framework for Spatio-Temporal Prediction of Environmental Data Using Deep Learning","authors":["Federico Amato","Fabian Guignard","Sylvain Robert","Mikhail Kanevski"],"date":"2020-07-23","year":2020,"venue":"Sci Rep 10, 22243 (2020)","venue_type":"journal","ids":{"arxiv":"2007.11836","doi":"10.1038/s41598-020-79148-7","openalex":"W3044704399"},"links":{"paper":"https://arxiv.org/abs/2007.11836","pdf":"https://arxiv.org/pdf/2007.11836"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"A deep learning framework reconstructs continuous space-time environmental fields from irregular station measurements using temporal basis functions and gridded spatial coefficients.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2020.3008033","title":"Precipitation Merging Based on the Triple Collocation Method Across Mainland China","authors":["Feng Lyu","Guoqiang Tang","Ali Behrangi","Tsechun Wang","Xiao Tan","Ziqiang Ma","Wentao Xiong"],"date":"2020-07-21","year":2020,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2020.3008033","openalex":"W3044411297"},"links":{"paper":"https://doi.org/10.1109/tgrs.2020.3008033"},"orgs":[],"topic":"observations-remote-sensing","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","stations"],"status":"research","summary":"Triple collocation merges CMORPH, PERSIANN and ERA5 precipitation over China, improving on each input product against rain-gauge data; the method is statistical rather than ML.","significance":2,"cited_by":92,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.10839","title":"Statistical Downscaling of Temperature Distributions from the Synoptic Scale to the Mesoscale Using Deep Convolutional Neural Networks","authors":["Tsuyoshi Thomas Sekiyama"],"date":"2020-07-20","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.10839","openalex":"W3044520644"},"links":{"paper":"https://arxiv.org/abs/2007.10839","pdf":"https://arxiv.org/pdf/2007.10839"},"orgs":["jma"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A deep CNN downscales 22-km synoptic temperature fields to 5-km mesoscale, cutting RMSE over high terrain from 2.7 K to 1.0 K.","significance":3,"cited_by":7,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.07978","title":"CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds","authors":["A. H. Nielsen","A. Iosifidis","H. Karstoft"],"date":"2020-07-15","year":2020,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 3485-3494, 2021","venue_type":"journal","ids":{"arxiv":"2007.07978","doi":"10.1109/jstars.2021.3062936","openalex":"W3043084273"},"links":{"paper":"https://arxiv.org/abs/2007.07978","pdf":"https://arxiv.org/pdf/2007.07978"},"orgs":[],"topic":"benchmarks-data-eval","topics":["nowcasting"],"type":"benchmark","method":["cnn","rnn","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Releases CloudCast, a 70,080-frame satellite dataset of 10 cloud types over Europe at 3 km and 15-min resolution, with ConvLSTM, GAN and optical-flow video prediction baselines.","significance":5,"cited_by":22,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.07383","title":"Supervised learning from noisy observations: Combining machine-learning techniques with data assimilation","authors":["Georg A. Gottwald","Sebastian Reich"],"date":"2020-07-14","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.07383","doi":"10.1016/j.physd.2021.132911"},"links":{"paper":"https://arxiv.org/abs/2007.07383","pdf":"https://arxiv.org/pdf/2007.07383"},"orgs":[],"topic":"data-assimilation","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Combines random feature map forecasting with ensemble Kalman filter data assimilation, learning sequentially from noisy observations to give long forecast skill, reliable ensembles and closure for multiscale chaotic systems.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12142203","title":"Extreme Gradient Boosting Model for Rain Retrieval using Radar Reflectivity from Various Elevation Angles","authors":["Chih‐Chiang Wei","Chen-Chia Hsu"],"date":"2020-07-09","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12142203","openalex":"W3041119055"},"links":{"paper":"https://doi.org/10.3390/rs12142203","pdf":"https://www.mdpi.com/2072-4292/12/14/2203/pdf?version=1594371040"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"XGBoost retrieves rainfall from radar reflectivity at multiple elevation angles, beating Marshall-Palmer and regression baselines for typhoon rainfall in Taiwan.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-13-3661-2020","title":"Exploration of machine learning methods for the classification of infrared limb spectra of polar stratospheric clouds","authors":["Rocco Sedona","Lars Hoffmann","Reinhold Spang","Gabriele Cavallaro","Sabine G. Griessbach","Michael Höpfner","Matthias Book","Morris Riedel"],"date":"2020-07-08","year":2020,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-13-3661-2020","openalex":"W3005819738"},"links":{"paper":"https://doi.org/10.5194/amt-13-3661-2020","pdf":"https://amt.copernicus.org/articles/13/3661/2020/amt-13-3661-2020.pdf"},"orgs":["kit","juelich"],"topic":"observations-remote-sensing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Random forest and SVM classify polar stratospheric clouds from MIPAS infrared limb spectra, with random forest the most promising and less prone to overfitting.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10503602.1","title":"Improving machine learning-based weather forecast 1 post-processing with clustering and transfer learning","authors":["Xiaomeng Huang","Xiaomeng Huang","Yuwen Chen","Yi Li","Yue Chen","Chi Yan Tsui","Xing Huang","Xing Huang","Mingqing Wang","Jonathon S. Wright"],"date":"2020-07-08","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10503602.1","openalex":"W4206836047"},"links":{"paper":"https://doi.org/10.1002/essoar.10503602.1"},"orgs":["tsinghua-university"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"K-means station clustering and decision-tree transfer learning post-process operational temperature forecasts at 301 Chinese stations, cutting 7-day RMSE by up to 39.4%.","significance":4,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10503594.1","title":"A Volume-to-Point Approach of QPE with Radar Data","authors":["Ting‐Shuo Yo","Shih‐Hao Su","Jung‐Lien Chu","Chiao‐Wei Chang","Hung‐Chi Kuo"],"date":"2020-07-08","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10503594.1","openalex":"W4205221277"},"links":{"paper":"https://doi.org/10.1002/essoar.10503594.1"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"Machine learning maps gridded radar reflectivity volumes to hourly station precipitation in Taiwan, outperforming the operational QPE scheme for heavy rain.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.04417","title":"SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecture","authors":["Kevin Trebing","Tomasz Stanczyk","Siamak Mehrkanoon"],"date":"2020-07-08","year":2020,"venue":"Pattern Recognition Letters","venue_type":"journal","ids":{"arxiv":"2007.04417","doi":"10.1016/j.patrec.2021.01.036","openalex":"W3042094193"},"links":{"paper":"https://doi.org/10.1016/j.patrec.2021.01.036","pdf":"https://arxiv.org/pdf/2007.04417"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"SmaAt-UNet, a lightweight attention U-Net with depthwise convolutions, matches baselines for precipitation nowcasting using a quarter of the parameters.","significance":4,"cited_by":511,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1073-pnas.1918964117","title":"Adversarial super-resolution of climatological wind and solar data","authors":["Karen Stengel","Andrew Glaws","Dylan Hettinger","Ryan N. King"],"date":"2020-07-06","year":2020,"venue":"Proceedings of the National Academy of Sciences","venue_type":"journal","ids":{"doi":"10.1073/pnas.1918964117","openalex":"W3039441806"},"links":{"paper":"https://doi.org/10.1073/pnas.1918964117"},"orgs":[],"topic":"downscaling","topics":["applications-impacts"],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":["global","regional"],"data":["cmip"],"status":"research","summary":"Adversarial deep learning super-resolves wind and solar outputs from global climate models by up to 50x, producing physically consistent fields for renewable resource assessment.","significance":5,"cited_by":287,"score":50,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-w12071909","title":"Monthly Precipitation Forecasts Using Wavelet Neural Networks Models in a Semiarid Environment","authors":["Javier Estévez","Juan Antonio Bellido-Jiménez","Xiaodong Liu","Amanda Penélope García-Marín"],"date":"2020-07-04","year":2020,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w12071909","openalex":"W3039590110"},"links":{"paper":"https://doi.org/10.3390/w12071909","pdf":"https://www.mdpi.com/2073-4441/12/7/1909/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Wavelet-decomposed neural networks predict monthly precipitation at sixteen Andalusian stations, reaching correlations of 0.76 to 0.90.","significance":2,"cited_by":41,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019jc015947","title":"El Niño Detection Via Unsupervised Clustering of Argo Temperature Profiles","authors":["Isabel Houghton","James David Wilson"],"date":"2020-07-04","year":2020,"venue":"Journal of Geophysical Research Oceans","venue_type":"journal","ids":{"doi":"10.1029/2019jc015947","openalex":"W3039583663"},"links":{"paper":"https://doi.org/10.1029/2019jc015947"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Unsupervised clustering of Argo ocean temperature profiles detects El Niño events without geographic inputs, offering an alternative to SST-based ENSO indices.","significance":3,"cited_by":38,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.12567","title":"Wind speed prediction using multidimensional convolutional neural networks","authors":["Kevin Trebing","Siamak Mehrkanoon"],"date":"2020-07-04","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.12567"},"links":{"paper":"https://arxiv.org/abs/2007.12567","pdf":"https://arxiv.org/pdf/2007.12567"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A multidimensional CNN forecasts wind speed from multivariate station weather histories in Danish and Dutch cities, outperforming 2D and 3D CNN baselines.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.01639","title":"Validation of GFS day-ahead solar irradiance forecasts in China","authors":["Yue Zhang","Yanbo Shen","Xiangao Xia","Guangyu Shi"],"date":"2020-07-03","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.01639"},"links":{"paper":"https://arxiv.org/abs/2007.01639","pdf":"https://arxiv.org/pdf/2007.01639"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Validates GFS day-ahead solar irradiance at 18 China stations; a gradient-boosting correction of GFS gives the best accuracy, beating persistence.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2007.01444","title":"Generative Modeling for Atmospheric Convection","authors":["Griffin Mooers","Jens Tuyls","Stephan Mandt","Michael Pritchard","Tom Beucler"],"date":"2020-07-03","year":2020,"venue_type":"preprint","ids":{"arxiv":"2007.01444"},"links":{"paper":"https://arxiv.org/abs/2007.01444","pdf":"https://arxiv.org/pdf/2007.01444"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["gan-vae"],"timescale":["climate"],"spatial":[],"data":["km-scale-sim"],"status":"research","summary":"A VAE trained on about 6 million high-resolution vertical velocity samples reconstructs convection and clusters organization regimes, supporting stochastic convection parameterizations.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11070701","title":"A Data-Driven Approach for Winter Precipitation Classification Using Weather Radar and NWP Data","authors":["Bong‐Chul Seo"],"date":"2020-07-01","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11070701","openalex":"W3038801525"},"links":{"paper":"https://doi.org/10.3390/atmos11070701","pdf":"https://www.mdpi.com/2073-4433/11/7/701/pdf?version=1593603583"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"Random forest and other supervised classifiers combine weather radar and NWP data to classify winter precipitation type, beating a temperature and thickness threshold baseline.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-5.0014016","title":"PV power output prediction from sky images using convolutional neural network: The comparison of sky-condition-specific sub-models and an end-to-end model","authors":["Yuhao Nie","Yuchi Sun","Yuanlei Chen","Rachel Orsini","Adam R. Brandt"],"date":"2020-07-01","year":2020,"venue":"Journal of Renewable and Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1063/5.0014016","openalex":"W3080550762"},"links":{"paper":"https://doi.org/10.1063/5.0014016"},"orgs":["stanford"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"A cloudiness-classified CNN framework nowcasts PV output from sky images, reaching 2.20 kW RMSE and improving on an end-to-end CNN by 6%.","significance":3,"cited_by":54,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11269-020-02580-x","title":"Real-time Extreme Rainfall Evaluation System for the Construction Industry Using Deep Convolutional Neural Networks","authors":["Chih‐Chiang Wei"],"date":"2020-07-01","year":2020,"venue":"Water Resources Management","venue_type":"journal","ids":{"doi":"10.1007/s11269-020-02580-x","openalex":"W3038356744"},"links":{"paper":"https://doi.org/10.1007/s11269-020-02580-x"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"application","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"pre-operational","summary":"Deep CNN real-time system for evaluating extreme rainfall to support construction-industry decisions; the abstract is missing, so details are limited.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10503549.1","title":"Improving machine learning-based weather forecast post-processing with clustering and transfer learning","authors":["Xiaomeng Huang","Xiaomeng Huang","Yuwen Chen","Yi Li","Yue Chen","Chi Yan Tsui","Xing Huang","Xing Huang","Mingqing Wang","Jonathon S. Wright"],"date":"2020-07-01","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10503549.1","openalex":"W3093925037"},"links":{"paper":"https://doi.org/10.1002/essoar.10503549.1"},"orgs":["tsinghua-university"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"research","summary":"K-means station clustering and decision-tree transfer learning post-process operational temperature forecasts at 301 Chinese stations, cutting 7-day RMSE by up to 39.4%.","significance":4,"cited_by":6,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.16678","title":"ARPEGE Cloud Cover Forecast Post-Processing with Convolutional Neural Network","authors":["Florian Dupuy","Olivier Mestre","Mathieu Serrurier","Mohamed Chafik Bakkay","Valentin Kivachuk Burdá","Naty Citlali Cabrera-Gutiérrez","Jean-Christophe Jouhaud","Maud-Alix Mader","Guillaume Oller","Michaël Zamo"],"date":"2020-06-30","year":2020,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"arxiv":"2006.16678","doi":"10.1175/waf-d-20-0093.1","openalex":"W3039349910"},"links":{"paper":"https://doi.org/10.1175/waf-d-20-0093.1","pdf":"https://arxiv.org/pdf/2006.16678"},"orgs":["meteo-france"],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","satellite"],"status":"research","summary":"A U-Net with a learned predictor-weighting layer post-processes ARPEGE cloud cover forecasts over Europe, outperforming random forests and logistic quantile regression.","significance":3,"cited_by":40,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.16162","title":"A didactic approach to the Machine Learning application to weather forecast","authors":["Marcello Raffaele","Maria Teresa Caccamo","Giuseppe Castorina","Gianmarco Munaò","Salvatore Magazù"],"date":"2020-06-29","year":2020,"venue":"Atti della Accademia Peloritana dei Pericolanti. Classe di Scienze Fisiche, Matematiche e Naturali/Atti della Accademia Peloritana dei Pericolanti, Classe di Scienze Fisiche, Matematiche e Naturali","venue_type":"journal","ids":{"arxiv":"2006.16162","openalex":"W3202235987"},"links":{"paper":"https://arxiv.org/abs/2006.16162","pdf":"https://arxiv.org/pdf/2006.16162"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"A didactic machine learning approach classifies rainfall categories near Etna and Stromboli from a weather station, with Stau and Foehn effects considered.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.15628","title":"Deep Orthogonal Decompositions for Convective Nowcasting","authors":["Daniel J. Tait"],"date":"2020-06-28","year":2020,"venue_type":"preprint","ids":{"arxiv":"2006.15628","openalex":"W3037395587"},"links":{"paper":"https://arxiv.org/abs/2006.15628","pdf":"https://arxiv.org/pdf/2006.15628"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["physics-constrained","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A physically structured deep model learns a low-dimensional space with minimal dynamics, outperforming model-free and hybrid nowcasting on precipitation and sea-surface temperature data.","significance":4,"cited_by":1,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11070676","title":"Machine Learning in Tropical Cyclone Forecast Modeling: A Review","authors":["Rui Chen","Weimin Zhang","Xiang Wang"],"date":"2020-06-27","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11070676","openalex":"W3037369538"},"links":{"paper":"https://doi.org/10.3390/atmos11070676","pdf":"https://www.mdpi.com/2073-4433/11/7/676/pdf?version=1593654182"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":[],"timescale":["short","medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Reviews machine learning for tropical cyclone genesis, track, intensity, rainfall, storm surge and numerical model improvement, highlighting opportunities and challenges.","significance":3,"cited_by":247,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10503512.1","title":"Using Gaussian process regression and stable isotopologues of water vapor to estimate shallow convective moistening in the southeastern Pacific marine stratocumulus region","authors":["Joseph Galewsky","Camille Risi","Hélène Brogniez"],"date":"2020-06-26","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10503512.1","openalex":"W4238258961"},"links":{"paper":"https://doi.org/10.1002/essoar.10503512.1"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Gaussian process regression on water vapor isotopes estimates shallow convective moistening over the SE Pacific better than conventional fields alone.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.14515","title":"Surrogate Models for Rainfall Nowcasting","authors":["Naty Citlali Cabrera-Gutiérrez","Hadrien Godé","Jean-Christophe Jouhaud","Mohamed Chafik Bakkay","Valentin Kivachuk Burdá","Florian Dupuy","Maud-Alix Mader","Olivier Mestre","Guillaume Oller","Mathieu Serrurier","Michaël Zamo"],"date":"2020-06-25","year":2020,"venue_type":"preprint","ids":{"arxiv":"2006.14515"},"links":{"paper":"https://arxiv.org/abs/2006.14515","pdf":"https://arxiv.org/pdf/2006.14515"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml","other"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"POD combined with Kriging or Random Forest emulates Arome-NWC rainfall nowcasts over France at 1-minute resolution with much lower computational cost.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.14276","title":"Combining Ensemble Kalman Filter and Reservoir Computing to predict spatio-temporal chaotic systems from imperfect observations and models","authors":["Futo Tomizawa","Yohei Sawada"],"date":"2020-06-25","year":2020,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"2006.14276","doi":"10.5194/gmd-14-5623-2021","openalex":"W3080545603"},"links":{"paper":"https://doi.org/10.5194/gmd-14-5623-2021","pdf":"https://arxiv.org/pdf/2006.14276"},"orgs":["jma"],"topic":"data-assimilation","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Reservoir computing trained on LETKF analyses predicts the Lorenz 96 system under sparse, noisy observations and imperfect models, outperforming LETKF when the model is imperfect.","significance":4,"cited_by":21,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-forecast2020011","title":"Performance Comparison between Deep Learning and Optical Flow-Based Techniques for Nowcast Precipitation from Radar Images","authors":["Marino Marrocu","Luca Massidda"],"date":"2020-06-24","year":2020,"venue":"Forecasting","venue_type":"journal","ids":{"doi":"10.3390/forecast2020011","openalex":"W3037627778"},"links":{"paper":"https://doi.org/10.3390/forecast2020011","pdf":"https://www.mdpi.com/2571-9394/2/2/11/pdf?version=1593507386"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A generative neural network nowcasts radar precipitation up to one hour ahead and beats optical-flow methods on five years of Japanese radar data.","significance":3,"cited_by":43,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-19-0372.1","title":"Deep Learning on Three-Dimensional Multiscale Data for Next-Hour Tornado Prediction","authors":["Ryan Lagerquist","Amy McGovern","Cameron R. Homeyer","David John Gagne II","Travis Smith"],"date":"2020-06-24","year":2020,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-19-0372.1","openalex":"W3025786591"},"links":{"paper":"https://doi.org/10.1175/mwr-d-19-0372.1"},"orgs":["ncar","university-of-oklahoma"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"CNNs using radar images and proximity soundings predict next-hour tornado occurrence with AUC above 0.9, with a GridRad critical success index of 0.31.","significance":4,"cited_by":102,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1038-s41598-020-67146-8","title":"Projection of meteorological droughts in Nigeria during growing seasons under climate change scenarios","authors":["Mohammed Sanusi Shiru","Shamsuddin Shahid","Ashraf Mahmmood Dewan","‪Eun‐Sung Chung","Noraliani  Binti Alias","Kamal Ahmed","Quazi K. Hassan"],"date":"2020-06-22","year":2020,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-020-67146-8","openalex":"W3035953616"},"links":{"paper":"https://doi.org/10.1038/s41598-020-67146-8","pdf":"https://www.nature.com/articles/s41598-020-67146-8.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Machine-learning multi-model ensemble and bias correction of GCMs project Nigerian meteorological drought changes under RCP scenarios through 2099.","significance":2,"cited_by":143,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10044-020-00898-1","title":"Deep learning-based effective fine-grained weather forecasting model","authors":["Pradeep Hewage","Marcello Trovati","Ella Pereira","Ardhendu Behera"],"date":"2020-06-22","year":2020,"venue":"Pattern Analysis and Applications","venue_type":"journal","ids":{"doi":"10.1007/s10044-020-00898-1","openalex":"W3035548318"},"links":{"paper":"https://doi.org/10.1007/s10044-020-00898-1","pdf":"https://link.springer.com/content/pdf/10.1007/s10044-020-00898-1.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Lightweight LSTM and TCN models forecast surface weather from station records and are reported to beat classical methods and the WRF NWP model.","significance":3,"cited_by":244,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3127729981","title":"Geometric deep learning for medium-range weather prediction","authors":["Icíar Lloréns Jover"],"date":"2020-06-19","year":2020,"venue_type":"other","ids":{"openalex":"W3127729981"},"links":{"paper":"https://infoscience.epfl.ch/record/278138"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["gnn"],"timescale":["medium"],"spatial":["global"],"data":[],"status":"research","summary":"Geometric (graph-based) deep learning for medium-range global weather prediction; no abstract is available, so details come from the title only.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ab9e98","title":"Machine learning-based integration of large-scale climate drivers can improve the forecast of seasonal rainfall probability in Australia","authors":["Puyu Feng","Bin Wang","De Li Liu","Fei Ji","Xiaoli Niu","Hongyan Ruan","Lijie Shi","Qiang Yu"],"date":"2020-06-19","year":2020,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ab9e98","openalex":"W3036907729"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ab9e98","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ab9e98/pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Random forest using Pacific, Indian and Southern Ocean climate indices beats the Queensland SOI phase model for Australian seasonal rainfall probability, improving accuracy by 28-219%.","significance":3,"cited_by":36,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-acp-20-7125-2020","title":"Linking large-scale circulation patterns to low-cloud properties","authors":["Timothy W. Juliano","Zachary J. Lebo"],"date":"2020-06-17","year":2020,"venue":"Atmospheric chemistry and physics","venue_type":"journal","ids":{"doi":"10.5194/acp-20-7125-2020","openalex":"W2981066841"},"links":{"paper":"https://doi.org/10.5194/acp-20-7125-2020","pdf":"https://acp.copernicus.org/articles/20/7125/2020/acp-20-7125-2020.pdf"},"orgs":["ncar"],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"Unsupervised clustering of 850-hPa circulation over the NE Pacific links synoptic regimes to marine boundary-layer cloud droplet properties and cloud radiative forcing.","significance":3,"cited_by":16,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.08712","title":"Statistical post‐processing of heat index ensemble forecasts: Is there a royal road?","authors":["Sándor Baran","Ágnes Baran","Florian Pappenberger","Zied Ben Bouallègue"],"date":"2020-06-17","year":2020,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"arxiv":"2001.08712","doi":"10.1002/qj.3853","openalex":"W3002392759"},"links":{"paper":"https://doi.org/10.1002/qj.3853","pdf":"https://rmets.onlinelibrary.wiley.com/doi/pdfdirect/10.1002/qj.3853"},"orgs":["ecmwf"],"topic":"post-processing","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":["short","medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Compares calibration of heat index ensembles, finding direct GEV-based EMOS gives the best skill up to day 6; machine learning performs comparably only for warning categories.","significance":3,"cited_by":13,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-iet-rpg.2019.0941","title":"Data‐driven weather forecasting models performance comparison for improving offshore wind turbine availability and maintenance","authors":["Ravi Pandit","Athanasios Kolios","David G. Infield"],"date":"2020-06-16","year":2020,"venue":"IET Renewable Power Generation","venue_type":"journal","ids":{"doi":"10.1049/iet-rpg.2019.0941","openalex":"W3036573057"},"links":{"paper":"https://doi.org/10.1049/iet-rpg.2019.0941","pdf":"https://strathprints.strath.ac.uk/72882/1/Pandit_etal_IET_RPG_2020_Data_driven_weather_forecasting_models_performance_comparison.pdf"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"application","method":["rnn"],"timescale":["medium"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM and Markov chain models forecast offshore wind and wave conditions from FINO3 station measurements to support turbine maintenance planning; the study compares the two models.","significance":2,"cited_by":34,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.08901","title":"Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows","authors":["Suraj Pawar","Omer San"],"date":"2020-06-16","year":2020,"venue":"Physical Review Fluids","venue_type":"journal","ids":{"arxiv":"2006.08901","doi":"10.1103/physrevfluids.6.050501","openalex":"W3163000876"},"links":{"paper":"https://doi.org/10.1103/physrevfluids.6.050501","pdf":"https://arxiv.org/pdf/2006.08901"},"orgs":[],"topic":"hybrid-parameterization","topics":["data-assimilation"],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Data assimilation corrects neural-network subgrid closures during online runs, improving long-term prediction of chaotic Lorenz 96 and Kraichnan turbulence dynamics.","significance":4,"cited_by":47,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.07972","title":"Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances","authors":["Sijie He","Xinyan Li","Timothy DelSole","Pradeep Ravikumar","Arindam Banerjee"],"date":"2020-06-14","year":2020,"venue_type":"preprint","ids":{"arxiv":"2006.07972"},"links":{"paper":"https://arxiv.org/abs/2006.07972","pdf":"https://arxiv.org/pdf/2006.07972"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["s2s","seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Benchmarks ten ML methods for US sub-seasonal forecasting; gradient boosting performs best and beats climatology, with ENSO and soil moisture as key predictors.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.07718","title":"A generative adversarial network approach to (ensemble) weather prediction","authors":["Alexander Bihlo"],"date":"2020-06-13","year":2020,"venue":"Neural Networks","venue_type":"journal","ids":{"arxiv":"2006.07718","doi":"10.1016/j.neunet.2021.02.003","openalex":"W3034487564"},"links":{"paper":"https://doi.org/10.1016/j.neunet.2021.02.003","pdf":"https://arxiv.org/pdf/2006.07718"},"orgs":[],"topic":"probabilistic-ensembles","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A conditional convolutional GAN forecasts 500 hPa height, 2 m temperature and precipitation over Europe for 24 h, and MC dropout yields a deep learning ensemble.","significance":3,"cited_by":118,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-13-2631-2020","title":"RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting","authors":["Georgy Ayzel","Tobias Scheffer","Maik Heistermann"],"date":"2020-06-11","year":2020,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-13-2631-2020","openalex":"W3009216045"},"links":{"paper":"https://doi.org/10.5194/gmd-13-2631-2020"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"RainNet, a U-Net/SegNet-style CNN, nowcasts German radar precipitation to 60 min, beating optical flow on MAE and CSI but underpredicting heavy rain.","significance":4,"cited_by":361,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-cli8060076","title":"Application of Machine Learning to Attribution and Prediction of Seasonal Precipitation and Temperature Trends in Canberra, Australia","authors":["Joshua Hartigan","Shev MacNamara","Lance M. Leslie"],"date":"2020-06-11","year":2020,"venue":"Climate","venue_type":"journal","ids":{"doi":"10.3390/cli8060076","openalex":"W3034291375"},"links":{"paper":"https://doi.org/10.3390/cli8060076"},"orgs":[],"topic":"climate-analysis-attribution","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["seasonal","climate"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Uses linear regression and support vector regression to attribute and predict Canberra's seasonal precipitation and temperature from ENSO, SAM and IOD drivers, with SVR reaching r=0.737 for precipitation.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-feart.2020.00146","title":"Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China","authors":["Xiaoxiao Min","Ziqiang Ma","Jintao Xu","Kang He","Zhige Wang","Qingliang Huang","Jun Li"],"date":"2020-06-10","year":2020,"venue":"Frontiers in Earth Science","venue_type":"journal","ids":{"doi":"10.3389/feart.2020.00146","openalex":"W3034749008"},"links":{"paper":"https://doi.org/10.3389/feart.2020.00146","pdf":"https://www.frontiersin.org/articles/10.3389/feart.2020.00146/pdf"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"SVM and BPNN downscale IMERG daily precipitation over Zhejiang; SVM raises R² from 0.344 to 0.615 against gauges.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12111872","title":"Temperature and Humidity Profile Retrieval from FY4-GIIRS Hyperspectral Data Using Artificial Neural Networks","authors":["Xi Cai","Yansong Bao","George P. Petropoulos","Feng Lu","Qifeng Lu","Liuhua Zhu","Ying Wu"],"date":"2020-06-09","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12111872","openalex":"W3034862025"},"links":{"paper":"https://doi.org/10.3390/rs12111872","pdf":"https://www.mdpi.com/2072-4292/12/11/1872/pdf?version=1591702717"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","stations"],"status":"research","summary":"Artificial neural networks retrieve temperature and humidity profiles from FY-4 GIIRS hyperspectral radiances, outperforming a simulation-trained network and matching AIRS consistency.","significance":3,"cited_by":50,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-ascmo-6-61-2020","title":"Robust regional clustering and modeling of nonstationary summer temperature extremes across Germany","authors":["Meagan Carney","Hölger Kantz"],"date":"2020-06-08","year":2020,"venue":"Advances in statistical climatology, meteorology and oceanography","venue_type":"journal","ids":{"doi":"10.5194/ascmo-6-61-2020","openalex":"W3034572537"},"links":{"paper":"https://doi.org/10.5194/ascmo-6-61-2020","pdf":"https://ascmo.copernicus.org/articles/6/61/2020/ascmo-6-61-2020.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Kernel k-means clustering of German station series yields robust regions, enabling a nonstationary model of summer temperature extremes above 35 °C.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3092696446","title":"Weather Forecasting using Linear Regression In Machine Learning","authors":["Om Narayan Jaiswal"],"date":"2020-06-07","year":2020,"venue_type":"other","ids":{"openalex":"W3092696446"},"links":{"paper":"https://easychair.org/publications/preprint_open/Q2DV"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Applies linear regression to weather forecasting; no abstract is available, so scope and results rest on the title alone.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app10113965","title":"A Novel Deep Learning Approach for Tropical Cyclone Track Prediction Based on Auto-Encoder and Gated Recurrent Unit Networks","authors":["Jie Lian","Pingping Dong","Yuping Zhang","Jianguo Pan"],"date":"2020-06-07","year":2020,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app10113965","openalex":"W3033421405"},"links":{"paper":"https://doi.org/10.3390/app10113965","pdf":"https://www.mdpi.com/2076-3417/10/11/3965/pdf?version=1591927904"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short","medium"],"spatial":["regional"],"data":["other"],"status":"research","summary":"An autoencoder plus GRU model forecasts typhoon landing locations, beating NWP by 15-56% in absolute position error at 24-72 hours.","significance":3,"cited_by":35,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.37896-aj9.6-009","title":"Weather Forecasts Based on Rainfall Prediction Using Machine Learning Methodologies","authors":[],"date":"2020-06-06","year":2020,"venue":"ADALYA","venue_type":"journal","ids":{"doi":"10.37896/aj9.6/009","openalex":"W4205974081"},"links":{"paper":"https://doi.org/10.37896/aj9.6/009"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Applies machine learning methods to rainfall prediction for weather forecasts; no abstract is available, so details are limited.","significance":1,"cited_by":11,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.agrformet.2020.108043","title":"Quantifying the impacts of pre-occurred ENSO signals on wheat yield variation using machine learning in Australia","authors":["Bin Wang","Puyu Feng","Cathy Waters","James Cleverly","De Li Liu","Qiang Yu"],"date":"2020-06-05","year":2020,"venue":"Agricultural and Forest Meteorology","venue_type":"journal","ids":{"doi":"10.1016/j.agrformet.2020.108043","openalex":"W3033674502"},"links":{"paper":"https://doi.org/10.1016/j.agrformet.2020.108043"},"orgs":[],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Uses machine learning to quantify how pre-occurring ENSO signals drive Australian wheat yield variation, linking seasonal climate drivers to agricultural impacts; abstract unavailable.","significance":2,"cited_by":42,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s20113181","title":"PortWeather: A Lightweight Onboard Solution for Real-Time Weather Prediction","authors":["Petros S. Karvelis","Daniele Mazzei","Matteo Biviano","Chrysostomos D. Stylios"],"date":"2020-06-03","year":2020,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s20113181","openalex":"W3033319396"},"links":{"paper":"https://doi.org/10.3390/s20113181","pdf":"https://www.mdpi.com/1424-8220/20/11/3181/pdf?version=1591334496"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A lightweight regression model runs on a microcontroller beside a weather station to forecast wind speed and direction offline, tested on real maritime data.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s20113167","title":"A Regional NWP Tropospheric Delay Inversion Method Based on a General Regression Neural Network Model","authors":["Lei Li","Ying Xu","Lizi Yan","Shengli Wang","Guolin Liu","Fan Liu"],"date":"2020-06-03","year":2020,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s20113167","openalex":"W3033309374"},"links":{"paper":"https://doi.org/10.3390/s20113167","pdf":"https://www.mdpi.com/1424-8220/20/11/3167/pdf?version=1591243990"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"A general regression neural network corrects zenith tropospheric delay from ECMWF and NCEP reanalysis over Japan, improving accuracy for GNSS positioning.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.29121-ijetmr.v7.i5.2020.685","title":"USING ARTIFICIAL INTELLIGENCE TO ASSESS SOLAR RADIATION FROM THE TOTAL SKY IMAGES","authors":["Chi‐Chang Chen","Chien-Hsing Huang"],"date":"2020-06-03","year":2020,"venue":"International Journal of Engineering Technologies and Management Research","venue_type":"journal","ids":{"doi":"10.29121/ijetmr.v7.i5.2020.685","openalex":"W3033799550"},"links":{"paper":"https://doi.org/10.29121/ijetmr.v7.i5.2020.685","pdf":"https://www.granthaalayahpublication.org/ijetmr-ojms/index.php/ijetmr/article/download/IJETMR20_A05_2102/567"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Optical flow on sky images tracks cloud motion, and a neural network links it to short-term whole-sky solar radiation changes for plant efficiency estimates.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-19-0258.1","title":"Generating Probabilistic Next-Day Severe Weather Forecasts from Convection-Allowing Ensembles Using Random Forests","authors":["Eric D. Loken","Adam James Clark","Christopher D. Karstens"],"date":"2020-06-03","year":2020,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-19-0258.1","openalex":"W3033714468"},"links":{"paper":"https://doi.org/10.1175/waf-d-19-0258.1"},"orgs":["noaa","university-of-oklahoma"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Random forests convert convection-allowing ensemble forecasts into day-1 severe weather probabilities, beating calibrated updraft helicity and SPC outlooks in Brier skill, especially for wind and hail.","significance":4,"cited_by":44,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.02581","title":"Prediction of short and long-term droughts using artificial neural networks and hydro-meteorological variables","authors":["Yousef Hassanzadeh","Mohammadvaghef Ghazvinian","Amin Abdi","Saman Baharvand","Ali Jozaghi"],"date":"2020-06-03","year":2020,"venue_type":"preprint","ids":{"arxiv":"2006.02581"},"links":{"paper":"https://arxiv.org/abs/2006.02581","pdf":"https://arxiv.org/pdf/2006.02581"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies artificial neural networks to predict drought (SPI at 3 to 48 months) in Tabriz, Iran, using station precipitation and other hydro-meteorological variables from 1992 to 2010.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2006.02064","title":"Hybrid Scheme of Kinematic Analysis and Lagrangian Koopman Operator Analysis for Short-term Precipitation Forecasting","authors":["Shitao Zheng","Takashi Miyamoto","Koyuru Iwanami","Shingo Shimizu","Ryohei Kato"],"date":"2020-06-03","year":2020,"venue":"Journal of Disaster Research","venue_type":"journal","ids":{"arxiv":"2006.02064","doi":"10.20965/jdr.2022.p1140","openalex":"W4311015939"},"links":{"paper":"https://doi.org/10.20965/jdr.2022.p1140","pdf":"https://arxiv.org/pdf/2006.02064"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Combines kinematic advection analysis with Lagrangian Koopman operator analysis to improve short-term precipitation forecasts, with stable long-period predictions.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21729-ksds.2020.13.2.27","title":"Prediction of Temperature and Heat Wave Occurrence for Summer Season Using Machine Learning","authors":["Young In Kim","Donghyun Kim","Seung Oh Lee"],"date":"2020-06-01","year":2020,"venue":"Journal of Korean Society of Disaster and Security","venue_type":"journal","ids":{"doi":"10.21729/ksds.2020.13.2.27","openalex":"W3109142465"},"links":{"paper":"https://doi.org/10.21729/ksds.2020.13.2.27"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Applies machine learning to predict summer temperatures and heat wave occurrence in Korea at seasonal lead; abstract unavailable, so judged from the title only.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijrte.a2747.059120","title":"Rainfall Prediction using Machine Learning and Neural Network","authors":["Kaushik Dutta","Gouthaman. P"],"date":"2020-05-30","year":2020,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.a2747.059120","openalex":"W4230042244"},"links":{"paper":"https://doi.org/10.35940/ijrte.a2747.059120"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares machine learning and neural network approaches for rainfall prediction from past rainfall records and selects the more accurate one; no quantitative results given.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-npg-27-329-2020","title":"From research to applications – examples of operational ensemble post-processing in France using machine learning","authors":["Maxime Taillardat","Olivier Mestre"],"date":"2020-05-29","year":2020,"venue":"Nonlinear processes in geophysics","venue_type":"journal","ids":{"doi":"10.5194/npg-27-329-2020","openalex":"W2999591108"},"links":{"paper":"https://doi.org/10.5194/npg-27-329-2020","pdf":"https://npg.copernicus.org/articles/27/329/2020/npg-27-329-2020.pdf"},"orgs":["meteo-france"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"operational","summary":"Operational quantile regression forests and ensemble copula coupling improve station temperature and gridded hourly rainfall forecasts in France, better capturing cold and heat waves than raw ensembles.","significance":4,"cited_by":63,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-13-2487-2020","title":"Correcting a bias in a climate model with an augmented emulator","authors":["Doug McNeall","Jonny Williams","Richard Betts","Ben B. B. Booth","Peter Challenor","Peter Good","Andy Wiltshire"],"date":"2020-05-29","year":2020,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-13-2487-2020","openalex":"W2964730897"},"links":{"paper":"https://doi.org/10.5194/gmd-13-2487-2020","pdf":"https://gmd.copernicus.org/articles/13/2487/2020/gmd-13-2487-2020.pdf"},"orgs":["met-office"],"topic":"climate-analysis-attribution","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A Gaussian process emulator with an augmented bias term corrects Amazon climate biases in a land-surface model and identifies plausible parameter values despite structural error.","significance":3,"cited_by":14,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12111741","title":"Estimation of Hourly near Surface Air Temperature Across Israel Using an Ensemble Model","authors":["Bin Zhou","Evyatar Erell","Ian Hough","Alexandra Shtein","Allan C. Just","Victor Novack","Jonathan D. Rosenblatt","Itai Kloog"],"date":"2020-05-28","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12111741","openalex":"W3029927724"},"links":{"paper":"https://doi.org/10.3390/rs12111741","pdf":"https://www.mdpi.com/2072-4292/12/11/1741/pdf?version=1590677755"},"orgs":["pik"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations","era5"],"status":"research","summary":"Three-stage random forest and XGBoost ensemble estimates hourly 1 km air temperature over Israel from geostationary satellite skin temperature and station data.","significance":3,"cited_by":31,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-asce-nh.1527-6996.0000390","title":"Hurricane Risk Assessment for Residential Buildings in the Southeastern US Coastal Region in Changing Climate Conditions Using Artificial Neural Networks","authors":["Chi‐Ying Lin","Eun Jeong"],"date":"2020-05-28","year":2020,"venue":"Natural Hazards Review","venue_type":"journal","ids":{"doi":"10.1061/(asce)nh.1527-6996.0000390","openalex":"W3029718617"},"links":{"paper":"https://doi.org/10.1061/(asce)nh.1527-6996.0000390"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Neural networks project future hurricane parameters under RCP8.5 for southeastern US coast, showing economic losses rising sharply under climate change.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.12322","title":"Indicator patterns of forced change learned by an artificial neural network","authors":["Elizabeth A. Barnes","Benjamin Toms","James W. Hurrell","Imme Ebert-Uphoff","Chuck Anderson","David Anderson"],"date":"2020-05-25","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2005.12322","doi":"10.1029/2020ms002195","openalex":"W3029338315"},"links":{"paper":"https://doi.org/10.1029/2020ms002195","pdf":"https://arxiv.org/pdf/2005.12322"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A neural network trained to predict the year from climate model temperature and precipitation maps, with relevance visualization, reveals indicator patterns of forced climate change.","significance":4,"cited_by":116,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.11862","title":"Climbing down Charney's ladder: Machine Learning and the post-Dennard era of computational climate science","authors":["V. Balaji"],"date":"2020-05-24","year":2020,"venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2005.11862","doi":"10.1098/rsta.2020.0085","openalex":"W3027335838"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0085","pdf":"https://arxiv.org/pdf/2005.11862"},"orgs":["noaa","princeton-university"],"topic":"hybrid-parameterization","topics":[],"type":"position","method":[],"timescale":["climate"],"spatial":["global"],"data":[],"status":"research","summary":"Prospectus arguing that the end of Dennard scaling will push climate science toward combining machine learning pattern recognition with physical equations, reshaping how weather and climate are simulated.","significance":5,"cited_by":56,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.12401","title":"Wind Speed Prediction and Visualization Using Long Short-Term Memory Networks (LSTM)","authors":["Md Amimul Ehsan","Amir Shahirinia","Nian Zhang","Timothy Oladunni"],"date":"2020-05-22","year":2020,"venue_type":"preprint","ids":{"arxiv":"2005.12401"},"links":{"paper":"https://arxiv.org/abs/2005.12401","pdf":"https://arxiv.org/pdf/2005.12401"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares twelve AI algorithms for wind speed prediction from meteorological station data, with LSTM reaching 97.8% accuracy for wind farm planning.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.11296","title":"Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows","authors":["Suraj Pawar","Shady E. Ahmed","Omer San","Adil Rasheed","Ionel M. Navon"],"date":"2020-05-22","year":2020,"venue_type":"preprint","ids":{"arxiv":"2005.11296","doi":"10.1063/5.0012853"},"links":{"paper":"https://arxiv.org/abs/2005.11296","pdf":"https://arxiv.org/pdf/2005.11296"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"LSTM-learned nudging gain for data assimilation outperforms EKF and EnKF on Lorenz 96 with sparse observations, acting as a stabilizer at lower computational cost.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12101648","title":"A Neural Network-Based Rain Effect Correction Method for HY-2A Scatterometer Backscatter Measurements","authors":["Xuetong Xie","Jing Wang","Mingsen Lin"],"date":"2020-05-21","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12101648","openalex":"W3026705033"},"links":{"paper":"https://doi.org/10.3390/rs12101648","pdf":"https://www.mdpi.com/2072-4292/12/10/1648/pdf?version=1590051708"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"A neural network removes rain-induced bias from HY-2A scatterometer backscatter, using ECMWF winds as reference, so retrieved sea-surface winds deviate much less in rain.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-1206212x.2020.1766769","title":"A comparative study of prediction and classification models on NCDC weather data","authors":["Ibrahim Gad","Doreswamy Hosahalli"],"date":"2020-05-20","year":2020,"venue":"International Journal of Computers and Applications","venue_type":"journal","ids":{"doi":"10.1080/1206212x.2020.1766769","openalex":"W3027204411"},"links":{"paper":"https://doi.org/10.1080/1206212x.2020.1766769"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares classical machine learning classifiers and regressors on NCDC station weather data, finding CART, XGBoost and AdaBoost most accurate for classification.","significance":1,"cited_by":41,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.10374","title":"Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network","authors":["Jussi Leinonen","Daniele Nerini","Alexis Berne"],"date":"2020-05-20","year":2020,"venue":"IEEE Transactions on Geoscience and Remote Sensing, 59 (9), 7211-7223, 2021","venue_type":"journal","ids":{"arxiv":"2005.10374","doi":"10.1109/tgrs.2020.3032790","openalex":"W3026449040"},"links":{"paper":"https://arxiv.org/abs/2005.10374","pdf":"https://arxiv.org/pdf/2005.10374","code":"https://github.com/jleinonen/downscaling-rnn-gan"},"orgs":["meteoswiss"],"topic":"downscaling","topics":[],"type":"model","method":["gan-vae","rnn"],"timescale":[],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"A recurrent stochastic GAN generates ensembles of temporally consistent high-resolution precipitation radar and cloud optical thickness fields from low-resolution sequences.","significance":5,"cited_by":217,"score":75,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1088-1748-9326-ab7df9","title":"Comparative assessment of environmental variables and machine learning algorithms for maize yield prediction in the US Midwest","authors":["Yanghui Kang","Mutlu Ozdogan","Xiaojin Zhu","Zhiwei Ye","Christopher Hain","Martha Anderson"],"date":"2020-05-19","year":2020,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ab7df9","openalex":"W3011178959"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ab7df9"},"orgs":["nasa"],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["classical-ml","rnn","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Compares six ML algorithms for county-level maize yield prediction and finds XGBoost best; the target is crop yield rather than the atmosphere.","significance":3,"cited_by":238,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2005.09056","title":"Tropical and Extratropical Cyclone Detection Using Deep Learning","authors":["Christina Kumler-Bonfanti","Jebb Stewart","David Hall","Mark Govett"],"date":"2020-05-18","year":2020,"venue_type":"preprint","ids":{"arxiv":"2005.09056","doi":"10.1175/jamc-d-20-0117.1"},"links":{"paper":"https://arxiv.org/abs/2005.09056","pdf":"https://arxiv.org/pdf/2005.09056"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","satellite"],"status":"research","summary":"Four U-Net models detect tropical and extratropical cyclone regions from GFS precipitable water and GOES imagery, with Dice scores of 0.51 to 0.76 and 3x speedup over a heuristic.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.08748","title":"Deep Learning for Post-Processing Ensemble Weather Forecasts","authors":["Peter Grönquist","Chengyuan Yao","Tal Ben-Nun","Nikoli Dryden","Peter Dueben","Shigang Li","Torsten Hoefler"],"date":"2020-05-18","year":2020,"venue":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2005.08748","doi":"10.1098/rsta.2020.0092","openalex":"W3025325835"},"links":{"paper":"https://arxiv.org/abs/2005.08748","pdf":"https://arxiv.org/pdf/2005.08748"},"orgs":["ecmwf","eth-zurich"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"A deep neural network post-processes a subset of ensemble trajectories, improving CRPS by over 14% and allowing fewer members to match the full ensemble.","significance":5,"cited_by":201,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1002-qj.3823","title":"Texture‐based classification of high‐resolution precipitation forecasts with machine‐learning methods","authors":["Yamina Hamidi","Laure Raynaud","Lucie Rottner","Philippe Arbogast"],"date":"2020-05-16","year":2020,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.3823","openalex":"W3025663580"},"links":{"paper":"https://doi.org/10.1002/qj.3823"},"orgs":["meteo-france"],"topic":"benchmarks-data-eval","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Random forests classify continuous versus intermittent precipitation textures in AROME high-resolution forecasts, outperforming other classifiers and transferring to gridded observations for verification.","significance":3,"cited_by":2,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.aej.2020.04.035","title":"Precipitation forecast of the Wujiang River Basin based on artificial bee colony algorithm and backpropagation neural network","authors":["Yongtao Wang","Jian Liu","Rong Li","Xinyu Suo","Enhui Lu"],"date":"2020-05-15","year":2020,"venue":"Alexandria Engineering Journal","venue_type":"journal","ids":{"doi":"10.1016/j.aej.2020.04.035","openalex":"W3025114369"},"links":{"paper":"https://doi.org/10.1016/j.aej.2020.04.035","pdf":"https://www.sciencedirect.com/science/article/pii/S1110016820301861/pdf"},"orgs":[],"topic":"local-forecasting","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["decadal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Combines artificial bee colony optimization with a backpropagation network to forecast basin precipitation from 17 stations over two decades, linked to wavelet periodicity and drought/flood years.","significance":2,"cited_by":43,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.07243","title":"Unsupervised Severe Weather Detection Via Joint Representation Learning Over Textual and Weather Data","authors":["Athanasios Davvetas","Iraklis A. Klampanos"],"date":"2020-05-14","year":2020,"venue_type":"preprint","ids":{"arxiv":"2005.07243"},"links":{"paper":"https://arxiv.org/abs/2005.07243","pdf":"https://arxiv.org/pdf/2005.07243"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Unsupervised representation learning over text and weather data improves clustering for detecting severe weather events such as windstorms, floods and tornado outbreaks.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-19-0218.1","title":"Assessment of Cloud Retrieval for IASI 1D-Var Cloudy-Sky Assimilation and Improvement with an ANN Approach","authors":["Ahreum Lee","Byung-Ju Sohn","E. Pavelin","Yoonjae Kim","Hyun‐Suk Kang","Roger W. Saunders","Young‐Chan Noh"],"date":"2020-05-13","year":2020,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-19-0218.1","openalex":"W3024326514"},"links":{"paper":"https://doi.org/10.1175/waf-d-19-0218.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/35/4/wafD190218.pdf"},"orgs":["met-office","kma"],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"pre-operational","summary":"An artificial neural network estimates IASI cloud-top pressure and fraction closer to optimal values, cutting retrieval time and improving 1D-Var cloudy-sky assimilation with near-neutral forecast impact.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6617","title":"Fine scale surface climate in complex terrain using machine learning","authors":["Thomas C. M. Martin","Humberto Ribeiro da Rocha","Gabriel M. P. Perez"],"date":"2020-05-13","year":2020,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6617","openalex":"W3024895859"},"links":{"paper":"https://doi.org/10.1002/joc.6617"},"orgs":["university-of-reading"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","cmip"],"status":"research","summary":"Machine learning with PCA, ANN and quantile mapping downscales GCM output to 30 m sub-daily temperature, humidity and wind in complex terrain, improving on GCM accuracy.","significance":3,"cited_by":14,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.06524","title":"Deep Learning for Classifying and Characterizing Atmospheric Ducting within the Maritime Setting","authors":["Hilarie Sit","Christopher J. Earls"],"date":"2020-05-13","year":2020,"venue_type":"preprint","ids":{"arxiv":"2005.06524","doi":"10.1016/j.cageo.2021.104919"},"links":{"paper":"https://arxiv.org/abs/2005.06524","pdf":"https://arxiv.org/pdf/2005.06524"},"orgs":[],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Deep learning first classifies marine atmospheric duct type from sparse propagation factor measurements, then estimates refractivity parameters for real-time radar-performance applications.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21608-jisse.2020.27734.1024","title":"Time Series Statistical Analysis by Using Artificial Neural Network techniques Case study: Forecasting Models","authors":["Afrah Al‐Bossly"],"date":"2020-05-11","year":2020,"venue":"Journal of International Society for Science and Engineering ","venue_type":"journal","ids":{"doi":"10.21608/jisse.2020.27734.1024","openalex":"W3024635659"},"links":{"paper":"https://doi.org/10.21608/jisse.2020.27734.1024"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Reviews neural network regression for weather time-series forecasting and assesses ANN performance on country site data; methodological contribution is limited.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.04988","title":"A review of radar-based nowcasting of precipitation and applicable machine learning techniques","authors":["Rachel Prudden","Samantha Adams","Dmitry Kangin","Niall Robinson","Suman Ravuri","Shakir Mohamed","Alberto Arribas"],"date":"2020-05-11","year":2020,"venue_type":"preprint","ids":{"arxiv":"2005.04988","openalex":"W3021496143"},"links":{"paper":"https://arxiv.org/abs/2005.04988","pdf":"https://arxiv.org/pdf/2005.04988"},"orgs":[],"topic":"nowcasting","topics":["benchmarks-data-eval"],"type":"review","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Reviews radar-based precipitation nowcasting methods from environmental science and the machine learning techniques applicable to them, arguing for closer collaboration between the two communities.","significance":3,"cited_by":62,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-19-0289.1","title":"Spatial and Temporal Downscaling of TRMM Precipitation with Novel Algorithms","authors":["Huihui Zhang","Hugo A. Loáiciga","Da Ha","Qingyun Du"],"date":"2020-05-07","year":2020,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-19-0289.1","openalex":"W3022992207"},"links":{"paper":"https://doi.org/10.1175/jhm-d-19-0289.1"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Two downscaling methods (GWR and BP-ANN, plus bias correction and PCA) refine TRMM rainfall from 25 km to 1 km over Hubei, validated against 27 gauges.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2020.5046","title":"Weather prediction based on LSTM model implemented AWS Machine Learning Platform","authors":["D. T. Hoang"],"date":"2020-05-06","year":2020,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2020.5046","openalex":"W4241626125"},"links":{"paper":"https://doi.org/10.22214/ijraset.2020.5046","pdf":"https://doi.org/10.22214/ijraset.2020.5046"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM trained on NOAA station parameters (temperature, humidity, pressure, wind) on AWS predicts good or bad weather conditions; a small-scale applied study.","significance":1,"cited_by":17,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.06613","title":"A framework for probabilistic weather forecast post-processing across models and lead times using machine learning","authors":["Charlie Kirkwood","Theo Economou","Henry Odbert","Nicolas Pugeault"],"date":"2020-05-06","year":2020,"venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","venue_type":"journal","ids":{"arxiv":"2005.06613","doi":"10.1098/rsta.2020.0099","openalex":"W3024663870"},"links":{"paper":"https://doi.org/10.1098/rsta.2020.0099","pdf":"https://arxiv.org/pdf/2005.06613"},"orgs":["met-office"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Quantile regression forests post-process and combine multiple NWP models across lead times into calibrated probabilistic road surface temperature forecasts.","significance":3,"cited_by":43,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.03126","title":"Evaluation, Tuning and Interpretation of Neural Networks for Meteorological Applications","authors":["Imme Ebert-Uphoff","Kyle A. Hilburn"],"date":"2020-05-06","year":2020,"venue_type":"preprint","ids":{"arxiv":"2005.03126","openalex":"W3023870883"},"links":{"paper":"https://arxiv.org/abs/2005.03126","pdf":"https://arxiv.org/pdf/2005.03126"},"orgs":["colorado-state-university"],"topic":"xai-uq-physics","topics":[],"type":"review","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Practical guidance on evaluating, tuning and interpreting meteorological neural networks, covering effective receptive fields, relevant performance measures, and layer-wise relevance propagation for image classification and translation.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2005.02265","title":"Predicting atmospheric optical properties for radiative transfer computations using neural networks","authors":["Menno A. Veerman","Robert Pincus","Robin Stoffer","Caspar van Leeuwen","Damian Podareanu","Chiel C. van Heerwaarden"],"date":"2020-05-05","year":2020,"venue":"Phil. Trans. R. Soc. A. 379: 20200095 (2021)","venue_type":"journal","ids":{"arxiv":"2005.02265","doi":"10.1098/rsta.2020.0095","openalex":"W3022467776"},"links":{"paper":"https://arxiv.org/abs/2005.02265","pdf":"https://arxiv.org/pdf/2005.02265"},"orgs":["noaa"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Neural networks emulate the RRTMGP gas optics scheme, running up to 4x faster while keeping radiative flux errors within 0.5 W/m2.","significance":4,"cited_by":63,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3029296926","title":"Using Deep Learning to Improve Prediction and Understanding of High-impact Weather","authors":["Ryan Lagerquist"],"date":"2020-05-01","year":2020,"venue":"SHAREOK (University of Oklahoma; Oklahoma State University; Central Oklahoma University)","venue_type":"preprint","ids":{"openalex":"W3029296926"},"links":{"paper":"https://hdl.handle.net/11244/324145"},"orgs":[],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","era5"],"status":"research","summary":"CNNs predict next-hour tornado occurrence (AUC 0.94) and detect fronts in reanalysis, with interpretation methods explaining tornadogenesis failure.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-19-0344.1","title":"Forecasting Severe Weather with Random Forests","authors":["Aaron J. Hill","Gregory R. Herman","Russ S. Schumacher"],"date":"2020-05-01","year":2020,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-19-0344.1","openalex":"W3014703899"},"links":{"paper":"https://doi.org/10.1175/mwr-d-19-0344.1"},"orgs":["colorado-state-university"],"topic":"extremes-hazards","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Random forests trained on GEFS reforecasts give calibrated Day 1-3 severe weather outlooks that beat SPC at Days 2-3, and blending with SPC improves Day 1 outlooks.","significance":3,"cited_by":105,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.35940-ijeat.d9130.049420","title":"Weather Prediction using Machine Learning and IOT","authors":[],"date":"2020-04-30","year":2020,"venue":"International Journal of Engineering and Advanced Technology","venue_type":"journal","ids":{"doi":"10.35940/ijeat.d9130.049420","openalex":"W4248524965"},"links":{"paper":"https://doi.org/10.35940/ijeat.d9130.049420","pdf":"https://doi.org/10.35940/ijeat.d9130.049420"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Arduino-based sensor system with machine learning to predict rainfall from local temperature and humidity records; limited methodological novelty.","significance":1,"cited_by":4,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-asce-he.1943-5584.0001926","title":"Optimization and Variants of Quantile-Based Methods for Bias Corrections of Statistically Downscaled Precipitation Data","authors":["Aneesh Goly","Ramesh S. V. Teegavarapu"],"date":"2020-04-30","year":2020,"venue":"Journal of Hydrologic Engineering","venue_type":"journal","ids":{"doi":"10.1061/(asce)he.1943-5584.0001926","openalex":"W3023738816"},"links":{"paper":"https://doi.org/10.1061/(asce)he.1943-5584.0001926"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Neural-network-augmented quantile mapping bias corrects GCM-downscaled precipitation at 18 Florida gauges, reproducing extreme precipitation indices better than existing quantile methods.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.34917-2396381","title":"Association of oceanic-atmospheric oscillations and hydroclimatic variables in the Colorado River Basin","authors":["Ajay Kalra"],"date":"2020-04-29","year":2020,"venue":"Digital Scholarship - UNLV (University of Nevada Reno)","venue_type":"preprint","ids":{"doi":"10.34917/2396381","openalex":"W26912054"},"links":{"paper":"https://doi.org/10.34917/2396381"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Support vector machines use Pacific and Atlantic oscillation indices to extend precipitation and streamflow forecast lead times in the Colorado River Basin, with KNN for finer precipitation resolution.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-13-2109-2020","title":"Configuration and intercomparison of deep learning neural models for statistical downscaling","authors":["Jorge Baño-Medina","Rodrigo Manzanas","José Manuel Gutiérrez"],"date":"2020-04-28","year":2020,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-13-2109-2020","openalex":"W2981977644"},"links":{"paper":"https://doi.org/10.5194/gmd-13-2109-2020"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Systematic VALUE-based comparison of CNN downscaling against linear benchmarks over Europe finds CNNs help mainly for precipitation and temperature extremes, including under warm-period extrapolation.","significance":4,"cited_by":283,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.34218-ijeet.11.4.2020.049","title":"FEATURE SELECTION TECHNIQUES FOR WEATHER FORECASTING MODELS USING MACHINE LEARNING TECHNIQUES","authors":["T. Malathi","M. A. P. Manimekalai"],"date":"2020-04-28","year":2020,"venue":"INTERNATIONAL JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY","venue_type":"journal","ids":{"doi":"10.34218/ijeet.11.4.2020.049","openalex":"W3203838871"},"links":{"paper":"https://doi.org/10.34218/ijeet.11.4.2020.049"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Feature selection study for machine-learning weather forecasting; abstract unavailable, so contribution is unclear and likely incremental.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12091398","title":"Estimation of All-Weather 1 km MODIS Land Surface Temperature for Humid Summer Days","authors":["Cheolhee Yoo","Jungho Im","Dongjin Cho","Naoto Yokoya","Junshi Xia","Benjamin Bechtel"],"date":"2020-04-28","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12091398","openalex":"W3022888954"},"links":{"paper":"https://doi.org/10.3390/rs12091398","pdf":"https://www.mdpi.com/2072-4292/12/9/1398/pdf?version=1588682621"},"orgs":[],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random forest fuses AMSR2 microwave data with MODIS annual-cycle terms to produce all-weather 1 km land surface temperature over South Korea, including cloudy days, with daytime RMSE of 2.5 °C.","significance":2,"cited_by":57,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22564-rbgf.v38i2.2042","title":"Artificial Neural Network for Data Assimilation by WRF Model in Rio de Janeiro, Brazil","authors":["Vinícius Albuquerque de Almeida","Gutemberg Borges França","Haroldo Fraga de Campos Velho","Nelson F. F. Ebecken"],"date":"2020-04-28","year":2020,"venue":"Brazilian Journal of Geophysics","venue_type":"journal","ids":{"doi":"10.22564/rbgf.v38i2.2042","openalex":"W3096113005"},"links":{"paper":"https://doi.org/10.22564/rbgf.v38i2.2042"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural network emulates WRF 3D-Var data assimilation over Rio de Janeiro using airport station data, matching analyses to about 0.3 K and running 71 times faster.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-020-03211-6","title":"Post-processing of the North American multi-model ensemble for monthly forecast of precipitation based on neural network models","authors":["Morteza Pakdaman","Yashar Falamarzi","Iman Babaeian","Zohreh Javanshiri"],"date":"2020-04-27","year":2020,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-020-03211-6","openalex":"W3019859214"},"links":{"paper":"https://doi.org/10.1007/s00704-020-03211-6"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Neural networks post-process the North American multi-model ensemble to improve monthly precipitation forecasts; abstract unavailable.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6616","title":"Climate change projections and extremes for Costa Rica using tailored predictors from CORDEX model output through statistical downscaling with artificial neural networks","authors":["Dánnell Quesada‐Chacón","Klemens Barfus","Christian Bernhofer"],"date":"2020-04-27","year":2020,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6616","openalex":"W3018022318"},"links":{"paper":"https://doi.org/10.1002/joc.6616","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.6616"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","era5","stations"],"status":"research","summary":"Perfect-prognosis artificial neural networks statistically downscale precipitation and temperature for Costa Rica using tailored CORDEX predictors and station data, with projected extremes to 2100.","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019ms001876","title":"Machine Learning‐Based Prediction of Spatiotemporal Uncertainties in Global Wind Velocity Reanalyses","authors":["Christopher Irrgang","Jan Saynisch‐Wagner","Maik Thomas"],"date":"2020-04-26","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2019ms001876","openalex":"W3020184660"},"links":{"paper":"https://doi.org/10.1029/2019ms001876","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2019MS001876"},"orgs":[],"topic":"xai-uq-physics","topics":["data-assimilation"],"type":"model","method":["rnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Recurrent network predicts global spatiotemporal uncertainty of 10 m ocean wind reanalyses, trained at a few locations and generalizing globally, for ensemble generation and assimilation.","significance":3,"cited_by":14,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019ms001909","title":"Optimization of Deep Learning Precipitation Models Using Categorical Binary Metrics","authors":["Pablo Larraondo","Luigi J. Renzullo","Albert I. J. M. van Dijk","Iñaki Inza","Jose Antonio Lozano"],"date":"2020-04-24","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2019ms001909","openalex":"W3019495891"},"links":{"paper":"https://doi.org/10.1029/2019ms001909"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Differentiable versions of probability of detection and false alarm rate let neural precipitation forecasts be trained directly on categorical skill scores.","significance":3,"cited_by":44,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl087005","title":"Deep Learning Emulation of Subgrid‐Scale Processes in Turbulent Shear Flows","authors":["Anikesh Pal"],"date":"2020-04-23","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl087005","openalex":"W3017476219"},"links":{"paper":"https://doi.org/10.1029/2020gl087005","pdf":"https://www.osti.gov/servlets/purl/1965279"},"orgs":["ornl"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["km-scale-sim"],"status":"research","summary":"Deep neural networks emulate subgrid viscosity and diffusivity for turbulent stratified shear flows, giving a 2-2.5x simulation speedup while preserving kinetic and density variance budgets.","significance":3,"cited_by":24,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00500-020-04954-0","title":"Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station","authors":["Pradeep Hewage","Ardhendu Behera","Marcello Trovati","Ella Pereira","Morteza Ghahremani","Francesco Palmieri","Yonghuai Liu"],"date":"2020-04-23","year":2020,"venue":"Soft Computing","venue_type":"journal","ids":{"doi":"10.1007/s00500-020-04954-0","openalex":"W3019433526"},"links":{"paper":"https://doi.org/10.1007/s00500-020-04954-0","pdf":"https://link.springer.com/content/pdf/10.1007/s00500-020-04954-0.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Temporal convolutional network applied to local weather station time series outperforms LSTM and classical ML for short-range forecasts of farm-scale weather.","significance":2,"cited_by":739,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-19-0209.1","title":"A Causal Inference Model Based on Random Forests to Identify the Effect of Soil Moisture on Precipitation","authors":["Lu Li","Wei Shangguan","Yi Deng","Jiafu Mao","jinjing Pan","Nan Wei","Hua Yuan","Shupeng Zhang","Yonggen Zhang","Yongjiu Dai"],"date":"2020-04-22","year":2020,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-19-0209.1","openalex":"W3019284798"},"links":{"paper":"https://doi.org/10.1175/jhm-d-19-0209.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/hydr/21/5/jhm-d-19-0209.1.pdf"},"orgs":["ornl"],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Random-forest-based Granger causal framework isolates soil moisture to precipitation feedback over the US and uses it to benchmark Earth system models for land-atmosphere coupling.","significance":4,"cited_by":41,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.10130","title":"Natural Disaster Classification using Aerial Photography Explainable for Typhoon Damaged Feature","authors":["Takato Yasuno","Masazumi Amakata","Masahiro Okano"],"date":"2020-04-21","year":2020,"venue":"ICPR2020 Workshops and Challenges (forthcoming on 10 January 2021)","venue_type":"journal","ids":{"arxiv":"2004.10130","openalex":"W3017716761"},"links":{"paper":"https://arxiv.org/abs/2004.10130","pdf":"https://arxiv.org/pdf/2004.10130"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Grad-CAM CNN classifies typhoon-damaged areas in Chiba aerial photos, producing explainable damage maps to support faster disaster response.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s20082343","title":"Modeling and Forecasting the GPS Zenith Troposphere Delay in West Antarctica Based on Different Blind Source Separation Methods and Deep Learning","authors":["Qingchuan Zhang","Fei Li","Shengkai Zhang","Wenhao Li"],"date":"2020-04-20","year":2020,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s20082343","openalex":"W3017112758"},"links":{"paper":"https://doi.org/10.3390/s20082343","pdf":"https://www.mdpi.com/1424-8220/20/8/2343/pdf?version=1587390553"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"PCA/ICA with BP network and LSTM model GPS zenith tropospheric delay in West Antarctica; six-hour forecasts reach 7.2 mm RMS.","significance":2,"cited_by":35,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019jf005237","title":"Using Ice Cores and Gaussian Process Emulation to Recover Changes in the Greenland Ice Sheet During the Last Interglacial","authors":["Dario Domingo","Irene Malmierca‐Vallet","Louise C. Sime","Jochen Voß","Émilie Capron"],"date":"2020-04-20","year":2020,"venue":"Journal of Geophysical Research Earth Surface","venue_type":"journal","ids":{"doi":"10.1029/2019jf005237","openalex":"W3020193799"},"links":{"paper":"https://doi.org/10.1029/2019jf005237","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2019JF005237"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Gaussian process emulator of an isotope-enabled climate model constrains Last Interglacial Greenland ice sheet geometry against ice core isotope data, reducing uncertainty.","significance":2,"cited_by":15,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-13-1953-2020","title":"SegCloud: a novel cloud image segmentation model using a deep convolutional neural network for ground-based all-sky-view camera observation","authors":["Wanyi Xie","Dong Liu","Ming–Hsuan Yang","Shaoqing Chen","Benge Wang","Zhenzhu Wang","Yingwei Xia","Yong Liu","Yi-Ren Wang","Chaofan Zhang"],"date":"2020-04-17","year":2020,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-13-1953-2020","openalex":"W2990032788"},"links":{"paper":"https://doi.org/10.5194/amt-13-1953-2020","pdf":"https://amt.copernicus.org/articles/13/1953/2020/amt-13-1953-2020.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"SegCloud, an encoder-decoder CNN, segments ground-based all-sky camera images into cloud masks and estimates cloud cover better than traditional methods.","significance":3,"cited_by":112,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-19-0146.1","title":"A Deep Learning Network for Cloud-to-Ground Lightning Nowcasting with Multisource Data","authors":["Kanghui Zhou","Yongguang Zheng","Wansheng Dong","Tingbo Wang"],"date":"2020-04-17","year":2020,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-19-0146.1","openalex":"W3016496098"},"links":{"paper":"https://doi.org/10.1175/jtech-d-19-0146.1"},"orgs":["cma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar","stations"],"status":"research","summary":"LightningNet, a 3D convolutional encoder-decoder fusing Himawari-8, radar and lightning data, gives 0-1 h cloud-to-ground lightning nowcasts over China with threat score 0.453.","significance":4,"cited_by":94,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.07906","title":"Development and Interpretation of a Neural Network-Based Synthetic Radar Reflectivity Estimator Using GOES-R Satellite Observations","authors":["Kyle A. Hilburn","Imme Ebert-Uphoff","Steven D. Miller"],"date":"2020-04-16","year":2020,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"arxiv":"2004.07906","doi":"10.1175/jamc-d-20-0084.1","openalex":"W3016545165"},"links":{"paper":"https://arxiv.org/abs/2004.07906","pdf":"https://arxiv.org/pdf/2004.07906"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"A CNN converts GOES-R radiances and lightning into synthetic radar reflectivity, enabling convective radar assimilation with much better skill than pixel-wise methods.","significance":4,"cited_by":53,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-tc-14-1209-2020","title":"Unprecedented atmospheric conditions (1948–2019) drive the 2019 exceptional melting season over the Greenland ice sheet","authors":["Marco Tedesco","Xavier Fettweis"],"date":"2020-04-15","year":2020,"venue":"˜The œcryosphere","venue_type":"journal","ids":{"doi":"10.5194/tc-14-1209-2020","openalex":"W2991298899"},"links":{"paper":"https://doi.org/10.5194/tc-14-1209-2020","pdf":"https://tc.copernicus.org/articles/14/1209/2020/tc-14-1209-2020.pdf"},"orgs":["nasa","columbia-leap"],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"Artificial neural networks classify 500 hPa circulation patterns, showing the 2019 Greenland melt season was about five standard deviations anomalous in atmospheric persistence.","significance":3,"cited_by":217,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.10652","title":"A Fortran-Keras Deep Learning Bridge for Scientific Computing","authors":["Jordan Ott","Mike Pritchard","Natalie Best","Erik Linstead","Milan Curcic","Pierre Baldi"],"date":"2020-04-14","year":2020,"venue":"Scientific Programming","venue_type":"journal","ids":{"arxiv":"2004.10652","doi":"10.1155/2020/8888811","openalex":"W3018068085"},"links":{"paper":"https://doi.org/10.1155/2020/8888811","pdf":"https://arxiv.org/pdf/2004.10652"},"orgs":[],"topic":"infra-software","topics":["hybrid-parameterization"],"type":"model","method":[],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Fortran-Keras Bridge transfers Keras networks into Fortran; a climate case study tests over 100 DNN emulators of subgrid cloud and radiation physics inside a global model.","significance":4,"cited_by":134,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.06582","title":"Statistical Postprocessing for Weather Forecasts -- Review, Challenges and Avenues in a Big Data World","authors":["Stéphane Vannitsem","John Bjørnar Bremnes","Jonathan Demaeyer","Gavin R. Evans","Jonathan Flowerdew","Stephan Hemri","Sebastian Lerch","Nigel Roberts","Susanne Theis","Aitor Atencia","Zied Ben Bouallègue","Jonas Bhend","Markus Dabernig","Lesley De Cruz","Leila Hieta","Olivier Mestre","Lionel Moret","Iris Odak Plenković","Maurice Schmeits","Maxime Taillardat","Joris Van den Bergh","Bert Van Schaeybroeck","Kirien Whan","Jussi Ylhaisi"],"date":"2020-04-14","year":2020,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"arxiv":"2004.06582","doi":"10.1175/bams-d-19-0308.1","openalex":"W3016791436"},"links":{"paper":"https://arxiv.org/abs/2004.06582","pdf":"https://arxiv.org/pdf/2004.06582"},"orgs":["dwd","ecmwf","kit","knmi","met-norway","met-office","meteo-france","meteoswiss"],"topic":"post-processing","topics":[],"type":"review","method":[],"timescale":[],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Review of statistical postprocessing methods for NWP forecasts and their challenges in big-data settings, with little explicit machine learning focus.","significance":6,"cited_by":214,"score":69,"highlight":true,"highlight_reason":"Broad multi-centre review of statistical postprocessing with challenges and outlook; a useful reference for the field.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.2166-wcc.2020.217","title":"Rainfall regionalization and variability of extreme precipitation using artificial neural networks: a case study from western central Morocco","authors":["Abdelhafid El Alaoui El Fels","Mohamed El Mehdi Saidi","Assma Bouiji","Mounia Benrhanem"],"date":"2020-04-13","year":2020,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2020.217","openalex":"W3016964980"},"links":{"paper":"https://doi.org/10.2166/wcc.2020.217"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Uses principal component analysis and artificial neural networks on 47 years of station data to regionalize rainfall and map extreme precipitation in western Morocco.","significance":2,"cited_by":34,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.05793","title":"STAS: Adaptive Selecting Spatio-Temporal Deep Features for Improving Bias Correction on Precipitation","authors":["Yiqun Liu","Shouzhen Chen","Lei Chen","Hai Chu","Xiaoyang Xu","Junping Zhang","Leiming Ma"],"date":"2020-04-13","year":2020,"venue_type":"preprint","ids":{"arxiv":"2004.05793","openalex":"W3015762015"},"links":{"paper":"https://arxiv.org/abs/2004.05793","pdf":"https://arxiv.org/pdf/2004.05793"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"STAS, an end-to-end deep model with adaptive spatio-temporal feature selection, corrects ECMWF precipitation forecast bias and beats eight published BCoP methods on threat scores.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15276-hait.01.2020.2","title":"SEGMENTATION OF CLOUD ORGANIZATION PATTERNS FROM SATELLITE IMAGES USING DEEP NEURAL NETWORKS","authors":["Borys I. Tymchenko","Philip O. Marchenko","Dmitry V. Spodarets"],"date":"2020-04-10","year":2020,"venue":"Herald of Advanced Information Technology","venue_type":"journal","ids":{"doi":"10.15276/hait.01.2020.2","openalex":"W4387944594"},"links":{"paper":"https://doi.org/10.15276/hait.01.2020.2","pdf":"https://hait.od.ua/index.php/journal/article/download/41/117/46"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Multi-task CNN classifies and segments cloud organization types in single colour satellite images, learning from coarse noisy masks and ranking in the top 3% of a competition.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.04353","title":"Deep learning the atmospheric boundary layer height","authors":["David R. Vivas","Estiven Sánchez","John H. Reina"],"date":"2020-04-09","year":2020,"venue_type":"preprint","ids":{"arxiv":"2004.04353"},"links":{"paper":"https://arxiv.org/abs/2004.04353","pdf":"https://arxiv.org/pdf/2004.04353"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A CNN retrieves atmospheric boundary layer height automatically from LiDAR signals on real, non-ideal data, enabling real-time sensing of aerosols.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10502701.1","title":"Automatic Detection and Classification of Orographic Precipitation using Machine Learning","authors":["Ana Paula Barros","Malarvizhi Arulraj"],"date":"2020-04-08","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10502701.1","openalex":"W3024177547"},"links":{"paper":"https://doi.org/10.1002/essoar.10502701.1"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","radar","nwp-analysis"],"status":"research","summary":"Random forest and CNN framework corrects GPM DPR orographic precipitation retrievals using HRRR, cutting false alarms by 77% over the Southern Appalachians.","significance":4,"cited_by":0,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020eo142422","title":"Machine Learning Improves Weather and Climate Models","authors":["Kate Wheeling"],"date":"2020-04-07","year":2020,"venue":"Eos","venue_type":"journal","ids":{"doi":"10.1029/2020eo142422","openalex":"W3015648822"},"links":{"paper":"https://doi.org/10.1029/2020eo142422"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"review","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Eos commentary on a study finding GANs can produce stochastic parameterizations that improve how weather and climate models represent unresolved subgrid processes.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6579","title":"Stochastic event set generation for tropical cyclone using machine‐learning approach guided by environmental data","authors":["Vishal Bongirwar"],"date":"2020-04-05","year":2020,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6579","openalex":"W3015092912"},"links":{"paper":"https://doi.org/10.1002/joc.6579"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A k-nearest-neighbour model conditioned on reanalysis environment generates stochastic tropical cyclone event sets for the South West Pacific for cyclone risk assessment.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en13071671","title":"Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting","authors":["Tyler C. McCandless","Pedro A. Jiménez"],"date":"2020-04-03","year":2020,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en13071671","openalex":"W3014417905"},"links":{"paper":"https://doi.org/10.3390/en13071671","pdf":"https://www.mdpi.com/1996-1073/13/7/1671/pdf?version=1585879496"},"orgs":["ncar"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Random forest cloud mask from GOES-16 radiances matches the operational GOES-R clear-sky product and aids solar irradiance forecasting.","significance":3,"cited_by":27,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10502649.1","title":"The Prediction Method of Tropical Cyclone Intensity Change Based on Deep Learning","authors":["Wenke Wang","Xin Wang"],"date":"2020-04-03","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10502649.1","openalex":"W3017623228"},"links":{"paper":"https://doi.org/10.1002/essoar.10502649.1"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"A 3D convolutional network using environmental fields and sea surface temperature predicts 24-hour tropical cyclone intensity change, with better strengthening/weakening classification accuracy.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.01457","title":"Resampling with neural networks for stochastic parameterization in multiscale systems","authors":["Daan Crommelin","Wouter Edeling"],"date":"2020-04-03","year":2020,"venue_type":"preprint","ids":{"arxiv":"2004.01457","doi":"10.1016/j.physd.2021.132894"},"links":{"paper":"https://arxiv.org/abs/2004.01457","pdf":"https://arxiv.org/pdf/2004.01457"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Uses neural-network probabilistic classification of reference data to build a stochastic parameterization for unresolved scales, validated on Lorenz 96 under two challenging settings.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14383-cri.2020.15.1.35","title":"A Deep Neural Network Approach to Prediction of Rice Yields in China","authors":["부경대학교 지구환경시스템과학부 공간정보시스템공학전공 석사과정","Subin Cho","Nari Kim","Soo‐Jin Lee","Kyung‐Ja Ha","Yangwon Lee"],"date":"2020-03-31","year":2020,"venue":"Journal of Climate Research","venue_type":"journal","ids":{"doi":"10.14383/cri.2020.15.1.35","openalex":"W3021226352"},"links":{"paper":"https://doi.org/10.14383/cri.2020.15.1.35"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"A deep neural network predicts Chinese rice yields from climate model data, improving correlation about 38.7% over multiple linear regression.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2004.11123","title":"Imputation of missing sub-hourly precipitation data in a large sensor network: a machine learning approach","authors":["Benedict Delahaye Chivers","John Wallbank","Steven J. Cole","Ondrej Sebek","Simon Stanley","Matthew Fry","Georgios Leontidis"],"date":"2020-03-30","year":2020,"venue":"Journal of Hydrology 2020","venue_type":"journal","ids":{"arxiv":"2004.11123","doi":"10.1016/j.jhydrol.2020.125126"},"links":{"paper":"https://arxiv.org/abs/2004.11123","pdf":"https://arxiv.org/pdf/2004.11123"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Two-step classifier and regressor impute missing 30-minute rainfall at 37 UK weather stations, outperforming a neighbour-based surface fitting baseline.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6570","title":"Estimating near‐surface air temperature across Israel using a machine learning based hybrid approach","authors":["Bin Zhou","Evyatar Erell","Ian Hough","Jonathan D. Rosenblatt","Allan C. Just","Victor Novack","Itai Kloog"],"date":"2020-03-29","year":2020,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6570","openalex":"W3013449388"},"links":{"paper":"https://doi.org/10.1002/joc.6570","pdf":"https://rmets.onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.6570"},"orgs":["pik"],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","stations"],"status":"research","summary":"Two-stage random forest hybrid estimates gridded 1 km intra-daily near-surface air temperature over Israel from satellite skin temperature, with out-of-sample R2 of 0.96 for air temperature.","significance":3,"cited_by":49,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-info11040183","title":"An Innovative Acoustic Rain Gauge Based on Convolutional Neural Networks","authors":["Roberta Avanzato","Francesco Beritelli"],"date":"2020-03-28","year":2020,"venue":"Information","venue_type":"journal","ids":{"doi":"10.3390/info11040183","openalex":"W3013612618"},"links":{"paper":"https://doi.org/10.3390/info11040183","pdf":"https://www.mdpi.com/2078-2489/11/4/183/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN applied to audio from a low-cost acoustic sensor classifies rain intensity into seven classes, reaching 75% accuracy and 93% when adjacent-class errors are ignored.","significance":2,"cited_by":43,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-asce-he.1943-5584.0001924","title":"Gridded Extreme Precipitation Intensity–Duration–Frequency Estimates for the Canadian Landmass","authors":["Abhishek Gaur","André Schardong","Slobodan P. Simonović"],"date":"2020-03-27","year":2020,"venue":"Journal of Hydrologic Engineering","venue_type":"journal","ids":{"doi":"10.1061/(asce)he.1943-5584.0001924","openalex":"W3014039916"},"links":{"paper":"https://doi.org/10.1061/(asce)he.1943-5584.0001924"},"orgs":[],"topic":"extremes-hazards","topics":["downscaling"],"type":"benchmark","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"Produces a gridded Canadian extreme precipitation IDF dataset by linking reanalysis predictors to extremes with a support vector machine, with 5–25% RMSE against observations.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.12140","title":"MetNet: A Neural Weather Model for Precipitation Forecasting","authors":["Casper Kaae Sønderby","Lasse Espeholt","Jonathan Heek","Mostafa Dehghani","Avital Oliver","Tim Salimans","Shreya Agrawal","Jason Hickey","Nal Kalchbrenner"],"date":"2020-03-24","year":2020,"venue_type":"preprint","ids":{"arxiv":"2003.12140","openalex":"W3013229294"},"links":{"paper":"https://arxiv.org/abs/2003.12140","pdf":"https://arxiv.org/pdf/2003.12140"},"orgs":["google-research"],"topic":"nowcasting","topics":[],"type":"model","method":["transformer"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"MetNet uses axial self-attention on radar and satellite inputs to forecast precipitation up to 8 hours at 1 km, beating NWP for 7-8 hour lead times over the US.","significance":7,"cited_by":295,"score":73,"highlight":true,"highlight_reason":"MetNet is a high-resolution neural nowcasting model beating NWP out to 7-8 hours; influential for ML precipitation forecasting.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-rs12061030","title":"PreciPatch: A Dictionary-based Precipitation Downscaling Method","authors":["Mengchao Xu","Qian Liu","Dexuan Sha","Manzhu Yu","Daniel Q. Duffy","William Putman","Mark Carroll","Tsengdar J. Lee","Chaowei Phil Yang"],"date":"2020-03-23","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12061030","openalex":"W3012808645"},"links":{"paper":"https://doi.org/10.3390/rs12061030","pdf":"https://www.mdpi.com/2072-4292/12/6/1030/pdf?version=1585218988"},"orgs":["nasa"],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"PreciPatch uses dictionary learning to downscale hourly GCM precipitation, outperforming bicubic, RainFARM and DeepSD on IMERG data.","significance":3,"cited_by":17,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.13779","title":"Semantic-based End-to-End Learning for Typhoon Intensity Prediction","authors":["Hamada M. Zahera","Mohamed Ahmed Sherif","Axel Ngonga"],"date":"2020-03-22","year":2020,"venue_type":"preprint","ids":{"arxiv":"2003.13779","openalex":"W3014258333"},"links":{"paper":"https://arxiv.org/abs/2003.13779","pdf":"https://arxiv.org/pdf/2003.13779"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Adds word-embedding features from disaster tweets to CNN and BiLSTM models to improve typhoon intensity prediction, gaining 12.1% and 3.1% F1 over those baselines.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.09957","title":"Software System for Road Condition Forecast Correction","authors":["Dmitrii Smolyakov","Evgeny Burnaev"],"date":"2020-03-22","year":2020,"venue_type":"preprint","ids":{"arxiv":"2003.09957"},"links":{"paper":"https://arxiv.org/abs/2003.09957","pdf":"https://arxiv.org/pdf/2003.09957"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Road weather station network with ML that flags faulty sensor data and corrects physical road-ice forecasts, aiming to improve winter road safety.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.21561927","title":"Weather Forecasting System","authors":["Ashley Mohanani","Rucha Kalode","Aishwarya Dhumane","Aman Zade","Shweta Hiwanj","C B Tripathi"],"date":"2020-03-21","year":2020,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.21561927","openalex":"W7171053613"},"links":{"paper":"https://doi.org/10.5281/zenodo.21561927"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares RNN, LSTM, GRU, linear regression and random forest for station relative-humidity prediction from date and time inputs, ranking which gives best accuracy under limited resources.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2020.124875","title":"Sequence-based statistical downscaling and its application to hydrologic simulations based on machine learning and big data","authors":["Qingrui Wang","Jing Hua Huang","Ruimin Liu","Cong Men","Lijia Guo","Yuexi Miao","Lijun Jiao","Yifan Wang","Muhammad Shoaib","Xinghui Xia"],"date":"2020-03-21","year":2020,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2020.124875","openalex":"W3012319822"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2020.124875"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Sequence-based machine-learning statistical downscaling of climate data for hydrologic simulation; abstract not available, so classification is based on the title only.","significance":2,"cited_by":65,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.11916","title":"Analysis of Greenhouse Gases","authors":["Shalin Shah"],"date":"2020-03-21","year":2020,"venue_type":"preprint","ids":{"arxiv":"2003.11916"},"links":{"paper":"https://arxiv.org/abs/2003.11916","pdf":"https://arxiv.org/pdf/2003.11916"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Applies linear, quadratic and Gaussian process regression to monthly greenhouse gas data to extrapolate temperature anomalies, with results said to resemble IPCC projections.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1127-metz-2020-1005","title":"Feature selection, ensemble learning, and artificial neural networks for short-range wind speed forecasts","authors":["Petrina Papazek","Irene Schicker","Claudia Plant","Alexander Kann","Yong Wang"],"date":"2020-03-17","year":2020,"venue":"Meteorologische Zeitschrift","venue_type":"journal","ids":{"doi":"10.1127/metz/2020/1005","openalex":"W3010877918"},"links":{"paper":"https://doi.org/10.1127/metz/2020/1005"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"ZiANN combines feature selection, ensemble learning and neural networks to post-process NWP output for six-hour nowcasts and 40-hour point wind forecasts in Austria, outperforming operational INCA and AROME.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10502527.1","title":"A Machine-Learning-Based Global Atmospheric Forecast Model","authors":["Istvan Szunyogh","Troy Arcomano","Jaideep Pathak","Alexander Wikner","Brian R. Hunt","Edward Ott"],"date":"2020-03-17","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1002/essoar.10502527.1","openalex":"W4236966469"},"links":{"paper":"https://doi.org/10.1029/2020gl087776"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Builds a low-resolution machine learning global forecast model that beats persistence for about five days and better matches humidity and temperature than a physics model.","significance":3,"cited_by":153,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en13061372","title":"A Comprehensive Wind Power Forecasting System Integrating Artificial Intelligence and Numerical Weather Prediction","authors":["Branko Kosović","Sue Ellen Haupt","Daniel R. Adriaansen","Stefano Alessandrini","Gerry M. Wiener","Luca Delle Monache","Yubao Liu","Seth Linden","Tara L. Jensen","William Y. Y. Cheng","Marcia K. Politovich","Paul Prestopnik"],"date":"2020-03-16","year":2020,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en13061372","openalex":"W3010710435"},"links":{"paper":"https://doi.org/10.3390/en13061372","pdf":"https://www.mdpi.com/1996-1073/13/6/1372/pdf?version=1584356674"},"orgs":["ncar"],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml","other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"operational","summary":"NCAR's updated wind power system combines NWP with ML power conversion, analog ensembles, radar ramp forecasts and fuzzy-logic icing alerts for Xcel Energy.","significance":3,"cited_by":94,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41467-020-15195-y","title":"Causal networks for climate model evaluation and constrained projections","authors":["Peer Nowack","Jakob Runge","Veronika Eyring","Joanna D. Haigh"],"date":"2020-03-16","year":2020,"venue":"Nature Communications","venue_type":"journal","ids":{"doi":"10.1038/s41467-020-15195-y","openalex":"W3012135229"},"links":{"paper":"https://doi.org/10.1038/s41467-020-15195-y"},"orgs":[],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip","era5"],"status":"research","summary":"Causal networks from sea level pressure fingerprints objectively evaluate climate models and better constrain precipitation projections than storm-track metrics.","significance":5,"cited_by":182,"score":50,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2003.11927","title":"Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere","authors":["Jonathan A. Weyn","Dale R. Durran","Rich Caruana"],"date":"2020-03-15","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2003.11927","doi":"10.1029/2020ms002109","openalex":"W3048374358"},"links":{"paper":"https://arxiv.org/abs/2003.11927","pdf":"https://arxiv.org/pdf/2003.11927"},"orgs":["microsoft-research","university-of-washington"],"topic":"global-medium-range","topics":[],"type":"model","method":["cnn"],"timescale":["medium","s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"CNN on a cubed-sphere grid with multi-step loss gives stable global forecasts for weeks, beating persistence, climatology and coarse NWP at short-to-medium range.","significance":6,"cited_by":366,"score":69,"highlight":true,"highlight_reason":"Cubed-sphere CNN gives stable, improved data-driven global forecasts, an important step toward later ML weather models.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2019ea000740","title":"Comparative Assessment of Various Machine Learning‐Based Bias Correction Methods for Numerical Weather Prediction Model Forecasts of Extreme Air Temperatures in Urban Areas","authors":["Dongjin Cho","Cheolhee Yoo","Jungho Im","Dong‐Hyun Cha"],"date":"2020-03-14","year":2020,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2019ea000740","openalex":"W3011863222"},"links":{"paper":"https://doi.org/10.1029/2019ea000740","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2019EA000740"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Random forest, SVR, ANN and a multi-model ensemble correct next-day LDAPS extreme temperature forecasts in Seoul, cutting maximum-temperature RMSE from 2.08 to about 1.6 °C.","significance":3,"cited_by":199,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.06549","title":"Interpreting and Stabilizing Machine-learning Parametrizations of Convection","authors":["Noah D. Brenowitz","Tom Beucler","Michael Pritchard","Christopher S. Bretherton"],"date":"2020-03-14","year":2020,"venue":"Journal of the Atmospheric Sciences","venue_type":"journal","ids":{"arxiv":"2003.06549","doi":"10.1175/jas-d-20-0082.1","openalex":"W3010657409"},"links":{"paper":"https://doi.org/10.1175/jas-d-20-0082.1","pdf":"https://arxiv.org/pdf/2003.06549"},"orgs":["ai2","columbia-leap","university-of-washington"],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Introduces tools to interpret neural convection parameterizations and diagnose gravity-wave instability when coupled to climate models, using SPCAM and cloud-resolving training data.","significance":5,"cited_by":166,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3188825417","title":"Seasonal precipitation forecast model in wet and dry seasons using global monthly surface temperature by deep learning","authors":["Shingo Zenkoji","Taichi TEBAKARI","Kazutoshi Sakakibara"],"date":"2020-03-13","year":2020,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W3188825417"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2020/subject/AHW37-P06/detail"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep learning model predicts seasonal wet and dry season precipitation from global monthly surface temperature fields (abstract not available).","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3186225136","title":"Deep learning for seasonal to sub-seasonal rainfall prediction in Chaophraya river basin","authors":["Kiyoharu Hasegawa","Shinjiro Kanae"],"date":"2020-03-13","year":2020,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W3186225136"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2020/subject/AHW37-P05/detail"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other"],"timescale":["s2s","seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies deep learning to seasonal and sub-seasonal rainfall prediction in the Chao Phraya river basin in Thailand; conference abstract not available.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3139363360","title":"Investigation on convolutional neural network models for the improvement of rainfall nowcasting from the Multi Parameter Phased Array Weather Radar observations","authors":["Dongkyun Kim","Taku Suezawa","Tomoo Ushio"],"date":"2020-03-13","year":2020,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W3139363360"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2020/subject/AAS14-P20/detail"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"Investigates convolutional neural networks for rainfall nowcasting from multi-parameter phased array weather radar observations (abstract not available).","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.05763","title":"Exploiting deep learning in forecasting the occurrence of severe haze in Southeast Asia","authors":["Chien Wang"],"date":"2020-03-12","year":2020,"venue_type":"preprint","ids":{"arxiv":"2003.05763"},"links":{"paper":"https://arxiv.org/abs/2003.05763","pdf":"https://arxiv.org/pdf/2003.05763"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["era5","stations"],"status":"research","summary":"A CNN trained on 35 years of meteorological maps and visibility data forecasts severe haze occurrence in Singapore, beating a no-skill baseline but missing many haze events.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1371-journal.pone.0230114","title":"Convcast: An embedded convolutional LSTM based architecture for precipitation nowcasting using satellite data","authors":["Ashutosh Kumar","Tanvir Islam","Yoshihide Sekimoto","Chris A. Mattmann","Brian D. Wilson"],"date":"2020-03-11","year":2020,"venue":"PLoS ONE","venue_type":"journal","ids":{"doi":"10.1371/journal.pone.0230114","openalex":"W3011438087"},"links":{"paper":"https://doi.org/10.1371/journal.pone.0230114","pdf":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0230114&type=printable"},"orgs":["nasa","caltech"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Convcast, a convolutional LSTM trained on NASA IMERG satellite precipitation, nowcasts up to 150 minutes with 0.805 mm/h RMSE at 30 minutes, outperforming optical flow.","significance":3,"cited_by":114,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.46855-energy-proceedings-4506","title":"Variabilty of Long Term Estimates of Hydro Power Generation on a European Scale","authors":["Valentina Sessa","Edi Assoumou","S. C. P. Carvalho"],"date":"2020-03-10","year":2020,"venue_type":"other","ids":{"doi":"10.46855/energy-proceedings-4506","openalex":"W3022938204"},"links":{"paper":"https://doi.org/10.46855/energy-proceedings-4506","pdf":"http://www.energy-proceedings.org/wp-content/uploads/2020/03/974_Paper_0830065652.pdf"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Machine learning links climate variables from regional and global climate models to European hydropower capacity factors under future scenarios.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12050896","title":"Estimation of Hourly Rainfall during Typhoons Using Radar Mosaic-Based Convolutional Neural Networks","authors":["Chih‐Chiang Wei","Po-Yu Hsieh"],"date":"2020-03-10","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12050896","openalex":"W3012459813"},"links":{"paper":"https://doi.org/10.3390/rs12050896","pdf":"https://www.mdpi.com/2072-4292/12/5/896/pdf?version=1583979900"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"Proposes a radar-mosaic CNN for estimating hourly typhoon rainfall in Taiwan, outperforming Z-R relationships at three stations; it reduces relative RMSE to 0.713 at Hualien.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1117-1.oe.59.8.081803","title":"Image shift due to atmospheric refraction: prediction by numerical weather modeling and machine learning","authors":["Wardeh S. Al-Younis","Christina Nevarez","Mohammad Abdullah-Al-Mamun","Steven Sandoval","Sukanta Basu","David Voelz"],"date":"2020-03-10","year":2020,"venue":"Optical Engineering","venue_type":"journal","ids":{"doi":"10.1117/1.oe.59.8.081803","openalex":"W3011587594"},"links":{"paper":"https://doi.org/10.1117/1.oe.59.8.081803","pdf":"https://www.spiedigitallibrary.org/journals/optical-engineering/volume-59/issue-8/081803/Image-shift-due-to-atmospheric-refraction--prediction-by-numerical/10.1117/1.OE.59.8.081803.pdf"},"orgs":[],"topic":"applications-impacts","topics":["observations-remote-sensing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares ray tracing on numerical weather data with a machine learning model for predicting atmospheric refraction-induced image displacement, consistent with field measurements in overall amplitude and phase.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.05024","title":"Prediction of Bayesian Intervals for Tropical Storms","authors":["Max Chiswick","Sam Ganzfried"],"date":"2020-03-10","year":2020,"venue_type":"preprint","ids":{"arxiv":"2003.05024","openalex":"W3038032687"},"links":{"paper":"https://arxiv.org/abs/2003.05024","pdf":"https://arxiv.org/pdf/2003.05024"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Uses an RNN with dropout to predict tropical storm trajectories with Bayesian intervals, giving evacuation-relevant uncertainty ranges from about 500 Atlantic storms.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-8680436","title":"Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin","authors":["Xu Ren","Nengcheng Chen","Yumin Chen","Zeqiang Chen"],"date":"2020-03-09","year":2020,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2020/8680436","openalex":"W3009276176"},"links":{"paper":"https://doi.org/10.1155/2020/8680436","pdf":"https://downloads.hindawi.com/journals/amete/2020/8680436.pdf"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Bayesian model averaging with SVR, MLP and random forest downscales eight CMIP5 models' precipitation in the Upper Han basin, with best PCC 0.82.","significance":3,"cited_by":69,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11030267","title":"Precipitation Nowcasting with Orographic Enhanced Stacked Generalization: Improving Deep Learning Predictions on Extreme Events","authors":["Gabriele Franch","Daniele Nerini","Marta Pendesini","Luca Coviello","Giuseppe Jurman","Cesare Furlanello"],"date":"2020-03-07","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11030267","openalex":"W3010027900"},"links":{"paper":"https://doi.org/10.3390/atmos11030267","pdf":"https://www.mdpi.com/2073-4433/11/3/267/pdf?version=1585046885"},"orgs":["meteoswiss"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Stacking TrajGRU ensemble members with orographic features via a CNN roughly doubles skill on extreme rain rates, matching Lagrangian persistence on TAASRAD19 radar data.","significance":4,"cited_by":97,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s42452-020-2327-x","title":"Machine-learning regression applied to diagnose horizontal visibility from mesoscale NWP model forecasts","authors":["Driss Bari","Abdelali Ouagabi"],"date":"2020-03-05","year":2020,"venue":"SN Applied Sciences","venue_type":"journal","ids":{"doi":"10.1007/s42452-020-2327-x","openalex":"W3009579196"},"links":{"paper":"https://doi.org/10.1007/s42452-020-2327-x","pdf":"https://link.springer.com/content/pdf/10.1007/s42452-020-2327-x.pdf"},"orgs":["meteo-france"],"topic":"post-processing","topics":["local-forecasting"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine-learning regression diagnoses horizontal visibility from mesoscale NWP forecasts; abstract not available, so the scope is inferred from the title.","significance":2,"cited_by":34,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-iet-rpg.2019.1208","title":"PV power intra‐day predictions using PDE models of polynomial networks based on operational calculus","authors":["Ladislav Zjavka"],"date":"2020-03-04","year":2020,"venue":"IET Renewable Power Generation","venue_type":"journal","ids":{"doi":"10.1049/iet-rpg.2019.1208","openalex":"W3010115709"},"links":{"paper":"https://doi.org/10.1049/iet-rpg.2019.1208","pdf":"https://ietresearch.onlinelibrary.wiley.com/doi/pdfdirect/10.1049/iet-rpg.2019.1208"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Differential polynomial neural network predicts intra-day PV power by estimating clear-sky index from 1–9 hour input shifts, applying atmospheric PDE dynamics to solar energy forecasting.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w12030687","title":"Estimating Current and Future Rainfall Erosivity in Greece Using Regional Climate Models and Spatial Quantile Regression Forests","authors":["Konstantinos Vantas","Epaminondas G. Sidiropoulos","Athanasios G. Loukas"],"date":"2020-03-03","year":2020,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w12030687","openalex":"W3009678401"},"links":{"paper":"https://doi.org/10.3390/w12030687","pdf":"https://www.mdpi.com/2073-4441/12/3/687/pdf?version=1584877650"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Spatial quantile regression forests map rainfall erosivity in Greece using RCM projections to 2100, with regional climate models validated against gauges.","significance":2,"cited_by":27,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-19-0163.1","title":"Quantifying the Benefits of Nonlinear Methods for Global Statistical Hindcasts of Tropical Cyclones Intensity","authors":["S. Neetu","Matthieu Lengaigne","Jérôme Vialard","Morgan Mangeas","Christophe Eugène Menkès","Iyyappan Suresh","Julie A. Leloup","John A. Knaff"],"date":"2020-03-03","year":2020,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-19-0163.1","openalex":"W3010604541"},"links":{"paper":"https://doi.org/10.1175/waf-d-19-0163.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/35/3/waf-d-19-0163.1.pdf"},"orgs":["noaa"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml","other"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Builds the first global nonlinear SVM and neural-network tropical cyclone intensity hindcast schemes; globally trained SVM improves skill by about 10% over regional linear schemes.","significance":4,"cited_by":6,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2003.00646","title":"A review of machine learning applications in wildfire science and management","authors":["Piyush Jain","Sean C P Coogan","Sriram Ganapathi Subramanian","Mark Crowley","Steve Taylor","Mike D Flannigan"],"date":"2020-03-02","year":2020,"venue":"Environmental Reviews. 28(4): 478-505, 2020","venue_type":"journal","ids":{"arxiv":"2003.00646","doi":"10.1139/er-2020-0019"},"links":{"paper":"https://arxiv.org/abs/2003.00646","pdf":"https://arxiv.org/pdf/2003.00646"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Scoping review of 298 studies applying machine learning across wildfire science, including fire weather and climate change, and identifying gaps for deep learning.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3103-s1068373920030012","title":"Statistical Correction of the COSMO Model Weather Forecasts Based on Neural Networks","authors":["Быков Филипп Леонидович"],"date":"2020-03-01","year":2020,"venue":"Russian Meteorology and Hydrology","venue_type":"journal","ids":{"doi":"10.3103/s1068373920030012","openalex":"W3026397925"},"links":{"paper":"https://doi.org/10.3103/s1068373920030012"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural-network correction of COSMO-Ru13 surface forecasts up to 117 hours, tested on 23 million 2018 forecasts, reduces errors even at unobserved points.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-met.1905","title":"A deep‐learning model to predict thunderstorms within 400 km2 South Texas domains","authors":["Hamid Kamangir","Waylon G. Collins","Philippe E. Tissot","Scott A. King"],"date":"2020-03-01","year":2020,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.1905","openalex":"W3017220412"},"links":{"paper":"https://doi.org/10.1002/met.1905","pdf":"https://rmets.onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.1905"},"orgs":["noaa"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["other","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Stacked denoising autoencoder with logistic regression predicts thunderstorm occurrence up to 15 hours ahead over 400 km2 South Texas, beating shallow networks and forecasters.","significance":3,"cited_by":37,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36825-riti.08.15.004","title":"Revisión de literatura de modelos computacionales para la predicción de la velocidad del viento de 2004 a 2016","authors":["Carolina Tripp-Barba"],"date":"2020-02-29","year":2020,"venue":"Revista de Investigación en Tecnologías de la Información","venue_type":"journal","ids":{"doi":"10.36825/riti.08.15.004","openalex":"W3007159084"},"links":{"paper":"https://doi.org/10.36825/riti.08.15.004"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml","other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Reviews 2004–2016 literature on wind speed forecasting models, classifying regression, neural network, time series, fuzzy logic and Gaussian process approaches; ANN and fuzzy logic are flagged as future directions.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-6484812","title":"Convolutional Residual-Attention: A Deep Learning Approach for Precipitation Nowcasting","authors":["Qing You Yan","Fuxin Ji","Kaichao Miao","Qi Wu","Yi Xia","Teng Li"],"date":"2020-02-29","year":2020,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2020/6484812","openalex":"W3007355926"},"links":{"paper":"https://doi.org/10.1155/2020/6484812","pdf":"https://downloads.hindawi.com/journals/amete/2020/6484812.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","transformer"],"timescale":["nowcast"],"spatial":["local","regional"],"data":["radar"],"status":"research","summary":"Dual-channel CNN with multihead attention and residual connections improves radar-based local precipitation nowcasting, reaching state-of-the-art accuracy on a radar echo dataset.","significance":3,"cited_by":52,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7217151054","title":"Statistical Approach to Estimate the Weather Prediction","authors":["Arindam Roy","Dharmpal Singh","Sudipta Sahana","Ira Nath"],"date":"2020-02-28","year":2020,"venue":"International Journal of Computer Sciences and Engineering","venue_type":"journal","ids":{"openalex":"W7217151054"},"links":{"paper":"https://ijcseonline.org/index.php/j/article/view/5989","pdf":"https://ijcseonline.org/index.php/j/article/download/5989/5975"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Compares curve-fitting and soft computing models to predict India's annual average temperature; ML is only loosely central and the study is weak.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app10051609","title":"Forecasting Daily Temperatures with Different Time Interval Data Using Deep Neural Networks","authors":["Sungjae Lee","Yung-Seop Lee","Youngdoo Son"],"date":"2020-02-28","year":2020,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app10051609","openalex":"W3009823625"},"links":{"paper":"https://doi.org/10.3390/app10051609","pdf":"https://www.mdpi.com/2076-3417/10/5/1609/pdf?version=1583391520"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["cnn","rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares MLP, RNN and CNN on hourly inputs for daily temperature forecasts at three sites; hourly data beats daily inputs and CNN performs best.","significance":2,"cited_by":52,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.12592","title":"Wind Speed Prediction using Deep Ensemble Learning with a Jet-like Architecture","authors":["Aqsa Saeed Qureshi","Asifullah Khan","Muhammad Waleed Khan"],"date":"2020-02-28","year":2020,"venue_type":"preprint","ids":{"arxiv":"2002.12592"},"links":{"paper":"https://arxiv.org/abs/2002.12592","pdf":"https://arxiv.org/pdf/2002.12592"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["cnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"DEL-Jet ensemble of CNNs, autoencoder and nonlinear PCA forecasts wind speed for renewable energy, offering a more robust ensemble than single models.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-asce-he.1943-5584.0001900","title":"New Approach to Multisite Downscaling of Precipitation by Identifying Different Set of Atmospheric Predictor Variables","authors":["Bidroha Basu","María Nogal","Alan O’Connor"],"date":"2020-02-27","year":2020,"venue":"Journal of Hydrologic Engineering","venue_type":"journal","ids":{"doi":"10.1061/(asce)he.1943-5584.0001900","openalex":"W3008901926"},"links":{"paper":"https://doi.org/10.1061/(asce)he.1943-5584.0001900","pdf":"https://ascelibrary.org/doi/pdf/10.1061/%28ASCE%29HE.1943-5584.0001900"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Support vector regression multisite precipitation downscaling with climatological sub-regions, producing 2012–2050 rainfall projections for Ireland under four RCP scenarios.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-acp-20-2303-2020","title":"Technical note: Deep learning for creating surrogate models of precipitation in Earth system models","authors":["Theodore Weber","Austin Corotan","Brian Hutchinson","Ben Kravitz","Robert Link"],"date":"2020-02-26","year":2020,"venue":"Atmospheric chemistry and physics","venue_type":"journal","ids":{"doi":"10.5194/acp-20-2303-2020","openalex":"W2937082058"},"links":{"paper":"https://doi.org/10.5194/acp-20-2303-2020","pdf":"https://acp.copernicus.org/articles/20/2303/2020/acp-20-2303-2020.pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A CNN surrogate trained on CanESM2 monthly precipitation outperforms persistence and stays skillful over 120-month rollouts, with scheduled sampling and preforecasting documented.","significance":3,"cited_by":33,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2020gl087338","title":"Ground‐Based Cloud Classification Using Task‐Based Graph Convolutional Network","authors":["Shuang Liu","Mei Li","Zhong Zhang","Xiaozhong Cao","T.S. Durrani"],"date":"2020-02-26","year":2020,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2020gl087338","openalex":"W3006744923"},"links":{"paper":"https://doi.org/10.1029/2020gl087338"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["gnn","cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Proposes a task-based graph convolutional network for ground-based cloud classification and releases a large labeled sky-image database (GRSCD).","significance":3,"cited_by":45,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-19-0159.1","title":"Development of a Probabilistic Subfreezing Road Temperature Nowcast and Forecast Using Machine Learning","authors":["Shawn L. Handler","Heather Dawn Reeves","Amy McGovern"],"date":"2020-02-25","year":2020,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-19-0159.1","openalex":"W3007591951"},"links":{"paper":"https://doi.org/10.1175/waf-d-19-0159.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/35/5/wafD190159.pdf"},"orgs":["noaa","university-of-oklahoma"],"topic":"post-processing","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Random forest on HRRR surface fields produces gridded CONUS probabilistic subfreezing road temperature forecasts, with a 2-h Brier skill score of 0.66.","significance":3,"cited_by":26,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.uclim.2020.100606","title":"Hyper-local, efficient extreme heat projection and analysis using machine learning to augment a hybrid dynamical-statistical downscaling technique","authors":["Luke E. Madaus","Patrick L. McDermott","Joshua P. Hacker","Julie Pullen"],"date":"2020-02-25","year":2020,"venue":"Urban Climate","venue_type":"journal","ids":{"doi":"10.1016/j.uclim.2020.100606","openalex":"W3008739781"},"links":{"paper":"https://doi.org/10.1016/j.uclim.2020.100606"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Uses machine learning to augment a hybrid dynamical-statistical downscaling method for hyper-local extreme heat projections; based on title only, abstract missing.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.11167","title":"Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning","authors":["Ashesh Chattopadhyay","Adam Subel","Pedram Hassanzadeh"],"date":"2020-02-25","year":2020,"venue":"Journal of Advances in Modeling Earth Systems 2020","venue_type":"journal","ids":{"arxiv":"2002.11167","doi":"10.1029/2020ms002084","openalex":"W3008664735"},"links":{"paper":"https://arxiv.org/abs/2002.11167","pdf":"https://arxiv.org/pdf/2002.11167"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Data-driven super-parameterization with RNNs matches super-parameterization long-term statistics at much lower cost on Lorenz 96, with transfer learning improving generalization.","significance":4,"cited_by":71,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.10878","title":"Gaussian Process Regression for Probabilistic Short-term Solar Output Forecast","authors":["Fatemeh Najibi","Dimitra Apostolopoulou","Eduardo Alonso"],"date":"2020-02-23","year":2020,"venue_type":"preprint","ids":{"arxiv":"2002.10878","doi":"10.1016/j.ijepes.2021.106916"},"links":{"paper":"https://arxiv.org/abs/2002.10878","pdf":"https://arxiv.org/pdf/2002.10878"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Gaussian process regression with Matern kernel predicts short-term PV plant output from irradiance, temperature and solar angles, with a 95% error range of about -1.6% to 1.4%.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.09573","title":"Causal structure learning from time series: Large regression coefficients may predict causal links better in practice than small p-values","authors":["Sebastian Weichwald","Martin E Jakobsen","Phillip B Mogensen","Lasse Petersen","Nikolaj Thams","Gherardo Varando"],"date":"2020-02-21","year":2020,"venue":"Proceedings of the NeurIPS 2019 Competition and Demonstration Track, Proceedings of Machine Learning Research, 123:27-36, 2020 ( http://proceedings.mlr.press/v123/weichwald20a.html )","venue_type":"journal","ids":{"arxiv":"2002.09573"},"links":{"paper":"https://arxiv.org/abs/2002.09573","pdf":"https://arxiv.org/pdf/2002.09573","code":"https://github.com/sweichwald/tidybench"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Winning NeurIPS Causality 4 Climate algorithms combine linear methods for causal structure learning from Earth science time series, with open benchmark implementations.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10502348.1","title":"Distilling an Analog Ensemble into a Deep Neural Network","authors":["Salvatore Candido","Aakanksha Singh","Luca Delle Monache"],"date":"2020-02-20","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10502348.1","openalex":"W3006922662"},"links":{"paper":"https://doi.org/10.1002/essoar.10502348.1"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Distills the analog ensemble post-processing into a small neural network, enabling fast on-the-fly ECMWF lower-stratosphere wind corrections with a model of only hundreds of kilobytes.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.08525","title":"Towards Physically-consistent, Data-driven Models of Convection","authors":["Tom Beucler","Michael Pritchard","Pierre Gentine","Stephan Rasp"],"date":"2020-02-20","year":2020,"venue_type":"preprint","ids":{"arxiv":"2002.08525"},"links":{"paper":"https://arxiv.org/abs/2002.08525","pdf":"https://arxiv.org/pdf/2002.08525"},"orgs":[],"topic":"hybrid-parameterization","topics":["xai-uq-physics"],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Enforces physical constraints in neural convection emulators via loss or architecture, and rescales data so models generalize to unseen climates.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2020.2972153","title":"Lightning Distance Estimation Using LF Lightning Radio Signals via Analytical and Machine-Learned Models","authors":["Andre Lucas Antunes de Sa","Robert Andrew Marshall"],"date":"2020-02-19","year":2020,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2020.2972153","openalex":"W3008419670"},"links":{"paper":"https://doi.org/10.1109/tgrs.2020.2972153"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Trains machine-learned models to estimate lightning distance from single-receiver VLF/LF sferics, reaching 53 km RMSE on observed Kansas data.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3233-ida-184446","title":"Label distribution learning with climate probability for ensemble forecasting","authors":["Xuebing Yang","Yajing Wu","Wensheng Zhang","Wei Tang"],"date":"2020-02-18","year":2020,"venue":"Intelligent Data Analysis","venue_type":"journal","ids":{"doi":"10.3233/ida-184446","openalex":"W3008632533"},"links":{"paper":"https://doi.org/10.3233/ida-184446"},"orgs":["cma"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Introduces Label Distribution Learning with Climate Probability to post-process ensemble precipitation forecasts in East China, improving RMSE and CRPS over baselines.","significance":3,"cited_by":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.07875","title":"Lake Ice Monitoring with Webcams and Crowd-Sourced Images","authors":["Rajanie Prabha","Manu Tom","Mathias Rothermel","Emmanuel Baltsavias","Laura Leal-Taixe","Konrad Schindler"],"date":"2020-02-18","year":2020,"venue_type":"preprint","ids":{"arxiv":"2002.07875"},"links":{"paper":"https://arxiv.org/abs/2002.07875","pdf":"https://arxiv.org/pdf/2002.07875"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"DeepLab-based models segment lake ice in webcam images with about 70% IoU across unseen cameras and winters, and introduce a new benchmark dataset.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-esd-11-139-2020","title":"Emulating Earth system model temperatures with MESMER: from global mean temperature trajectories to grid-point-level realizations on land","authors":["Lea Beusch","Lukas Gudmundsson","Sonia I. Seneviratne"],"date":"2020-02-17","year":2020,"venue":"Earth System Dynamics","venue_type":"journal","ids":{"doi":"10.5194/esd-11-139-2020","openalex":"W2953669636"},"links":{"paper":"https://doi.org/10.5194/esd-11-139-2020"},"orgs":["eth-zurich"],"topic":"climate-emulation","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"MESMER statistically emulates grid-point land temperature from CMIP5 models, producing a 40-model superensemble at negligible computational cost.","significance":5,"cited_by":136,"score":40,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-jtech-d-19-0179.1","title":"Development of a Method to Detect High Ice Water Content Environments Using Machine Learning","authors":["Julie A. Haggerty","Allyson Rugg","Rodney J. Potts","Alain Protat","John Walter Strapp","Thomas Ratvasky","Kristopher M. Bedka","Alice Grandin"],"date":"2020-02-17","year":2020,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-19-0179.1","openalex":"W3006390524"},"links":{"paper":"https://doi.org/10.1175/jtech-d-19-0179.1"},"orgs":["nasa","ncar","bom-australia"],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","radar","nwp-analysis"],"status":"pre-operational","summary":"Fuzzy-logic ALPHA algorithm fuses satellite, NWP and radar data to detect high ice water content for aviation, with AUC 0.85 against in situ measurements.","significance":3,"cited_by":9,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-020-05173-x","title":"A data-driven multi-model ensemble for deterministic and probabilistic precipitation forecasting at seasonal scale","authors":["Lei Xu","Nengcheng Chen","Xiang Zhang","Zeqiang Chen"],"date":"2020-02-17","year":2020,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-020-05173-x","openalex":"W3008648992"},"links":{"paper":"https://doi.org/10.1007/s00382-020-05173-x"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Data-driven multi-model ensemble combining seasonal forecasts for deterministic and probabilistic precipitation prediction; abstract missing, so classification is based on the title only.","significance":2,"cited_by":53,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.07040","title":"Lake Ice Detection from Sentinel-1 SAR with Deep Learning","authors":["Manu Tom","Roberto Aguilar","Pascal Imhof","Silvan Leinss","Emmanuel Baltsavias","Konrad Schindler"],"date":"2020-02-17","year":2020,"venue_type":"preprint","ids":{"arxiv":"2002.07040"},"links":{"paper":"https://arxiv.org/abs/2002.07040","pdf":"https://arxiv.org/pdf/2002.07040"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A deep CNN segments lake ice from Sentinel-1 SAR imagery across three Swiss lakes, reaching mIoU above 90%, independent of cloud cover.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.05398","title":"Ensemble methods for neural network-based weather forecasts","authors":["Sebastian Scher","Gabriele Messori"],"date":"2020-02-13","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2002.05398","doi":"10.1029/2020ms002331","openalex":"W3108795590"},"links":{"paper":"https://arxiv.org/abs/2002.05398","pdf":"https://arxiv.org/pdf/2002.05398"},"orgs":[],"topic":"probabilistic-ensembles","topics":[],"type":"evaluation","method":["other"],"timescale":["short","medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Compares four ensemble generation methods for a neural weather model; retraining gives the largest gain, but ensembles remain less skillful than operational NWP.","significance":4,"cited_by":87,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2002.07579","title":"Modeling Cloud Reflectance Fields using Conditional Generative Adversarial Networks","authors":["Victor Schmidt","Mustafa Alghali","Kris Sankaran","Tianle Yuan","Yoshua Bengio"],"date":"2020-02-10","year":2020,"venue_type":"preprint","ids":{"arxiv":"2002.07579"},"links":{"paper":"https://arxiv.org/abs/2002.07579","pdf":"https://arxiv.org/pdf/2002.07579","code":"https://github.com/krisrs1128/clouds_dist"},"orgs":[],"topic":"hybrid-parameterization","topics":["observations-remote-sensing"],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Conditional GAN generates realistic cloud reflectance fields from sea surface temperature and humidity, a step toward stochastic cloud parameterization.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019ms001798","title":"A Machine Learning Assisted Development of a Model for the Populations of Convective and Stratiform Clouds","authors":["Samson Hagos","Zhe Feng","Robert Stephen Plant","Alain Protat"],"date":"2020-02-08","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2019ms001798","openalex":"W3004479127"},"links":{"paper":"https://doi.org/10.1029/2019ms001798","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2019MS001798"},"orgs":["university-of-reading","bom-australia"],"topic":"hybrid-parameterization","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["radar","km-scale-sim"],"status":"research","summary":"Uses machine learning on Darwin C-band radar data to derive transition functions for a stochastic convective-stratiform cloud model aimed at global climate model parameterization.","significance":4,"cited_by":8,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2002.00469","title":"WeatherBench: A benchmark dataset for data-driven weather forecasting","authors":["Stephan Rasp","Peter D. Dueben","Sebastian Scher","Jonathan A. Weyn","Soukayna Mouatadid","Nils Thuerey"],"date":"2020-02-02","year":2020,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"2002.00469","doi":"10.1029/2020ms002203","openalex":"W3003709258"},"links":{"paper":"https://arxiv.org/abs/2002.00469","pdf":"https://arxiv.org/pdf/2002.00469","code":"https://github.com/pangeo-data/WeatherBench"},"orgs":["ecmwf","tum","university-of-washington"],"topic":"benchmarks-data-eval","topics":["global-medium-range"],"type":"benchmark","method":["classical-ml","cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"WeatherBench introduces an ERA5-derived benchmark with standard metrics and baselines (linear regression, deep learning, physical models) for data-driven medium-range global weather forecasting.","significance":8,"cited_by":658,"score":97,"highlight":true,"highlight_reason":"WeatherBench became the standard benchmark for data-driven global weather forecasting, enabling comparison that led to later models; essential reference.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-2002.00416","title":"Using Machine Learning for Model Physics: an Overview","authors":["Vladimir Krasnopolsky","Aleksei A. Belochitski"],"date":"2020-02-02","year":2020,"venue_type":"preprint","ids":{"arxiv":"2002.00416"},"links":{"paper":"https://arxiv.org/abs/2002.00416","pdf":"https://arxiv.org/pdf/2002.00416"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Overview of machine learning for model physics, covering emulating existing parameterizations, developing new ones, and enforcing physical constraints in atmospheric models.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en13030616","title":"Artificial Learning Dispatch Planning with Probabilistic Forecasts: Using Uncertainties as an Asset","authors":["Ana Carolina do amaral Burghi","Tobias Hirsch","Robert Pitz‐Paal"],"date":"2020-02-01","year":2020,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en13030616","openalex":"W3004183351"},"links":{"paper":"https://doi.org/10.3390/en13030616","pdf":"https://www.mdpi.com/1996-1073/13/3/616/pdf?version=1580554081"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Extends concentrated solar dispatch planning with probabilistic weather forecasts and an ML calibration step, reporting up to 15% higher revenue than a persistence approach.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3091627406","title":"MEDIUM TERM WIND SPEED FORECASTING USING COMBINATION OF LINEAR AND NONLINEAR MODELS","authors":["Sana Mohsin Babbar","Chee-Yong Lau"],"date":"2020-01-31","year":2020,"venue":"Solid State Technology","venue_type":"journal","ids":{"openalex":"W3091627406"},"links":{"paper":"http://solidstatetechnology.us/index.php/JSST/article/view/777"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Multistage ensemble of linear regression, ANN and SVM refines NWP wind speed for wind-farm forecasts, reaching 0.13% MAPE at 72 hours.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-020-03098-3","title":"Performance of statistical and machine learning ensembles for daily temperature downscaling","authors":["Xinyi Li","Zhong Li","Wendy Huang","Pengxiao Zhou"],"date":"2020-01-29","year":2020,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-020-03098-3","openalex":"W3003728117"},"links":{"paper":"https://doi.org/10.1007/s00704-020-03098-3"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares statistical and machine learning ensembles for daily temperature downscaling; abstract unavailable, so judgment rests on the title.","significance":2,"cited_by":88,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2020-5124274","title":"A Convection Nowcasting Method Based on Machine Learning","authors":["Aifang Su","Han Li","Liman Cui","Yungang Chen"],"date":"2020-01-27","year":2020,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2020/5124274","openalex":"W3001898521"},"links":{"paper":"https://doi.org/10.1155/2020/5124274","pdf":"https://downloads.hindawi.com/journals/amete/2020/5124274.pdf"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"ConvLSTM with optical-flow features nowcasts convective radar echoes, better capturing rotation, merging and separation than traditional methods.","significance":3,"cited_by":22,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019ea000812","title":"A Deep Learning‐Based Methodology for Precipitation Nowcasting With Radar","authors":["Lei Chen","Yuan Cao","Leiming Ma","Junping Zhang"],"date":"2020-01-26","year":2020,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2019ea000812","openalex":"W3001630685"},"links":{"paper":"https://doi.org/10.1029/2019ea000812"},"orgs":["fudan-university"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"ConvLSTM with star-shape bridge and rain-oriented loss improves radar precipitation nowcasting over convolutional LSTM baselines and extrapolation.","significance":3,"cited_by":170,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10501976.1","title":"A Quantum Mechanical Approach for Data Assimilation in Climate Dynamics","authors":["Dimitrios Giannakis","Joanna Sławińska","A. Ourmazd"],"date":"2020-01-21","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10501976.1","openalex":"W3082589275"},"links":{"paper":"https://doi.org/10.1002/essoar.10501976.1"},"orgs":["nyu-m2lines"],"topic":"data-assimilation","topics":["s2s-seasonal"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Quantum-mechanics-inspired, kernel-based data assimilation using Koopman operators, applied to Indo-Pacific SST and Niño 3.4 probabilistic forecasts. Novel but early-stage.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12020316","title":"Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS","authors":["Vesta Afzali Gorooh","Subodh Kalia","Phu Nguyen","Kuolin Hsu","Soroosh Sorooshian","Sangram Ganguly","Ramakrishna Nemani"],"date":"2020-01-18","year":2020,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12020316","openalex":"W3001346916"},"links":{"paper":"https://doi.org/10.3390/rs12020316","pdf":"https://www.mdpi.com/2072-4292/12/2/316/pdf?version=1579600843"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"DeepCTC neural network classifies cloud types from GOES-16 ABI imagery using CloudSat labels and evaluates PERSIANN-CCS precipitation by cloud type against MRMS.","significance":3,"cited_by":37,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.09055","title":"Forecasting Corn Yield with Machine Learning Ensembles","authors":["Mohsen Shahhosseini","Guiping Hu","Sotirios V. Archontoulis"],"date":"2020-01-18","year":2020,"venue":"Frontiers in Plant Science 11 (2020) 1120","venue_type":"journal","ids":{"arxiv":"2001.09055","doi":"10.3389/fpls.2020.01120"},"links":{"paper":"https://arxiv.org/abs/2001.09055","pdf":"https://arxiv.org/pdf/2001.09055"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Ensemble ML models forecast county-level corn yields in three US states from in-season weather, achieving RRMSE 7.8% with forecasts possible by 1 June.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.06270","title":"Bayesian inference of chaotic dynamics by merging data assimilation, machine learning and expectation-maximization","authors":["Marc Bocquet","Julien Brajard","Alberto Carrassi","Laurent Bertino"],"date":"2020-01-17","year":2020,"venue":"Foundations of Data Science, 2, 55-80, 2020","venue_type":"journal","ids":{"arxiv":"2001.06270","doi":"10.3934/fods.2020004"},"links":{"paper":"https://arxiv.org/abs/2001.06270","pdf":"https://arxiv.org/pdf/2001.06270"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Unifies data assimilation, machine learning and expectation-maximization to jointly estimate model, state trajectory and error statistics for noisy observations of low-order chaotic geophysical models.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3023956265","title":"Predicting Hurricane Genesis and Evolution with Deep Learning","authors":["Tianle Yuan"],"date":"2020-01-16","year":2020,"venue":"100th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3023956265"},"links":{"paper":"https://ams.confex.com/ams/2020Annual/webprogram/Paper369074.html"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep learning approach to predicting hurricane genesis and evolution; only the conference listing is available, so details are unverified.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3005813347","title":"Deep Learning to Improve Numerical Weather Prediction Cloud Forecasts","authors":["Billy D. Felton"],"date":"2020-01-16","year":2020,"venue":"100th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3005813347"},"links":{"paper":"https://ams.confex.com/ams/2020Annual/webprogram/Paper366613.html"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Deep learning applied to correct NWP model cloud forecasts; abstract unavailable, so classification rests on the title alone.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5120-ijca2020919818","title":"Developing a Neuro-Fuzzy Model for Weather Prediction","authors":["Hatem Mohamed","Amr Ibrahim"],"date":"2020-01-16","year":2020,"venue":"International Journal of Computer Applications","venue_type":"journal","ids":{"doi":"10.5120/ijca2020919818","openalex":"W3000209043"},"links":{"paper":"https://doi.org/10.5120/ijca2020919818","pdf":"https://doi.org/10.5120/ijca2020919818"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neuro-fuzzy model forecasts monthly temperature, humidity, wind and rainfall for a region of Egypt using station records; modest gains, regional scope.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos11010111","title":"The Development of a Quantitative Precipitation Forecast Correction Technique Based on Machine Learning for Hydrological Applications","authors":["Chul-Min Ko","Yeong Yun Jeong","Youngmi Lee","Byung‐Sik Kim"],"date":"2020-01-16","year":2020,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos11010111","openalex":"W2999965837"},"links":{"paper":"https://doi.org/10.3390/atmos11010111","pdf":"https://www.mdpi.com/2073-4433/11/1/111/pdf?version=1579780091"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"XGBoost corrects KMA quantitative precipitation forecasts for heavy rain in Seoul, cutting MAE by up to about 30% at some sites.","significance":3,"cited_by":35,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10501903.1","title":"Analog Ensemble Probabilistic Forecasting using Deep Generative Models","authors":["Alessandro Fanfarillo"],"date":"2020-01-16","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10501903.1","openalex":"W3198046156"},"links":{"paper":"https://doi.org/10.1002/essoar.10501903.1"},"orgs":["ncar"],"topic":"probabilistic-ensembles","topics":["post-processing"],"type":"model","method":["gan-vae"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A conditional VAE replaces the historical archive in analog ensemble wind speed correction for NAM, matching AnEn skill with up to 25x less memory.","significance":3,"cited_by":1,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.05948","title":"Machine learning for total cloud cover prediction","authors":["Ágnes Baran","Sebastian Lerch","Mehrez El Ayari","Sándor Baran"],"date":"2020-01-16","year":2020,"venue":"Neural Computing and Applications 33 (2021), 2605-2620","venue_type":"journal","ids":{"arxiv":"2001.05948","doi":"10.1007/s00521-020-05139-4","openalex":"W3000358280"},"links":{"paper":"https://arxiv.org/abs/2001.05948","pdf":"https://arxiv.org/pdf/2001.05948"},"orgs":["kit"],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Compares MLP, gradient boosting and random forest calibration of ECMWF total cloud cover ensembles as oktas classification; MLP and GBM give the best skill gains.","significance":3,"cited_by":34,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3135233508","title":"Tropical Cyclone Storm Surge Prediction Using Artificial Neural Network","authors":["Mahmoud Ayyad"],"date":"2020-01-15","year":2020,"venue":"100th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3135233508"},"links":{"paper":"https://ams.confex.com/ams/2020Annual/webprogram/Paper370837.html"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Artificial neural network approach to predicting tropical cyclone storm surge; only the title is available, so details are unverified.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3006442815","title":"Taking Advantage of Machine Learning Methods to Better Represent Fire Radiative Power (FRP) for Smoke and Weather Forecasting Models","authors":["Christina Bonfanti","Stevan Maksimović","Jebb Q. Stewart","Ravan Ahmadov","Mark Govett"],"date":"2020-01-15","year":2020,"venue":"100th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3006442815"},"links":{"paper":"https://ams.confex.com/ams/2020Annual/webprogram/Paper368056.html"},"orgs":["noaa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":[],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Applies machine learning to satellite fire radiative power to improve fire representation in smoke and weather forecasting models; abstract not available.","significance":2,"cited_by":0,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-019-57183-3","title":"Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms","authors":["Manali Pal","Rajib Maity","J. V. Ratnam","Masami Nonaka","Swadhin Kumar Behera"],"date":"2020-01-15","year":2020,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-019-57183-3","openalex":"W2999039443"},"links":{"paper":"https://doi.org/10.1038/s41598-019-57183-3","pdf":"https://www.nature.com/articles/s41598-019-57183-3.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"Support vector regression and random forest forecast the ENSO Modoki index 6 and 12 months ahead, with SVR performing better than RF.","significance":3,"cited_by":43,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10501799.1","title":"An Assessment of Machine Learning Techniques for Replicating Physical Forcing Mechanisms in Climate Models","authors":["Garrett C Limon","Christiane Jablonowski"],"date":"2020-01-15","year":2020,"venue_type":"other","ids":{"doi":"10.1002/essoar.10501799.1","openalex":"W3049610443"},"links":{"paper":"https://doi.org/10.1002/essoar.10501799.1"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"evaluation","method":["classical-ml","cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Random forests, linear regression and CNN-based networks emulate CAM6 physical forcings offline; tuning is needed to capture detailed patterns, with online coupling left for future work.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-019-57162-8","title":"A machine learning based prediction system for the Indian Ocean Dipole","authors":["J. V. Ratnam","Henk A. Dijkstra","Swadhin Kumar Behera"],"date":"2020-01-14","year":2020,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-019-57162-8","openalex":"W2998978152"},"links":{"paper":"https://doi.org/10.1038/s41598-019-57162-8","pdf":"https://www.nature.com/articles/s41598-019-57162-8.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["era5","nwp-analysis"],"status":"research","summary":"Artificial neural network ensemble predicts the Indian Ocean Dipole from February-April predictors for May-November, outperforming NMME models in correlation and RMSE.","significance":3,"cited_by":43,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.04650","title":"Deep learning-based air temperature mapping by fusing remote sensing, station, simulation and socioeconomic data","authors":["Huanfeng Shen","Yun Jiang","Tongwen Li","Qing Cheng","Chao Zeng","Liangpei Zhang"],"date":"2020-01-14","year":2020,"venue_type":"preprint","ids":{"arxiv":"2001.04650"},"links":{"paper":"https://arxiv.org/abs/2001.04650","pdf":"https://arxiv.org/pdf/2001.04650"},"orgs":[],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations","other"],"status":"research","summary":"A deep belief network fuses satellite, station, simulation and socioeconomic data to map daily maximum air temperature across China at 0.01°, achieving RMSE 1.996°C.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3034892652","title":"Convective Storm Nowcasting Using a Deep Learning Approach","authors":["Lei Han"],"date":"2020-01-13","year":2020,"venue":"100th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3034892652"},"links":{"paper":"https://ams.confex.com/ams/2020Annual/webprogram/Paper367634.html"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Conference abstract applying deep learning to convective storm nowcasting; no abstract available, so the specific method and gain are unclear.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3005719708","title":"A Pure Deep Learning Approach to Precipitation Nowcasting","authors":["Jason J. Hickey"],"date":"2020-01-13","year":2020,"venue":"100th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3005719708"},"links":{"paper":"https://ams.confex.com/ams/2020Annual/webprogram/Paper369961.html"},"orgs":["google-research"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Pure deep learning approach to precipitation nowcasting from radar; abstract unavailable, so classification rests on the title alone.","significance":3,"cited_by":0,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.03151","title":"Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions","authors":["Janni Yuval","Paul A. O'Gorman"],"date":"2020-01-09","year":2020,"venue":"Nature communications. 2020 Jul 3;11(1):1-0","venue_type":"journal","ids":{"arxiv":"2001.03151","doi":"10.1038/s41467-020-17142-3","openalex":"W3040129451"},"links":{"paper":"https://arxiv.org/abs/2001.03151","pdf":"https://arxiv.org/pdf/2001.03151"},"orgs":["mit"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A random forest subgrid parameterization learned from 3D high-resolution output yields stable coarse-resolution climate simulations that reproduce precipitation extremes.","significance":7,"cited_by":283,"score":48,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1016-j.neunet.2019.12.030","title":"Transductive LSTM for time-series prediction: An application to weather forecasting","authors":["Zahra Karevan","Johan A. K. Suykens"],"date":"2020-01-08","year":2020,"venue":"Neural Networks","venue_type":"journal","ids":{"doi":"10.1016/j.neunet.2019.12.030","openalex":"W3000500483"},"links":{"paper":"https://doi.org/10.1016/j.neunet.2019.12.030"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Proposes a transductive LSTM for time-series prediction, applied to weather forecasting from observed meteorological series.","significance":2,"cited_by":569,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.02614","title":"An empirical, Bayesian approach to modelling the impact of weather on crop yield: maize in the US","authors":["Raphael Shirley","Edward Pope","Myles Bartlett","Seb Oliver","Novi Quadrianto","Peter Hurley","Steven Duivenvoorden","Phil Rooney","Adam B. Barrett","Chris Kent","James Bacon"],"date":"2020-01-08","year":2020,"venue_type":"preprint","ids":{"arxiv":"2001.02614"},"links":{"paper":"https://arxiv.org/abs/2001.02614","pdf":"https://arxiv.org/pdf/2001.02614"},"orgs":[],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other","stations"],"status":"research","summary":"Bayesian generative models relate US maize yield to monthly temperature and precipitation, projecting a 2°C warming to reduce yield by 8% and triple its variance.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-2050-7038.12325","title":"Day‐ahead probabilistic wind power forecasting based on ranking and combining NWPs","authors":["Antonio Bracale","Pierluigi Caramia MS","Guido Carpinelli MS","Pasquale De Falco"],"date":"2020-01-06","year":2020,"venue":"International Transactions on Electrical Energy Systems","venue_type":"journal","ids":{"doi":"10.1002/2050-7038.12325","openalex":"W2999034066"},"links":{"paper":"https://doi.org/10.1002/2050-7038.12325"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Ranking and combining spatially distributed NWPs with gradient boosting and quantile regression improves day-ahead probabilistic wind farm power forecasts by up to 1.8%.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.01520","title":"Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 model","authors":["Julien Brajard","Alberto Carassi","Marc Bocquet","Laurent Bertino"],"date":"2020-01-06","year":2020,"venue":"Journal of Computational Science, Volume 44, 2020","venue_type":"journal","ids":{"arxiv":"2001.01520","doi":"10.1016/j.jocs.2020.101171","openalex":"W2998192345"},"links":{"paper":"https://arxiv.org/abs/2001.01520","pdf":"https://arxiv.org/pdf/2001.01520","code":"https://github.com/brajard/GMD-code"},"orgs":["university-of-reading"],"topic":"data-assimilation","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Iterating an ensemble Kalman filter with a neural network emulates the chaotic Lorenz-96 model from sparse noisy observations, giving forecast skill up to two Lyapunov times.","significance":4,"cited_by":321,"score":46,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"openalex-W3021464272","title":"Weather prediction using Machine Learning","authors":["Harsh Agarwal","K. Sri Ram Charan","S. Harsha Vardhan","Jalesh Kumar","P. Someshwar Goud","V V S Vijaya Krishna"],"date":"2020-01-05","year":2020,"venue":"International journal of advance research, ideas and innovations in technology","venue_type":"journal","ids":{"doi":"10.2139/ssrn.3836085","openalex":"W3021464272"},"links":{"paper":"https://www.ijariit.com/manuscript/weather-prediction-using-machine-learning/"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Decision tree with stepwise regression predicts weather from temperature, pressure and humidity; a basic station-based application with little novelty.","significance":1,"cited_by":13,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-2001.03100","title":"Temporal Consistency Optimization for Alpine Lake Turbulent Flux Observations: A Machine Learning Approach","authors":["Zheng Jin"],"date":"2020-01-04","year":2020,"venue_type":"preprint","ids":{"arxiv":"2001.03100"},"links":{"paper":"https://arxiv.org/abs/2001.03100","pdf":"https://arxiv.org/pdf/2001.03100"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural networks trained on micrometeorological features improve eddy covariance flux estimates at an alpine lake on the Tibetan Plateau, with stable 10-fold cross-validation bias.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en13010216","title":"A Novel Ensemble Algorithm for Solar Power Forecasting Based on Kernel Density Estimation","authors":["Mohamed Lotfi","Mohammad Sadegh Javadi","Gerardo J. Osório","Cláudio Monteiro","João P. S. Catalào"],"date":"2020-01-02","year":2020,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en13010216","openalex":"W2996953123"},"links":{"paper":"https://doi.org/10.3390/en13010216","pdf":"https://www.mdpi.com/1996-1073/13/1/216/pdf?version=1577953549"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Kernel-density analogue ensemble forecasts PV output from weather forecasts in Portugal, beating a neural network in most cases and running 32 times faster.","significance":2,"cited_by":45,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41558-019-0666-7","title":"Climate change now detectable from any single day of weather at global scale","authors":["Sebastian Sippel","Nicolai Meinshausen","Erich M. Fischer","Enikő Székely","Reto Knutti"],"date":"2020-01-02","year":2020,"venue":"Nature Climate Change","venue_type":"journal","ids":{"doi":"10.1038/s41558-019-0666-7","openalex":"W2998677958"},"links":{"paper":"https://doi.org/10.1038/s41558-019-0666-7"},"orgs":["eth-zurich","sdsc"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Machine-learning-based detection indicates the climate change signal is identifiable from a single day of global weather; abstract unavailable, so classification is tentative.","significance":6,"cited_by":263,"score":64,"highlight":true,"highlight_reason":"ML detects the climate change signal in a single day of global weather; influential, widely cited detection and attribution result.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"openalex-W3082448257","title":"A Machine-Learning Assist to Predicting Hurricane Intensity","authors":["Naomi Hartono"],"date":"2020-01-01","year":2020,"venue_type":"other","ids":{"openalex":"W3082448257"},"links":{"paper":"https://www.nasa.gov/feature/jpl/a-machine-learning-assist-to-predicting-hurricane-intensity/"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":[],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"NASA report on a machine learning aid for predicting hurricane rapid intensification, giving communities more warning time; technical details are limited.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3080248858","title":"Weather Prediction: Improving Accuracy Using Data Mining And Forecasting Techniques","authors":["Pedro Alejandro Marquez"],"date":"2020-01-01","year":2020,"venue":"scholarworks - UTEP (The University of Texas at El Paso)","venue_type":"preprint","ids":{"openalex":"W3080248858"},"links":{"paper":"https://scholarworks.utep.edu/open_etd/3104","pdf":"https://scholarworks.utep.edu/open_etd/3104"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares data mining and machine learning methods for predicting next-year precipitation from weather records; largely a comparative study.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.7780-kjrs.2020.36.5.4.4","title":"A Study for Estimation of High Resolution Temperature Using Satellite Imagery and Machine Learning Models during Heat Waves","authors":["Dalgeun Lee","Mi Hee Lee","Boeun Kim","Jeonghum Yu","Yeongju Oh","Jinyi Park"],"date":"2020-01-01","year":2020,"venue":"National Remote Sensing Bulletin","venue_type":"journal","ids":{"doi":"10.7780/kjrs.2020.36.5.4.4","openalex":"W3109671457"},"links":{"paper":"https://doi.org/10.7780/kjrs.2020.36.5.4.4"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":[],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Machine learning on satellite imagery estimates high-resolution temperature during heat waves; abstract unavailable, so details are unverified.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.7780-kjrs.2020.36.5.3.4","title":"Multi-task Learning Based Tropical Cyclone Intensity Monitoring and Forecasting through Fusion of Geostationary Satellite Data and Numerical Forecasting Model Output","authors":["Juhyun Lee","Cheolhee Yoo","Jungho Im","Yeji Shin","Dongjin Cho"],"date":"2020-01-01","year":2020,"venue":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","venue_type":"preprint","ids":{"doi":"10.7780/kjrs.2020.36.5.3.4","openalex":"W3130207954"},"links":{"paper":"https://doi.org/10.7780/kjrs.2020.36.5.3.4"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["other"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Multi-task deep learning fuses COMS geostationary images with CFSv2 forecasts, cutting 6h and 12h tropical cyclone intensity forecast RMSE by 13% and 16%.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.29121-ijesrt.v9.i10.2020.14","title":"AN ARTIFICIAL NEURAL NETWORK BASED DEVELOPMENT OF CLOUD BURST FORECASTING MODEL BY USING TIME-SERIES DATA.","authors":[],"date":"2020-01-01","year":2020,"venue":"International Journal of Engineering Sciences & Research Technology","venue_type":"journal","ids":{"doi":"10.29121/ijesrt.v9.i10.2020.14","openalex":"W4247625093"},"links":{"paper":"https://doi.org/10.29121/ijesrt.v9.i10.2020.14"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"PSO-optimised neural network forecasts cloudburst rainfall in India from historical records; accuracy figures are not given in the abstract.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25675-3.04762","title":"Airborne radar quality control and analysis of the rapid intensification of Hurricane Michael (2018)","authors":["Alexander J. DesRosiers","Bell, Michael M.","Barnes, Elizabeth","Chen, Suren"],"date":"2020-01-01","year":2020,"venue":"Digital Collections of Colorado (Colorado State University)","venue_type":"preprint","ids":{"doi":"10.25675/3.04762","openalex":"W3119760797"},"links":{"paper":"https://doi.org/10.25675/3.04762"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["radar"],"status":"research","summary":"Random forest automates quality control of tail Doppler radar data from Hurricane Michael's rapid intensification, classifying over 99% of radar gates correctly.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25082-reie.2020.01.001","title":"Investigation of the effect of climate change on heat waves","authors":["Safieh Javadinejad","Rebwar Nasir Dara","Forough Jafary"],"date":"2020-01-01","year":2020,"venue":"Resources Environment and Information Engineering","venue_type":"journal","ids":{"doi":"10.25082/reie.2020.01.001","openalex":"W3096308490"},"links":{"paper":"https://doi.org/10.25082/reie.2020.01.001","pdf":"https://www.syncsci.com/journal/REIE/article/download/468/392"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Uses neural networks to identify heat waves in CMIP5 RCP8.5 projections for southern Iran, finding mostly decreasing frequency for 2040–2074; ML role is minor.","significance":1,"cited_by":15,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25046-aj050217","title":"Big Data Analytics using Deep LSTM Networks: A Case Study for Weather Prediction","authors":["Shweta Mittal","Om Prakash Sangwan"],"date":"2020-01-01","year":2020,"venue":"Advances in Science Technology and Engineering Systems Journal","venue_type":"journal","ids":{"doi":"10.25046/aj050217","openalex":"W3011105697"},"links":{"paper":"https://doi.org/10.25046/aj050217","pdf":"https://www.astesj.com/?smd_process_download=1&download_id=12903"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Deep LSTM networks trained on 15 years of hourly Brazilian station data for 1-hour and 24-hour weather prediction; two hidden layers balance accuracy and runtime.","significance":1,"cited_by":7,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2480-agrmet.d-20-00027","title":"Bias correction for spatially interpolated daily mean air temperature during winter in eastern Hokkaido using multimodal machine learning","authors":["Keach Murakami","Tomoyoshi Hirota","Seiji Shimoda","Tomotsugu Yazaki"],"date":"2020-01-01","year":2020,"venue":"Journal of Agricultural Meteorology","venue_type":"journal","ids":{"doi":"10.2480/agrmet.d-20-00027","openalex":"W3092367252"},"links":{"paper":"https://doi.org/10.2480/agrmet.d-20-00027","pdf":"https://www.jstage.jst.go.jp/article/agrmet/76/4/76_D-20-00027/_pdf"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Multimodal machine learning corrects 1 km gridded winter air temperature biases at 88 Hokkaido sites, reducing RMSE by about 0.1°C with a nested model.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.23689-fidgeo-4726","title":"WeatherBench: A Benchmark Data Set for Data-Driven Weather Forecasting","authors":["Stephan Rasp","Peter Dominik Dueben","Sebastian Scher","Jonathan A. Weyn","Soukayna Mouatadid","Nils Thuerey"],"date":"2020-01-01","year":2020,"venue":"arXiv (Cornell University)","venue_type":"preprint","ids":{"doi":"10.23689/fidgeo-4726","openalex":"W3197361419"},"links":{"paper":"https://doi.org/10.23689/fidgeo-4726","code":"https://github.com/pangeo-data/WeatherBench"},"orgs":["ecmwf","university-of-washington","tum"],"topic":"benchmarks-data-eval","topics":["global-medium-range"],"type":"benchmark","method":["classical-ml","cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"WeatherBench provides an ERA5-derived benchmark with metrics and baselines for data-driven global medium-range forecasting, enabling direct model comparison.","significance":8,"cited_by":0,"score":77,"highlight":true,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2208-jscejhe.76.2-i-373","title":"CHARACTERISTICS OF PRECIPITATION DOWNSCALING BY MEANS OF DEEP LEARNING METHOD","authors":["Takeyoshi Nagasato","Kei Ishida","Makoto UEDA","Kazuki Yokoo","Masato Kiyama","Motoki Amagasaki"],"date":"2020-01-01","year":2020,"venue":"Journal of Japan Society of Civil Engineers Ser B1 (Hydraulic Engineering)","venue_type":"journal","ids":{"doi":"10.2208/jscejhe.76.2_i_373","openalex":"W3216265328"},"links":{"paper":"https://doi.org/10.2208/jscejhe.76.2_i_373","pdf":"https://www.jstage.jst.go.jp/article/jscejhe/76/2/76_I_373/_pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Examines how CNN precipitation downscaling from atmospheric fields depends on input domain, pressure levels and variables. Finds more inputs do not always improve basin rainfall accuracy.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2208-jscejhe.76.2-i-331","title":"ATTEMPT OF ONE-MONTH WEATHER FORECAST USING MACHINE LEARNING","authors":["Hiroki MONDA","Ryo Kaneko","Shiho Onomura","Makoto NAKAYOSHI"],"date":"2020-01-01","year":2020,"venue":"Journal of Japan Society of Civil Engineers Ser B1 (Hydraulic Engineering)","venue_type":"journal","ids":{"doi":"10.2208/jscejhe.76.2_i_331","openalex":"W3215458648"},"links":{"paper":"https://doi.org/10.2208/jscejhe.76.2_i_331","pdf":"https://www.jstage.jst.go.jp/article/jscejhe/76/2/76_I_331/_pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"LSTM and CNN predict monthly mean temperature and precipitation from station and sea-surface temperature data, with mixed skill.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2208-jscejer.76.5-i-471","title":"APPLICATION OF A DEEP-LEARNING METHOD INCLUDING SHORTCUT PATHS TO CORRECT THE PRECIPITATION OUTPUTS OF A NUMERICAL WEATHER PREDICTION MODEL","authors":["Takeru Kurakami","Kazuyoshi Souma","Takashi Miyamoto","Takahiko FURUYA","Jun Magome","Hiroshi Ishidaira"],"date":"2020-01-01","year":2020,"venue":"Journal of Japan Society of Civil Engineers Ser G (Environmental Research)","venue_type":"journal","ids":{"doi":"10.2208/jscejer.76.5_i_471","openalex":"W3125900171"},"links":{"paper":"https://doi.org/10.2208/jscejer.76.5_i_471","pdf":"https://www.jstage.jst.go.jp/article/jscejer/76/5/76_I_471/_pdf"},"orgs":[],"topic":"post-processing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"U-Net with shortcut connections corrects NWP precipitation outputs for Kansai heavy rain, improving strong-rain representation over plain CNNs.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2208-jscejam.76.1-22","title":"DATA-DRIVEN ANALYSIS OF NONLINEAR DYNAMICS BASED ON KOOPMAN OPERATOR THEORY AND ITS APPLICATION TO SHORT-TERM PRECIPITATION FORECAST","authors":["Takashi Miyamoto","Shitao Zheng","Masato ABE","Koyuru Iwanami"],"date":"2020-01-01","year":2020,"venue":"Journal of Japan Society of Civil Engineers Ser A2 (Applied Mechanics (AM))","venue_type":"journal","ids":{"doi":"10.2208/jscejam.76.1_22","openalex":"W3043725338"},"links":{"paper":"https://doi.org/10.2208/jscejam.76.1_22","pdf":"https://www.jstage.jst.go.jp/article/jscejam/76/1/76_22/_pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Combines Koopman operator analysis with kinematic analysis for short-term precipitation forecasting; abstract is in Japanese and the ML contribution is modest.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.18488-journal.72.2020.41.11.18","title":"Comparable Investigation for Rainfall Forecasting using Different Data Mining Approaches in Sulaymaniyah City in Iraq","authors":["Sherko H. Murad","Yusra Mohammed M. Salih"],"date":"2020-01-01","year":2020,"venue":"International Journal of Advances in Life Science and Technology","venue_type":"journal","ids":{"doi":"10.18488/journal.72.2020.41.11.18","openalex":"W3028988192"},"links":{"paper":"https://doi.org/10.18488/journal.72.2020.41.11.18","pdf":"https://archive.conscientiabeam.com/index.php/72/article/download/1775/2472"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares ANN, Naive Bayes and SVM classifiers for rainfall prediction in Sulaymaniyah, Iraq, using station weather records; no single headline number given.","significance":1,"cited_by":11,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijw.2020.112711","title":"Artificial neural network modelling technique in predicting Western Australian seasonal rainfall","authors":["Iqbal Hossain","H. M. Rasel","Fatemeh Mekanik","Monzur Alam Imteaz"],"date":"2020-01-01","year":2020,"venue":"International Journal of Water","venue_type":"journal","ids":{"doi":"10.1504/ijw.2020.112711","openalex":"W4229582068"},"links":{"paper":"https://doi.org/10.1504/ijw.2020.112711"},"orgs":[],"topic":"s2s-seasonal","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Artificial neural networks using ENSO and IOD indices forecast seasonal spring rainfall at three Western Australian stations, with testing correlations up to 0.96.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.13016-m2izgp-yw55","title":"Using Machine Learning Techniques for Supercell Tornado Prediction with Environmental Sounding Data","authors":["Brice E. Coffer","Michaela Kubacki","Yixin Wen","Ting Zhang","Carlos Barajas","Matthias K. Gobbert"],"date":"2020-01-01","year":2020,"venue":"Maryland Shared Open Access Repository (USMAI Consortium)","venue_type":"preprint","ids":{"doi":"10.13016/m2izgp-yw55","openalex":"W3045538543"},"links":{"paper":"https://doi.org/10.13016/m2izgp-yw55"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"evaluation","method":["classical-ml","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Random forest and CNN on RUC pre-storm soundings predict supercell tornadoes, reaching about 66% accuracy for tornadic cases after resampling.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11834-jrs.20209124","title":"Deep learning estimation of tropical cyclone intensity along the southeast coast of China using FY-4A satellite","authors":["Linli CUI","Zhao CHEN","Xingxing YU","Guangchen CHEN","Xiaofeng Wang","Yiwen LU","Wei Guo"],"date":"2020-01-01","year":2020,"venue":"National Remote Sensing Bulletin","venue_type":"journal","ids":{"doi":"10.11834/jrs.20209124","openalex":"W4383117950"},"links":{"paper":"https://doi.org/10.11834/jrs.20209124","pdf":"http://www.ygxb.ac.cn/rc-pub/front/front-article/download?siteId=91&id=8281803&attachType=lowqualitypdf&token=&language=zh"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"CNN estimates FY-4A satellite tropical cyclone intensity off southeast China with over 97% class accuracy and 1.75 m/s mean absolute error.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2020.2995158","title":"A Center Location Algorithm for Tropical Cyclone in Satellite Infrared Images","authors":["Pingping Wang","Ping Wang","Cong Wang","Yue Yuan","Di Wang"],"date":"2020-01-01","year":2020,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2020.2995158","openalex":"W3027830921"},"links":{"paper":"https://doi.org/10.1109/jstars.2020.2995158","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/8994817/09095212.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Two-step deep detection and segmentation locates tropical cyclone centers in satellite infrared images with about 0.237° average position error.","significance":3,"cited_by":51,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2020.2970253","title":"Deep Learning Algorithm for Satellite Imaging Based Cyclone Detection","authors":["Snehlata Shakya","Sanjeev Kumar","Mayank Goswami"],"date":"2020-01-01","year":2020,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2020.2970253","openalex":"W3003708426"},"links":{"paper":"https://doi.org/10.1109/jstars.2020.2970253","pdf":"https://ieeexplore.ieee.org/ielx7/4609443/8994817/08977395.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"CNN classifies storm versus non-storm satellite images for cyclone detection after augmentation, reporting 90% accuracy, with linear regression for track prediction.","significance":2,"cited_by":62,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.3026364","title":"Notice of Violation of IEEE Publication Principles: Ground-Based Cloud Image Recognition System Based on Multi-CNN and Feature Screening and Fusion","authors":["Ma Jingyi","Tiejun Zhang","Jing Guodong","Yan Wenjun","Yang Bin"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.3026364","openalex":"W3088500914"},"links":{"paper":"https://doi.org/10.1109/access.2020.3026364","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09205205.pdf"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Retraction notice for a CNN-based ground-based cloud image recognition system that duplicated prior work; the underlying topic is cloud classification.","significance":1,"cited_by":6,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.3022047","title":"A New Approach for Surface Urban Heat Island Monitoring Based on Machine Learning Algorithm and Spatiotemporal Fusion Model","authors":["Yuan Yao","Cun Chang","Felix Ndayisaba","Shuang Wang"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.3022047","openalex":"W3083948194"},"links":{"paper":"https://doi.org/10.1109/access.2020.3022047","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09187236.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"Random forest downscaling of Landsat LST fused with MODIS tracks Chengdu summer urban heat island intensity rising from 2.78 °C to 4.04 °C over 2009–2018.","significance":2,"cited_by":38,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.3021034","title":"Evaluating Multivariable Statistical Methods for Downscaling Nighttime Land Surface Temperature in Urban Areas","authors":["Pengcheng Qi","Yan Cui","Haijun Zhang","Shixiong Hu","Lunguang Yao","Larry Bailian Li"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.3021034","openalex":"W3082347656"},"links":{"paper":"https://doi.org/10.1109/access.2020.3021034","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09184064.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Compares multivariable ML methods for downscaling coarse nighttime urban land surface temperature; daytime visible-NIR predictors perform as well as physical variables, MAE within 2 K.","significance":2,"cited_by":10,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.3012306","title":"Research on Ultra-Short-Term Wind Power Prediction Considering Source Relevance","authors":["Yong Sun","Zhenyuan Li","Xinnan Yu","Baoju Li","Mao Yang"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.3012306","openalex":"W3047168149"},"links":{"paper":"https://doi.org/10.1109/access.2020.3012306","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09154667.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Ultra-short-term wind power forecasting combines day-ahead NWP-based timing of low-accuracy periods with a neural network and persistence, improving accuracy over classical methods.","significance":2,"cited_by":53,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.2995187","title":"MPL-GAN: Toward Realistic Meteorological Predictive Learning Using Conditional GAN","authors":["Hongbin Liu","Ickjai Lee"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.2995187","openalex":"W3027406589"},"links":{"paper":"https://doi.org/10.1109/access.2020.2995187","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09094665.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Conditional GAN with a predictive learning module sharpens meteorological image forecasts, achieving 14% better sharpness than the baseline.","significance":3,"cited_by":33,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.2992083","title":"A Novel Data-Driven Tropical Cyclone Track Prediction Model Based on CNN and GRU With Multi-Dimensional Feature Selection","authors":["Jie Lian","Pingping Dong","Yuping Zhang","Jianguo Pan","Kehao Liu"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.2992083","openalex":"W3021357433"},"links":{"paper":"https://doi.org/10.1109/access.2020.2992083","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09085360.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"CNN-GRU model with feature selection predicts tropical cyclone tracks from 1945-2017 data, outperforming NWP and statistical baselines; no numeric gain given.","significance":3,"cited_by":53,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.2991923","title":"Predicting Lightning-Related Outages in Power Distribution Systems: A Statistical Approach","authors":["Milad Doostan","Badrul Chowdhury"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.2991923","openalex":"W3022246423"},"links":{"paper":"https://doi.org/10.1109/access.2020.2991923","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09084149.pdf"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["radar","other"],"status":"research","summary":"Clusters lightning-related utility outages and predicts daily outage groups from radar thunderstorm forecasts, handling class imbalance.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.2982772","title":"A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry","authors":["Wei Tian","Wei Huang","Yi Lei","Liguang Wu","Chao Wang"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.2982772","openalex":"W3040858621"},"links":{"paper":"https://doi.org/10.1109/access.2020.2982772","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09044856.pdf"},"orgs":["fudan-university","nuist"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Hybrid CNN with classification and BP network estimates tropical cyclone intensity from satellite images with RMSE of 8.91 kt.","significance":3,"cited_by":32,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.2982035","title":"Classifying El Niño-Southern Oscillation Combining Network Science and Machine Learning","authors":["Matheus A. De Castro Santos","Didier A. Vega‐Oliveros","Liang Zhao","Lilian Berton"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.2982035","openalex":"W3011835423"},"links":{"paper":"https://doi.org/10.1109/access.2020.2982035","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09042254.pdf"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Climate-network topology features from surface air temperature feed ten classifiers that predict next-season strong or weak ENSO phases with 80% AUC.","significance":2,"cited_by":14,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.2980977","title":"Hybrid Deep Learning Approach for Multi-Step-Ahead Daily Rainfall Prediction Using GCM Simulations","authors":["Mohd Imran Khan","Rajib Maity"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.2980977","openalex":"W3011867832"},"links":{"paper":"https://doi.org/10.1109/access.2020.2980977","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09036966.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Hybrid Conv1D-MLP model predicts daily rainfall 1 to 5 days ahead at twelve sites using GCM meteorological inputs, outperforming MLP and SVR.","significance":2,"cited_by":109,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2020.2974785","title":"ResLap: Generating High-Resolution Climate Prediction Through Image Super-Resolution","authors":["Jianxin Cheng","Qiuming Kuang","Chenkai Shen","Jin Liu","Xicheng Tan","Wang Liu"],"date":"2020-01-01","year":2020,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2020.2974785","openalex":"W3008141216"},"links":{"paper":"https://doi.org/10.1109/access.2020.2974785","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09001044.pdf"},"orgs":["cma"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"ResLap applies a residual-dense Laplacian pyramid super-resolution network to downscale China Meteorological Administration climate data and releases datasets.","significance":2,"cited_by":51,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-16000870.2019.1696142","title":"Probabilistic thunderstorm forecasting by blending multiple ensembles","authors":["François Bouttier","Hugo Marchal"],"date":"2020-01-01","year":2020,"venue":"Tellus A Dynamic Meteorology and Oceanography","venue_type":"journal","ids":{"doi":"10.1080/16000870.2019.1696142","openalex":"W3000473633"},"links":{"paper":"https://doi.org/10.1080/16000870.2019.1696142"},"orgs":["meteo-france"],"topic":"post-processing","topics":["extremes-hazards","probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short","medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"ML-tuned blending of multiple ensembles gives probabilistic thunderstorm forecasts from 9 hours to 4 days, clearly better than raw ensemble output.","significance":4,"cited_by":31,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs12010108","title":"Tropical Cyclone Intensity Estimation Using Multi-Dimensional Convolutional Neural Networks from Geostationary Satellite Data","authors":["Juhyun Lee","Jungho Im","Dong‐Hyun Cha","Haemi Park","Seongmun Sim"],"date":"2019-12-28","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs12010108","openalex":"W2998068843"},"links":{"paper":"https://doi.org/10.3390/rs12010108","pdf":"https://www.mdpi.com/2072-4292/12/1/108/pdf?version=1577527824"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"2D and 3D CNNs estimate tropical cyclone intensity from multispectral geostationary imagery, reaching 8.32 kt RMSE, about 35% better than single-channel CNNs.","significance":3,"cited_by":131,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-19-0227.1","title":"Ensemble Postprocessing Using Quantile Function Regression Based on Neural Networks and Bernstein Polynomials","authors":["John Bjørnar Bremnes"],"date":"2019-12-27","year":2019,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-19-0227.1","openalex":"W2980462578"},"links":{"paper":"https://doi.org/10.1175/mwr-d-19-0227.1"},"orgs":["met-norway"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural-network quantile function regression with Bernstein polynomials postprocesses 60 h ensemble wind speed at 125 Norwegian stations, improving quantile skill score by nearly 1%.","significance":3,"cited_by":80,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2019jd031551","title":"Detection of Non‐Gaussian Behavior Using Machine Learning Techniques: A Case Study on the Lorenz 63 Model","authors":["Michael Goodliff","Steven J. Fletcher","Anton J. Kliewer","John M. Forsythe","Andrew S. Jones"],"date":"2019-12-27","year":2019,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2019jd031551","openalex":"W2997445836"},"links":{"paper":"https://doi.org/10.1029/2019jd031551"},"orgs":["colorado-state-university"],"topic":"data-assimilation","topics":["xai-uq-physics"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Support vector machines and neural networks detect non-Gaussian error distributions in the Lorenz-63 model, informing relaxation of Gaussian assumptions in data assimilation.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3197406226","title":"Weather Forecasting Prediction of Tamilnadu Cities Using Machine Learning","authors":["B. Krishna Sai","S. Magesh Kumar","D. Mahalakshmi"],"date":"2019-12-26","year":2019,"venue":"TEST Engineering & Management","venue_type":"journal","ids":{"openalex":"W3197406226"},"links":{"paper":"https://www.testmagzine.biz/index.php/testmagzine/article/download/769/690"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Random Forest models predict daily maximum and minimum temperatures for Tamil Nadu cities from a month of prior weather data, beating linear regression.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10501494.1","title":"Towards data-driven approaches for simulating rainfall in climate models","authors":["Ramalingam Saravanan","Junho Yang","Mikyoung Jun","Courtney Schumacher","Jiayi Wang","Raymond Wong"],"date":"2019-12-24","year":2019,"venue_type":"other","ids":{"doi":"10.1002/essoar.10501494.1","openalex":"W2999638341"},"links":{"paper":"https://doi.org/10.1002/essoar.10501494.1"},"orgs":[],"topic":"hybrid-parameterization","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"Statistical models predict tropical rainfall type and amount over the next 6 hours from MERRA-2 atmospheric profiles, trained on TRMM data, capturing time-mean spatial patterns.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-isprs-archives-xlii-4-w19-63-2019","title":"TOWARDS PREDICTING RICE LOSS DUE TO TYPHOONS IN THE PHILIPPINES","authors":["S. Boeke","Marc J. C. Van den Homberg","Aklilu Teklesadik","J. L. D. Fabila","D. Riquet","Maryam Alimardani"],"date":"2019-12-23","year":2019,"venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","venue_type":"journal","ids":{"doi":"10.5194/isprs-archives-xlii-4-w19-63-2019","openalex":"W2997434286"},"links":{"paper":"https://doi.org/10.5194/isprs-archives-xlii-4-w19-63-2019","pdf":"https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4-W19/63/2019/isprs-archives-XLII-4-W19-63-2019.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Support vector models predict typhoon-driven rice area loss in the Philippines from geographic and typhoon features, with regression MAE of 6.83 percentage points.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5377-torreon.v8i22.9028","title":"Modelo de pronóstico de precipitación para la ciudad de Managua utilizando redes neuronales artificiales en el contexto de la gestión ambiental","authors":["Alina María Ortíz"],"date":"2019-12-20","year":2019,"venue":"Revista Torreón Universitario","venue_type":"journal","ids":{"doi":"10.5377/torreon.v8i22.9028","openalex":"W2996592093"},"links":{"paper":"https://doi.org/10.5377/torreon.v8i22.9028","pdf":"https://www.lamjol.info/index.php/torreon/article/download/9028/10195"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"A multilayer perceptron forecasts precipitation for Managua from three weather stations and teleconnection indices (NAO, SOI, ONI and others), for climate-sensitive planning.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2019-2385310","title":"Estimation of Summer Air Temperature over China Using Himawari-8 AHI and Numerical Weather Prediction Data","authors":["Hailei Liu","Qi Zhou","Shenglan Zhang","Xiaobo Deng"],"date":"2019-12-18","year":2019,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2019/2385310","openalex":"W2994883585"},"links":{"paper":"https://doi.org/10.1155/2019/2385310","pdf":"https://downloads.hindawi.com/journals/amete/2019/2385310.pdf"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations","nwp-analysis"],"status":"research","summary":"Himawari-8 brightness temperatures and NWP predictors estimate summer air temperature over China; a neural network reaches R=0.97 and RMSE 1.72°C against stations.","significance":3,"cited_by":26,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2019.2955538","title":"MCSIP Net: Multichannel Satellite Image Prediction via Deep Neural Network","authors":["Jae-Hyeok Lee","Sangmin S. Lee","Hak Gu Kim","Sa-Kwang Song","Seongchan Kim","Yong Man Ro"],"date":"2019-12-17","year":2019,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2019.2955538","openalex":"W2996543533"},"links":{"paper":"https://doi.org/10.1109/tgrs.2019.2955538"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"MCSIP Net uses adversarial spatio-temporal discriminators and meteorological analysis critics to predict multichannel satellite images for weather nowcasting.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11243035","title":"Cloud Detection from FY-4A’s Geostationary Interferometric Infrared Sounder Using Machine Learning Approaches","authors":["Qi Zhang","Yi Yu","Weimin Zhang","Tengling Luo","Xiang Wang"],"date":"2019-12-16","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11243035","openalex":"W2995649053"},"links":{"paper":"https://doi.org/10.3390/rs11243035","pdf":"https://www.mdpi.com/2072-4292/11/24/3035/pdf?version=1576738943"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Logistic regression over land and extra-trees over sea detect clouds in FY-4A GIIRS hyperspectral infrared data, reaching HSS 0.78 land and 0.95 sea.","significance":3,"cited_by":32,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jcli-d-19-0512.1","title":"The Importance of Past MJO Activity in Determining the Future State of the Midlatitude Circulation","authors":["Kai‐Chih Tseng","Elizabeth A. Barnes","Eric Daniel Maloney"],"date":"2019-12-16","year":2019,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-19-0512.1","openalex":"W2996173156"},"links":{"paper":"https://doi.org/10.1175/jcli-d-19-0512.1"},"orgs":["colorado-state-university"],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["other"],"status":"research","summary":"Logistic regression with linear baroclinic model simulations shows the past 15 days of MJO activity improve midlatitude circulation predictability beyond 15 days ahead.","significance":3,"cited_by":15,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1912.09425","title":"Precipitation Forecasting via Multi-Scale Deconstructed ConvLSTM","authors":["Xinyu Xiao","Qiuming Kuang","Shiming Xiang","Junnan Hu","Chunhong Pan"],"date":"2019-12-15","year":2019,"venue_type":"preprint","ids":{"arxiv":"1912.09425","openalex":"W2995770089"},"links":{"paper":"http://arxiv.org/abs/1912.09425","pdf":"https://arxiv.org/pdf/1912.09425"},"orgs":["cma"],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A multi-scale deconstructed ConvLSTM encoder-decoder forecasts precipitation from multiple meteorological fields on EC and CM datasets, combining NWP data with deep learning.","significance":3,"cited_by":5,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jestch.2019.11.006","title":"Prediction of tropospheric wet delay by an artificial neural network model based on meteorological and GNSS data","authors":["Mahmut Oğuz Selbesoğlu"],"date":"2019-12-12","year":2019,"venue":"Engineering Science and Technology an International Journal","venue_type":"journal","ids":{"doi":"10.1016/j.jestch.2019.11.006","openalex":"W2998702723"},"links":{"paper":"https://doi.org/10.1016/j.jestch.2019.11.006","pdf":"https://www.sciencedirect.com/science/article/pii/S2215098619316003/pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A neural network predicts GNSS zenith wet delay up to six hours ahead from in-situ meteorological data, reaching 1.5 cm RMSE at two Austrian stations.","significance":2,"cited_by":40,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1912.12132","title":"Machine Learning for Precipitation Nowcasting from Radar Images","authors":["Shreya Agrawal","Luke Barrington","Carla Bromberg","John Burge","Cenk Gazen","Jason Hickey"],"date":"2019-12-11","year":2019,"venue_type":"preprint","ids":{"arxiv":"1912.12132","openalex":"W2998557500"},"links":{"paper":"https://arxiv.org/abs/1912.12132","pdf":"https://arxiv.org/pdf/1912.12132"},"orgs":["google-research"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"A U-Net treats 1-hour, 1 km precipitation nowcasting as image-to-image translation and outperforms optical flow, persistence and HRRR.","significance":6,"cited_by":228,"score":69,"highlight":true,"highlight_reason":"Early influential UNet radar nowcasting result beating HRRR and optical flow at 1 km; precursor to later operational nowcasting models.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-gmd-12-5137-2019","title":"PALEO-PGEM v1.0: a statistical emulator of Pliocene–Pleistocene climate","authors":["Philip B. Holden","Neil Robert Edwards","Thiago Fernando Rangel","Elisa B. Pereira","Giang Tran","Richard D. Wilkinson"],"date":"2019-12-10","year":2019,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-12-5137-2019","openalex":"W2899637610"},"links":{"paper":"https://doi.org/10.5194/gmd-12-5137-2019","pdf":"https://gmd.copernicus.org/articles/12/5137/2019/gmd-12-5137-2019.pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Gaussian process emulators of PLASIM-GENIE ensembles produce a downscaled, high-resolution reconstruction of Pliocene-Pleistocene temperature and precipitation at 1,000-year intervals.","significance":3,"cited_by":55,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3158461109","title":"Image Labeler: Label Earth Science Images for Machine Learning","authors":["Ashish Acharya","Brian M. Freitag","Iksha Gurung","Manil Maskey","Rahul Ramachandran","Aaron S. Kaulfus"],"date":"2019-12-09","year":2019,"venue":"NASA Technical Reports Server (NASA)","venue_type":"preprint","ids":{"openalex":"W3158461109"},"links":{"paper":"https://ntrs.nasa.gov/api/citations/20190033505/downloads/20190033505.pdf"},"orgs":["nasa"],"topic":"infra-software","topics":["benchmarks-data-eval"],"type":"benchmark","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Web-based Image Labeler tool speeds labeling of Earth science images, such as hurricane imagery, to build shareable datasets for deep learning.","significance":1,"cited_by":1,"score":39,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10501303.1","title":"Linear and nonlinear causality in monthly atmospheric and ocean time series","authors":["Maria Gabriela Louzada Malfatti","Lucas Massaroppe","Pedro Leite da Silva Dias"],"date":"2019-12-08","year":2019,"venue_type":"other","ids":{"doi":"10.1002/essoar.10501303.1","openalex":"W2995366448"},"links":{"paper":"https://doi.org/10.1002/essoar.10501303.1"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Partial directed coherence and a kernel nonlinear variant reveal linear and nonlinear causal links among ENSO, PDO, AMO and other teleconnection indices from 1950 to 2018.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1912.03758","title":"The Probabilistic Backbone of Data-Driven Complex Networks: An example in Climate","authors":["Catharina Graafland","José M. Gutiérrez","Juan M. López","Diego Pazó","Miguel A. Rodríguez"],"date":"2019-12-08","year":2019,"venue":"Sci Rep 10, 11484 (2020)","venue_type":"journal","ids":{"arxiv":"1912.03758","doi":"10.1038/s41598-020-67970-y"},"links":{"paper":"https://arxiv.org/abs/1912.03758","pdf":"https://arxiv.org/pdf/1912.03758"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Proposes Bayesian networks as a sparse, non-redundant alternative to correlation networks for building data-driven climate networks, illustrated on a global climate dataset.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019gl085190","title":"Discovering the Importance of Mesoscale Cloud Organization Through Unsupervised Classification","authors":["Leif Denby"],"date":"2019-12-05","year":2019,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2019gl085190","openalex":"W2991909169"},"links":{"paper":"https://doi.org/10.1029/2019gl085190"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"An unsupervised neural network finds hierarchical trade-wind cloud organization regimes in 10,000 GOES-16 images, linking regimes to radiative properties for climate model evaluation.","significance":4,"cited_by":72,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3092533268","title":"Statistical downscaling of monthly precipitation over India using long short term memory neural network (LSTM)","authors":["Daanish Mahajan","Manish Kumar Goyal"],"date":"2019-12-04","year":2019,"venue_type":"other","ids":{"openalex":"W3092533268"},"links":{"paper":"http://dspace.iiti.ac.in:8080/jspui/handle/123456789/2227"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["rnn"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"LSTM network statistically downscales monthly precipitation over India, aiming to produce finer regional rainfall estimates from large-scale predictors.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10501254.1","title":"40 Years of Föhn Winds on the Antarctic Peninsula: Impact on Surface Melt from 1979-2018","authors":["Matthew K. Laffin","Charles Sutton Zender","Sameer Singh","Jan Melchior van Wessem"],"date":"2019-12-04","year":2019,"venue_type":"other","ids":{"doi":"10.1002/essoar.10501254.1","openalex":"W2996002457"},"links":{"paper":"https://doi.org/10.1002/essoar.10501254.1"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","era5","other"],"status":"research","summary":"A machine-learning föhn detector trained on Antarctic weather stations finds föhn-driven melt strongest near Larsen C, with no significant increase over 1979-2018.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1912.02276","title":"Enhancing Stratospheric Weather Analyses and Forecasts by Deploying Sensors from a Weather Balloon","authors":["Kiwan Maeng","Iskender Kushan","Brandon Lucia","Ashish Kapoor"],"date":"2019-12-04","year":2019,"venue_type":"preprint","ids":{"arxiv":"1912.02276"},"links":{"paper":"https://arxiv.org/abs/1912.02276","pdf":"https://arxiv.org/pdf/1912.02276"},"orgs":[],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["regional"],"data":["stations","nwp-analysis"],"status":"pre-operational","summary":"Uses a Gaussian process to decide when to release sensors from a weather balloon, targeting better stratospheric analyses and forecasts, tested on real flights.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1912.01752","title":"Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability","authors":["Benjamin A. Toms","Elizabeth A. Barnes","Imme Ebert-Uphoff"],"date":"2019-12-04","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"1912.01752","doi":"10.1029/2019ms002002","openalex":"W2993514765"},"links":{"paper":"https://arxiv.org/abs/1912.01752","pdf":"https://arxiv.org/pdf/1912.01752"},"orgs":["colorado-state-university"],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml","other"],"timescale":[],"spatial":["global"],"data":["era5","cmip"],"status":"research","summary":"Applies backwards optimization and layerwise relevance propagation to neural networks, recovering scientifically meaningful patterns in climate variability data.","significance":4,"cited_by":359,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1912.01277","title":"Make Thunderbolts Less Frightening -- Predicting Extreme Weather Using Deep Learning","authors":["Christian Schön","Jens Dittrich"],"date":"2019-12-03","year":2019,"venue_type":"preprint","ids":{"arxiv":"1912.01277","openalex":"W2993893245"},"links":{"paper":"https://arxiv.org/abs/1912.01277","pdf":"https://arxiv.org/pdf/1912.01277"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A UNet++/ResNet-inspired CNN on satellite images predicts lightning and thunderstorms 15 minutes ahead with over 94% probability of detection.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4273-ijvss.11.3.22","title":"Development and Evaluation of AI System to Specify Favourable Launch Windows of Space Vehicles from the MST Radar Data","authors":["B. P. Madhusudan","Polaiah Bojja"],"date":"2019-12-02","year":2019,"venue":"International Journal of Vehicle Structures and Systems","venue_type":"journal","ids":{"doi":"10.4273/ijvss.11.3.22","openalex":"W2994004286"},"links":{"paper":"https://doi.org/10.4273/ijvss.11.3.22"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["other"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A feed-forward backpropagation network predicts wind speed, direction and turbulence from MST radar data to help choose space launch windows.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1127-metz-2019-0977","title":"Machine Learning Approach to Summer Precipitation Nowcasting over the Eastern Alps","authors":["Linye Song","Irene Schicker","Petrina Papazek","Alexander Kann","Benedikt Bica","Yong Wang","Mingxuan Chen"],"date":"2019-12-02","year":2019,"venue":"Meteorologische Zeitschrift","venue_type":"journal","ids":{"doi":"10.1127/metz/2019/0977","openalex":"W2992852944"},"links":{"paper":"https://doi.org/10.1127/metz/2019/0977"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"An MLP neural network nowcasts hourly summer precipitation over the Eastern Alps, outperforming the INCA nowcasting system and a multiple linear regression baseline.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3129185571","title":"The Potential of Integrated Machine Learning Algorithms for Tropical Cyclone Detection in Advanced Climate Modeling","authors":["Warren Davis","Kevin A. Reed","Timothy M. Shead","Himasree Kolla","Gideon Popoola","Philip Kegelmeyer","Ashish Konduri"],"date":"2019-12-01","year":2019,"venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","venue_type":"preprint","ids":{"openalex":"W3129185571"},"links":{"paper":"https://www.osti.gov/biblio/1643419","pdf":"https://www.osti.gov/servlets/purl/1643419"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Integrated machine learning is proposed for detecting tropical cyclones in advanced climate models; no abstract is provided, so the method is not verifiable.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2981942628","title":"Using Lidar and Machine Learning to Identify Planetary Boundary Layer Heights","authors":["Jennifer Sleeman","Vanessa Caicedo","Milton Halem","Belay Demoz","Rubén Delgado"],"date":"2019-12-01","year":2019,"venue_type":"other","ids":{"openalex":"W2981942628"},"links":{"paper":"https://ebiquity.umbc.edu/paper/html/id/870/Using-Lidar-and-Machine-Learning-to-Identify-Planetary-Boundary-Layer-Heights"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A deep neural network applied to lidar backscatter images identifies planetary boundary layer height and outperforms a double-derivative method in preliminary results.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.15446-dyna.v86n211.7607","title":"Using Artificial Neural Networks to predict monthly precipitation for the Cali river basin, Colombia","authors":["Daniel David Montenegro-Murillo","Mayra Alejandra Pérez-Ortiz","Viviana Vargas-Franco"],"date":"2019-12-01","year":2019,"venue":"Magazine Portal Bibliotech Digital (Universidad Nacional de Colombia)","venue_type":"preprint","ids":{"doi":"10.15446/dyna.v86n211.7607","openalex":"W3044752982"},"links":{"paper":"https://doi.org/10.15446/dyna.v86n211.7607","pdf":"https://revistas.unal.edu.co/index.php/dyna/article/view/76079"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Artificial neural networks statistically downscale CMIP5 models to monthly rainfall for the Cali river basin, projecting a shift of rainfall toward the middle and lower basin by 2100.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-18-0324.1","title":"Leveraging Modern Artificial Intelligence for Remote Sensing and NWP: Benefits and Challenges","authors":["Sid-Ahmed Boukabara","Vladimir Krasnopolsky","Jebb Q. Stewart","Eric S. Maddy","Narges Shahroudi","Ross N. Hoffman"],"date":"2019-12-01","year":2019,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-18-0324.1","openalex":"W2981217223"},"links":{"paper":"https://doi.org/10.1175/bams-d-18-0324.1"},"orgs":["colorado-state-university","noaa"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Review arguing modern AI can augment or replace parts of satellite remote sensing and NWP processing chains, from observations to forecasts.","significance":4,"cited_by":117,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.35940-ijrte.d8261.118419","title":"Deep Reinforcement Learning Based Weather Monitoring Systemusing Arduino for Smart Environment","authors":["Mr. R. Sathya Vignesh*","M. Sivakumar","Mr. M. Shyam","Mrs. J. Yogapriya"],"date":"2019-11-30","year":2019,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.d8261.118419","openalex":"W4247772335"},"links":{"paper":"https://doi.org/10.35940/ijrte.d8261.118419"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Describes an Arduino and WiFi weather monitoring setup with a claimed deep-learning forecaster; the ML description is vague and gives no quantitative results.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijrte.d5281.118419","title":"Optimized K Nearest Neighbor Classification Algorithm for Weather Prediction","authors":["A Zakiuddin Ahmed*","T. Abdul Razak"],"date":"2019-11-30","year":2019,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.d5281.118419","openalex":"W4244473393"},"links":{"paper":"https://doi.org/10.35940/ijrte.d5281.118419"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Applies WEKA classification algorithms, including an optimized KNN, to past weather datasets to predict rainfall, humidity and temperature.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1912.00134","title":"STConvS2S: Spatiotemporal Convolutional Sequence to Sequence Network for Weather Forecasting","authors":["Rafaela Castro","Yania M. Souto","Eduardo Ogasawara","Fabio Porto","Eduardo Bezerra"],"date":"2019-11-30","year":2019,"venue":"Neurocomputing","venue_type":"journal","ids":{"arxiv":"1912.00134","doi":"10.1016/j.neucom.2020.09.060","openalex":"W2991559313"},"links":{"paper":"https://doi.org/10.1016/j.neucom.2020.09.060","pdf":"https://arxiv.org/pdf/1912.00134"},"orgs":[],"topic":"regional-km-scale","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["era5","other"],"status":"research","summary":"STConvS2S uses only convolutional layers for sequence-to-sequence weather forecasting of South American temperature and rainfall, 23% better than an RNN baseline and five times faster to train.","significance":3,"cited_by":116,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2994389464","title":"Weather Prediction Model using Recurrent Neural Network","authors":["A. Mohana Priya","Atluri Vani Vathsala"],"date":"2019-11-29","year":2019,"venue":"Think India Journal","venue_type":"journal","ids":{"openalex":"W2994389464"},"links":{"paper":"https://journals.eduindex.org/index.php/think-india/article/view/12116"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":[],"data":["radar","stations"],"status":"research","summary":"Compares RNN and LSTM models for weather prediction from radar, ship and ground observations, reporting the RNN as more accurate than other neural networks.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.agrformet.2019.107858","title":"Seasonal forecasting of daily mean air temperatures using a coupled global climate model and machine learning algorithm for field-scale agricultural management","authors":["Ju‐Young Shin","Kyu Rang Kim","Jong-Chul Ha"],"date":"2019-11-29","year":2019,"venue":"Agricultural and Forest Meteorology","venue_type":"journal","ids":{"doi":"10.1016/j.agrformet.2019.107858","openalex":"W2990957319"},"links":{"paper":"https://doi.org/10.1016/j.agrformet.2019.107858"},"orgs":["kma"],"topic":"s2s-seasonal","topics":["applications-impacts","post-processing"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Machine learning corrects a coupled climate model's seasonal forecasts of daily air temperature for field-scale agricultural management.","significance":2,"cited_by":45,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1911.13061","title":"Detecting anthropogenic cloud perturbations with deep learning","authors":["Duncan Watson-Parris","Samuel Sutherland","Matthew Christensen","Anthony Caterini","Dino Sejdinovic","Philip Stier"],"date":"2019-11-29","year":2019,"venue_type":"preprint","ids":{"arxiv":"1911.13061"},"links":{"paper":"https://arxiv.org/abs/1911.13061","pdf":"https://arxiv.org/pdf/1911.13061"},"orgs":[],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"application","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Deep convolutional networks detect two anthropogenic aerosol-driven perturbations in satellite cloud imagery to assess their prevalence and climatic effects.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-19-0110.1","title":"PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks","authors":["Mojtaba Sadeghi","Ata Akbari Asanjan","Mohammad Faridzad","Phu Nguyen","Kuolin Hsu","Soroosh Sorooshian","Dan Braithwaite"],"date":"2019-11-27","year":2019,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-19-0110.1","openalex":"W2977666392"},"links":{"paper":"https://doi.org/10.1175/jhm-d-19-0110.1"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"PERSIANN-CNN applies CNNs to geostationary infrared and water vapor channels, beating PERSIANN-CCS by 54% in CSI and cutting RMSE by 37%.","significance":5,"cited_by":189,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2019gl084944","title":"Viewing Forced Climate Patterns Through an AI Lens","authors":["Elizabeth A. Barnes","James W. Hurrell","Imme Ebert‐Uphoff","Chuck Anderson","David Anderson"],"date":"2019-11-27","year":2019,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2019gl084944","openalex":"W2991419155"},"links":{"paper":"https://doi.org/10.1029/2019gl084944"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"A neural network trained to predict year from temperature maps detects forced climate patterns without explicitly separating signal from noise.","significance":4,"cited_by":177,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-su11236681","title":"Precipitation Forecasting Using Multilayer Neural Network and Support Vector Machine Optimization Based on Flow Regime Algorithm Taking into Account Uncertainties of Soft Computing Models","authors":["Fatemeh Barzegari Banadkooki","Mohammad Ehteram","Ali Najah Ahmed","Chow Ming Fai","Haitham Abdulmohsin Afan","Wani M. Ridwam","Ahmed Sefelnasr","Ahmed El‐Shafie"],"date":"2019-11-26","year":2019,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su11236681","openalex":"W2989916071"},"links":{"paper":"https://doi.org/10.3390/su11236681","pdf":"https://www.mdpi.com/2071-1050/11/23/6681/pdf?version=1574760391"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Hybrid MLP and SVR models optimized with a flow regime algorithm forecast monthly precipitation in East Azarbaijan, Iran, outperforming other models.","significance":2,"cited_by":40,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-19-0105.1","title":"Calibration of Machine Learning–Based Probabilistic Hail Predictions for Operational Forecasting","authors":["Amanda L. Burke","Nathan Snook","David John Gagne","Sarah McCorkle","Amy McGovern"],"date":"2019-11-26","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-19-0105.1","openalex":"W2989751705"},"links":{"paper":"https://doi.org/10.1175/waf-d-19-0105.1"},"orgs":["ncar","university-of-oklahoma"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"pre-operational","summary":"Random forest postprocesses HREFv2 ensembles for hail, with isotonic calibration matching SPC outlook reliability for operational day-1 forecasts.","significance":4,"cited_by":60,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019gl084969","title":"Detecting Climate Change Effects on Vb Cyclones in a 50‐Member Single‐Model Ensemble Using Machine Learning","authors":["Magdalena Mittermeier","Marco Braun","M. Hofstätter","Yu Wang","Ralf Ludwig"],"date":"2019-11-26","year":2019,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2019gl084969","openalex":"W2991377956"},"links":{"paper":"https://doi.org/10.1029/2019gl084969","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2019GL084969"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"A neural network filters a 50-member regional climate ensemble to show Vb cyclones shift from summer to spring under RCP8.5.","significance":3,"cited_by":31,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos10120740","title":"Retrieval of Horizontal Visibility Using MODIS Data: A Deep Learning Approach","authors":["Bo Hu","Xingying Zhang","Rui Sun","Xianchun Zhu"],"date":"2019-11-25","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10120740","openalex":"W2990612792"},"links":{"paper":"https://doi.org/10.3390/atmos10120740","pdf":"https://www.mdpi.com/2073-4433/10/12/740/pdf?version=1574677127"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"Deep belief network retrieves horizontal visibility from MODIS aerosol optical depth and ECMWF data over Eastern China, with validation correlation near 0.70.","significance":3,"cited_by":9,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2997954543","title":"Data-driven super-parametrization using deep learning for large scale turbulent flow in weather/climate modeling","authors":["Ashesh Chattopadhyay","Adam Subel","Pedram Hassanzadeh","Krishna V. Palem"],"date":"2019-11-24","year":2019,"venue":"Bulletin of the American Physical Society","venue_type":"journal","ids":{"openalex":"W2997954543"},"links":{"paper":"http://absimage.aps.org/image/DFD19/MWS_DFD19-2019-001643.pdf"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Proposes deep-learning data-driven super-parametrization of turbulent flow for weather and climate models; the abstract is unavailable, so details are limited.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s19235144","title":"A Weather Forecast Model Accuracy Analysis and ECMWF Enhancement Proposal by Neural Network","authors":["Jaroslav Frnda","Marek Ďurica","Jan Nedoma","Stanislav Žabka","Radek Martínek","Michal Kostelánský"],"date":"2019-11-24","year":2019,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s19235144","openalex":"W2990093656"},"links":{"paper":"https://doi.org/10.3390/s19235144","pdf":"https://www.mdpi.com/1424-8220/19/23/5144/pdf?version=1574587244"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["other"],"timescale":["medium"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Neural network uses automatic weather station sensor data to correct ECMWF forecasts of temperature and precipitation for regional accuracy gains.","significance":2,"cited_by":35,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ab4e55","title":"Machine learning and artificial intelligence to aid climate change research and preparedness","authors":["Chris Huntingford","Elizabeth S. Jeffers","Michael B. Bonsall","Hannah M. Christensen","Thomas Lees","Hui Yang"],"date":"2019-11-22","year":2019,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ab4e55","openalex":"W2990621239"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ab4e55","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ab4e55/pdf"},"orgs":["university-of-oxford"],"topic":"climate-analysis-attribution","topics":[],"type":"position","method":[],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Perspective arguing that machine learning should mine existing climate data and simulations for teleconnections and warnings, not only improve Earth system models.","significance":3,"cited_by":466,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-ascmo-5-147-2019","title":"Automated detection of weather fronts using a deep learning neural network","authors":["James C Biard","Kenneth E. Kunkel"],"date":"2019-11-21","year":2019,"venue":"Advances in statistical climatology, meteorology and oceanography","venue_type":"journal","ids":{"doi":"10.5194/ascmo-5-147-2019","openalex":"W2990571969"},"links":{"paper":"https://doi.org/10.5194/ascmo-5-147-2019","pdf":"https://ascmo.copernicus.org/articles/5/147/2019/ascmo-5-147-2019.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"DL-FRONT, a 2-D CNN trained on five surface variables, detects about 90% of manually analyzed fronts over North America for 2008–2015.","significance":3,"cited_by":55,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1911.09001","title":"Weather event severity prediction using buoy data and machine learning","authors":["Vikas Ramachandra"],"date":"2019-11-17","year":2019,"venue_type":"preprint","ids":{"arxiv":"1911.09001","openalex":"W2983281260"},"links":{"paper":"https://arxiv.org/abs/1911.09001","pdf":"https://arxiv.org/pdf/1911.09001"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Uses buoy wind and air temperature time series with Kalman-filter imputation and standard ML models to predict severity of tropical storms and hurricanes.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos10110718","title":"Temperature Prediction Using the Missing Data Refinement Model Based on a Long Short-Term Memory Neural Network","authors":["Inyoung Park","Hyun Soo Kim","Jiwon Lee","Joon Ha Kim","Chul Han Song","Hong Kook Kim"],"date":"2019-11-16","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10110718","openalex":"W2988847054"},"links":{"paper":"https://doi.org/10.3390/atmos10110718","pdf":"https://www.mdpi.com/2073-4433/10/11/718/pdf?version=1574330647"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM with a missing-data refinement step forecasts station temperature at 6 to 24 hours and 7 to 14 days ahead, with lowest RMSE among compared models.","significance":2,"cited_by":76,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app9224931","title":"Comparative Analysis of Rainfall Prediction Models Using Machine Learning in Islands with Complex Orography: Tenerife Island","authors":["Ricardo Aguasca-Colomo","Dagoberto Castellanos–Nieves","Máximo Méndez"],"date":"2019-11-16","year":2019,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app9224931","openalex":"W2988198700"},"links":{"paper":"https://doi.org/10.3390/app9224931","pdf":"https://www.mdpi.com/2076-3417/9/22/4931/pdf?version=1574244934"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations","era5"],"status":"research","summary":"Compares random forest and gradient boosting for monthly rainfall prediction on Tenerife using station and reanalysis predictors over four decades.","significance":2,"cited_by":40,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en12224355","title":"An Accurate, Light-Weight Wind Speed Predictor for Renewable Energy Management Systems","authors":["Saira Al-Zadjali","Ahmed Al Maashri","Amer Al‐Hinai","Sultan Al-Yahyai","Mostafa Bakhtvar"],"date":"2019-11-15","year":2019,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en12224355","openalex":"W2982727641"},"links":{"paper":"https://doi.org/10.3390/en12224355","pdf":"https://www.mdpi.com/1996-1073/12/22/4355/pdf?version=1573808708"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Lightweight perturbed-observation ensemble neural network nowcasts wind speed at masts, cutting NRMSE by 20.9% and running an order of magnitude faster than rivals.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-asce-nh.1527-6996.0000345","title":"Concluding the 2017 Hurricane Season: Evaluation of Impact Level Forecasts with Varied Meteorological Hazards","authors":["Stephanie Pilkington","Hussam N Mahmoud"],"date":"2019-11-14","year":2019,"venue":"Natural Hazards Review","venue_type":"journal","ids":{"doi":"10.1061/(asce)nh.1527-6996.0000345","openalex":"W2989306093"},"links":{"paper":"https://doi.org/10.1061/(asce)nh.1527-6996.0000345"},"orgs":["colorado-state-university"],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Evaluates a neural-network hurricane impact-level forecast over 2017 storms, finding best accuracy about 30 h before landfall and wind speed as the key driver.","significance":3,"cited_by":1,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1911.06185","title":"Convolutional Neural Network for Convective Storm Nowcasting Using 3D Doppler Weather Radar Data","authors":["Lei Han","Juanzhen Sun","Wei Zhang"],"date":"2019-11-12","year":2019,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"1911.06185","doi":"10.1109/tgrs.2019.2948070","openalex":"W2989173953"},"links":{"paper":"https://arxiv.org/abs/1911.06185","pdf":"https://arxiv.org/pdf/1911.06185"},"orgs":["ncar"],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A CNN with cross-channel 3D convolution nowcasts convective storms from 3D Doppler radar in Beijing-Tianjin-Hebei, outperforming traditional ML baselines on 3.7 million samples.","significance":3,"cited_by":105,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1911.04932","title":"Short-term forecasting of solar irradiance without local telemetry: a generalized model using satellite data","authors":["Jesus Lago","Karel De Brabandere","Fjo De Ridder","Bart De Schutter"],"date":"2019-11-12","year":2019,"venue":"Solar Energy 173 (2018), pages 566-577","venue_type":"journal","ids":{"arxiv":"1911.04932","doi":"10.1016/j.solener.2018.07.050"},"links":{"paper":"https://arxiv.org/abs/1911.04932","pdf":"https://arxiv.org/pdf/1911.04932"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":[],"timescale":["nowcast","short"],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"A location-generalizing deep network forecasts short-term solar irradiance from satellite and NWP inputs without local ground data, matching local models (31.31% vs 32.01% rRMSE) across 25 Dutch sites.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-19-0087.1","title":"Application of a Dynamic Clustered Bayesian Model Averaging (DCBA) Algorithm for Merging Multisatellite Precipitation Products over Pakistan","authors":["Khalil Ur Rahman","Songhao Shang","Muhammad Shahid","Yeqiang Wen","Zeeshan Khan"],"date":"2019-11-11","year":2019,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-19-0087.1","openalex":"W2985698636"},"links":{"paper":"https://doi.org/10.1175/jhm-d-19-0087.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/hydr/21/1/jhm-d-19-0087.1.pdf"},"orgs":["tsinghua-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations","era5"],"status":"research","summary":"Dynamic clustered Bayesian model averaging merges four satellite precipitation products over Pakistan, outperforming each input product against gauges.","significance":2,"cited_by":41,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41612-019-0098-0","title":"Nowcasting lightning occurrence from commonly available meteorological parameters using machine learning techniques","authors":["Amirhossein Mostajabi","D Finney","Marcos Rubinstein","Farhad Rachidi"],"date":"2019-11-08","year":2019,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"doi":"10.1038/s41612-019-0098-0","openalex":"W2984597037"},"links":{"paper":"https://doi.org/10.1038/s41612-019-0098-0","pdf":"https://www.nature.com/articles/s41612-019-0098-0.pdf"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning nowcasts lightning up to 30 minutes ahead from four surface variables at single stations, beating persistence, electric-field and CAPE baselines.","significance":3,"cited_by":135,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos10110684","title":"Study on Wind Simulations Using Deep Learning Techniques during Typhoons: A Case Study of Northern Taiwan","authors":["Chih‐Chiang Wei"],"date":"2019-11-07","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10110684","openalex":"W2988342776"},"links":{"paper":"https://doi.org/10.3390/atmos10110684","pdf":"https://www.mdpi.com/2073-4433/10/11/684/pdf?version=1573124541"},"orgs":[],"topic":"extremes-hazards","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Deep neural network emulates WRF-simulated typhoon wind speeds at arbitrary locations in Northern Taiwan, matching WRF accuracy across 47 typhoon events.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.36478-rjasci.2018.252.257","title":"Neural Network for Maritime Weather Prediction","authors":["Wimala Lalitya Dhanistha","Herman Pratikno","Silvianita"],"date":"2019-11-05","year":2019,"venue":"Research Journal of Applied Sciences","venue_type":"journal","ids":{"doi":"10.36478/rjasci.2018.252.257","openalex":"W2986063112"},"links":{"paper":"https://doi.org/10.36478/rjasci.2018.252.257","pdf":"http://docsdrive.com/pdfs/medwelljournals/rjasci/2018/252-257.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural network applied to maritime weather prediction; the abstract is missing, so the scope and results could not be verified.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1911.04227","title":"Cumulo: A Dataset for Learning Cloud Classes","authors":["Valentina Zantedeschi","Fabrizio Falasca","Alyson Douglas","Richard Strange","Matt J. Kusner","Duncan Watson-Parris"],"date":"2019-11-05","year":2019,"venue":"Tackling Climate Change with Machine Learning Workshop, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada","venue_type":"journal","ids":{"arxiv":"1911.04227","openalex":"W2983577600"},"links":{"paper":"https://arxiv.org/abs/1911.04227","pdf":"https://arxiv.org/pdf/1911.04227"},"orgs":["university-of-oxford","alan-turing-institute"],"topic":"benchmarks-data-eval","topics":["observations-remote-sensing"],"type":"benchmark","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Cumulo is a global dataset pairing one year of 1km MODIS imagery with CloudSat cloud labels, with a flow-based baseline for cloud classification.","significance":4,"cited_by":10,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app9214688","title":"Spatial Interpolation of GNSS Troposphere Wet Delay by a Newly Designed Artificial Neural Network Model","authors":["Mahmut Oğuz Selbesoğlu"],"date":"2019-11-04","year":2019,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app9214688","openalex":"W2984555428"},"links":{"paper":"https://doi.org/10.3390/app9214688","pdf":"https://www.mdpi.com/2076-3417/9/21/4688/pdf?version=1573464361"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Backpropagation neural network interpolates GNSS zenith wet troposphere delay across Austria from meteorological station data at 40 reference sites.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-19-0118.1","title":"PERSIANN Dynamic Infrared–Rain Rate Model (PDIR) for High-Resolution, Real-Time Satellite Precipitation Estimation","authors":["Phu Nguyen","Eric Jay Shearer","Mohammed Ombadi","Vesta Afzali Gorooh","Kuolin Hsu","Soroosh Sorooshian","William S. Logan","Marty Ralph"],"date":"2019-11-04","year":2019,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-19-0118.1","openalex":"W2984819106"},"links":{"paper":"https://doi.org/10.1175/bams-d-19-0118.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/bams/101/3/bams-d-19-0118.1.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"operational","summary":"PDIR, a neural-network infrared precipitation algorithm with climatology-based dynamic rain-rate mapping, improves real-time estimates over the western CONUS, including atmospheric river events.","significance":4,"cited_by":66,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.isprsjprs.2019.10.002","title":"Statistical retrieval of atmospheric profiles with deep convolutional neural networks","authors":["David Malmgren-Hansen","Valero Laparra","Allan Aasbjerg Nielsen","Gustau Camps‐Valls"],"date":"2019-11-04","year":2019,"venue":"ISPRS Journal of Photogrammetry and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1016/j.isprsjprs.2019.10.002","openalex":"W2986750949"},"links":{"paper":"https://doi.org/10.1016/j.isprsjprs.2019.10.002"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["satellite","nwp-analysis"],"status":"research","summary":"Deep convolutional networks retrieve atmospheric profiles from satellite radiances as a statistical retrieval, though the abstract is unavailable.","significance":3,"cited_by":38,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1911.00630","title":"Predicting Weather Uncertainty with Deep Convnets","authors":["Peter Grönquist","Tal Ben-Nun","Nikoli Dryden","Peter Dueben","Luca Lavarini","Shigang Li","Torsten Hoefler"],"date":"2019-11-02","year":2019,"venue_type":"preprint","ids":{"arxiv":"1911.00630","openalex":"W2983145787"},"links":{"paper":"https://arxiv.org/abs/1911.00630","pdf":"https://arxiv.org/pdf/1911.00630"},"orgs":["ecmwf","eth-zurich"],"topic":"probabilistic-ensembles","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Deep 3D U-Net variants estimate weather forecast ensemble spread from a small set of numerical simulations, reducing the compute needed for uncertainty quantification.","significance":4,"cited_by":10,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-18-0195.1","title":"Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning","authors":["Amy McGovern","Ryan Lagerquist","David John Gagne","G. Eli Jergensen","Kimberly L. Elmore","Cameron R. Homeyer","Travis Smith"],"date":"2019-11-01","year":2019,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-18-0195.1","openalex":"W2969309273"},"links":{"paper":"https://doi.org/10.1175/bams-d-18-0195.1"},"orgs":["ncar","noaa","university-of-oklahoma"],"topic":"xai-uq-physics","topics":["extremes-hazards"],"type":"review","method":["classical-ml","cnn"],"timescale":[],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"Synthesizes ML interpretation methods such as saliency maps and permutation importance, demonstrated on tornado, hail and convective-mode applications.","significance":5,"cited_by":562,"score":75,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1126-sciadv.aau4996","title":"Detecting and quantifying causal associations in large nonlinear time series datasets","authors":["Jakob Runge","Peer Nowack","Marlene Kretschmer","Seth Flaxman","Dino Sejdinovic"],"date":"2019-11-01","year":2019,"venue":"Science Advances","venue_type":"journal","ids":{"arxiv":"1702.07007","doi":"10.1126/sciadv.aau4996","openalex":"W2593118993"},"links":{"paper":"https://doi.org/10.1126/sciadv.aau4996"},"orgs":["alan-turing-institute","pik","university-of-oxford"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Nonlinear causal discovery method estimates interdependency networks from large generic time series datasets.","significance":5,"cited_by":993,"score":70,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1109-jstars.2019.2952976","title":"Convective Initiation Nowcasting Over China From Fengyun-4A Measurements Based on TV-L 1 Optical Flow and BP_Adaboost Neural Network Algorithms","authors":["Fenglin Sun","Danyu Qin","Min Min","Bo Li","Fu Wang"],"date":"2019-11-01","year":2019,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2019.2952976","openalex":"W2996757245"},"links":{"paper":"https://doi.org/10.1109/jstars.2019.2952976"},"orgs":["cma"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Nowcasts convective initiation 17-40 minutes ahead from FY-4A satellite data using optical flow and BP-AdaBoost, reaching detection probability 0.80 in South China.","significance":3,"cited_by":16,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-019-52293-4","title":"Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data","authors":["J. Sakari Salonen","Mikko Korpela","John Warren Williams","Miska Luoto"],"date":"2019-11-01","year":2019,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-019-52293-4","openalex":"W2984135768"},"links":{"paper":"https://doi.org/10.1038/s41598-019-52293-4","pdf":"https://www.nature.com/articles/s41598-019-52293-4.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Tests boosted regression trees and neural networks for palaeoclimate reconstruction from fossil pollen, with a spatially blocked cross-validation scheme.","significance":3,"cited_by":88,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019ea000657","title":"Long‐Term Precipitation Estimates Generated by a Downscaling‐Calibration Procedure Over the Tibetan Plateau From 1983 to 2015","authors":["Ziqiang Ma","Darren J. Ghent","Xiao Tan","Kang He","H. Y. Li","Xiuzhen Han","Qin Huang","Jie Gang Peng"],"date":"2019-11-01","year":2019,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2019ea000657","openalex":"W2986658580"},"links":{"paper":"https://doi.org/10.1029/2019ea000657"},"orgs":["cma"],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Cubist regression downscales PERSIANN-CDR to 1 km and calibrates it, yielding 1983–2015 Tibetan Plateau precipitation with bias reduced from 41% to about 5%.","significance":2,"cited_by":13,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.26748-ksoe.2019.065","title":"Study on Prediction of Similar Typhoons through Neural Network Optimization","authors":["Yeon-Joong Kim","Tae-Woo Kim","Jong-Sung Yoon","Inho Kim"],"date":"2019-10-30","year":2019,"venue":"Journal of Ocean Engineering and Technology","venue_type":"journal","ids":{"doi":"10.26748/ksoe.2019.065","openalex":"W2982874382"},"links":{"paper":"https://doi.org/10.26748/ksoe.2019.065","pdf":"http://www.joet.org/upload/pdf/KSOE-2019-065.pdf"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Neural network optimisation for predicting similar typhoons; the abstract is only a generic AI sentence, so the contribution is unclear from the abstract.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.13767","title":"Nowcasting the turbulence at the Paranal Observatory","authors":["J. Milli","R. Gonzalez","P. R. Fluxa","A. Chacon","J. Navarette","M. Sarazin","E. Pena","R. Carrasco-Davis","A. Solarz","J. Smoker","C. Martayan","C. Melo","E. Sedaghati","S. Mieske","O. Hainaut","L. Tacconi-Garman"],"date":"2019-10-30","year":2019,"venue_type":"preprint","ids":{"arxiv":"1910.13767","openalex":"W2982476616"},"links":{"paper":"https://arxiv.org/abs/1910.13767","pdf":"https://arxiv.org/pdf/1910.13767"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning on Paranal monitoring data forecasts optical turbulence and seeing over the next two hours, a turbulence nowcasting study for VLT scheduling.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.13827","title":"Predicting Rainfall using Machine Learning Techniques","authors":["Nikhil Oswal"],"date":"2019-10-29","year":2019,"venue_type":"preprint","ids":{"arxiv":"1910.13827"},"links":{"paper":"https://arxiv.org/abs/1910.13827","pdf":"https://arxiv.org/pdf/1910.13827"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A comparison of standard machine learning classifiers predicts next-day rain in major Australian cities from station weather records, assessing inputs and preprocessing choices.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.13524","title":"Deep Integro-Difference Equation Models for Spatio-Temporal Forecasting","authors":["Andrew Zammit-Mangion","Christopher K. Wikle"],"date":"2019-10-29","year":2019,"venue":"Spatial Statistics","venue_type":"journal","ids":{"arxiv":"1910.13524","doi":"10.1016/j.spasta.2020.100408","openalex":"W2982441595"},"links":{"paper":"https://doi.org/10.1016/j.spasta.2020.100408","pdf":"https://arxiv.org/pdf/1910.13524"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"CNN-based deep integro-difference model with an ensemble Kalman filter gives calibrated SST forecasts and 10-minute Sydney radar nowcasts, reusing the ocean-trained model.","significance":3,"cited_by":48,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.13408","title":"A framework for deep learning emulation of numerical models with a case study in satellite remote sensing","authors":["Kate Duffy","Thomas Vandal","Weile Wang","Ramakrishna Nemani","Auroop R. Ganguly"],"date":"2019-10-29","year":2019,"venue":"IEEE Transactions on Neural Networks and Learning Systems","venue_type":"journal","ids":{"arxiv":"1910.13408","doi":"10.1109/tnnls.2022.3169958","openalex":"W4229023237"},"links":{"paper":"https://doi.org/10.1109/tnnls.2022.3169958","pdf":"https://arxiv.org/pdf/1910.13408"},"orgs":["nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Deep learning emulates a satellite remote-sensing surrogate model, reproducing its outputs with acceptable accuracy and often faster runtime than the surrogate.","significance":3,"cited_by":20,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11276-019-02168-3","title":"Study of short term rain forecasting using machine learning based approach","authors":["M. S. Balamurugan","R. Manojkumar"],"date":"2019-10-26","year":2019,"venue":"Wireless Networks","venue_type":"journal","ids":{"doi":"10.1007/s11276-019-02168-3","openalex":"W2981794663"},"links":{"paper":"https://doi.org/10.1007/s11276-019-02168-3"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning is applied to short-term rain forecasting; the abstract is missing, so the scope and results are unclear.","significance":1,"cited_by":37,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.12125","title":"Deep learning for subgrid-scale turbulence modeling in large-eddy simulations of the atmospheric boundary layer","authors":["Yu Cheng","Marco Giometto","Pit Kauffmann","Ling Lin","Chen Cao","Cody Zupnick","Harold Li","Qi Li","Ryan Abernathey","Pierre Gentine"],"date":"2019-10-26","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"1910.12125","doi":"10.1029/2021ms002847","openalex":"W2981871057"},"links":{"paper":"https://doi.org/10.1029/2021ms002847","pdf":"https://arxiv.org/pdf/1910.12125"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"Deep neural networks learn subgrid stresses from DNS of the atmospheric boundary layer, achieving higher correlation than Smagorinsky-based models across stability regimes and resolutions.","significance":4,"cited_by":36,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-isprs-archives-xlii-3-w9-89-2019","title":"AENN: A GENERATIVE ADVERSARIAL NEURAL NETWORK FOR WEATHER RADAR ECHO EXTRAPOLATION","authors":["Jinrui Jing","Qian Li","X. Y. Ding","Nengli Sun","R. Tang","Y. L. Cai"],"date":"2019-10-25","year":2019,"venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","venue_type":"journal","ids":{"doi":"10.5194/isprs-archives-xlii-3-w9-89-2019","openalex":"W2981732294"},"links":{"paper":"https://doi.org/10.5194/isprs-archives-xlii-3-w9-89-2019","pdf":"https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3-W9/89/2019/isprs-archives-XLII-3-W9-89-2019.pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A GAN with conditional generator and two discriminators extrapolates radar echoes 0.5 to 1.5 h ahead, reducing blur and outperforming baseline models.","significance":4,"cited_by":38,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.11736","title":"Machine learning of committor functions for predicting high impact climate events","authors":["Dario Lucente","Stefan Duffner","Corentin Herbert","Joran Rolland","Freddy Bouchet"],"date":"2019-10-25","year":2019,"venue":"Climate Informatics, Oct 2019, Paris, France","venue_type":"journal","ids":{"arxiv":"1910.11736"},"links":{"paper":"https://arxiv.org/abs/1910.11736","pdf":"https://arxiv.org/pdf/1910.11736"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Committor functions are shown to quantify intrinsic predictability of ENSO events in the Jin-Timmerman model, and neural-network inference of committors from data is compared to direct estimation.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-hydro.2019.084","title":"Nearshore two-step typhoon wind-wave prediction using deep recurrent neural networks","authors":["Chih‐Chiang Wei","Ju-Yueh Cheng"],"date":"2019-10-24","year":2019,"venue":"Journal of Hydroinformatics","venue_type":"journal","ids":{"doi":"10.2166/hydro.2019.084","openalex":"W2981339097"},"links":{"paper":"https://doi.org/10.2166/hydro.2019.084","pdf":"https://iwaponline.com/jh/article-pdf/22/2/346/666583/jh0220346.pdf"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Deep recurrent networks in a two-step model predict typhoon wind speed and wave height at a Taiwan buoy, beating a one-step wave-height baseline.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app9214487","title":"Gridded Visibility Products over Marine Environments Based on Artificial Neural Network Analysis","authors":["Yulong Shan","Ren Zhang","Ismail Gültepe","Yaojia Zhang","Ming Li","Yangjun Wang"],"date":"2019-10-23","year":2019,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app9214487","openalex":"W2981974467"},"links":{"paper":"https://doi.org/10.3390/app9214487","pdf":"https://www.mdpi.com/2076-3417/9/21/4487/pdf?version=1571837235"},"orgs":["eccc"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","nwp-analysis"],"status":"research","summary":"A neural network infers gridded marine surface visibility over the Indian Ocean from satellite optical thickness and reanalysis, with mean error under 8%.","significance":3,"cited_by":11,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.10566","title":"Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data","authors":["Sophie Giffard-Roisin","Mo Yang","Guillaume Charpiat","Christina Kumler-Bonfanti","Balázs Kégl","Claire Monteleoni"],"date":"2019-10-23","year":2019,"venue":"Frontiers in Big Data","venue_type":"journal","ids":{"arxiv":"1910.10566","doi":"10.3389/fdata.2020.00001","openalex":"W3002152246"},"links":{"paper":"https://doi.org/10.3389/fdata.2020.00001","pdf":"https://arxiv.org/pdf/1910.10566"},"orgs":["inria","noaa"],"topic":"extremes-hazards","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["era5","other"],"status":"research","summary":"A neural network fusing past storm trajectories with reanalysis wind and pressure fields forecasts 24 h tropical cyclone displacement in seconds, complementary to dynamical models.","significance":3,"cited_by":129,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-19-0109.1","title":"Postprocessing Next-Day Ensemble Probabilistic Precipitation Forecasts Using Random Forests","authors":["Eric D. Loken","Adam James Clark","Amy McGovern","Montgomery L. Flora","Kent H. Knopfmeier"],"date":"2019-10-17","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-19-0109.1","openalex":"W2981173151"},"links":{"paper":"https://doi.org/10.1175/waf-d-19-0109.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/34/6/waf-d-19-0109_1.pdf"},"orgs":["noaa","university-of-oklahoma"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Random forest calibrates 12–36 h SREF and HREFv2 precipitation ensembles over CONUS, improving reliability and Brier skill over raw and smoothed probabilities.","significance":4,"cited_by":37,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.08063","title":"Bayesian analysis of multifidelity computer models with local features and non-nested experimental designs: Application to the WRF model","authors":["Bledar A. Konomi","Karagiannis, Georgios"],"date":"2019-10-17","year":2019,"venue":"Technometrics","venue_type":"journal","ids":{"arxiv":"1910.08063","doi":"10.1080/00401706.2020.1855253","openalex":"W4288091500"},"links":{"paper":"https://doi.org/10.1080/00401706.2020.1855253","pdf":"https://arxiv.org/pdf/1910.08063"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A multi-fidelity Bayesian treed co-kriging emulator handles non-nested designs for WRF model output, giving full predictive distributions at each fidelity level.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41612-019-0094-4","title":"Robust observations of land-to-atmosphere feedbacks using the information flows of FLUXNET","authors":["Tobias Gerken","Benjamin L. Ruddell","Rong Yu","Paul C. Stoy","Darren T. Drewry"],"date":"2019-10-15","year":2019,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"doi":"10.1038/s41612-019-0094-4","openalex":"W2980523834"},"links":{"paper":"https://doi.org/10.1038/s41612-019-0094-4","pdf":"https://www.nature.com/articles/s41612-019-0094-4.pdf"},"orgs":["nasa"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other","stations"],"status":"research","summary":"Information-flow analysis of FLUXNET eddy-covariance sites with a neural network maps global land-atmosphere coupling, revealing hotspots and aridity dependence.","significance":3,"cited_by":52,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.07633","title":"Towards a Precipitation Bias Corrector against Noise and Maldistribution","authors":["Xiaoyang Xu","Yiqun Liu","Hanqing Chao","Youcheng Luo","Hai Chu","Lei Chen","Junping Zhang","Leiming Ma"],"date":"2019-10-15","year":2019,"venue_type":"preprint","ids":{"arxiv":"1910.07633","openalex":"W2980537980"},"links":{"paper":"https://arxiv.org/abs/1910.07633","pdf":"https://arxiv.org/pdf/1910.07633"},"orgs":["fudan-university"],"topic":"post-processing","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Expert-free denoising autoencoder with ordinal regression corrects ECMWF precipitation forecasts, outperforming classical ML and deep baselines on threat scores.","significance":3,"cited_by":6,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-12-4261-2019","title":"Fast domain-aware neural network emulation of a planetary boundary layer parameterization in a numerical weather forecast model","authors":["Jiali Wang","Prasanna Balaprakash","Veerabhadra Rao Kotamarthi"],"date":"2019-10-10","year":2019,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-12-4261-2019","openalex":"W2942924023"},"links":{"paper":"https://doi.org/10.5194/gmd-12-4261-2019","pdf":"https://gmd.copernicus.org/articles/12/4261/2019/gmd-12-4261-2019.pdf"},"orgs":["argonne"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Domain-aware deep neural network emulates a WRF planetary boundary layer scheme over the full diurnal cycle and transfers to nearby locations.","significance":4,"cited_by":61,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos10100613","title":"Downscaling Precipitation in the Data-Scarce Inland River Basin of Northwest China Based on Earth System Data Products","authors":["Jingping Zuo","Jianhua Xu","Yaning Chen","Chong Wang"],"date":"2019-10-10","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10100613","openalex":"W2979753329"},"links":{"paper":"https://doi.org/10.3390/atmos10100613","pdf":"https://www.mdpi.com/2073-4433/10/10/613/pdf?version=1571226661"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Statistical downscaling of monthly precipitation to 1 km for the Tarim River Basin, combining polynomial regression with batch gradient descent; it outperforms ordinary polynomial regression.","significance":3,"cited_by":20,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-02626667.2019.1677905","title":"A hybrid approach of artificial neural network and multiple regression to forecast typhoon rainfall and groundwater-level change","authors":["Ping‐Cheng Hsieh","Wei-An Tong","Yung‐Chieh Wang"],"date":"2019-10-08","year":2019,"venue":"Hydrological Sciences Journal","venue_type":"journal","ids":{"doi":"10.1080/02626667.2019.1677905","openalex":"W2979405346"},"links":{"paper":"https://doi.org/10.1080/02626667.2019.1677905","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/02626667.2019.1677905?needAccess=true&role=button"},"orgs":[],"topic":"extremes-hazards","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Hybrid ANN and multiple regression forecasts typhoon total rainfall and groundwater-level change in Taiwan's Zhuoshui basin, raising accuracy to about 80% from station data.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2019.2942280","title":"A Machine Learning System for Precipitation Estimation Using Satellite and Ground Radar Network Observations","authors":["Haonan Chen","V. Chandrasekar","Robert C. Cifelli","Pingping Xie"],"date":"2019-10-07","year":2019,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2019.2942280","openalex":"W2980276221"},"links":{"paper":"https://doi.org/10.1109/tgrs.2019.2942280"},"orgs":["noaa","colorado-state-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"An MLP fuses geostationary and LEO satellite data with dual-polarization ground radar to improve precipitation estimates over Dallas-Fort Worth.","significance":3,"cited_by":151,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11192303","title":"Multi-Channel Weather Radar Echo Extrapolation with Convolutional Recurrent Neural Networks","authors":["Quang-Khai Tran","Sa-Kwang Song"],"date":"2019-10-02","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11192303","openalex":"W2978043874"},"links":{"paper":"https://doi.org/10.3390/rs11192303","pdf":"https://www.mdpi.com/2072-4292/11/19/2303/pdf"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"A convolutional recurrent network for 3D radar echo extrapolation uses a per-channel output block to fix cross-channel contamination and shows gains from augmentation.","significance":3,"cited_by":52,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-zenodo.14911970","title":"MEAN SQUARED ERROR APPLIED IN BACK PROPAGATION FOR NON LINEAR RAINFALL PREDICTION","authors":["N Shobha","T Asha"],"date":"2019-10-01","year":2019,"venue":"Zenodo (CERN European Organization for Nuclear Research)","venue_type":"preprint","ids":{"doi":"10.5281/zenodo.14911970","openalex":"W3043540852"},"links":{"paper":"https://doi.org/10.5281/zenodo.14911970"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Multiple linear regression feeds a backpropagation neural network to forecast low, average and heavy rainfall at Bengaluru from five years of station data.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.enconman.2019.111799","title":"A review of deep learning for renewable energy forecasting","authors":["Huaizhi Wang","Zhenxing Lei","Xian Zhang","Bin Zhou","Jianchun Peng"],"date":"2019-10-01","year":2019,"venue":"Energy Conversion and Management","venue_type":"journal","ids":{"arxiv":"2019.11179","doi":"10.1016/j.enconman.2019.111799","openalex":"W2960560113"},"links":{"paper":"https://doi.org/10.1016/j.enconman.2019.111799"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Reviews deep learning for renewable energy forecasting, with the energy system rather than the atmosphere as main target.","significance":2,"cited_by":1199,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s13351-019-8162-6","title":"Forecasting Different Types of Convective Weather: A Deep Learning Approach","authors":["Kanghui Zhou","Yongguang Zheng","Бо Ли","Wansheng Dong","Xiaoling Zhang"],"date":"2019-10-01","year":2019,"venue":"气象学报：英文版","venue_type":"journal","ids":{"doi":"10.1007/s13351-019-8162-6","openalex":"W2985739459"},"links":{"paper":"https://doi.org/10.1007/s13351-019-8162-6"},"orgs":["cma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Deep learning approach to forecasting different convective weather types; the abstract is missing, so details are limited.","significance":2,"cited_by":126,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1910.00527","title":"A Three-dimensional Convolutional-Recurrent Network for Convective Storm Nowcasting","authors":["Wei Zhang","Wei Li","Lei Han"],"date":"2019-10-01","year":2019,"venue":"In 2019 IEEE International Conference on Big Knowledge (ICBK) (pp. 333-340) 2019","venue_type":"journal","ids":{"arxiv":"1910.00527","doi":"10.1109/icbk.2019.00052"},"links":{"paper":"https://arxiv.org/abs/1910.00527","pdf":"https://arxiv.org/pdf/1910.00527"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","nwp-analysis"],"status":"research","summary":"A hybrid 3D CNN and ConvLSTM encoder-decoder fuses radar and 3D re-analysis fields to nowcast convective storms, outperforming extrapolation baselines.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11192277","title":"Convective/Stratiform Precipitation Classification Using Ground-Based Doppler Radar Data Based on the K-Nearest Neighbor Algorithm","authors":["Zhida Yang","Peng Liu","Yi Yang"],"date":"2019-09-29","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11192277","openalex":"W2978764760"},"links":{"paper":"https://doi.org/10.3390/rs11192277","pdf":"https://www.mdpi.com/2072-4292/11/19/2277/pdf?version=1569755202"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"K-nearest neighbour classifies convective and stratiform rain from Doppler radar using TRMM labels, achieving 78% POD for convective and 95% for stratiform.","significance":2,"cited_by":22,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1061-asce-he.1943-5584.0001862","title":"Development of Precipitation Forecast Model Based on Artificial Intelligence and Subseasonal Clustering","authors":["Laleh Parviz","Kabir Rasouli"],"date":"2019-09-28","year":2019,"venue":"Journal of Hydrologic Engineering","venue_type":"journal","ids":{"doi":"10.1061/(asce)he.1943-5584.0001862","openalex":"W2976057303"},"links":{"paper":"https://doi.org/10.1061/(asce)he.1943-5584.0001862"},"orgs":[],"topic":"s2s-seasonal","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid clustering, ARIMA and neural network model forecasts subseasonal station precipitation, reducing RMSE by 24–48% versus seasonal ARIMA in Iran.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1909.11865","title":"Probabilistic Forecasting using Deep Generative Models","authors":["Alessandro Fanfarillo","Behrooz Roozitalab","Weiming Hu","Guido Cervone"],"date":"2019-09-26","year":2019,"venue":"GeoInformatica","venue_type":"journal","ids":{"arxiv":"1909.11865","doi":"10.1007/s10707-020-00425-8","openalex":"W2975726533"},"links":{"paper":"https://doi.org/10.1007/s10707-020-00425-8","pdf":"https://arxiv.org/pdf/1909.11865"},"orgs":["ncar"],"topic":"post-processing","topics":["probabilistic-ensembles"],"type":"model","method":["gan-vae"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Deep generative models replace stored archives in the analog ensemble method, cutting memory needs by orders of magnitude for probabilistic NWP post-processing at stations.","significance":3,"cited_by":25,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1909.11616","title":"Benchmarking Tropical Cyclone Rapid Intensification with Satellite Images and Attention-based Deep Models","authors":["Ching-Yuan Bai","Buo-Fu Chen","Hsuan-Tien Lin"],"date":"2019-09-25","year":2019,"venue_type":"preprint","ids":{"arxiv":"1909.11616"},"links":{"paper":"https://arxiv.org/abs/1909.11616","pdf":"https://arxiv.org/pdf/1909.11616"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"benchmark","method":["cnn","transformer"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Benchmark of satellite images for tropical cyclone rapid intensification, with an attention-based spatiotemporal model showing deep learning feasibility for RI prediction.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2019.2938204","title":"Tropical Cyclone Intensity Estimation Using Two-Branch Convolutional Neural Network From Infrared and Water Vapor Images","authors":["Rui Zhang","Qingshan Liu","Renlong Hang"],"date":"2019-09-24","year":2019,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2019.2938204","openalex":"W2976850564"},"links":{"paper":"https://doi.org/10.1109/tgrs.2019.2938204"},"orgs":["nuist"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A two-branch CNN estimates northwest Pacific tropical cyclone intensity from infrared and water vapour images, reaching RMSE 5.13 m/s with 60×60 pixel inputs.","significance":3,"cited_by":78,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jweia.2019.103983","title":"Knowledge-enhanced deep learning for simulation of tropical cyclone boundary-layer winds","authors":["Reda Snaiki","Teng Wu"],"date":"2019-09-19","year":2019,"venue":"Journal of Wind Engineering and Industrial Aerodynamics","venue_type":"journal","ids":{"doi":"10.1016/j.jweia.2019.103983","openalex":"W2974759324"},"links":{"paper":"https://doi.org/10.1016/j.jweia.2019.103983","pdf":"https://www.sciencedirect.com/science/article/am/pii/S0167610519305835?via%3Dihub"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":[],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Knowledge-enhanced deep learning emulates tropical cyclone boundary-layer wind fields; abstract unavailable, so assessment is based on the title.","significance":3,"cited_by":76,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41586-019-1559-7","title":"Deep learning for multi-year ENSO forecasts","authors":["Yoo-Geun Ham","Jeong-Hwan Kim","Jing-Jia Luo"],"date":"2019-09-18","year":2019,"venue":"Nature","venue_type":"journal","ids":{"doi":"10.1038/s41586-019-1559-7","openalex":"W2973731563"},"links":{"paper":"https://doi.org/10.1038/s41586-019-1559-7"},"orgs":["nuist"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Deep learning model trained on climate model simulations produces multi-year ENSO forecasts, a landmark result for long-lead ENSO prediction.","significance":7,"cited_by":1264,"score":78,"highlight":true,"highlight_reason":"Landmark Nature paper: CNN trained on climate simulations gives skilful ENSO forecasts up to 18 months ahead, influencing seasonal ML prediction.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos10090555","title":"Generative Adversarial Networks Capabilities for Super-Resolution Reconstruction of Weather Radar Echo Images","authors":["Hongguang Chen","Xing Zhang","Yintian Liu","Qiangyu Zeng"],"date":"2019-09-16","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10090555","openalex":"W2973508606"},"links":{"paper":"https://doi.org/10.3390/atmos10090555","pdf":"https://www.mdpi.com/2073-4433/10/9/555/pdf?version=1568886618"},"orgs":["cma"],"topic":"observations-remote-sensing","topics":["downscaling"],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"GAN-based super-resolution of degraded weather radar echo images produces sharper reconstructions with higher PSNR and SSIM than classical methods.","significance":3,"cited_by":38,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1909.07520","title":"Towards Unsupervised Segmentation of Extreme Weather Events","authors":["Adam Rupe","Karthik Kashinath","Nalini Kumar","Victor Lee","Prabhat","James P. Crutchfield"],"date":"2019-09-16","year":2019,"venue_type":"preprint","ids":{"arxiv":"1909.07520"},"links":{"paper":"https://arxiv.org/abs/1909.07520","pdf":"https://arxiv.org/pdf/1909.07520"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Physics-based unsupervised representation learning segments extreme weather structures in CAM5.1 water vapor climate model output, a route to identifying events without labels.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s19183988","title":"MLC-LSTM: Exploiting the Spatiotemporal Correlation between Multi-Level Weather Radar Echoes for Echo Sequence Extrapolation","authors":["Jinrui Jing","Qian Li","Xuan Peng"],"date":"2019-09-15","year":2019,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s19183988","openalex":"W2972792628"},"links":{"paper":"https://doi.org/10.3390/s19183988","pdf":"https://www.mdpi.com/1424-8220/19/18/3988/pdf?version=1568542173"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"MLC-LSTM with adversarial training extrapolates multi-level radar echoes, reaching average POD of about 0.65 for short-term echo forecasts.","significance":3,"cited_by":56,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1909.07786","title":"High Resolution Forecasting of Heat Waves impacts on Leaf Area Index by Multiscale Multitemporal Deep Learning","authors":["Andrea Gobbi","Marco Cristoforetti","Giuseppe Jurman","Cesare Furlanello"],"date":"2019-09-13","year":2019,"venue_type":"preprint","ids":{"arxiv":"1909.07786","openalex":"W2973908897"},"links":{"paper":"https://arxiv.org/abs/1909.07786","pdf":"https://arxiv.org/pdf/1909.07786"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["cnn"],"timescale":["medium"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Deep learning forecasts 300 m leaf area index 10 days ahead over Europe using weather inputs, aiming at heat-wave crop warnings; weather prediction itself is not ML.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3906-elk-1907-218","title":"Time series forecasting on multivariate solar radiation data using deep learning (LSTM)","authors":["Murat Cihan Sorkun","Özlem Durmaz İncel","Christophe Paoli"],"date":"2019-09-12","year":2019,"venue":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","venue_type":"journal","ids":{"doi":"10.3906/elk-1907-218","openalex":"W3004545085"},"links":{"paper":"https://doi.org/10.3906/elk-1907-218"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM with multivariate meteorological inputs forecasts one-hour global solar radiation, outperforming earlier univariate models.","significance":2,"cited_by":52,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3177246934","title":"Deep Learning-Based Tropical Cyclone Intensity Estimation Portal","authors":["Brian M. Freitag","Manil Maskey","Rahul Ramachandran","Muthukumaran Ramasubramanian","Iksha Gurung","Jon K. Miller"],"date":"2019-09-10","year":2019,"venue":"NASA Technical Reports Server (NASA)","venue_type":"preprint","ids":{"openalex":"W3177246934"},"links":{"paper":"https://ntrs.nasa.gov/api/citations/20190030780/downloads/20190030780.pdf"},"orgs":["nasa"],"topic":"extremes-hazards","topics":["infra-software"],"type":"application","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Describes a deep-learning portal for estimating tropical cyclone intensity; no abstract is available, so the detail is limited.","significance":2,"cited_by":0,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1909.04711","title":"Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model","authors":["David John Gagne","Hannah M. Christensen","Aneesh C. Subramanian","Adam H. Monahan"],"date":"2019-09-10","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"1909.04711","doi":"10.1029/2019ms001896","openalex":"W3007927169"},"links":{"paper":"https://doi.org/10.1029/2019ms001896","pdf":"https://arxiv.org/pdf/1909.04711"},"orgs":["ncar","university-of-oxford"],"topic":"hybrid-parameterization","topics":["probabilistic-ensembles"],"type":"model","method":["gan-vae"],"timescale":["medium","climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Trains a GAN as a stochastic sub-grid parameterization for the Lorenz '96 model; some configurations beat a bespoke scheme at weather and climate timescales.","significance":4,"cited_by":190,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-wene.365","title":"The future of forecasting for renewable energy","authors":["Conor Sweeney","Ricardo J. Bessa","Jethro Browell","Pierre Pinson"],"date":"2019-09-09","year":2019,"venue":"WIREs Energy and Environment","venue_type":"journal","ids":{"doi":"10.1002/wene.365","openalex":"W2972425174"},"links":{"paper":"https://doi.org/10.1002/wene.365"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Reviews wind and solar energy forecasting; ML is not a main contribution and the focus is on energy.","significance":2,"cited_by":297,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-rs11182087","title":"Nighttime Reflectance Generation in the Visible Band of Satellites","authors":["Kimoon Kim","Ji-Hye Kim","Yong‐Jae Moon","Eunsu Park","Gyungin Shin","Taeyoung Kim","Yerin Kim","Sungwook Hong"],"date":"2019-09-06","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11182087","openalex":"W2972430292"},"links":{"paper":"https://doi.org/10.3390/rs11182087","pdf":"https://www.mdpi.com/2072-4292/11/18/2087/pdf?version=1567763089"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A conditional GAN generates nighttime visible-band COMS/MI satellite images from infrared data, reaching correlation 0.88 with observed images in summer.","significance":3,"cited_by":32,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019gl083662","title":"Improving Atmospheric River Forecasts With Machine Learning","authors":["W. E. Chapman","A. C. Subramanian","L. Delle Monache","S. P. Xie","F. M. Ralph"],"date":"2019-09-06","year":2019,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2019gl083662","openalex":"W2970999468"},"links":{"paper":"https://doi.org/10.1029/2019gl083662"},"orgs":[],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["short","medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A CNN postprocesses GFS integrated vapor transport forecasts, cutting RMSE by 9-17% from 3 hours to 7 days and improving atmospheric river forecasts over the western US.","significance":4,"cited_by":90,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1038-s41598-019-49281-z","title":"Improving seasonal forecasts of air temperature using a genetic algorithm","authors":["J. V. Ratnam","Henk A. Dijkstra","Takeshi Doi","Yushi Morioka","Masami Nonaka","Swadhin Kumar Behera"],"date":"2019-09-04","year":2019,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-019-49281-z","openalex":"W2971767930"},"links":{"paper":"https://doi.org/10.1038/s41598-019-49281-z","pdf":"https://www.nature.com/articles/s41598-019-49281-z.pdf"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A genetic algorithm learns optimal weights for 24 SINTEX-F2 ensemble members, significantly improving boreal summer 2m air temperature anomaly forecasts over several regions versus the unweighted mean.","significance":3,"cited_by":15,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-19-0048.1","title":"Intelligent Wind Retrieval from Chinese Gaofen-3 SAR Imagery in Quad Polarization","authors":["Weizeng Shao","Shuai Zhu","Xiaopeng Zhang","Shuiping Gou","Changzhe Jiao","Xinzhe Yuan","Liangbo Zhao"],"date":"2019-09-03","year":2019,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-19-0048.1","openalex":"W2972024752"},"links":{"paper":"https://doi.org/10.1175/jtech-d-19-0048.1"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Neural network retrieves ocean surface wind speed from Gaofen-3 quad-polarization SAR, reaching 0.74 m/s RMSE versus 0.88 m/s for CMOD7.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1909.00912","title":"Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems","authors":["Tom Beucler","Michael Pritchard","Stephan Rasp","Jordan Ott","Pierre Baldi","Pierre Gentine"],"date":"2019-09-03","year":2019,"venue":"Phys. Rev. Lett. 126, 098302 (2021)","venue_type":"journal","ids":{"arxiv":"1909.00912","doi":"10.1103/physrevlett.126.098302","openalex":"W2971940059"},"links":{"paper":"https://arxiv.org/abs/1909.00912","pdf":"https://arxiv.org/pdf/1909.00912"},"orgs":["columbia-leap","tum"],"topic":"xai-uq-physics","topics":[],"type":"model","method":["physics-constrained","other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Architectural and loss-based constraints make neural emulators of convection conserve physical laws to machine precision without degrading accuracy.","significance":4,"cited_by":446,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.22214-ijraset.2019.8139","title":"Advanced Weather Forecasting Prediction using Deep Learning","authors":["Arasada Subashini"],"date":"2019-08-31","year":2019,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2019.8139","openalex":"W2981018562"},"links":{"paper":"https://doi.org/10.22214/ijraset.2019.8139","pdf":"https://doi.org/10.22214/ijraset.2019.8139"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM networks trained on NCDC station variables to predict weather conditions, with no quantitative skill reported in the abstract.","significance":1,"cited_by":10,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3929-ethz-b-000398592","title":"Applying Machine Learning Methods to the Assessment of Tropical Cyclone Impacts","authors":["Samuel Lüthi"],"date":"2019-08-30","year":2019,"venue":"Repository for Publications and Research Data (ETH Zurich)","venue_type":"preprint","ids":{"doi":"10.3929/ethz-b-000398592","openalex":"W3005673182"},"links":{"paper":"https://doi.org/10.3929/ethz-b-000398592"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Thesis-style work applying machine learning to tropical cyclone impact assessment; the abstract is unavailable, so scope and results are unclear.","significance":1,"cited_by":9,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijeat.f9390.088619","title":"Soft Computing Research For Weather Prediction Using Multilayer Architecture","authors":["S. Sheik Mohideen Shah*","Sathiskumar Meganathan","A. Kamali"],"date":"2019-08-30","year":2019,"venue":"International Journal of Engineering and Advanced Technology","venue_type":"journal","ids":{"doi":"10.35940/ijeat.f9390.088619","openalex":"W4212766393"},"links":{"paper":"https://doi.org/10.35940/ijeat.f9390.088619"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Feed-forward neural network predicts rainfall from time series for agriculture and drought or flood warning, with no quantitative results given.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1908.11051","title":"Data-based wind disaster climate identification algorithm and extreme wind speed prediction","authors":["Wei Cui","Teng Ma","Lin Zhao","Yaojun Ge"],"date":"2019-08-29","year":2019,"venue_type":"preprint","ids":{"arxiv":"1908.11051"},"links":{"paper":"https://arxiv.org/abs/1908.11051","pdf":"https://arxiv.org/pdf/1908.11051"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Pattern-recognition algorithm identifies mixed wind hazard climate types from station records, then recalculates extreme wind speeds and design return periods for southeast China.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1908.10964","title":"Distributed Deep Learning for Precipitation Nowcasting","authors":["Siddharth Samsi","Christopher J. Mattioli","Mark S. Veillette"],"date":"2019-08-28","year":2019,"venue_type":"preprint","ids":{"arxiv":"1908.10964","doi":"10.1109/hpec.2019.8916416"},"links":{"paper":"https://arxiv.org/abs/1908.10964","pdf":"https://arxiv.org/pdf/1908.10964"},"orgs":[],"topic":"nowcasting","topics":["infra-software"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Data-parallel CNN training across GPUs cuts precipitation nowcasting training time from 59 hours to about one hour.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-19-0063.1","title":"Using a Coevolutionary Postprocessor to Improve Skill for Both Forecasts of Surface Temperature and Nowcasts of Convection Occurrence","authors":["Paul J. Roebber","John G. Crockett"],"date":"2019-08-27","year":2019,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-19-0063.1","openalex":"W2970087552"},"links":{"paper":"https://doi.org/10.1175/mwr-d-19-0063.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/mwre/147/11/mwr-d-19-0063.1.pdf"},"orgs":["noaa","colorado-state-university"],"topic":"post-processing","topics":["nowcasting"],"type":"model","method":["other"],"timescale":["short","nowcast"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Coevolutionary evolutionary-programming postprocessor improves 72-h surface temperature forecasts and 60-min convection nowcasts over bias-corrected NWP and logistic regression.","significance":4,"cited_by":2,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-019-01721-y","title":"Machine learning for downscaling: the use of parallel multiple populations in genetic programming","authors":["Dhanapala Arachchige Sachindra","Shinjiro Kanae"],"date":"2019-08-27","year":2019,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-019-01721-y","openalex":"W2970789506"},"links":{"paper":"https://doi.org/10.1007/s00477-019-01721-y","pdf":"https://link.springer.com/content/pdf/10.1007/s00477-019-01721-y.pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Parallel multi-population genetic programming downscales large-scale predictors to daily station Tmin and Tmax, generalising better than single-deme GP with fewer outliers.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijitee.j9607.0881019","title":"A Novel Method of Rainfall Prediction using MLP-FFN and Hybrid Neural Network Algorithm","authors":["G. Thailambal","Ms. P. Shanmugalakshmi","R. Durga"],"date":"2019-08-24","year":2019,"venue":"International Journal of Innovative Technology and Exploring Engineering","venue_type":"journal","ids":{"doi":"10.35940/ijitee.j9607.0881019","openalex":"W4245804322"},"links":{"paper":"https://doi.org/10.35940/ijitee.j9607.0881019"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Hybrid clustering and neural-network model claims superiority over MLP feed-forward networks for rainfall prediction, with no quantitative results given.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-019-9023-z","title":"A Model Output Machine Learning Method for Grid Temperature Forecasts in the Beijing Area","authors":["Haochen Li","Yu Chen","Jiangjiang Xia","Yingchun Wang","Jiang Zhu","Pingwen Zhang"],"date":"2019-08-20","year":2019,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-019-9023-z","openalex":"W2969752514"},"links":{"paper":"https://doi.org/10.1007/s00376-019-9023-z"},"orgs":["iap-cas"],"topic":"post-processing","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Machine learning post-processing of model output to produce grid-point temperature forecasts for the Beijing area.","significance":2,"cited_by":62,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s19163611","title":"Seasonal Time Series Forecasting by F1-Fuzzy Transform","authors":["Ferdinando Di Martino","Salvatore Sessa"],"date":"2019-08-19","year":2019,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s19163611","openalex":"W2967463374"},"links":{"paper":"https://doi.org/10.3390/s19163611","pdf":"https://www.mdpi.com/1424-8220/19/16/3611/pdf?version=1566373348"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Proposes a fuzzy-transform seasonal forecaster for station heat index in Campania, Italy, outperforming ARIMA and ANN baselines; the ML contribution is modest.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019ms001705","title":"Can Machines Learn to Predict Weather? Using Deep Learning to Predict Gridded 500‐hPa Geopotential Height From Historical Weather Data","authors":["Jonathan A. Weyn","Dale R. Durran","Rich Caruana"],"date":"2019-08-17","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2019ms001705","openalex":"W2963973018"},"links":{"paper":"https://doi.org/10.1029/2019ms001705"},"orgs":["microsoft-research","university-of-washington"],"topic":"global-medium-range","topics":[],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"CNNs forecast 500-hPa geopotential height up to 14 days, beating persistence and barotropic vorticity model but not the operational NWP model.","significance":5,"cited_by":346,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1002-met.1826","title":"Prediction of the ENSO and EQUINOO indices during June–September using a deep learning method","authors":["Moumita Saha","Ravi Shankar Nanjundiah"],"date":"2019-08-15","year":2019,"venue":"Meteorological Applications","venue_type":"journal","ids":{"doi":"10.1002/met.1826","openalex":"W2967174540"},"links":{"paper":"https://doi.org/10.1002/met.1826","pdf":"https://rmets.onlinelibrary.wiley.com/doi/pdfdirect/10.1002/met.1826"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["other","classical-ml"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Autoencoder features with regression trees predict the EQUINOO index 7 months ahead (r=0.88) and ENSO 1 month ahead (r=0.87).","significance":3,"cited_by":16,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.7232-jkiie.2019.45.4.349","title":"Predicting Maximum Wind Speed of Typhoons based on Convolutional Recurrent Neural Network via COMS Satellite Data","authors":["Minhyung Lee","Soobong Lee","Jung-Hwan Lee","Sung Won Han"],"date":"2019-08-11","year":2019,"venue":"Journal of Korean Institute of Industrial Engineers","venue_type":"journal","ids":{"doi":"10.7232/jkiie.2019.45.4.349","openalex":"W2968147280"},"links":{"paper":"https://doi.org/10.7232/jkiie.2019.45.4.349"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["rnn","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Uses a CNN-LSTM on COMS satellite channels to estimate typhoon maximum wind speed, reaching 9.84 knot RMSE with the WV channel.","significance":3,"cited_by":2,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijrte.b1117.0782s319","title":"Deep Learning in Data Science","authors":["UJ Exam Papers Admin"],"date":"2019-08-10","year":2019,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.b1117.0782s319","openalex":"W4255933109"},"links":{"paper":"https://doi.org/10.35940/ijrte.b1117.0782s319","pdf":"https://doi.org/10.35940/ijrte.b1117.0782s319"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Short review of deep learning models for climate and weather prediction, claiming accuracy gains over statistical methods without quantitative results.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijrte.b1109.0782s319","title":"Rainfall Prediction using Apriori Algorithm","authors":[],"date":"2019-08-10","year":2019,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.b1109.0782s319","openalex":"W4247780588"},"links":{"paper":"https://doi.org/10.35940/ijrte.b1109.0782s319","pdf":"https://doi.org/10.35940/ijrte.b1109.0782s319"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Apriori association-rule mining on Chennai rainfall data claims about 95% accuracy for rainfall occurrence, with no independent validation described.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijrte.b1098.0782s319","title":"Rainfall Prediction using Regression Model","authors":[],"date":"2019-08-10","year":2019,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.b1098.0782s319","openalex":"W4238312258"},"links":{"paper":"https://doi.org/10.35940/ijrte.b1098.0782s319","pdf":"https://doi.org/10.35940/ijrte.b1098.0782s319"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Linear regression on temperature, humidity and wind predicts monthly rainfall from one area's historical records, claimed to beat traditional systems without numbers.","significance":1,"cited_by":19,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w11081653","title":"Optimized Artificial Neural Networks-Based Methods for Statistical Downscaling of Gridded Precipitation Data","authors":["Amir Hossein Salimi","Jafar Masoompour Samakosh","Ehsan Sharifi","Mohammad Reza Hassanvand","Amir Noori","Hary von Rautenkranz"],"date":"2019-08-10","year":2019,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w11081653","openalex":"W2968363666"},"links":{"paper":"https://doi.org/10.3390/w11081653","pdf":"https://www.mdpi.com/2073-4441/11/8/1653/pdf?version=1565423751"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Neural networks optimized by PSO, ICA and GA downscale satellite precipitation over Austria, with ICA best and RMSE of 5.26 mm against 54 rain gauges.","significance":3,"cited_by":33,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00521-019-04410-7","title":"Deep-PHURIE: deep learning based hurricane intensity estimation from infrared satellite imagery","authors":["Muhammad Dawood","Amina Asif","Fayyaz Minhas"],"date":"2019-08-09","year":2019,"venue":"Neural Computing and Applications","venue_type":"journal","ids":{"doi":"10.1007/s00521-019-04410-7","openalex":"W2968114327"},"links":{"paper":"https://doi.org/10.1007/s00521-019-04410-7"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Deep-PHURIE uses deep learning to estimate hurricane intensity from infrared satellite imagery; the abstract is unavailable, so accuracy is unknown.","significance":2,"cited_by":51,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.3635","title":"Extreme precipitation events over northern Italy. Part I: A systematic classification with machine‐learning techniques","authors":["Federico Grazzini","George C. Craig","Christian Keil","Gabriele Antolini","Valentina Pavan"],"date":"2019-08-08","year":2019,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.3635","openalex":"W2969209290"},"links":{"paper":"https://doi.org/10.1002/qj.3635","pdf":"https://rmets.onlinelibrary.wiley.com/doi/pdfdirect/10.1002/qj.3635"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations","era5"],"status":"research","summary":"Classifies 887 northern Italian extreme precipitation events into three dynamical classes using K-means and random forests, with integrated water vapour transport as key predictor.","significance":3,"cited_by":83,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-19-0013.1","title":"A Climatological Analysis of Tropical Cyclone Rapid Intensification in Environments of Upper-Tropospheric Troughs","authors":["Michael S. Fischer","Brian H. Tang","Kristen L. Corbosiero"],"date":"2019-08-05","year":2019,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-19-0013.1","openalex":"W2966654050"},"links":{"paper":"https://doi.org/10.1175/mwr-d-19-0013.1"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"K-means clustering of upper-tropospheric troughs shows rapid intensification is more likely with shorter-wavelength troughs and cutoff lows 500–1000 km southwest of the storm.","significance":2,"cited_by":41,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2985507087","title":"Klasifikasi Intensitas Angin Siklon Tropis Pada Citra Inframerah Satelit Menggunakan Metode Svm","authors":["Adam Agus Kurniawan","Koredianto Usman","R Yunendah Nur Fuadah"],"date":"2019-08-01","year":2019,"venue":"eProceedings of Engineering","venue_type":"journal","ids":{"openalex":"W2985507087"},"links":{"paper":"https://openlibrarypublications.telkomuniversity.ac.id/index.php/engineering/article/view/10624"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Classifies tropical cyclone intensity from infrared satellite images using GLCM texture features and an SVM, reaching 88% accuracy against the Saffir-Simpson scale.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2963960945","title":"Using Machine Learning Applications and HREFv2 to Enhance Hail Prediction for Operations","authors":["Amanda L. Burke"],"date":"2019-08-01","year":2019,"venue":"SHAREOK (University of Oklahoma; Oklahoma State University; Central Oklahoma University)","venue_type":"preprint","ids":{"openalex":"W2963960945"},"links":{"paper":"https://hdl.handle.net/11244/320425","pdf":"https://hdl.handle.net/11244/320425"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"research","summary":"Random forests post-processing HREFv2 ensembles with isotonic calibration give severe hail probabilities comparable to SPC outlooks over CONUS.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-cp-2019-91","title":"A comprehensive history of climate and habitat stability of the last 800&thinsp,000 years","authors":["Mario Krapp","Robert M. Beyer","Stephen L. Edmundson","Paul J. Valdes","Andrea Manica"],"date":"2019-08-01","year":2019,"venue_type":"other","ids":{"doi":"10.5194/cp-2019-91","openalex":"W2965488363"},"links":{"paper":"https://doi.org/10.5194/cp-2019-91","pdf":"https://cp.copernicus.org/preprints/cp-2019-91/cp-2019-91.pdf"},"orgs":["university-of-cambridge"],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Statistical emulator GCMET reconstructs global climate over the last 800,000 years at high spatial detail, revealing stable habitat refugia.","significance":3,"cited_by":0,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019eo129967","title":"Artificial Intelligence May Be Key to Better Weather Forecasts","authors":["Sid‐Ahmed Boukabara","Vladimir M. Krasnopolsky","Jebb Q. Stewart","Stephen Gregory Penny","Ross N. Hoffman","Eric S. Maddy"],"date":"2019-08-01","year":2019,"venue":"Eos","venue_type":"journal","ids":{"doi":"10.1029/2019eo129967","openalex":"W2965850099"},"links":{"paper":"https://doi.org/10.1029/2019eo129967"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"position","method":[],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Perspective piece arguing that machine learning could turn weather data into faster, more accurate and more detailed forecasts.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.solener.2019.06.041","title":"Short-term solar power forecast with deep learning: Exploring optimal input and output configuration","authors":["Yuchi Sun","Vignesh Venugopal","Adam R. Brandt"],"date":"2019-08-01","year":2019,"venue":"Solar Energy","venue_type":"journal","ids":{"doi":"10.1016/j.solener.2019.06.041","openalex":"W2955010283"},"links":{"paper":"https://doi.org/10.1016/j.solener.2019.06.041"},"orgs":["stanford"],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Explores deep learning input and output configurations for short-term solar power forecasts; the target is energy output rather than weather.","significance":1,"cited_by":196,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s11554-019-00899-2","title":"A real-time typhoon eye detection method based on deep learning for meteorological information forensics","authors":["Liling Zhao","Yifei Chen","Victor S. Sheng"],"date":"2019-08-01","year":2019,"venue":"Journal of Real-Time Image Processing","venue_type":"journal","ids":{"doi":"10.1007/s11554-019-00899-2","openalex":"W2966715221"},"links":{"paper":"https://doi.org/10.1007/s11554-019-00899-2"},"orgs":["nuist"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Real-time deep learning detector locates typhoon eyes in images for meteorological information; the abstract is unavailable, so accuracy is unknown.","significance":2,"cited_by":20,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.35940-ijrte.b2078.078219","title":"Prediction and Validation of Rainfall Classes for Vaigai River Catchment using El Nino","authors":["Mahadevan Palanichamy","Ramaswamy Sankaralingam Narayanasamy"],"date":"2019-07-30","year":2019,"venue":"International Journal of Recent Technology and Engineering (IJRTE)","venue_type":"journal","ids":{"doi":"10.35940/ijrte.b2078.078219","openalex":"W4235653382"},"links":{"paper":"https://doi.org/10.35940/ijrte.b2078.078219"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Quadratic discriminant analysis and neural networks classify Vaigai catchment rainfall classes from ENSO indices over 1959–2016 at seven rain gauges.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019gl083646","title":"Single‐Column Emulation of Reanalysis of the Northeast Pacific Marine Boundary Layer","authors":["Jeremy McGibbon","Christopher S. Bretherton"],"date":"2019-07-29","year":2019,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2019gl083646","openalex":"W2965752768"},"links":{"paper":"https://doi.org/10.1029/2019gl083646","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2019GL083646"},"orgs":["university-of-washington"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"A neural network trained prognostically on ERA5 emulates northeast Pacific boundary-layer tendencies in single-column runs over 7-day periods, outperforming the underlying forecast model in tracking reanalysis.","significance":4,"cited_by":14,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1093-comjnl-bxz087","title":"Study on Data Transfer in Meteorological Forecast of Small and Medium-Sized Cities and Its Application in Zhaoqing City","authors":["Tianwen Huang","Fei Jiao"],"date":"2019-07-28","year":2019,"venue":"The Computer Journal","venue_type":"journal","ids":{"doi":"10.1093/comjnl/bxz087","openalex":"W2973161963"},"links":{"paper":"https://doi.org/10.1093/comjnl/bxz087"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Instance-based transfer learning borrows records from neighboring cities to extend scarce station data for temperature and precipitation forecasts in Zhaoqing, China.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1907.12013","title":"Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow","authors":["Thomas Vandal","Ramakrishna Nemani"],"date":"2019-07-28","year":2019,"venue_type":"preprint","ids":{"arxiv":"1907.12013"},"links":{"paper":"https://arxiv.org/abs/1907.12013","pdf":"https://arxiv.org/pdf/1907.12013"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Deep optical-flow interpolation upsamples GOES-R ABI imagery from 15 to 1 minute, improving severe-weather temporal resolution over baselines.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2019.259","title":"Efficacy of hybrid neural networks in statistical downscaling of precipitation of the Bagmati River basin","authors":["K. Vinoth Kumar","V. P. Singh","Thendiyath Roshni"],"date":"2019-07-26","year":2019,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2019.259","openalex":"W2966345212"},"links":{"paper":"https://doi.org/10.2166/wcc.2019.259"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml","other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Feed-forward and wavelet neural networks statistically downscale GCM predictors to Bagmati basin precipitation, projecting 2014–2036 decreases at the study sites.","significance":2,"cited_by":14,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2019.2926776","title":"A Generative Adversarial Gated Recurrent Unit Model for Precipitation Nowcasting","authors":["Lin Tian","Xutao Li","Yunming Ye","Pengfei Xie","Yan Li"],"date":"2019-07-26","year":2019,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2019.2926776","openalex":"W2965679379"},"links":{"paper":"https://doi.org/10.1109/lgrs.2019.2926776"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Generative adversarial ConvGRU model produces sharper radar echo extrapolations than ConvGRU and optical flow for precipitation nowcasting.","significance":3,"cited_by":131,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1907.11617","title":"Analog forecasting of extreme-causing weather patterns using deep learning","authors":["Ashesh Chattopadhyay","Ebrahim Nabizadeh","Pedram Hassanzadeh"],"date":"2019-07-26","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"1907.11617","doi":"10.1029/2019ms001958","openalex":"W2965580012"},"links":{"paper":"https://arxiv.org/abs/1907.11617","pdf":"https://arxiv.org/pdf/1907.11617"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Capsule networks on Z500 patterns predict North American heat and cold waves 1-5 days ahead, beating CNNs and logistic regression with about 80% accuracy when temperature is added.","significance":4,"cited_by":224,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-waf-d-18-0206.1","title":"Using a 10-Year Radar Archive for Nowcasting Precipitation Growth and Decay: A Probabilistic Machine Learning Approach","authors":["Loris Foresti","Ioannis Vasileios Sideris","Daniele Nerini","Lea Beusch","Urs Germann"],"date":"2019-07-25","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-18-0206.1","openalex":"W2963511153"},"links":{"paper":"https://doi.org/10.1175/waf-d-18-0206.1"},"orgs":["meteoswiss","eth-zurich"],"topic":"nowcasting","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Neural networks and quantile trees nowcast precipitation growth and decay in Swiss Alps radar archive, with persistence inputs cutting RMSE by 20-30% in mountains.","significance":3,"cited_by":60,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-18-0141.1","title":"Quasi-Operational Testing of Real-Time Storm-Longevity Prediction via Machine Learning","authors":["Amy McGovern","Christopher D. Karstens","Travis M. Smith","Ryan Lagerquist"],"date":"2019-07-25","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-18-0141.1","openalex":"W2963292962"},"links":{"paper":"https://doi.org/10.1175/waf-d-18-0141.1"},"orgs":["noaa","university-of-oklahoma"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"pre-operational","summary":"Random forests, boosted trees and elastic nets predict storm longevity in NWS quasi-operational testing, with lower error than human forecasters.","significance":4,"cited_by":11,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.neucom.2019.07.058","title":"A gated recurrent unit neural networks based wind speed error correction model for short-term wind power forecasting","authors":["Min Ding","Hao Zhou","Hua Xie","Min Wu","Yosuke Nakanishi","Ryuichi Yokoyama"],"date":"2019-07-25","year":2019,"venue":"Neurocomputing","venue_type":"journal","ids":{"doi":"10.1016/j.neucom.2019.07.058","openalex":"W2963599060"},"links":{"paper":"https://doi.org/10.1016/j.neucom.2019.07.058"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"GRU-based correction of wind speed forecast errors to improve short-term wind power forecasting.","significance":2,"cited_by":193,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11151741","title":"Retrieval of Total Precipitable Water from Himawari-8 AHI Data: A Comparison of Random Forest, Extreme Gradient Boosting, and Deep Neural Network","authors":["Yeonjin Lee","Daehyeon Han","Myoung‐Hwan Ahn","Jungho Im","Su Jeong Lee"],"date":"2019-07-24","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11151741","openalex":"W2962768350"},"links":{"paper":"https://doi.org/10.3390/rs11151741","pdf":"https://www.mdpi.com/2072-4292/11/15/1741/pdf?version=1565231693"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","era5","stations"],"status":"research","summary":"Compares random forest, XGBoost and a deep neural network for retrieving total precipitable water from Himawari-8 infrared channels; the DNN performs best against radiosondes.","significance":3,"cited_by":68,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1907.09725","title":"VARENN: Graphical representation of spatiotemporal data and application to climate studies","authors":["Takeshi Ise","Yurika Oba"],"date":"2019-07-23","year":2019,"venue":"npj Climate and Atmospheric Science","venue_type":"journal","ids":{"arxiv":"1907.09725","doi":"10.1038/s41612-020-0129-x","openalex":"W2963482216"},"links":{"paper":"https://doi.org/10.1038/s41612-020-0129-x","pdf":"https://arxiv.org/pdf/1907.09725"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Encodes multi-variable monthly climate series as RGB images and uses CNNs to classify temperature and precipitation rises and falls over 1901-2016.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1907.08069","title":"Precipitation Nowcasting with Star-Bridge Networks","authors":["Yuan Cao","Qiuying Li","Hongming Shan","Zhizhong Huang","Lei Chen","Leiming Ma","Junping Zhang"],"date":"2019-07-18","year":2019,"venue_type":"preprint","ids":{"arxiv":"1907.08069","openalex":"W2991204001"},"links":{"paper":"https://arxiv.org/abs/1907.08069","pdf":"https://arxiv.org/pdf/1907.08069"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"StarBriNet, an RNN with sub-networks per rainfall intensity and a star-shaped bridge, improves radar-based precipitation nowcasting over prior methods.","significance":3,"cited_by":17,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-12-3017-2019","title":"Reducing climate model biases by exploring parameter space with large ensembles of climate model simulations and statistical emulation","authors":["Sihan Li","David E. Rupp","Linnia Hawkins","Philip W. Mote","Doug McNeall","Sarah Sparrow","David C. H. Wallom","Richard Betts","J. J. Wettstein"],"date":"2019-07-17","year":2019,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-12-3017-2019","openalex":"W2957277828"},"links":{"paper":"https://doi.org/10.5194/gmd-12-3017-2019","pdf":"https://gmd.copernicus.org/articles/12/3017/2019/gmd-12-3017-2019.pdf"},"orgs":["met-office","university-of-oxford"],"topic":"climate-emulation","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Statistical emulators built from perturbed-physics ensembles iteratively tune weather@home parameters, cutting northwestern US warm biases by 74%.","significance":3,"cited_by":17,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-18-0316.1","title":"Interpretable Deep Learning for Spatial Analysis of Severe Hailstorms","authors":["David John Gagne II","Sue Ellen Haupt","Douglas W. Nychka","Gregory Thompson"],"date":"2019-07-17","year":2019,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-18-0316.1","openalex":"W2947707259"},"links":{"paper":"https://doi.org/10.1175/mwr-d-18-0316.1"},"orgs":["ncar"],"topic":"extremes-hazards","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"A CNN outperforms logistic regression at predicting severe hail from convection-allowing NWP fields, and interpretation reveals learned storm and environment features consistent with hail physics.","significance":4,"cited_by":216,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1907.05720","title":"Wind Estimation Using Quadcopter Motion: A Machine Learning Approach","authors":["Sam Allison","He Bai","Balaji Jayaraman"],"date":"2019-07-11","year":2019,"venue_type":"preprint","ids":{"arxiv":"1907.05720"},"links":{"paper":"https://arxiv.org/abs/1907.05720","pdf":"https://arxiv.org/pdf/1907.05720"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["rnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"An LSTM estimates atmospheric wind from quadcopter motion without a wind sensor, with lower errors than the wind-triangle method in simulated turbulence.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-12-2797-2019","title":"Weather and climate forecasting with neural networks: using general circulation models (GCMs) with different complexity as a study ground","authors":["Sebastian Scher","Gabriele Messori"],"date":"2019-07-10","year":2019,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-12-2797-2019","openalex":"W2956255334"},"links":{"paper":"https://doi.org/10.5194/gmd-12-2797-2019"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"evaluation","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural networks trained on simple GCMs (PUMA, PLASIM) forecast weather for a few days, with skill depending on model complexity and training length.","significance":3,"cited_by":169,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1907.04816","title":"A Data-Driven Approach for Accurate Rainfall Prediction","authors":["Shilpa Manandhar","Soumyabrata Dev","Yee Hui Lee","Yu Song Meng","Stefan Winkler"],"date":"2019-07-10","year":2019,"venue_type":"preprint","ids":{"arxiv":"1907.04816","doi":"10.1109/tgrs.2019.2926110"},"links":{"paper":"https://arxiv.org/abs/1907.04816","pdf":"https://arxiv.org/pdf/1907.04816"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Identifies PWV, solar radiation and seasonal/diurnal features as key predictors and uses them in an ML classifier, reaching 79.6% accuracy for rainfall prediction.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-lgrs.2019.2922326","title":"Learning to Generate Radar Image Sequences Using Two-Stage Generative Adversarial Networks","authors":["Chenyang Zhang","Xuebing Yang","Yongqiang Tang","Wensheng Zhang"],"date":"2019-07-07","year":2019,"venue":"IEEE Geoscience and Remote Sensing Letters","venue_type":"journal","ids":{"doi":"10.1109/lgrs.2019.2922326","openalex":"W2953596889"},"links":{"paper":"https://doi.org/10.1109/lgrs.2019.2922326"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Two-stage GANs generate synthetic radar reflectivity sequences for extreme precipitation in Shenzhen to address class imbalance in radar QPE.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1907.01351","title":"Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations","authors":["Stephan Rasp"],"date":"2019-07-02","year":2019,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"1907.01351","doi":"10.5194/gmd-2019-319","openalex":"W3000537280"},"links":{"paper":"https://doi.org/10.5194/gmd-13-2185-2020","pdf":"https://arxiv.org/pdf/1907.01351","code":"https://github.com/raspstephan/Lorenz-Online"},"orgs":["tum"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":[],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Proposes coupled online learning, where a neural parameterization runs alongside a high-resolution simulation with nudging, to reduce instabilities and biases; illustrated on Lorenz 96.","significance":5,"cited_by":115,"score":50,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1063-1.5110223","title":"Predicting day-ahead solar irradiance through gated recurrent unit using weather forecasting data","authors":["Bixuan Gao","Xiaoqiao Huang","Junsheng Shi","Yonghang Tai","Rui Xiao"],"date":"2019-07-01","year":2019,"venue":"Journal of Renewable and Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1063/1.5110223","openalex":"W2969305200"},"links":{"paper":"https://doi.org/10.1063/1.5110223"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"GRU combined with weather forecasts predicts 24-hour-ahead solar irradiance, cutting RMSE 11.9% versus RNN and 23.3% versus backpropagation.","significance":2,"cited_by":51,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1907.00662","title":"Short-term prediction of Electricity Outages Caused by Convective Storms","authors":["Roope Tervo","Joonas Karjalainen","Alexander Jung"],"date":"2019-07-01","year":2019,"venue_type":"preprint","ids":{"arxiv":"1907.00662","doi":"10.1109/tgrs.2019.2921809"},"links":{"paper":"https://arxiv.org/abs/1907.00662","pdf":"https://arxiv.org/pdf/1907.00662"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml","cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"Tracks radar-identified convective storm cells and classifies their power-outage damage potential with random forests and deep networks on imbalanced data.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33564-ijeast.2019.v04i02.010","title":"IMAGE BASED WEATHER AND TEMPERATURE ANALYSIS SYSTEM","authors":["Ashlin Francis","S Vineetha"],"date":"2019-06-30","year":2019,"venue":"International Journal of Engineering Applied Sciences and Technology","venue_type":"journal","ids":{"doi":"10.33564/ijeast.2019.v04i02.010","openalex":"W2962386652"},"links":{"paper":"https://doi.org/10.33564/ijeast.2019.v04i02.010","pdf":"https://doi.org/10.33564/ijeast.2019.v04i02.010"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN classifies weather conditions into six classes from photographs and derives temperature estimates from class scores; the approach is not benchmarked.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22214-ijraset.2019.6373","title":"An Integrated Approach for Weather Predictions using Machine Learning Technique","authors":["U A Manjushri"],"date":"2019-06-30","year":2019,"venue":"International Journal for Research in Applied Science and Engineering Technology","venue_type":"journal","ids":{"doi":"10.22214/ijraset.2019.6373","openalex":"W2979483098"},"links":{"paper":"https://doi.org/10.22214/ijraset.2019.6373","pdf":"https://doi.org/10.22214/ijraset.2019.6373"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Decision-tree model predicts five-day weather using machine learning as an alternative to physics-based forecasting; little methodological novelty.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25073-2588-1094-vnuees.4379","title":"Seasonal Predictions of the Number of Tropical Cyclones in the Vietnam East Sea Using Statistical Models","authors":["Ba Duy Dinh","Thanh Ngo‐Duc","Tran Quang Duc","Phan Van Tan"],"date":"2019-06-29","year":2019,"venue":"VNU Journal of Science Earth and Environmental Sciences","venue_type":"journal","ids":{"doi":"10.25073/2588-1094/vnuees.4379","openalex":"W2953524633"},"links":{"paper":"https://doi.org/10.25073/2588-1094/vnuees.4379","pdf":"https://js.vnu.edu.vn/EES/article/download/4379/3966"},"orgs":[],"topic":"s2s-seasonal","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Regression and ANN models forecast Vietnam East Sea tropical cyclone counts six months ahead; multiple linear regression performed best on independent data.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-03610918.2019.1615625","title":"A comparison of GSTAR-SUR models and a hybrid GSTAR-SUR/neural network model on residuals of precipitation forecasting","authors":["Atiek Iriany","Diana Rosyida","Arifin Arifin"],"date":"2019-06-27","year":2019,"venue":"Communications in Statistics - Simulation and Computation","venue_type":"journal","ids":{"doi":"10.1080/03610918.2019.1615625","openalex":"W2954957447"},"links":{"paper":"https://doi.org/10.1080/03610918.2019.1615625"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid GSTAR-SUR with neural network residual model improves 10-day precipitation forecasts at four West Java stations, reducing mean error from 4.33 to 3.89 mm.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2019gl082532","title":"Reconstruction of Cloud Vertical Structure With a Generative Adversarial Network","authors":["Jussi Leinonen","Alexandre Guillaume","Tianle Yuan"],"date":"2019-06-24","year":2019,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2019gl082532","openalex":"W2947589767"},"links":{"paper":"https://doi.org/10.1029/2019gl082532"},"orgs":["caltech","nasa"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"A conditional GAN reconstructs CloudSat-style cloud vertical structure from MODIS inputs, capturing multilayer clouds and providing uncertainty estimates.","significance":4,"cited_by":69,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-atmos10060341","title":"Using eXtreme Gradient BOOSTing to Predict Changes in Tropical Cyclone Intensity over the Western North Pacific","authors":["Qingwen Jin","Xiangtao Fan","Jian Liu","Zhuxin Xue","Hongdeng Jian"],"date":"2019-06-22","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10060341","openalex":"W2952174131"},"links":{"paper":"https://doi.org/10.3390/atmos10060341","pdf":"https://www.mdpi.com/2073-4433/10/6/341/pdf?version=1561198927"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"XGBoost predicts Western North Pacific tropical cyclone intensity changes at 6–24 h lead times, with lower MAE than a back-propagation network.","significance":2,"cited_by":35,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.09492","title":"Extended-range statistical ENSO prediction through operator-theoretic techniques for nonlinear dynamics","authors":["Xinyang Wang","Joanna Slawinska","Dimitrios Giannakis"],"date":"2019-06-22","year":2019,"venue":"Scientific Reports","venue_type":"journal","ids":{"arxiv":"1906.09492","doi":"10.1038/s41598-020-59128-7","openalex":"W3006164137"},"links":{"paper":"https://doi.org/10.1038/s41598-020-59128-7","pdf":"https://arxiv.org/pdf/1906.09492"},"orgs":["nyu-m2lines"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other","cmip"],"status":"research","summary":"Kernel analog forecasting, a Koopman-based nonparametric method, predicts Nino 3.4 out to 10 months, 3-7 months beyond a linear inverse model.","significance":5,"cited_by":40,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.08829","title":"Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM","authors":["Ashesh Chattopadhyay","Pedram Hassanzadeh","Devika Subramanian"],"date":"2019-06-20","year":2019,"venue":"Nonlin. Processes Geophys. 2020","venue_type":"journal","ids":{"arxiv":"1906.08829","doi":"10.5194/npg-27-373-2020"},"links":{"paper":"https://arxiv.org/abs/1906.08829","pdf":"https://arxiv.org/pdf/1906.08829"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"evaluation","method":["rnn","classical-ml"],"timescale":["short","climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Compares echo state networks, feed-forward ANNs and LSTMs on a multi-scale Lorenz 96 system; reservoir computing forecasts hundreds of steps and matches PDF tails.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-18-0201.1","title":"Prediction of Tropical Cyclone Genesis from Mesoscale Convective Systems Using Machine Learning","authors":["Tao Zhang","Wuyin Lin","Yanluan Lin","Minghua Zhang","Haiyang Yu","Kathy Cao","Wei Xue"],"date":"2019-06-18","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-18-0201.1","openalex":"W2950840445"},"links":{"paper":"https://doi.org/10.1175/waf-d-18-0201.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/34/4/waf-d-18-0201_1.pdf"},"orgs":["tsinghua-university"],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":[],"status":"research","summary":"AdaBoost classifies whether mesoscale convective systems become tropical cyclones, reaching 97.2% F1 at 6 h lead and beating the genesis potential index.","significance":4,"cited_by":44,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.06786","title":"Recovering the parameters underlying the Lorenz-96 chaotic dynamics","authors":["Soukayna Mouatadid","Pierre Gentine","Wei Yu","Steve Easterbrook"],"date":"2019-06-16","year":2019,"venue_type":"preprint","ids":{"arxiv":"1906.06786","openalex":"W2952808964"},"links":{"paper":"https://arxiv.org/abs/1906.06786","pdf":"https://arxiv.org/pdf/1906.06786"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Convolutional networks recover Lorenz-96 parameters from chaotic dynamics, a proxy for objectively inferring cloud parameterization constants in climate models.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.06622","title":"Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling","authors":["Tom Beucler","Stephan Rasp","Michael Pritchard","Pierre Gentine"],"date":"2019-06-15","year":2019,"venue_type":"preprint","ids":{"arxiv":"1906.06622","openalex":"W2950193666"},"links":{"paper":"https://arxiv.org/abs/1906.06622","pdf":"https://arxiv.org/pdf/1906.06622"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Architecture-level enforcement of linear energy and mass conservation in neural cloud emulators reaches numerical precision and improves generalization to warmer climates.","significance":6,"cited_by":93,"score":24,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-12-3183-2019","title":"A high-speed particle phase discriminator (PPD-HS) for the classification of airborne particles, as tested in a continuous flow diffusion chamber","authors":["Fabian Mahrt","Jörg Wieder","Remo Dietlicher","Helen R. Smith","Chris Stopford","Zamin Abdulali Kanji"],"date":"2019-06-14","year":2019,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-12-3183-2019","openalex":"W2915616476"},"links":{"paper":"https://doi.org/10.5194/amt-12-3183-2019","pdf":"https://amt.copernicus.org/articles/12/3183/2019/amt-12-3183-2019.pdf"},"orgs":["eth-zurich"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"An optical instrument uses a random forest to classify cloud particle phase, achieving under 5% misclassification above 3 µm in lab tests.","significance":2,"cited_by":10,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-18-0183.1","title":"Deep Learning for Spatially Explicit Prediction of Synoptic-Scale Fronts","authors":["Ryan Lagerquist","Amy McGovern","David John Gagne"],"date":"2019-06-13","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-18-0183.1","openalex":"W2950210192"},"links":{"paper":"https://doi.org/10.1175/waf-d-18-0183.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/34/4/waf-d-18-0183_1.pdf"},"orgs":["ncar","university-of-oklahoma"],"topic":"climate-analysis-attribution","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"pre-operational","summary":"CNN with a novel probability-to-object step detects synoptic warm and cold fronts in reanalysis grids, achieving 0.73 probability of detection at 250 km.","significance":3,"cited_by":124,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.04436","title":"Metrics for Learning in Topological Persistence","authors":["Henri Riihimäki","José Licón-Saláiz"],"date":"2019-06-11","year":2019,"venue_type":"preprint","ids":{"arxiv":"1906.04436"},"links":{"paper":"https://arxiv.org/abs/1906.04436","pdf":"https://arxiv.org/pdf/1906.04436"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Contour-based stable rank metrics from topological persistence produce descriptors that characterize spatial patterns of atmospheric cloud fields.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11111378","title":"Geographically Weighted Machine Learning and Downscaling for High-Resolution Spatiotemporal Estimations of Wind Speed","authors":["Lianfa Li"],"date":"2019-06-10","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11111378","openalex":"W2949545510"},"links":{"paper":"https://doi.org/10.3390/rs11111378"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Geographically weighted ensemble of ML learners plus residual-network downscaling of reanalysis yields high-resolution wind speed over China, improving R2 by 12–16%.","significance":3,"cited_by":70,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32622-ijrat.75201952","title":"Implication of Machine Learning towards Weather Prediction","authors":["Shivangi Raj","Deepak Arora","Pooja Khanna"],"date":"2019-06-10","year":2019,"venue":"International Journal of Research in Advent Technology","venue_type":"journal","ids":{"doi":"10.32622/ijrat.75201952","openalex":"W2971482715"},"links":{"paper":"https://doi.org/10.32622/ijrat.75201952","pdf":"https://doi.org/10.32622/ijrat.75201952"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Python workflow pulls open weather API data to forecast five days ahead at three-hour intervals; the machine learning contribution is minimal.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.05433","title":"Tackling Climate Change with Machine Learning","authors":["David Rolnick","Priya L. Donti","Lynn H. Kaack","Kelly Kochanski","Alexandre Lacoste","Kris Sankaran","Andrew Slavin Ross","Nikola Milojevic-Dupont","Natasha Jaques","Anna Waldman-Brown","Alexandra Luccioni","Tegan Maharaj","Evan D. Sherwin","S. Karthik Mukkavilli","Konrad P. Kording","Carla Gomes","Andrew Y. Ng","Demis Hassabis","John C. Platt","Felix Creutzig","Jennifer Chayes","Yoshua Bengio"],"date":"2019-06-10","year":2019,"venue":"ACM Computing Surveys","venue_type":"journal","ids":{"arxiv":"1906.05433","doi":"10.1145/3485128","openalex":"W4210916416"},"links":{"paper":"https://arxiv.org/abs/1906.05433","pdf":"https://arxiv.org/pdf/1906.05433"},"orgs":["eth-zurich","google-deepmind","google-research","lbnl-nersc","mit","nyu-m2lines","stanford","uc-berkeley"],"topic":"applications-impacts","topics":[],"type":"position","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Position paper surveying how machine learning can help climate change mitigation and adaptation across sectors such as energy and disaster management; not focused on weather or climate science.","significance":6,"cited_by":1027,"score":79,"highlight":true,"highlight_reason":"Highly cited agenda-setting survey that mobilised the ML community toward climate problems; broad rather than technically weather-specific.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1906.03479","title":"Learning Radiative Transfer Models for Climate Change Applications in Imaging Spectroscopy","authors":["Shubhankar Deshpande","Brian D. Bue","David R. Thompson","Vijay Natraj","Mario Parente"],"date":"2019-06-08","year":2019,"venue_type":"preprint","ids":{"arxiv":"1906.03479"},"links":{"paper":"https://arxiv.org/abs/1906.03479","pdf":"https://arxiv.org/pdf/1906.03479"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["local"],"data":["satellite","other"],"status":"research","summary":"Neural-network emulators of radiative transfer models speed up imaging-spectroscopy retrievals for greenhouse gas and coral reef monitoring by a multifold factor.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-18-0173.1","title":"A Feed Forward Neural Network Based on Model Output Statistics for Short-Term Hurricane Intensity Prediction","authors":["Kirkwood A. Cloud","Brian J. Reich","Christopher M. Rozoff","Stefano Alessandrini","William E. Lewis","Luca Delle Monache"],"date":"2019-06-05","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-18-0173.1","openalex":"W2948119210"},"links":{"paper":"https://doi.org/10.1175/waf-d-18-0173.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/34/4/waf-d-18-0173_1.pdf"},"orgs":["ncar"],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Feed-forward network on HWRF output beats operational intensity guidance at 24–57 h in cross-validation and quadruples rapid-intensification hits.","significance":4,"cited_by":60,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-dac.3999","title":"Estimating rainfall using machine learning strategies based on weather radar data","authors":["T. Aditya Sai Srinivas","Somula Ramasubbareddy","K. Govinda","Akriti Saxena","A. Pramod Reddy"],"date":"2019-06-05","year":2019,"venue":"International Journal of Communication Systems","venue_type":"journal","ids":{"doi":"10.1002/dac.3999","openalex":"W2975537862"},"links":{"paper":"https://doi.org/10.1002/dac.3999"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"LSTM and RNN models predict hourly rainfall levels from weather radar sequences, compared with random forest and XGBoost; gains are not quantified in the abstract.","significance":2,"cited_by":26,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.01906","title":"Combining crowd-sourcing and deep learning to explore the meso-scale organization of shallow convection","authors":["Stephan Rasp","Hauke Schulz","Sandrine Bony","Bjorn Stevens"],"date":"2019-06-05","year":2019,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"arxiv":"1906.01906","doi":"10.1175/bams-d-19-0324.1","openalex":"W2948614949"},"links":{"paper":"https://arxiv.org/abs/1906.01906","pdf":"https://arxiv.org/pdf/1906.01906"},"orgs":["mpi-meteorology","tum"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":[],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Crowd-labelled about 50,000 shallow cloud clusters in satellite images to train deep learning that maps four organization patterns and builds global climatologies.","significance":4,"cited_by":93,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.9756-iajse-v6i1-1910001","title":"Probabilistic Quantitative Precipitation Forecasting Using Machine Learning Methods and Probable Maximum Precipitation","authors":["Xaniyar Asgari-Motlagh","Mehdi Ketabchy","Ali Daghighi"],"date":"2019-06-04","year":2019,"venue":"International Academic Journal of Science and Engineering","venue_type":"journal","ids":{"doi":"10.9756/iajse/v6i1/1910001","openalex":"W2989216760"},"links":{"paper":"https://doi.org/10.9756/iajse/v6i1/1910001"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Probabilistic quantitative precipitation forecasting combining machine learning with probable maximum precipitation; abstract not available, so classification is low-confidence.","significance":1,"cited_by":6,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10015-019-00540-2","title":"El Niño-Southern Oscillation forecasting using complex networks analysis of LSTM neural networks","authors":["Clifford Broni-Bedaiko","Ferdinand Apietu Katsriku","Tatsuo Unemi","Masayasu Atsumi","Jamal‐Deen Abdulai","Norihiko Shinomiya","Ebenezer Owusu"],"date":"2019-06-04","year":2019,"venue":"Artificial Life and Robotics","venue_type":"journal","ids":{"doi":"10.1007/s10015-019-00540-2","openalex":"W2948315246"},"links":{"paper":"https://doi.org/10.1007/s10015-019-00540-2"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn"],"timescale":["seasonal"],"spatial":["global"],"data":[],"status":"research","summary":"LSTM networks analysed with complex-network methods are applied to ENSO forecasting; the abstract is missing, so results cannot be assessed.","significance":2,"cited_by":54,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11111334","title":"SMOS Neural Network Soil Moisture Data Assimilation in a Land Surface Model and Atmospheric Impact","authors":["Nemesio Jose Rodríguez-Fernández","Patricia de Rosnay","Clément Albergel","Philippe Richaume","Filipe Aires","Catherine Prigent","Yann H. Kerr"],"date":"2019-06-03","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11111334","openalex":"W2937513445"},"links":{"paper":"https://doi.org/10.3390/rs11111334"},"orgs":["ecmwf","meteo-france"],"topic":"data-assimilation","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":["satellite","stations","nwp-analysis"],"status":"research","summary":"Neural-network soil moisture retrievals from SMOS are assimilated into ECMWF's land model, improving Southern Hemisphere and some Northern Hemisphere forecasts through atmospheric feedback.","significance":3,"cited_by":74,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-18-0391.1","title":"Using Deep Learning to Estimate Tropical Cyclone Intensity from Satellite Passive Microwave Imagery","authors":["Anthony Wimmers","Christopher Velden","Joshua H. Cossuth"],"date":"2019-06-01","year":2019,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-18-0391.1","openalex":"W2932915765"},"links":{"paper":"https://doi.org/10.1175/mwr-d-18-0391.1"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"DeepMicroNet, a CNN on passive microwave satellite imagery, estimates tropical cyclone intensity with 9.6-14.3 kt RMSE, matching known best-track biases.","significance":3,"cited_by":166,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.21575-25254782rmetg2019vol4n3856","title":"PREDICTION OF OCCURRENCE OF CLOUD-TO-GROUND ELECTRICAL DISCHARGES USING FORECASTS OF THE BRAMS NUMERICAL MODEL","authors":["Alex de Almeida Fernandes","Glauston Roberto Teixeira de Lima","Stephan Stephany","Alan J. P. Calheiros"],"date":"2019-05-30","year":2019,"venue":"Revista Mundi Engenharia Tecnologia e Gestão","venue_type":"journal","ids":{"doi":"10.21575/25254782rmetg2019vol4n3856","openalex":"W2947199859"},"links":{"paper":"https://doi.org/10.21575/25254782rmetg2019vol4n3856"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","other"],"status":"research","summary":"Neural networks trained on past BRAMS forecasts and lightning density fields predict cloud-to-ground discharge occurrence as an ancillary convective-alert tool.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-iet-rpg.2018.5917","title":"Data‐driven wind speed forecasting using deep feature extraction and LSTM","authors":["Yu‐Xi Wu","Qingbiao Wu","Jia‐Qi Zhu"],"date":"2019-05-30","year":2019,"venue":"IET Renewable Power Generation","venue_type":"journal","ids":{"doi":"10.1049/iet-rpg.2018.5917","openalex":"W2947870382"},"links":{"paper":"https://doi.org/10.1049/iet-rpg.2018.5917"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn","classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Stacked denoising autoencoder features with LSTM improve South African wind speed forecasts by 17% over benchmarks, with NWP data cleaned by clustering.","significance":2,"cited_by":110,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jeconom.2019.05.005","title":"Statistical approximation of high-dimensional climate models","authors":["Alena Miftakhova","Kenneth L. Judd","Thomas S. Lontzek","Karl H. Schmedders"],"date":"2019-05-30","year":2019,"venue":"Journal of Econometrics","venue_type":"journal","ids":{"doi":"10.1016/j.jeconom.2019.05.005","openalex":"W2566847903"},"links":{"paper":"https://doi.org/10.1016/j.jeconom.2019.05.005","pdf":"https://www.sciencedirect.com/science/article/pii/S0304407619301083/pdf"},"orgs":["stanford"],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Low-dimensional statistical emulator of the MAGICC climate model, built from designed CO2 scenarios, gives out-of-sample temperature errors below 2%.","significance":2,"cited_by":9,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.13290","title":"Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network","authors":["Jennifer L Cardona","Michael F Howland","John O Dabiri"],"date":"2019-05-30","year":2019,"venue":"Advances in Neural Information Processing Systems 32 (2019)","venue_type":"journal","ids":{"arxiv":"1905.13290","openalex":"W2947259654"},"links":{"paper":"https://arxiv.org/abs/1905.13290","pdf":"https://arxiv.org/pdf/1905.13290"},"orgs":["caltech","stanford"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn","rnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Coupled CNN-RNN estimates local wind speed (0.75-11 m/s) from video of flags and trees, matching cup anemometer measurements.","significance":3,"cited_by":23,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.10653","title":"Gaussian Process Regression for Estimating EM Ducting Within the Marine Atmospheric Boundary Layer","authors":["Hilarie Sit","Christopher J. Earls"],"date":"2019-05-25","year":2019,"venue_type":"preprint","ids":{"arxiv":"1905.10653","doi":"10.1029/2019rs006890"},"links":{"paper":"https://arxiv.org/abs/1905.10653","pdf":"https://arxiv.org/pdf/1905.10653"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies Gaussian process regression to infer marine boundary layer electromagnetic duct height from radar propagation factors, including noisy-input handling.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2945740654","title":"High accuracy Philippine landfall prediction of Pacific cyclones at their genesis using neural networks","authors":["Roland Albert A. Romero","Giovanni Alarkon Tapang","Caesar A. Saloma"],"date":"2019-05-24","year":2019,"venue":"Proceedings of the Samahang Pisika ng Pilipinas","venue_type":"journal","ids":{"openalex":"W2945740654"},"links":{"paper":"https://paperview.spp-online.org/proceedings/article/view/SPP-2019-3F-01"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A three-layer backpropagation network predicts whether a West Pacific tropical cyclone will make Philippine landfall at genesis, with 91% accuracy at 54 hours.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-12-2033-2019","title":"Calculating the turbulent fluxes in the atmospheric surface layer with neural networks","authors":["Lukas Hubert Leufen","Gerd Schädler"],"date":"2019-05-24","year":2019,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-12-2033-2019","openalex":"W2901415630"},"links":{"paper":"https://doi.org/10.5194/gmd-12-2033-2019","pdf":"https://gmd.copernicus.org/articles/12/2033/2019/gmd-12-2033-2019.pdf"},"orgs":["kit","juelich"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"A one-hidden-layer neural network replaces Monin–Obukhov stability functions for surface-layer fluxes, matching the standard method at seven flux sites.","significance":3,"cited_by":18,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.09932","title":"Precipitation Nowcasting with Satellite Imagery","authors":["Vadim Lebedev","Vladimir Ivashkin","Irina Rudenko","Alexander Ganshin","Alexander Molchanov","Sergey Ovcharenko","Ruslan Grokhovetskiy","Ivan Bushmarinov","Dmitry Solomentsev"],"date":"2019-05-23","year":2019,"venue":"in Proceedings of The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2019","venue_type":"journal","ids":{"arxiv":"1905.09932","doi":"10.1145/3292500.3330762"},"links":{"paper":"https://arxiv.org/abs/1905.09932","pdf":"https://arxiv.org/pdf/1905.09932"},"orgs":[],"topic":"nowcasting","topics":[],"type":"application","method":[],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"operational","summary":"Yandex develops satellite-imagery-based precipitation nowcasting, extending coverage beyond radar regions and deployed in the Yandex.Weather map and alerts.","significance":3,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.09614","title":"Learning the Representations of Moist Convection with Convolutional Neural Networks","authors":["Shih-Wen Tsou","Chun-Yian Su","Chien-Ming Wu"],"date":"2019-05-23","year":2019,"venue_type":"preprint","ids":{"arxiv":"1905.09614","openalex":"W2946694328"},"links":{"paper":"https://arxiv.org/abs/1905.09614","pdf":"https://arxiv.org/pdf/1905.09614"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"CNN predicts moist convection effects on the environment at grey-zone resolution, using horizontal gradients, as a potential replacement for conventional cumulus parameterization.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-019-04818-w","title":"Event selection for dynamical downscaling: a neural network approach for physically-constrained precipitation events","authors":["Juan José Gómez‐Navarro","Christoph Cornelius Raible","Juan Andrés García Valero","Martina Messmer","Juan Pedro Montávez","Olivia Martius"],"date":"2019-05-21","year":2019,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-019-04818-w","openalex":"W2945681256"},"links":{"paper":"https://doi.org/10.1007/s00382-019-04818-w","pdf":"https://link.springer.com/content/pdf/10.1007/s00382-019-04818-w.pdf"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"Neural network selects physically constrained precipitation events to make dynamical downscaling of climate simulations more efficient; abstract unavailable.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.08700","title":"Artificial Intelligence Based Cloud Distributor (AI-CD): Probing Low Cloud Distribution with a Conditional Generative Adversarial Network","authors":["Tianle Yuan"],"date":"2019-05-21","year":2019,"venue_type":"preprint","ids":{"arxiv":"1905.08700"},"links":{"paper":"https://arxiv.org/abs/1905.08700","pdf":"https://arxiv.org/pdf/1905.08700"},"orgs":[],"topic":"hybrid-parameterization","topics":["observations-remote-sensing"],"type":"model","method":["gan-vae","cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Conditional GAN generates realistic MODIS marine low cloud reflectance fields from large-scale variables, proposed as a stochastic cloud parameterization for sub-grid cloud distributions.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11101195","title":"Machine Learning Approaches for Detecting Tropical Cyclone Formation Using Satellite Data","authors":["Minsang Kim","Myung‐Sook Park","Jungho Im","Seonyoung Park","Myong‐In Lee"],"date":"2019-05-20","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11101195","openalex":"W2946064216"},"links":{"paper":"https://doi.org/10.3390/rs11101195","pdf":"https://www.mdpi.com/2072-4292/11/10/1195/pdf"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Random forest, decision tree and SVM detect western North Pacific tropical cyclone formation from WindSat with 94–96% hit rates, 26–30 h early.","significance":3,"cited_by":86,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018gl081646","title":"Using Deep Neural Networks as Cost‐Effective Surrogate Models for Super‐Parameterized E3SM Radiative Transfer","authors":["Anikesh Pal","Salil Mahajan","Matthew Ross Norman"],"date":"2019-05-20","year":2019,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2018gl081646","openalex":"W2945963864"},"links":{"paper":"https://doi.org/10.1029/2018gl081646","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018GL081646"},"orgs":["ornl"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep neural networks emulate SP-E3SM shortwave and longwave radiation with 90–95% accuracy at 8–10 times lower cost than the original scheme.","significance":4,"cited_by":91,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.07892","title":"Learning Ensembles of Anomaly Detectors on Synthetic Data","authors":["D. Smolyakov","N. Sviridenko","V. Ishimtsev","E. Burikov","E. Burnaev"],"date":"2019-05-20","year":2019,"venue":"16th International Symposium on Neural Networks, ISNN 2019","venue_type":"journal","ids":{"arxiv":"1905.07892"},"links":{"paper":"https://arxiv.org/abs/1905.07892","pdf":"https://arxiv.org/pdf/1905.07892"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"pre-operational","summary":"Builds an ensemble of anomaly detectors with adaptive thresholds for meteorological station time series, integrated into a road weather information system.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.07700","title":"FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting","authors":["Chao Tan","Xin Feng","Jianwu Long","Li Geng"],"date":"2019-05-19","year":2019,"venue":"IEEE Conference of Visual Communications and Image Processing 2018","venue_type":"journal","ids":{"arxiv":"1905.07700"},"links":{"paper":"https://arxiv.org/abs/1905.07700","pdf":"https://arxiv.org/pdf/1905.07700"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Proposes FORECAST-CLSTM, a hierarchical ConvLSTM with a new forecaster loss for predicting infrared satellite cloud images, evaluated on a 40K-image dataset.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2019.05.010","title":"Application of machine learning to large hail prediction - The importance of radar reflectivity, lightning occurrence and convective parameters derived from ERA5","authors":["Bartosz Czernecki","Mateusz Taszarek","Michał Marosz","Marek Półrolniczak","Leszek Kolendowicz","Andrzej A. Wyszogrodzki","Jan Szturc"],"date":"2019-05-17","year":2019,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2019.05.010","openalex":"W2945435533"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2019.05.010"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["era5","radar"],"status":"research","summary":"Applies machine learning with ERA5 convective parameters and radar reflectivity to predict large hail, highlighting which predictors matter most.","significance":3,"cited_by":105,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.07366","title":"Stratospheric Aerosol Injection as a Deep Reinforcement Learning Problem","authors":["Christian Schroeder de Witt","Thomas Hornigold"],"date":"2019-05-17","year":2019,"venue_type":"preprint","ids":{"arxiv":"1905.07366","openalex":"W2945353373"},"links":{"paper":"https://arxiv.org/abs/1905.07366","pdf":"https://arxiv.org/pdf/1905.07366"},"orgs":[],"topic":"climate-emulation","topics":["applications-impacts"],"type":"model","method":["reinforcement-learning"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Frames stratospheric aerosol injection as deep reinforcement learning, using a deep-learning emulator of HadCM3 as the training environment; presented as a first DRL application in climate science.","significance":3,"cited_by":7,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W4297663160","title":"Machine Learning Techniques for Global Sensitivity Analysis in Earth System Models.","authors":["Cosmin Safta"],"date":"2019-05-15","year":2019,"venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","venue_type":"preprint","ids":{"openalex":"W4297663160"},"links":{"paper":"https://www.osti.gov/biblio/1512022","pdf":"https://www.osti.gov/servlets/purl/1512022"},"orgs":[],"topic":"xai-uq-physics","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Applies machine learning to global sensitivity analysis of Earth system models; abstract unavailable, so scope is inferred from the title.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.06841","title":"Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems","authors":["Jin-Long Wu","Karthik Kashinath","Adrian Albert","Dragos Chirila","Prabhat","Heng Xiao"],"date":"2019-05-13","year":2019,"venue":"Journal of Computational Physics","venue_type":"journal","ids":{"arxiv":"1905.06841","doi":"10.1016/j.jcp.2019.109209","openalex":"W2946794331"},"links":{"paper":"https://doi.org/10.1016/j.jcp.2019.109209","pdf":"https://arxiv.org/pdf/1905.06841"},"orgs":["lbnl-nersc"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":["regional"],"data":["km-scale-sim"],"status":"research","summary":"Covariance-constrained GAN emulates Rayleigh-Bénard convection, an idealized atmosphere-like turbulent flow, as a closure model and cuts training time by up to 80%.","significance":3,"cited_by":162,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.05037","title":"Precipitation nowcasting using a stochastic variational frame predictor with learned prior distribution","authors":["Alexander Bihlo"],"date":"2019-05-13","year":2019,"venue_type":"preprint","ids":{"arxiv":"1905.05037","openalex":"W2944151773"},"links":{"paper":"https://arxiv.org/abs/1905.05037","pdf":"https://arxiv.org/pdf/1905.05037"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["gan-vae","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Stochastic variational frame predictor with a learned prior for radar precipitation nowcasting up to 2.5 hours, giving less blur than ConvLSTM in case studies.","significance":3,"cited_by":29,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.knosys.2019.05.009","title":"Deep shared representation learning for weather elements forecasting","authors":["Siamak Mehrkanoon"],"date":"2019-05-11","year":2019,"venue":"Knowledge-Based Systems","venue_type":"journal","ids":{"doi":"10.1016/j.knosys.2019.05.009","openalex":"W2943852858"},"links":{"paper":"https://doi.org/10.1016/j.knosys.2019.05.009"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Deep shared-representation network for jointly forecasting several weather elements; abstract unavailable, so scope is inferred from the title.","significance":2,"cited_by":83,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00477-019-01680-4","title":"Stepwise extreme learning machine for statistical downscaling of daily maximum and minimum temperature","authors":["Mahsa Moradikhaneghahi","Taesam Lee","Vijay P. Singh"],"date":"2019-05-11","year":2019,"venue":"Stochastic Environmental Research and Risk Assessment","venue_type":"journal","ids":{"doi":"10.1007/s00477-019-01680-4","openalex":"W2944685396"},"links":{"paper":"https://doi.org/10.1007/s00477-019-01680-4"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["stations","cmip"],"status":"research","summary":"Stepwise extreme learning machine is applied to statistically downscale daily maximum and minimum temperature; abstract unavailable.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s10707-019-00355-0","title":"A hybrid CNN-LSTM model for typhoon formation forecasting","authors":["Rui Chen","Xiang Wang","Weimin Zhang","Xiaoyu Zhu","Aiping Li","Chao Yang"],"date":"2019-05-10","year":2019,"venue":"GeoInformatica","venue_type":"journal","ids":{"doi":"10.1007/s10707-019-00355-0","openalex":"W2944681516"},"links":{"paper":"https://doi.org/10.1007/s10707-019-00355-0"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["short"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Hybrid CNN-LSTM model forecasts typhoon formation; abstract unavailable, so the approach and results are inferred from the title only.","significance":3,"cited_by":188,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w11050977","title":"Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network","authors":["Qinghua Miao","Baoxiang Pan","Hao Eric Wang","Kuolin Hsu","Soroosh Sorooshian"],"date":"2019-05-09","year":2019,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w11050977","openalex":"W2928248204"},"links":{"paper":"https://doi.org/10.3390/w11050977","pdf":"https://www.mdpi.com/2073-4441/11/5/977/pdf?version=1557412675"},"orgs":["tsinghua-university"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["cnn","rnn"],"timescale":["medium"],"spatial":["regional"],"data":["era5","cmip","nwp-analysis"],"status":"research","summary":"CNN-LSTM statistical downscaling of ECMWF precipitation over a monsoon basin beats quantile mapping and SVM, with gains up to two-week lead times.","significance":3,"cited_by":142,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-geosciences9050209","title":"Machine Learning for Projecting Extreme Precipitation Intensity for Short Durations in a Changing Climate","authors":["Huiling Hu","Bilal M. Ayyub"],"date":"2019-05-09","year":2019,"venue":"Geosciences","venue_type":"journal","ids":{"doi":"10.3390/geosciences9050209","openalex":"W2944473798"},"links":{"paper":"https://doi.org/10.3390/geosciences9050209","pdf":"https://www.mdpi.com/2076-3263/9/5/209/pdf?version=1557408197"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["stations","cmip"],"status":"research","summary":"Machine learning temporally downscales climate projections to estimate short-duration extreme precipitation IDF curves, trained on about 2,000 US stations.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41598-019-43496-w","title":"Atmospheric Circulation Patterns Associated with Extreme United States Floods Identified via Machine Learning","authors":["K. Schlef","Hamid Moradkhani","Upmanu Lall"],"date":"2019-05-09","year":2019,"venue":"Scientific Reports","venue_type":"journal","ids":{"doi":"10.1038/s41598-019-43496-w","openalex":"W2944282747"},"links":{"paper":"https://doi.org/10.1038/s41598-019-43496-w","pdf":"https://www.nature.com/articles/s41598-019-43496-w.pdf"},"orgs":["columbia-leap"],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Self-organizing maps applied to reanalysis identify four circulation pattern types behind extreme US floods, including tropical moisture exports and tropical cyclones.","significance":4,"cited_by":65,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018ms001561","title":"Evaluation of Machine Learning Classifiers for Predicting Deep Convection","authors":["Peter Ukkonen","Antti Mäkelä"],"date":"2019-05-09","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2018ms001561","openalex":"W2944123510"},"links":{"paper":"https://doi.org/10.1029/2018ms001561","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018MS001561"},"orgs":[],"topic":"extremes-hazards","topics":["hybrid-parameterization"],"type":"evaluation","method":["classical-ml"],"timescale":["nowcast","climate"],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"Compares logistic regression, random forests, boosted trees and neural networks predicting ERA5 thunderstorm occurrence, with about twofold skill gain over CAPE at 0–45 min.","significance":4,"cited_by":81,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos10050252","title":"Prediction of North Atlantic Oscillation Index with Convolutional LSTM Based on Ensemble Empirical Mode Decomposition","authors":["Shijin Yuan","Xiaodan Luo","Bin Mu","Jing Li","Guokun Dai"],"date":"2019-05-07","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10050252","openalex":"W2944278636"},"links":{"paper":"https://doi.org/10.3390/atmos10050252","pdf":"https://www.mdpi.com/2073-4433/10/5/252/pdf?version=1558076231"},"orgs":["fudan-university"],"topic":"s2s-seasonal","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other","nwp-analysis"],"status":"research","summary":"EEMD-decomposed ConvLSTM forecasts the NAO index and outperforms six benchmarks and NOAA GFS and MRF ensemble-mean forecasts in the reported tests.","significance":3,"cited_by":29,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2019.2909838","title":"A Novel Approach to SAR Ocean Wind Retrieval","authors":["Vegard Nilsen","Geir Engen","Harald Johnsen"],"date":"2019-05-07","year":2019,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2019.2909838","openalex":"W2944603415"},"links":{"paper":"https://doi.org/10.1109/tgrs.2019.2909838"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Bayesian model using SAR spectral parameters retrieves ocean surface wind with about 1.7 m/s speed and 49° direction standard deviation against ECMWF.","significance":3,"cited_by":11,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-cli7050066","title":"A Climatology of Atmospheric Patterns Associated with Red River Valley Blizzards","authors":["Aaron Kennedy","Alexander Trellinger","Thomas J. Grafenauer","Gregory Gust"],"date":"2019-05-06","year":2019,"venue":"Climate","venue_type":"journal","ids":{"doi":"10.3390/cli7050066","openalex":"W2920918567"},"links":{"paper":"https://doi.org/10.3390/cli7050066","pdf":"https://www.mdpi.com/2225-1154/7/5/66/pdf?version=1557301385"},"orgs":["noaa"],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Climatology of Red River Valley blizzard patterns from 1979–2018 reanalysis, with a self-organizing map grouping events into an 8-class map.","significance":2,"cited_by":8,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.01110","title":"Seasonal prediction of climate-driven fire risk for decision-making and operational applications in a Mediterranean region","authors":["Marco Turco","Raul Marcos-Matamoros","Xavier Castro","Esteve Canyameras","Maria Carmen Llasat"],"date":"2019-05-03","year":2019,"venue":"Science of The Total Environment, 676 (2019) 577-583","venue_type":"journal","ids":{"arxiv":"1905.01110","doi":"10.1016/j.scitotenv.2019.04.296"},"links":{"paper":"https://arxiv.org/abs/1905.01110","pdf":"https://arxiv.org/pdf/1905.01110"},"orgs":[],"topic":"extremes-hazards","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Builds a data-driven model linking SPEI drought indices to Catalan burned areas, forecasting summer burned area seasonally with stakeholder co-design and cross-validated skill.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos10050244","title":"Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks","authors":["Quang-Khai Tran","Sa-Kwang Song"],"date":"2019-05-02","year":2019,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos10050244","openalex":"W2943446701"},"links":{"paper":"https://doi.org/10.3390/atmos10050244","pdf":"https://www.mdpi.com/2073-4433/10/5/244/pdf?version=1556790489"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Sequence-to-sequence ConvRNN for radar echo extrapolation trained with SSIM losses, reducing blurry 10-step precipitation predictions.","significance":3,"cited_by":114,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.03709","title":"Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks","authors":["Victor Schmidt","Alexandra Luccioni","S. Karthik Mukkavilli","Narmada Balasooriya","Kris Sankaran","Jennifer Chayes","Yoshua Bengio"],"date":"2019-05-02","year":2019,"venue_type":"preprint","ids":{"arxiv":"1905.03709"},"links":{"paper":"https://arxiv.org/abs/1905.03709","pdf":"https://arxiv.org/pdf/1905.03709"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["gan-vae"],"timescale":["climate"],"spatial":["local"],"data":["other"],"status":"research","summary":"CycleGAN transforms street-view house images to depict post-extreme-weather outcomes, paired with climate projections, to visualize 50-year climate change impacts for communication.","significance":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1166-jctn.2019.7835","title":"Weather Prediction Using Clustering Strategies in Machine Learning","authors":["Sravani Nalluri","Somula Ramasubbareddy","Govinda Kannayaram"],"date":"2019-05-01","year":2019,"venue":"Journal of Computational and Theoretical Nanoscience","venue_type":"journal","ids":{"doi":"10.1166/jctn.2019.7835","openalex":"W2953751705"},"links":{"paper":"https://doi.org/10.1166/jctn.2019.7835"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Uses clustering strategies in machine learning for weather prediction; no abstract is available to confirm the approach or results.","significance":1,"cited_by":25,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.34218-ijcet.10.2.2019.019","title":"APPLICATION OF NEURAL NETWORK IN DROUGHT FORECASTING; AN INTENSE LITERATURE REVIEW","authors":["Akhilesh Kumar Yadu","Gyanesh Shrivastava"],"date":"2019-04-30","year":2019,"venue":"INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY","venue_type":"journal","ids":{"doi":"10.34218/ijcet.10.2.2019.019","openalex":"W3000757893"},"links":{"paper":"https://doi.org/10.34218/ijcet.10.2.2019.019","pdf":"https://doi.org/10.34218/ijcet.10.2.2019.019"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"review","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Literature review of over 90 studies (2000–2017) on neural networks for drought and monsoon rainfall forecasting, mainly in India.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20527-jtiulm.v4i1.36","title":"IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORK FOR MONTHLY RAIN ATTACKS IN SOUTH KALIMANTAN","authors":["Nur Arminarahmah","Miftahul Munir"],"date":"2019-04-30","year":2019,"venue":"Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM)","venue_type":"journal","ids":{"doi":"10.20527/jtiulm.v4i1.36","openalex":"W2952878322"},"links":{"paper":"https://doi.org/10.20527/jtiulm.v4i1.36","pdf":"http://jtiulm.ti.ft.ulm.ac.id/index.php/jtiulm/article/download/36/35"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Neural network predicts monthly rainfall in South Kalimantan from monthly SST EOF predictors; accurate in dry season, weakest during the wet-season transition.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1904.13081","title":"Sequence to sequence deep learning models for solar irradiation forecasting","authors":["Bhaskar Pratim Mukhoty","Vikas Maurya","Sandeep Kumar Shukla"],"date":"2019-04-30","year":2019,"venue_type":"preprint","ids":{"arxiv":"1904.13081"},"links":{"paper":"https://arxiv.org/abs/1904.13081","pdf":"https://arxiv.org/pdf/1904.13081"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["nowcast","short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"LSTM sequence-to-sequence models forecast solar irradiance 1 to 24 hours ahead, outperforming GBRT and feed-forward baselines using neighbouring-site wind and irradiance features.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en12091621","title":"Day-Ahead Photovoltaic Forecasting: A Comparison of the Most Effective Techniques","authors":["Alfredo Nespoli","Emanuèle Ogliari","Sonia Leva","Alessandro Massi Pavan","A. Mellit","Vanni Lughi","Alberto Dolara"],"date":"2019-04-29","year":2019,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en12091621","openalex":"W2941419477"},"links":{"paper":"https://doi.org/10.3390/en12091621"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares two ANN day-ahead PV forecasters, one using daily weather forecasts; the hybrid wins on sunny days (NMAE below 1%) but is less stable.","significance":2,"cited_by":266,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-joe.2018.5488","title":"Application of cluster analysis in short‐term wind power forecasting model","authors":["Aoran Xu","Tao Yang","Jianwei Ji","Yang Gao","Cailian Gu"],"date":"2019-04-29","year":2019,"venue":"The Journal of Engineering","venue_type":"journal","ids":{"doi":"10.1049/joe.2018.5488","openalex":"W2943440041"},"links":{"paper":"https://doi.org/10.1049/joe.2018.5488","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/joe.2018.5488"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Clustering NWP-similar historical samples before a neural network improves short-term wind power forecasts at a northeast China farm by about 12%.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3389-frobt.2019.00032","title":"Forecasting Climatic Trends Using Neural Networks: An Experimental Study Using Global Historical Data","authors":["Takeshi Ise","Yurika Oba"],"date":"2019-04-26","year":2019,"venue":"Frontiers in Robotics and AI","venue_type":"journal","ids":{"doi":"10.3389/frobt.2019.00032","openalex":"W2941638788"},"links":{"paper":"https://doi.org/10.3389/frobt.2019.00032","pdf":"https://www.frontiersin.org/articles/10.3389/frobt.2019.00032/pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["cnn"],"timescale":["decadal"],"spatial":["global"],"data":["other"],"status":"research","summary":"LeNet CNN on images of 30 years of global monthly temperature predicts the next decade's trend with 97% reported accuracy, as a top-down alternative to physics models.","significance":2,"cited_by":80,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1904.10904","title":"Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction","authors":["Peter A. G. Watson"],"date":"2019-04-24","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"1904.10904","doi":"10.1029/2018ms001597","openalex":"W2950393127"},"links":{"paper":"https://arxiv.org/abs/1904.10904","pdf":"https://arxiv.org/pdf/1904.10904"},"orgs":["university-of-oxford"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml","physics-constrained"],"timescale":["medium","climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"ML learns timestep-by-timestep error corrections to a physical model; tested on Lorenz-96, it gives stable runs, better initialised skill and improved long-term statistics.","significance":4,"cited_by":77,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11080966","title":"Neural Network Approach to Forecast Hourly Intense Rainfall Using GNSS Precipitable Water Vapor and Meteorological Sensors","authors":["Pedro José Benevides","João Catalão","Giovanni Nico"],"date":"2019-04-23","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11080966","openalex":"W2941056923"},"links":{"paper":"https://doi.org/10.3390/rs11080966","pdf":"https://www.mdpi.com/2072-4292/11/8/966/pdf?version=1555999290"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite","stations"],"status":"research","summary":"NARX network fuses GNSS precipitable water and station data to forecast hourly intense rain in Lisbon, cutting false-positive rate to 21–36%.","significance":3,"cited_by":96,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2965661152","title":"Downscaling and Disaggregation of Wind Speed to River Basin in India for IPCC SRES Scenarios","authors":["Aavudai Anandhi"],"date":"2019-04-22","year":2019,"venue_type":"other","ids":{"openalex":"W2965661152"},"links":{"paper":"http://ijewfn.org/index.php/ijewfn/article/download/12/6"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","nwp-analysis"],"status":"research","summary":"Support vector machine downscales CGCM3 wind speed projections to an Indian river basin under SRES scenarios, then disaggregates to daily values with a k-nearest neighbour method.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-wics.1462","title":"Insurance risk assessment in the face of climate change: Integrating data science and statistics","authors":["Vyacheslav Lyubchich","Nathaniel K. Newlands","Azar Ghahari","Tahir Mahdi","Yulia R. Gel"],"date":"2019-04-17","year":2019,"venue":"Wiley Interdisciplinary Reviews Computational Statistics","venue_type":"journal","ids":{"doi":"10.1002/wics.1462","openalex":"W2936732373"},"links":{"paper":"https://doi.org/10.1002/wics.1462","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/wics.1462"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Review of statistical and machine learning methods for assessing climate-driven non-catastrophic weather risk in agricultural and home insurance.","significance":2,"cited_by":77,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1904.11576","title":"Forecasting Drought Using Multilayer Perceptron Artificial Neural Network Model","authors":["Zulifqar Ali","Ijaz Hussain","Muhammad Faisal","Hafiza Mamona Nazir","Tajammal Hussain","Muhammad Yousaf Shad","Alaa Mohamd Shoukry","Showkat Hussain Gani"],"date":"2019-04-17","year":2019,"venue_type":"preprint","ids":{"arxiv":"1904.11576","doi":"10.1155/2017/5681308"},"links":{"paper":"https://arxiv.org/abs/1904.11576","pdf":"https://arxiv.org/pdf/1904.11576"},"orgs":[],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An MLP neural network forecasts monthly SPEI drought index at 17 Pakistani climate stations, showing usable skill by MAE, RMSE and correlation.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1904.07979","title":"CloudSegNet: A Deep Network for Nychthemeron Cloud Image Segmentation","authors":["Soumyabrata Dev","Atul Nautiyal","Yee Hui Lee","Stefan Winkler"],"date":"2019-04-16","year":2019,"venue_type":"preprint","ids":{"arxiv":"1904.07979","doi":"10.1109/lgrs.2019.2912140"},"links":{"paper":"https://arxiv.org/abs/1904.07979","pdf":"https://arxiv.org/pdf/1904.07979"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"A light-weight CNN, CloudSegNet, segments clouds in ground sky-camera images across day and night in one framework, reaching state-of-the-art results on public databases.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1904.07192","title":"Comparison of statistical post-processing methods for probabilistic NWP forecasts of solar radiation","authors":["Kilian Bakker","Kirien Whan","Wouter Knap","Maurice Schmeits"],"date":"2019-04-15","year":2019,"venue":"Solar Energy, volume 191, 2019, pages 138-150","venue_type":"journal","ids":{"arxiv":"1904.07192","doi":"10.1016/j.solener.2019.08.044"},"links":{"paper":"https://arxiv.org/abs/1904.07192","pdf":"https://arxiv.org/pdf/1904.07192"},"orgs":[],"topic":"post-processing","topics":["observations-remote-sensing"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares seven statistical post-processing methods for probabilistic HARMONIE-AROME solar radiation forecasts; quantile regression and generalized random forests perform best.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-12-1477-2019","title":"Fldgen v1.0: an emulator with internal variability and space–time correlation for Earth system models","authors":["Robert P. Link","Abigail Snyder","Cary Lynch","Corinne A. Hartin","Ben Kravitz","Ben Bond‐Lamberty"],"date":"2019-04-12","year":2019,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-12-1477-2019","openalex":"W2937392972"},"links":{"paper":"https://doi.org/10.5194/gmd-12-1477-2019","pdf":"https://gmd.copernicus.org/articles/12/1477/2019/gmd-12-1477-2019.pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Fldgen emulates Earth system model temperature fields with internal variability and space-time correlation, producing large ensembles from global temperature input.","significance":3,"cited_by":50,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11080896","title":"Atmospheric Retrievals and Assessment for Microwave Observations from Chinese FY-3C Satellite during Hurricane Matthew","authors":["Jieying He","Haonan Chen"],"date":"2019-04-12","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11080896","openalex":"W2936277446"},"links":{"paper":"https://doi.org/10.3390/rs11080896","pdf":"https://www.mdpi.com/2072-4292/11/8/896/pdf?version=1555074567"},"orgs":["noaa","colorado-state-university"],"topic":"observations-remote-sensing","topics":["data-assimilation"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Neural network combined with 1D-variational retrieval of FY-3C microwave temperature and humidity profiles during Hurricane Matthew, improving WRF data-assimilation track forecasts.","significance":3,"cited_by":10,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-iet-rpg.2018.5354","title":"Confidence‐aware deep learning forecasting system for daily solar irradiance","authors":["Hyun-Yong Lee","Byung‐Tak Lee"],"date":"2019-04-12","year":2019,"venue":"IET Renewable Power Generation","venue_type":"journal","ids":{"doi":"10.1049/iet-rpg.2018.5354","openalex":"W2936521195"},"links":{"paper":"https://doi.org/10.1049/iet-rpg.2018.5354"},"orgs":[],"topic":"applications-impacts","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Bayesian deep learning gives daily solar irradiance forecasts from weather forecasts with confidence estimates; confident outputs show 5% max error versus 22.8% for non-confident ones.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2954307991","title":"How can we predict the accuracy of weather forecast with machine learning","authors":["Masahide Funaki"],"date":"2019-04-08","year":2019,"venue":"The Japanese Society for Artificial Intelligence","venue_type":"journal","ids":{"openalex":"W2954307991"},"links":{"paper":"https://confit.atlas.jp/guide/event/jsai2019/subject/2J3-J-13-02/detail"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":[],"data":[],"status":"research","summary":"Japanese conference paper proposing machine learning to predict the accuracy of weather forecasts; abstract unavailable, so details are unverified.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2944050660","title":"Development of method of spot weather forecast using machine learning","authors":["Takao Yoshikane"],"date":"2019-04-08","year":2019,"venue":"The Japanese Society for Artificial Intelligence","venue_type":"journal","ids":{"openalex":"W2944050660"},"links":{"paper":"https://confit.atlas.jp/guide/event/jsai2019/subject/4Rin1-33/date"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":[],"timescale":["short"],"spatial":["local"],"data":[],"status":"research","summary":"Japanese conference paper on machine-learning spot weather forecasting; abstract unavailable, so details are unverified.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1904.03327","title":"Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-graining","authors":["Noah D Brenowitz","Christopher S Bretherton"],"date":"2019-04-06","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"arxiv":"1904.03327","doi":"10.1029/2019ms001711","openalex":"W2930756996"},"links":{"paper":"https://arxiv.org/abs/1904.03327","pdf":"https://arxiv.org/pdf/1904.03327"},"orgs":["university-of-washington"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A neural network parameterization trained on coarse-grained 4 km cloud-resolving simulations is coupled to a GCM, and removing upper-level inputs stabilizes spatially extended runs.","significance":6,"cited_by":231,"score":44,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-en12071298","title":"A Hybrid Technique for Day-Ahead PV Generation Forecasting Using Clear-Sky Models or Ensemble of Artificial Neural Networks According to a Decision Tree Approach","authors":["S. Massucco","Gabriele Mosaico","M. Saviozzi","F. Silvestro"],"date":"2019-04-04","year":2019,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en12071298","openalex":"W2925435752"},"links":{"paper":"https://doi.org/10.3390/en12071298","pdf":"https://www.mdpi.com/1996-1073/12/7/1298/pdf?version=1554372075"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Hybrid day-ahead PV forecasting switches between clear-sky models and an ANN ensemble via a decision tree driven by the weather forecast, validated on a real plant.","significance":2,"cited_by":47,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-ab154b","title":"The effects of climate extremes on global agricultural yields","authors":["Elisabeth Vogel","Markus G. Donat","Lisa V. Alexander","Malte Alexander Meinshausen","Deepak K. Ray","David John Karoly","Nicolai Meinshausen","Katja Frieler"],"date":"2019-04-02","year":2019,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/ab154b","openalex":"W2927413391"},"links":{"paper":"https://doi.org/10.1088/1748-9326/ab154b","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/ab154b/pdf"},"orgs":["eth-zurich","pik"],"topic":"applications-impacts","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Uses machine learning on sub-national yield data to show climate extremes explain 18-43% of yield-anomaly variance, with temperature extremes dominating global crop losses.","significance":3,"cited_by":868,"score":42,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3008744268","title":"WEATHER PREDICTION AND CLIMATE CHANGE STUDIES USING DATA MINING TECHNIQUES","authors":["Shubhangi G. Malas","Pavan N.Mundhare"],"date":"2019-04-01","year":2019,"venue":"Journal of Emerging Technologies and Innovative Research","venue_type":"journal","ids":{"openalex":"W3008744268"},"links":{"paper":"https://www.jetir.org/papers/JETIRBD06022.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Applies neural networks and decision trees to 2000–2009 Ibadan, Nigeria station data for weather and extremes prediction; a low-novelty applied study.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1906.08852","title":"A Hybrid Precipitation Prediction Method based on Multicellular Gene Expression Programming","authors":["Hongya Li","Yuzhong Peng","Chuyan Deng","Yonghua Pan","Daoqing Gong","Hao Zhang"],"date":"2019-04-01","year":2019,"venue_type":"preprint","ids":{"arxiv":"1906.08852","openalex":"W2949531370"},"links":{"paper":"https://arxiv.org/abs/1906.08852","pdf":"https://arxiv.org/pdf/1906.08852"},"orgs":[],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A wavelet-denoised multicellular gene expression programming model (WTGEPRP) forecasts precipitation at Zhengzhou, Nanning and Melbourne, outperforming several baseline hybrid models.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1111-exsy.12394","title":"Big data solar power forecasting based on deep learning and multiple data sources","authors":["José Francisco Torres","Alicia Troncoso","Irena Koprinska","Zheng Wang","Francisco Martinez Alvarez"],"date":"2019-03-28","year":2019,"venue":"Expert Systems","venue_type":"journal","ids":{"doi":"10.1111/exsy.12394","openalex":"W2935631455"},"links":{"paper":"https://doi.org/10.1111/exsy.12394"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other","nwp-analysis"],"status":"research","summary":"Feed-forward deep learning decomposes day-ahead half-hourly PV power forecasting using weather data and forecasts from two years of Australian solar systems, with competitive accuracy and good scaling.","significance":2,"cited_by":74,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018ms001525","title":"An Artificial Neural Networks‐Based Tree Ring Width Proxy System Model for Paleoclimate Data Assimilation","authors":["Miao Fang","Xin Li"],"date":"2019-03-28","year":2019,"venue":"Journal of Advances in Modeling Earth Systems","venue_type":"journal","ids":{"doi":"10.1029/2018ms001525","openalex":"W2989239107"},"links":{"paper":"https://doi.org/10.1029/2018ms001525","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018MS001525"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":[],"data":["other"],"status":"research","summary":"A neural-network tree-ring width proxy system model outperforms linear and VS-Lite models for paleoclimate data assimilation, ranking best among the four compared.","significance":3,"cited_by":23,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jhm-d-18-0196.1","title":"Potential Predictability of Regional Precipitation and Discharge Extremes Using Synoptic-Scale Climate Information via Machine Learning: An Evaluation for the Eastern Continental United States","authors":["James O'Neil Knighton","Geoff Pleiss","Elizabeth K. Carter","Steve W. Lyon","M. Todd Walter","Scott Steinschneider"],"date":"2019-03-25","year":2019,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-18-0196.1","openalex":"W2924604776"},"links":{"paper":"https://doi.org/10.1175/jhm-d-18-0196.1"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards","climate-analysis-attribution"],"type":"model","method":["cnn","classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Archetypal analysis plus a 2D CNN predicts eastern US regional precipitation and discharge extremes from synoptic-scale fields, with the most reliable skill from 300 hPa geopotential height.","significance":3,"cited_by":26,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jamc-d-18-0175.1","title":"Local-Scale Valley Wind Retrieval Using an Artificial Neural Network Applied to Routine Weather Observations","authors":["Florian Dupuy","Gert‐Jan Duine","Pierre Durand","Thierry Hedde","Pierre Roubin","Eric R. Pardyjak"],"date":"2019-03-25","year":2019,"venue":"Journal of Applied Meteorology and Climatology","venue_type":"journal","ids":{"doi":"10.1175/jamc-d-18-0175.1","openalex":"W2922634008"},"links":{"paper":"https://doi.org/10.1175/jamc-d-18-0175.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/apme/58/5/jamc-d-18-0175.1.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"A neural network nowcasts downvalley wind speed and direction from routine station observations, with a -0.28 m/s speed bias and 84% of directions within 45 degrees.","significance":3,"cited_by":13,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1903.10274","title":"A data-driven approach to precipitation parameterizations using convolutional encoder-decoder neural networks","authors":["Pablo Rozas Larraondo","Luigi J. Renzullo","Inaki Inza","Jose A. Lozano"],"date":"2019-03-25","year":2019,"venue_type":"preprint","ids":{"arxiv":"1903.10274","openalex":"W2923650835"},"links":{"paper":"https://arxiv.org/abs/1903.10274","pdf":"https://arxiv.org/pdf/1903.10274"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Encoder-decoder CNNs learn total precipitation from geopotential height alone in NWP reanalysis data, offering a data-driven precipitation parameterization with high accuracy and a method to identify influential levels.","significance":4,"cited_by":30,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1903.10012","title":"A mixture of experts model for predicting persistent weather patterns","authors":["Maria Perez-Ortiz","Pedro A. Gutierrez","Peter Tino","Carlos Casanova-Mateo","Sancho Salcedo-Sanz"],"date":"2019-03-24","year":2019,"venue_type":"preprint","ids":{"arxiv":"1903.10012","openalex":"W2950207153"},"links":{"paper":"https://arxiv.org/abs/1903.10012","pdf":"https://arxiv.org/pdf/1903.10012"},"orgs":["university-of-cambridge"],"topic":"local-forecasting","topics":["post-processing"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Ordinal neural network refines a persistence baseline to predict airport low visibility, outperforming persistence and autoregressive models at longer horizons on station data.","significance":2,"cited_by":1,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-el.2019.0887","title":"interview","authors":["anonymous"],"date":"2019-03-22","year":2019,"venue":"Electronics Letters","venue_type":"journal","ids":{"doi":"10.1049/el.2019.0887","openalex":"W4254899223"},"links":{"paper":"https://doi.org/10.1049/el.2019.0887"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"position","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Interview on an RNN-based tropical cyclone intensity prediction model, arguing deep learning can address the black-box nature of typhoon forecasting.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-env.2567","title":"Statistics for climate informatics","authors":["Vyacheslav Lyubchich","A. N. Rhines","Samuel S. P. Shen"],"date":"2019-03-18","year":2019,"venue":"Environmetrics","venue_type":"journal","ids":{"doi":"10.1002/env.2567","openalex":"W2923024824"},"links":{"paper":"https://doi.org/10.1002/env.2567","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/env.2567"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Editorial introducing a special issue on statistics and machine learning for climate informatics, covering climate clustering, rainfall extremes and correlated extreme time series.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1903.07512","title":"A Comparison of Prediction Algorithms and Nexting for Short Term Weather Forecasts","authors":["Michael Koller","Johannes Feldmaier","Klaus Diepold"],"date":"2019-03-18","year":2019,"venue_type":"preprint","ids":{"arxiv":"1903.07512","openalex":"W2921473370"},"links":{"paper":"https://arxiv.org/abs/1903.07512","pdf":"https://arxiv.org/pdf/1903.07512"},"orgs":["tum"],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml","reinforcement-learning"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares neural networks, regression trees and Nexting for short-term local weather trend forecasts from historical data; no single method clearly wins, with Nexting good for slow signals.","significance":2,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1903.07358","title":"Representing ill-known parts of a numerical model using a machine learning approach","authors":["Julien Brajard","Anastase Charantonis","Jérôme Sirven"],"date":"2019-03-18","year":2019,"venue_type":"preprint","ids":{"arxiv":"1903.07358"},"links":{"paper":"https://arxiv.org/abs/1903.07358","pdf":"https://arxiv.org/pdf/1903.07358"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Hybrid model pairs a physical shallow-water model with a neural network trained on observations to represent unknown forcing and dissipation terms, reproducing them with correlation near 1.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4108-eai.7-12-2018.159405","title":"Predictive Analytics In Weather Forecasting Using Machine Learning Algorithms","authors":["Aastha Sharma","V. Vijayakumar"],"date":"2019-03-15","year":2019,"venue":"EAI Endorsed Transactions on Cloud Systems","venue_type":"journal","ids":{"doi":"10.4108/eai.7-12-2018.159405","openalex":"W2956307549"},"links":{"paper":"https://doi.org/10.4108/eai.7-12-2018.159405","pdf":"http://eudl.eu/pdf/10.4108/eai.7-12-2018.159405"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Surveys machine learning algorithms applied to weather forecasting for agriculture in India; the abstract is truncated, so the contribution is low-confidence.","significance":1,"cited_by":8,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3183506418","title":"Application of deep learning techniques to precipitation guidance in short-term weather predictions","authors":["Takeru Kurakami","Kazuyoshi Souma","Takashi Miyamoto","Takahiko Huruya","Jun Magome","Hiroshi Ishidaira"],"date":"2019-03-14","year":2019,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W3183506418"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2019/subject/E_ACG36-P05/detail"},"orgs":[],"topic":"nowcasting","topics":[],"type":"application","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":[],"status":"research","summary":"Applies deep learning to precipitation guidance for short-term weather prediction in Japan; the abstract is unavailable, so details are limited.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3175722958","title":"Volumetric Detection of Tornadic Vortices Associated with Typhoon Nanmadol (2017) Using PAWR and Deep Learning","authors":["Toru Adachi","Naoki Ishitsu","Kenichi Kusunoki","Hanako Inoue","Ken‐ichiro Arai","Chusei Fujiwara","Hiroto SUZUKI"],"date":"2019-03-14","year":2019,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W3175722958"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2019/subject/AAS02-11/detail"},"orgs":[],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"application","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Deep learning applied to phased-array weather radar volumes detects tornadic vortices in Typhoon Nanmadol (2017); the abstract gives no quantitative results.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3167068417","title":"Climate Predictions for Different Locations Using Machine Learning and Big Data","authors":["Aman Gupta","Praveen Kumar","Seema Rawat"],"date":"2019-03-14","year":2019,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"openalex":"W3167068417"},"links":{"paper":"https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3403960"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["stations","other"],"status":"research","summary":"Linear and logistic regression applied to open government and NOAA data predict weather at several locations, with no quantified skill reported.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-su11051501","title":"A Two-Step Approach to Solar Power Generation Prediction Based on Weather Data Using Machine Learning","authors":["Seul Gi Kim","Jae‐Yoon Jung","Min Kyu Sim"],"date":"2019-03-12","year":2019,"venue":"Sustainability","venue_type":"journal","ids":{"doi":"10.3390/su11051501","openalex":"W2920927670"},"links":{"paper":"https://doi.org/10.3390/su11051501","pdf":"https://www.mdpi.com/2071-1050/11/5/1501/pdf?version=1552444308"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A two-step model links unannounced weather variables to announced forecasts for one-day-ahead PV output; random forest reaches R-squared 0.705, beating the base approach.","significance":2,"cited_by":131,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6066","title":"Downscaling rainfall using deep learning long short‐term memory and feedforward neural network","authors":["Duong Tran Anh","Song Pham Van","Thanh Duc Dang","Long Phi Hoang"],"date":"2019-03-09","year":2019,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6066","openalex":"W2921706503"},"links":{"paper":"https://doi.org/10.1002/joc.6066"},"orgs":["tum"],"topic":"downscaling","topics":[],"type":"model","method":["rnn"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"LSTM and feedforward networks downscale CMIP5 precipitation for the Mekong Delta, projecting 20-25% wet-season increases and dry-season decreases for 2036-2065.","significance":3,"cited_by":82,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1903.03010","title":"Characterizing Evaporation Ducts Within the Marine Atmospheric Boundary Layer Using Artificial Neural Networks","authors":["Hilarie Sit","Christopher J. Earls"],"date":"2019-03-07","year":2019,"venue_type":"preprint","ids":{"arxiv":"1903.03010","doi":"10.1029/2019rs006798"},"links":{"paper":"https://arxiv.org/abs/1903.03010","pdf":"https://arxiv.org/pdf/1903.03010"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"application","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Multilayer perceptron retrieves evaporation duct heights in the marine boundary layer from sparse electromagnetic propagation measurements, enabling fast near-real-time estimates; architecture choices are documented.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-18-0136.1","title":"Estimating Tropical Cyclone Intensity by Satellite Imagery Utilizing Convolutional Neural Networks","authors":["Buo‐Fu Chen","Boyo Chen","Boyo Chen","Boyo Chen","Hsuan-Tien Lin","Russell L. Elsberry"],"date":"2019-03-01","year":2019,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-18-0136.1","openalex":"W2919354935"},"links":{"paper":"https://doi.org/10.1175/waf-d-18-0136.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/34/2/waf-d-18-0136_1.pdf"},"orgs":["ncar"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite","other"],"status":"research","summary":"A CNN trained on satellite infrared and microwave data estimates tropical cyclone intensity with 8.39 kt RMS error, offering an objective alternative to the Dvorak technique.","significance":4,"cited_by":129,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.ejrh.2019.100595","title":"Observed and model simulated twenty-first century hydro-climatic change of Northern Ethiopia","authors":["Samuale Tesfaye","Gebeyehu Taye","Emiru Birhane","Sjoerd EATM van der Zee"],"date":"2019-03-01","year":2019,"venue":"Journal of Hydrology Regional Studies","venue_type":"journal","ids":{"doi":"10.1016/j.ejrh.2019.100595","openalex":"W2920624939"},"links":{"paper":"https://doi.org/10.1016/j.ejrh.2019.100595","pdf":"https://www.sciencedirect.com/science/article/pii/S2214581818302866/pdf"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"ANNs downscale 30 CMIP5 GCMs for the Tekeze basin, projecting falling precipitation and streamflow to 2099 under RCP4.5 and RCP8.5, with multi-model ensembles more robust.","significance":2,"cited_by":41,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6050","title":"Integrating precipitation zoning with random forest regression for the spatial downscaling of satellite‐based precipitation: A case study of the Lancang–Mekong River basin","authors":["Jing Zhang","Hui Fan","Daming He","Jiwei Chen"],"date":"2019-02-26","year":2019,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6050","openalex":"W2917202993"},"links":{"paper":"https://doi.org/10.1002/joc.6050"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random forest with precipitation zoning downscales satellite rainfall to 1 km over the Lancang–Mekong basin, cutting RMSE by 1–17%.","significance":2,"cited_by":34,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-18-0087.1","title":"On the Use of Geophysical Parameters for the Top-of-Atmosphere Shortwave Clear-Sky Radiance-to-Flux Conversion in EarthCARE","authors":["Florian Tornow","Carlos Doménech","Juergen Fischer"],"date":"2019-02-15","year":2019,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-18-0087.1","openalex":"W2912937795"},"links":{"paper":"https://doi.org/10.1175/jtech-d-18-0087.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/atot/36/4/jtech-d-18-0087.1.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Neural networks with selected geophysical inputs convert EarthCARE clear-sky TOA radiance to flux with 2.7–4.0 W m-2 error, under the 10 W m-2 mission threshold.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs11040383","title":"Local Severe Storm Tracking and Warning in Pre-Convection Stage from the New Generation Geostationary Weather Satellite Measurements","authors":["Zijing Liu","Min Min","Jun Li","Fenglin Sun","Di Di","Yufei Ai","Zhenglong Li","Danyu Qin","Guicai Li","Yin-Jing Lin","Xiaolin Zhang"],"date":"2019-02-13","year":2019,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs11040383","openalex":"W2914579103"},"links":{"paper":"https://doi.org/10.3390/rs11040383","pdf":"https://www.mdpi.com/2072-4292/11/4/383/pdf?version=1551089942"},"orgs":["cma"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Random forest on Himawari-8 brightness temperatures and NWP water vapour classifies weak, medium and severe pre-convective storms over East Asia with 0.79 accuracy.","significance":3,"cited_by":37,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1038-s41586-019-0912-1","title":"Deep learning and process understanding for data-driven Earth system science","authors":["Markus Reichstein","Gustau Camps-Valls","Bjorn Stevens","Martin Jung","Joachim Denzler","Nuno Carvalhais","Prabhat"],"date":"2019-02-13","year":2019,"venue":"Nature","venue_type":"journal","ids":{"doi":"10.1038/s41586-019-0912-1","openalex":"W2913323966"},"links":{"paper":"https://doi.org/10.1038/s41586-019-0912-1"},"orgs":["lbnl-nersc","mpi-biogeochemistry","mpi-meteorology"],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Nature review on deep learning for data-driven Earth system science, covering weather, climate and process understanding; abstract absent, judged from title and venue.","significance":7,"cited_by":5617,"score":78,"highlight":true,"highlight_reason":"Widely cited Nature perspective defining how deep learning and process understanding should combine in Earth system science.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1902.04621","title":"Testing the Reliability of Interpretable Neural Networks in Geoscience Using the Madden-Julian Oscillation","authors":["Benjamin A. Toms","Karthik Kashinath","Prabhat","Da Yang"],"date":"2019-02-12","year":2019,"venue_type":"preprint","ids":{"arxiv":"1902.04621"},"links":{"paper":"https://arxiv.org/abs/1902.04621","pdf":"https://arxiv.org/pdf/1902.04621"},"orgs":[],"topic":"xai-uq-physics","topics":["climate-analysis-attribution"],"type":"evaluation","method":["cnn","other"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Tests backward optimization and layerwise relevance propagation on a neural network for the Madden-Julian Oscillation, recovering known spatial structure and suggesting seasonality shifts.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1902.04615","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","authors":["Taco S. Cohen","Maurice Weiler","Berkay Kicanaoglu","Max Welling"],"date":"2019-02-11","year":2019,"venue_type":"preprint","ids":{"arxiv":"1902.04615"},"links":{"paper":"https://arxiv.org/abs/1902.04615","pdf":"https://arxiv.org/pdf/1902.04615"},"orgs":[],"topic":"extremes-hazards","topics":["benchmarks-data-eval"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Gauge-equivariant CNNs on the icosahedron improve segmentation of global climate patterns, alongside omnidirectional images, with a single conv2d implementation.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1902.02950","title":"Differentiable Physics-informed Graph Networks","authors":["Sungyong Seo","Yan Liu"],"date":"2019-02-08","year":2019,"venue_type":"preprint","ids":{"arxiv":"1902.02950","openalex":"W2920116087"},"links":{"paper":"https://arxiv.org/abs/1902.02950","pdf":"https://arxiv.org/pdf/1902.02950"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["gnn","physics-constrained"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Differentiable physics-informed graph networks inject domain physics into latent space, improving climate prediction tasks and multistep forecasting; details are limited in the abstract.","significance":2,"cited_by":42,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1902.04458","title":"Uncovering temporal regularity in atmospheric dynamics through Hilbert phase analysis","authors":["Dario A. Zappalà","Cristina Masoller","Marcelo Barreiro"],"date":"2019-02-06","year":2019,"venue_type":"preprint","ids":{"arxiv":"1902.04458","doi":"10.1063/1.5091817"},"links":{"paper":"https://arxiv.org/abs/1902.04458","pdf":"https://arxiv.org/pdf/1902.04458"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Hilbert phase analysis with temporal averaging reveals hidden periodicities in surface air temperature, linked to El Niño, and yields features for time-series classification.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1902.01453","title":"PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic PowerForecasting from Numerical Weather Prediction","authors":["Johan Mathe","Nina Miolane","Nicolas Sebastien","Jeremie Lequeux"],"date":"2019-02-04","year":2019,"venue_type":"preprint","ids":{"arxiv":"1902.01453"},"links":{"paper":"https://arxiv.org/abs/1902.01453","pdf":"https://arxiv.org/pdf/1902.01453"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"PVNet, a convolutional LSTM over NOAA NWP fields, forecasts aggregated German PV output 24 and 48 hours ahead, outperforming persistence.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3154823957","title":"Prospects of Iran's heat extreams based on regional mesoscale model output REGCM4","authors":["Abdollah Ebrahimi"],"date":"2019-02-01","year":2019,"venue":"Geography","venue_type":"journal","ids":{"openalex":"W3154823957"},"links":{"paper":"https://rimag.ricest.ac.ir/en/Article/8936"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Self-organizing maps applied to downscaled REGCM4 projections divide Iran into nine extreme-heat regions and project increases in mid-century heat.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1166-jctn.2019.7742","title":"An Investigation Study on Clustering and Classification Techniques for Weather Forecasting","authors":["Settineni Pooja","S. Balan"],"date":"2019-02-01","year":2019,"venue":"Journal of Computational and Theoretical Nanoscience","venue_type":"journal","ids":{"doi":"10.1166/jctn.2019.7742","openalex":"W2939231052"},"links":{"paper":"https://doi.org/10.1166/jctn.2019.7742"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Investigation of clustering and classification ML and ensemble techniques for weather forecasting; the abstract gives no quantitative results.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1049-el.2018.8178","title":"Tropical cyclone intensity prediction based on recurrent neural networks","authors":["Bin Pan","Xia Xu","Zhenwei Shi"],"date":"2019-01-31","year":2019,"venue":"Electronics Letters","venue_type":"journal","ids":{"doi":"10.1049/el.2018.8178","openalex":"W2912394463"},"links":{"paper":"https://doi.org/10.1049/el.2018.8178"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"RNN trained on Western North Pacific tropical cyclone records predicts 24-hour intensity with 5.1 m/s error, beating some dynamical models.","significance":3,"cited_by":56,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.6020","title":"Regression‐based regionalization for bias correction of temperature and precipitation","authors":["Sanaz Moghim","Rafael L. Bras"],"date":"2019-01-25","year":2019,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.6020","openalex":"W2911554820"},"links":{"paper":"https://doi.org/10.1002/joc.6020"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Regression-based regionalization trains an ANN on a few pixels per region to bias-correct CCSM temperature and precipitation over northern South America.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w11010158","title":"Improving the Performance of Vegetable Leaf Wetness Duration Models in Greenhouses Using Decision Tree Learning","authors":["Hui Wang","Jorge Antonio Sánchez-Molina","Ming Li","Francisco Rodríguez"],"date":"2019-01-17","year":2019,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w11010158","openalex":"W2910274388"},"links":{"paper":"https://doi.org/10.3390/w11010158","pdf":"https://www.mdpi.com/2073-4441/11/1/158/pdf?version=1547704032"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Decision tree calibration of greenhouse leaf wetness duration models; the neural network model gives the best estimates, with MAE of 1.3 to 1.85 h.","significance":2,"cited_by":34,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s12647-018-00299-0","title":"Artificial Neural Network Technique for Statistical Downscaling of Global Climate Model","authors":["Rajashekhar S. Laddimath","Nagraj S. Patil"],"date":"2019-01-17","year":2019,"venue":"MAPAN","venue_type":"journal","ids":{"doi":"10.1007/s12647-018-00299-0","openalex":"W2909638469"},"links":{"paper":"https://doi.org/10.1007/s12647-018-00299-0"},"orgs":[],"topic":"downscaling","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Applies artificial neural networks for statistical downscaling of global climate model output to regional scales.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1901.05125","title":"Efficient surrogate modeling methods for large-scale Earth system models based on machine learning techniques","authors":["Dan Lu","Daniel Ricciuto"],"date":"2019-01-16","year":2019,"venue":"Geoscientific model development","venue_type":"journal","ids":{"arxiv":"1901.05125","doi":"10.5194/gmd-12-1791-2019","openalex":"W2910249264"},"links":{"paper":"https://doi.org/10.5194/gmd-12-1791-2019","pdf":"https://arxiv.org/pdf/1901.05125"},"orgs":["ornl"],"topic":"climate-emulation","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"SVD plus a Bayesian-optimized neural network emulates 42,660 carbon-flux outputs of an Earth system ecosystem model from only 20 simulations.","significance":3,"cited_by":77,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018wr024090","title":"Improving Precipitation Estimation Using Convolutional Neural Network","authors":["Baoxiang Pan","Kuolin Hsu","Amir AghaKouchak","Soroosh Sorooshian"],"date":"2019-01-15","year":2019,"venue":"Water Resources Research","venue_type":"journal","ids":{"doi":"10.1029/2018wr024090","openalex":"W2909984890"},"links":{"paper":"https://doi.org/10.1029/2018wr024090","pdf":"https://www.osti.gov/servlets/purl/1613789"},"orgs":[],"topic":"downscaling","topics":["hybrid-parameterization"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"CNN predicts daily precipitation at 14 US grid points from resolved dynamics, outperforming reanalysis and linear, forest and dense-network baselines.","significance":3,"cited_by":289,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1901.04881","title":"A deep learning approach to solar-irradiance forecasting in sky-videos","authors":["Talha A. Siddiqui","Samarth Bharadwaj","Shivkumar Kalyanaraman"],"date":"2019-01-15","year":2019,"venue_type":"preprint","ids":{"arxiv":"1901.04881"},"links":{"paper":"https://arxiv.org/abs/1901.04881","pdf":"https://arxiv.org/pdf/1901.04881"},"orgs":[],"topic":"nowcasting","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","other"],"status":"research","summary":"Deep networks on sky-camera videos estimate and forecast solar irradiance up to 4 hours ahead, reducing error relative to satellite-based approaches.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018ea000423","title":"Analyzing El Niño–Southern Oscillation Predictability Using Long‐Short‐Term‐Memory Models","authors":["Andrew Huang","Ben Vega‐Westhoff","Ryan L. Sriver"],"date":"2019-01-14","year":2019,"venue":"Earth and Space Science","venue_type":"journal","ids":{"doi":"10.1029/2018ea000423","openalex":"W2910716882"},"links":{"paper":"https://doi.org/10.1029/2018ea000423","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018EA000423"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"evaluation","method":["rnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"Compares LSTM and linear regression for ENSO prediction from 1 to 11-month leads, finding LSTM matches LR on monthly data and gains skill with daily SST at longer leads.","significance":3,"cited_by":24,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w11010125","title":"Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain","authors":["Javier Díez-Sierra","Manuel del Jesús"],"date":"2019-01-11","year":2019,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w11010125","openalex":"W2910760077"},"links":{"paper":"https://doi.org/10.3390/w11010125","pdf":"https://www.mdpi.com/2073-4441/11/1/125/pdf?version=1547211408"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Random forests downscale daily rainfall to subdaily statistics at over 700 Spanish gauges, improving skill and the Poisson cluster rainfall simulations built on it.","significance":3,"cited_by":48,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018jd028795","title":"Downscaling Satellite Precipitation Estimates With Multiple Linear Regression, Artificial Neural Networks, and Spline Interpolation Techniques","authors":["Ehsan Sharifi","Bahram Saghafian","Reinhold Steinacker"],"date":"2019-01-11","year":2019,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2018jd028795","openalex":"W2910618474"},"links":{"paper":"https://doi.org/10.1029/2018jd028795","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018JD028795"},"orgs":[],"topic":"downscaling","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Compares regression, ANN and spline downscaling of IMERG satellite rainfall in Austria; all improve accuracy, with spline best at correlation 0.56.","significance":2,"cited_by":204,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1901.04927","title":"A mixed model approach to drought prediction using artificial neural networks: Case of an operational drought monitoring environment","authors":["Chrisgone Adede","Robert Oboko","Peter Wagacha","Clement Atzberger"],"date":"2019-01-10","year":2019,"venue_type":"preprint","ids":{"arxiv":"1901.04927"},"links":{"paper":"https://arxiv.org/abs/1901.04927","pdf":"https://arxiv.org/pdf/1901.04927"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["s2s"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Neural network model using lagged precipitation and vegetation variables predicts drought one month ahead in Kenya, with R2 of 0.78 on out-of-sample data.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3004404188","title":"Physics-Informed Generative Learning to Emulate Unresolved Physics in Climate Models","authors":["Karthik Kashinath"],"date":"2019-01-09","year":2019,"venue":"99th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3004404188"},"links":{"paper":"https://ams.confex.com/ams/2019Annual/webprogram/Paper351828.html"},"orgs":["lbnl-nersc"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["physics-constrained"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Physics-informed generative learning is proposed to emulate unresolved climate-model physics; the abstract is missing, so details are limited.","significance":1,"cited_by":1,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.5990","title":"A hierarchical analysis of the impact of methodological decisions on statistical downscaling of daily precipitation and air temperatures","authors":["S. C. Pryor","Justin T. Schoof"],"date":"2019-01-09","year":2019,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.5990","openalex":"W2909002714"},"links":{"paper":"https://doi.org/10.1002/joc.5990","pdf":"https://www.osti.gov/servlets/purl/1612553"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Systematic comparison of GLM and ANN statistical downscaling choices at 10 US sites; ANNs beat GLMs for temperature, while PCA predictors help only extremes.","significance":4,"cited_by":6,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2971212461","title":"Application of Optical Flow and Machine Learning Methods in Nowcasting and Early Warning of Strong Convective Weather","authors":["Yungang Chen"],"date":"2019-01-08","year":2019,"venue":"99th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W2971212461"},"links":{"paper":"https://ams.confex.com/ams/2019Annual/webprogram/Paper351174.html"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Combines optical flow with machine learning for nowcasting and early warning of strong convective weather; abstract not available.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2018.2886070","title":"Diagnosis and Classification of Typhoon-Associated Low-Altitude Turbulence Using HKO-TDWR Radar Observations and Machine Learning","authors":["Jingxiao Cai","Yan Rockee Zhang","Richard J. Doviak","Yunish Shrestha","Pak Wai Chan"],"date":"2019-01-08","year":2019,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2018.2886070","openalex":"W2909625457"},"links":{"paper":"https://doi.org/10.1109/tgrs.2018.2886070"},"orgs":["noaa","university-of-oklahoma"],"topic":"observations-remote-sensing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["radar"],"status":"research","summary":"Neural network classifies typhoon low-altitude turbulence from Hong Kong terminal Doppler radar, validated against commercial aircraft turbulence measurements.","significance":3,"cited_by":13,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3000572704","title":"An Updated Machine Learning Ensemble for Atlantic Tropical Cyclone Rapid Intensification Forecasting","authors":["Andrew E. Mercer"],"date":"2019-01-07","year":2019,"venue":"99th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W3000572704"},"links":{"paper":"https://ams.confex.com/ams/2019Annual/webprogram/Paper348992.html"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":[],"status":"research","summary":"Updated machine learning ensemble for Atlantic tropical cyclone rapid intensification forecasting; no abstract is available, so details are limited.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10500383.1","title":"A High-Performance Computing System for Probabilistic Weather Forecasts","authors":["Weiming Hu","Guido Cervone","Vivek Balasubramanian","Matteo Turilli","Shantenu Jha"],"date":"2019-01-07","year":2019,"venue_type":"other","ids":{"doi":"10.1002/essoar.10500383.1","openalex":"W3157319156"},"links":{"paper":"https://doi.org/10.1002/essoar.10500383.1"},"orgs":[],"topic":"infra-software","topics":["probabilistic-ensembles"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":["nwp-analysis"],"status":"pre-operational","summary":"Describes a parallel HPC system generating probabilistic weather forecasts with the data-driven analog ensemble method, scaling ensemble generation across nodes.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10500352.1","title":"Retrieving temperature and relative humidity profiles from hyperspectral radiations via deep learning","authors":["Maosi Chen","Chaoshun Liu","Zhibin Sun","Wei Gao"],"date":"2019-01-07","year":2019,"venue_type":"other","ids":{"doi":"10.1002/essoar.10500352.1","openalex":"W3176688246"},"links":{"paper":"https://doi.org/10.1002/essoar.10500352.1"},"orgs":["colorado-state-university"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite","era5"],"status":"research","summary":"Retrieves temperature and humidity profiles from NPP CrIS hyperspectral radiances using autoencoders and a self-normalizing network trained on ECMWF data.","significance":3,"cited_by":0,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-essoar.10500350.1","title":"Prediction of agricultural drought in Chile from multiple spatio-temporal data sources","authors":["Francisco Zambrano","Anton Vrieling","Andy D. Nelson","Michele Meroni","Tsegaye Tadesse"],"date":"2019-01-07","year":2019,"venue_type":"other","ids":{"doi":"10.1002/essoar.10500350.1","openalex":"W3138535517"},"links":{"paper":"https://doi.org/10.1002/essoar.10500350.1"},"orgs":[],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Neural network and linear models predict Chilean agricultural drought from ENSO, PDO and precipitation indices at 1-6 month lead times.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s11063-018-09969-1","title":"Machine Learning Nowcasting of PV Energy Using Satellite Data","authors":["Alejandro Catalina","Alberto Torres‐Barrán","Carlos M. Alaíz","José R. Dorronsoro"],"date":"2019-01-05","year":2019,"venue":"Neural Processing Letters","venue_type":"journal","ids":{"doi":"10.1007/s11063-018-09969-1","openalex":"W2907541716"},"links":{"paper":"https://doi.org/10.1007/s11063-018-09969-1","pdf":"https://link.springer.com/content/pdf/10.1007/s11063-018-09969-1.pdf"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Applies machine learning to satellite data to nowcast photovoltaic energy output, linking cloud and irradiance nowcasting to solar power.","significance":2,"cited_by":15,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-018-04605-z","title":"Improving the North American multi-model ensemble (NMME) precipitation forecasts at local areas using wavelet and machine learning","authors":["Lei Xu","Nengcheng Chen","Xiang Zhang","Zeqiang Chen","Chuli Hu","Chao Wang"],"date":"2019-01-03","year":2019,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-018-04605-z","openalex":"W2908061964"},"links":{"paper":"https://doi.org/10.1007/s00382-018-04605-z"},"orgs":["cma"],"topic":"post-processing","topics":["s2s-seasonal"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Combines wavelet decomposition and machine learning to improve local precipitation forecasts from the NMME multi-model seasonal ensemble.","significance":3,"cited_by":60,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3086084367","title":"An Advanced Deep Learning Framework For Short-Term Precipitation Forecasting FromSatellite Information","authors":["Ata Akbari Asanjan"],"date":"2019-01-01","year":2019,"venue_type":"other","ids":{"openalex":"W3086084367"},"links":{"paper":"https://escholarship.org/content/qt39s3w73k/qt39s3w73k.pdf?t=pukryh"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"Dissertation proposing an LSTM model to forecast infrared cloud-top temperatures, combined with a satellite-to-rainfall mapping for 0-6 hour precipitation forecasts.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3036118026","title":"Adjusting Wind Speed Prediction of Numerical Weather Forecast Model Based on Machine Learning Methods","authors":["Quande Sun","Jiao Ruili","Jiangjiang Xia","Zhongwei Yan","Haochen Li","Jianhua Sun","Lizhi Wang","Zhaoming Liang"],"date":"2019-01-01","year":2019,"venue_type":"other","ids":{"openalex":"W3036118026"},"links":{"paper":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902235351143463"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Uses machine learning to correct wind speed predictions from a numerical weather prediction model, improving site-level forecast accuracy.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3023191369","title":"Improvements of short-term solar radiation forecasting techniques based on satellite and sky-camera imagery","authors":["Francisco Javier Rodríguez Benítez"],"date":"2019-01-01","year":2019,"venue":"Dialnet (Universidad de la Rioja)","venue_type":"preprint","ids":{"openalex":"W3023191369"},"links":{"paper":"https://dialnet.unirioja.es/servlet/tesis?codigo=267006"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["satellite"],"status":"research","summary":"Thesis develops sky-camera and satellite-based short-term solar radiation nowcasting, including machine learning blending models.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3003115921","title":"Using Large-Scale Meteorological Patterns to Better Understand Local-Scale Weather and Climate Extremes","authors":["Paul C. Loikith"],"date":"2019-01-01","year":2019,"venue":"PDXScholar  (Portland State University)","venue_type":"preprint","ids":{"openalex":"W3003115921"},"links":{"paper":"https://pdxscholar.library.pdx.edu/systems_science_seminar_series/5"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"position","method":[],"timescale":[],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Talk overview of large-scale circulation patterns linked to local extremes, using machine learning among methods to assess climate model projections.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2981245087","title":"Spatial and Temporal Analysis of Climate Change in the Future and Comparison of SDSM, LARS-WG and Artificial Neural Network Downscaling Methods (Case Study: Khuzestan Province)","authors":["Razieh Rahimi","Mahdi Rahimi"],"date":"2019-01-01","year":2019,"venue_type":"other","ids":{"openalex":"W2981245087"},"links":{"paper":"https://www.sid.ir/En/Journal/ViewPaper.aspx?ID=649814"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Compares SDSM, LARS-WG and ANN downscaling for future climate change in Khuzestan Province; the abstract is missing, so findings are unclear.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3808-jeil.201900012","title":"Prediction of Long-Term Near-Surface Temperature Based on NA-CORDEX Output","authors":["X. Y. Li","Zhong Li","Q. Q. Zhang","Peng Zhou","Wendy Huang"],"date":"2019-01-01","year":2019,"venue":"Journal of Environmental Informatics Letters","venue_type":"journal","ids":{"doi":"10.3808/jeil.201900012","openalex":"W2979639302"},"links":{"paper":"https://doi.org/10.3808/jeil.201900012","pdf":"http://www.jeiletters.org/index.php?journal=mys&page=article&op=download&path%5B%5D=201900012&path%5B%5D=pdf_201900012"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Neural networks (MLP, TLFN, NARX) correct daily near-surface temperature from NA-CORDEX output at Big Trout Lake, reaching R2 above 0.84.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.32614-rj-2018-049","title":"Stilt: Easy Emulation of Time Series AR(1) Computer Model Output in Multidimensional Parameter Space","authors":["Roman Olson","Kelsey L. Ruckert","Won Chang","Klaus Keller","Murali Haran","Soon‐Il An"],"date":"2019-01-01","year":2019,"venue":"The R Journal","venue_type":"journal","ids":{"doi":"10.32614/rj-2018-049","openalex":"W2909941368"},"links":{"paper":"https://doi.org/10.32614/rj-2018-049","pdf":"https://journal.r-project.org/archive/2018/RJ-2018-049/RJ-2018-049.pdf"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"R package stilt provides simple AR(1) Gaussian process emulation of time series climate model output, with cross-validation and no MCMC needed.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.29252-jwmr.9.18.80","title":"Performance Evaluation of Artificial Neural Network Models for Downscaling and Predicting of Climate Variables","authors":["Ebrahim Omidvar","Maryam Rezaei","Abdollah Pirnia"],"date":"2019-01-01","year":2019,"venue":"Journal of watershed management research","venue_type":"journal","ids":{"doi":"10.29252/jwmr.9.18.80","openalex":"W2914386312"},"links":{"paper":"https://doi.org/10.29252/jwmr.9.18.80"},"orgs":[],"topic":"downscaling","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Evaluates ANN models for downscaling and predicting climate variables; the abstract is only a title, so results are unclear.","significance":1,"cited_by":3,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2208-jscejhe.75.2-i-1207","title":"DEVELOPMENT OF A SEASONAL FORECAST MODEL OF PRECIPITATION USING GLOBAL SURFACE TEMPERATURE IMAGES BY DEEP LEARNING","authors":["Shingo Zenkoji","Taichi TEBAKARI","Kazutoshi Sakakibara","Takuya MATSUURA"],"date":"2019-01-01","year":2019,"venue":"Journal of Japan Society of Civil Engineers Ser B1 (Hydraulic Engineering)","venue_type":"journal","ids":{"doi":"10.2208/jscejhe.75.2_i_1207","openalex":"W3104195250"},"links":{"paper":"https://doi.org/10.2208/jscejhe.75.2_i_1207","pdf":"https://www.jstage.jst.go.jp/article/jscejhe/75/2/75_I_1207/_pdf"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"model","method":["cnn"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"CNN on global surface temperature images forecasts Chao Phraya basin precipitation two months ahead, performing better in the rainy season than the dry season.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2208-jscejer.75.i-33","title":"A DEEP-LEARNING METHOD TO CORRECT THE OUTPUT OF A NUMERICAL WEATHER PREDICTION MODEL USED FOR SHORT-TERM PRECIPITATION FORECAST","authors":["Takeru Kurakami","Kazuyoshi Souma","Takashi Miyamoto","Takahiko FURUYA","Jun Magome","Hiroshi Ishidaira"],"date":"2019-01-01","year":2019,"venue":"Journal of Japan Society of Civil Engineers Ser G (Environmental Research)","venue_type":"journal","ids":{"doi":"10.2208/jscejer.75.i_33","openalex":"W3013710461"},"links":{"paper":"https://doi.org/10.2208/jscejer.75.i_33","pdf":"https://www.jstage.jst.go.jp/article/jscejer/75/5/75_I_33/_pdf"},"orgs":[],"topic":"post-processing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"research","summary":"A CNN corrects cloud-resolving model precipitation output for very short-term rainfall forecasts, trained against JMA analysed rainfall over urban cells.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2151-sola.2019-028","title":"Automatic Detection of Stationary Fronts around Japan Using a Deep Convolutional Neural Network","authors":["Daisuke Matsuoka","Shiori Sugimoto","Y. E. Nakagawa","Shintaro Kawahara","Fumiaki Araki","Yosuke Onoue","Masaaki Iiyama","Koji Koyamada"],"date":"2019-01-01","year":2019,"venue":"SOLA","venue_type":"journal","ids":{"doi":"10.2151/sola.2019-028","openalex":"W2956154338"},"links":{"paper":"https://doi.org/10.2151/sola.2019-028","pdf":"https://www.jstage.jst.go.jp/article/sola/15/0/15_2019-028/_pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"U-Net detects stationary fronts around Japan from multi-variable weather fields, reproducing seasonal front shapes on an untrained year except during typhoons.","significance":3,"cited_by":16,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2139-ssrn.3350281","title":"Weather Forecasting using Machine Learning Techniques","authors":["Siddharth Singh","Mayank Kaushik","Ambuj Gupta","Anil Kumar Malviya"],"date":"2019-01-01","year":2019,"venue":"SSRN Electronic Journal","venue_type":"preprint","ids":{"doi":"10.2139/ssrn.3350281","openalex":"W3100187280"},"links":{"paper":"https://doi.org/10.2139/ssrn.3350281"},"orgs":[],"topic":"global-medium-range","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Generic study applying machine learning techniques to weather forecasting; the abstract is unavailable, so details are unclear.","significance":1,"cited_by":48,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijhst.2019.102316","title":"Climate modelling using ANN","authors":["Mehnaza Akhter","Manzoor Ahmad Ahanger"],"date":"2019-01-01","year":2019,"venue":"International Journal of Hydrology Science and Technology","venue_type":"journal","ids":{"doi":"10.1504/ijhst.2019.102316","openalex":"W2895861785"},"links":{"paper":"https://doi.org/10.1504/ijhst.2019.102316"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"ANN downscales GCM predictors to Jhelum basin stations, projecting 2100 warming of 1.4 to 1.6 C and a 31 to 35% precipitation drop.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijes.2019.098300","title":"A survey on rainfall forecasting using artificial neural network","authors":["Qi Liu","Yanyun Zou","Xiaodong Liu","Nigel Linge"],"date":"2019-01-01","year":2019,"venue":"International Journal of Embedded Systems","venue_type":"journal","ids":{"doi":"10.1504/ijes.2019.098300","openalex":"W4247173155"},"links":{"paper":"https://doi.org/10.1504/ijes.2019.098300"},"orgs":["nuist"],"topic":"post-processing","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Surveys artificial neural network methods for rainfall prediction and argues they improve accuracy over traditional NWP and statistical models.","significance":2,"cited_by":47,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijds.2019.10022087","title":"Analysis of weather data using various regression algorithms","authors":["Yeturu Jahnavi"],"date":"2019-01-01","year":2019,"venue":"International Journal of Data Science","venue_type":"journal","ids":{"doi":"10.1504/ijds.2019.10022087","openalex":"W4246060532"},"links":{"paper":"https://doi.org/10.1504/ijds.2019.10022087"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Compares linear regression, CART, MLP and SVM on station temperature, pressure and humidity data; no new method is proposed.","significance":1,"cited_by":19,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.13140-rg.2.2.25876.45441","title":"The Added Value of Machine Learning in Forecasting Wind Turbine Icing","authors":["Lukas Kugler"],"date":"2019-01-01","year":2019,"venue_type":"other","ids":{"doi":"10.13140/rg.2.2.25876.45441","openalex":"W3155863617"},"links":{"paper":"https://doi.org/10.13140/rg.2.2.25876.45441"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Machine learning classifiers using NWP and site data raise the economic value of wind turbine icing forecasts over logistic regression and empirical rules.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.13140-rg.2.2.22218.82885","title":"Development and interpretation of deep-learning models for nowcasting convective hazards","authors":["Ryan Lagerquist","Homeyer, Cameron","Mcgovern, Amy","Potvin, Corey K","Sandmael, Thea","Smith, Travis"],"date":"2019-01-01","year":2019,"venue_type":"other","ids":{"doi":"10.13140/rg.2.2.22218.82885","openalex":"W3118671649"},"links":{"paper":"https://doi.org/10.13140/rg.2.2.22218.82885"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"Develops and interprets deep learning models for nowcasting convective hazards, with attention to model explainability.","significance":3,"cited_by":5,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.12720-sgce.8.2.103-110","title":"Short-term wind power forecasting using long-short term memory based recurrent neural network model and variable selection","authors":["Ümit Cali","Vinayak Sharma"],"date":"2019-01-01","year":2019,"venue":"International Journal of Smart Grid and Clean Energy","venue_type":"journal","ids":{"doi":"10.12720/sgce.8.2.103-110","openalex":"W2959898713"},"links":{"paper":"https://doi.org/10.12720/sgce.8.2.103-110","pdf":"http://www.ijsgce.com/uploadfile/2019/0215/20190215023752989.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"LSTM-RNN forecasts Sotavento wind farm power 1 to 24 hours ahead using NWP inputs chosen by sensitivity analysis.","significance":2,"cited_by":65,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11648-j.eas.20190406.12","title":"Intelligent Methods Used for Obtaining Weather Derivatives: A Review","authors":["Gujanatti Rudrappa","Nataraj A. Vijapur"],"date":"2019-01-01","year":2019,"venue":"Engineering and Applied Sciences","venue_type":"journal","ids":{"doi":"10.11648/j.eas.20190406.12","openalex":"W2996316435"},"links":{"paper":"https://doi.org/10.11648/j.eas.20190406.12","pdf":"http://article.sciencepublishinggroup.com/pdf/10.11648.j.eas.20190406.12.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Survey of machine learning for weather parameter estimation tied to weather derivatives, with a proposed image-processing and neural network method.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11581-dtu-00000054","title":"Minute-Scale Wind Forecasting Using Lidar Inflow Measurements","authors":["Elliot Simon"],"date":"2019-01-01","year":2019,"venue":"DTU Data","venue_type":"preprint","ids":{"doi":"10.11581/dtu:00000054","openalex":"W2915799525"},"links":{"paper":"https://doi.org/10.11581/dtu:00000054"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Uses upstream lidar inflow measurements with classification and probabilistic regression for minute-scale wind and power forecasts.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2019-5692753","title":"Rainfall and Atmospheric Temperature against the Other Climatic Factors: A Case Study from Colombo, Sri Lanka","authors":["Anushka Perera","Upaka Rathnayake"],"date":"2019-01-01","year":2019,"venue":"Mathematical Problems in Engineering","venue_type":"journal","ids":{"doi":"10.1155/2019/5692753","openalex":"W2997018579"},"links":{"paper":"https://doi.org/10.1155/2019/5692753","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/2019/5692753"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"ANN models relate monthly temperature and rainfall in Colombo, Sri Lanka, to humidity and wind, with temperature predicted well and rainfall poorly.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2019.2939657","title":"Machine Learning-Based Prediction of Icing-Related Wind Power Production Loss","authors":["Sebastian Scher","Jennie Molinder"],"date":"2019-01-01","year":2019,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2019.2939657","openalex":"W2971571896"},"links":{"paper":"https://doi.org/10.1109/access.2019.2939657","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08825865.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Random forests use regional weather forecasts and on-site data to predict icing-related wind power losses up to 42 hours ahead.","significance":2,"cited_by":31,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-access.2019.2925565","title":"P_Segnet and NP_Segnet: New Neural Network Architectures for Cloud Recognition of Remote Sensing Images","authors":["Junyu Lu","Yuzhu Wang","Yueqin Zhu","Xiaohui Ji","Tingyan Xing","Wei Li","Albert Y. Zomaya"],"date":"2019-01-01","year":2019,"venue":"IEEE Access","venue_type":"journal","ids":{"doi":"10.1109/access.2019.2925565","openalex":"W2954810592"},"links":{"paper":"https://doi.org/10.1109/access.2019.2925565","pdf":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08750801.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["satellite"],"status":"research","summary":"Proposes P_SegNet and NP_SegNet, modified SegNet architectures for cloud segmentation in remote sensing imagery, with improved accuracy over FCN baselines.","significance":2,"cited_by":32,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.trpro.2019.07.214","title":"Development of a system for collecting and processing sky images and meteorological data used for weather prediction","authors":["Martin Šinko","Peter Sýkora","Patrik Kamencay","Róbert Hudec"],"date":"2019-01-01","year":2019,"venue":"Transportation research procedia","venue_type":"journal","ids":{"doi":"10.1016/j.trpro.2019.07.214","openalex":"W2966730076"},"links":{"paper":"https://doi.org/10.1016/j.trpro.2019.07.214","pdf":"https://www.sciencedirect.com/science/article/pii/S2352146519303850/pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations","other"],"status":"pre-operational","summary":"Builds a sky-camera and weather-station system and uses a CNN to classify sky condition with 97.8% accuracy for local short-term prediction.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.mex.2019.05.029","title":"Evaluation of performance of drought prediction in Indonesia based on TRMM and MERRA-2 using machine learning methods","authors":["Heri Kuswanto","Achmad Naufal"],"date":"2019-01-01","year":2019,"venue":"MethodsX","venue_type":"journal","ids":{"doi":"10.1016/j.mex.2019.05.029","openalex":"W2947019155"},"links":{"paper":"https://doi.org/10.1016/j.mex.2019.05.029"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["era5","satellite"],"status":"research","summary":"Random forest predicts 3-month SPI drought in East Nusa Tenggara with about 0.8 AUC, with MERRA-2 inputs outperforming TRMM.","significance":2,"cited_by":35,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.mex.2019.03.002","title":"Comparative study on typhoon’s wind speed prediction by a neural networks model and a hydrodynamical model","authors":["Tahereh Haghroosta"],"date":"2019-01-01","year":2019,"venue":"MethodsX","venue_type":"journal","ids":{"doi":"10.1016/j.mex.2019.03.002","openalex":"W2922983991"},"links":{"paper":"https://doi.org/10.1016/j.mex.2019.03.002"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Compares ANFIS neuro-fuzzy and WRF models for South China Sea typhoon wind speed; ANFIS gives higher correlation and lower RMSE.","significance":2,"cited_by":9,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1902.05631","title":"Super-Resolution Simulation for Real-Time Prediction of Urban Micrometeorology","authors":["Ryo Onishi","Daisuke Sugiyama","Keigo Matsuda"],"date":"2019-01-01","year":2019,"venue":"SOLA","venue_type":"journal","ids":{"arxiv":"1902.05631","doi":"10.2151/sola.2019-032","openalex":"W2914907552"},"links":{"paper":"https://doi.org/10.2151/sola.2019-032","pdf":"https://www.jstage.jst.go.jp/article/sola/15/0/15_2019-032/_pdf"},"orgs":[],"topic":"downscaling","topics":["regional-km-scale"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["km-scale-sim"],"status":"research","summary":"CNN super-resolution applied to low-resolution urban micrometeorology simulations gives 4x finer predictions faster than high-resolution runs, beating interpolation.","significance":3,"cited_by":50,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5753-jidm.2018.2044","title":"Identifying Finest Machine Learning Algorithm for Climate Data Imputation in the State of Minas Gerais, Brazil","authors":["Lucas O. Bayma","Marconi de Arruda Pereira"],"date":"2018-12-30","year":2018,"venue":"Journal of Information and Data Management","venue_type":"journal","ids":{"doi":"10.5753/jidm.2018.2044","openalex":"W3091610863"},"links":{"paper":"https://doi.org/10.5753/jidm.2018.2044","pdf":"https://sol.sbc.org.br/journals/index.php/jidm/article/download/2044/1733"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Compares neural networks, bagged trees and random forest for filling missing station climate records in Minas Gerais, Brazil; random forest performs best.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1812.10915","title":"Spatiotemporal Data Fusion for Precipitation Nowcasting","authors":["Vladimir Ivashkin","Vadim Lebedev"],"date":"2018-12-28","year":2018,"venue_type":"preprint","ids":{"arxiv":"1812.10915","openalex":"W2908415820"},"links":{"paper":"https://arxiv.org/abs/1812.10915","pdf":"https://arxiv.org/pdf/1812.10915"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["global"],"data":["radar","satellite"],"status":"research","summary":"Computer-vision pipeline with soft-mask inpainting fuses satellite and radar observations to extend precipitation nowcasting beyond radar coverage.","significance":3,"cited_by":4,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1812.09758","title":"Detecting British Columbia Coastal Rainfall Patterns by Clustering Gaussian Processes","authors":["Forrest Paton","Paul D. McNicholas"],"date":"2018-12-23","year":2018,"venue_type":"preprint","ids":{"arxiv":"1812.09758"},"links":{"paper":"https://arxiv.org/abs/1812.09758","pdf":"https://arxiv.org/pdf/1812.09758"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Gaussian process clustering by covariance kernel groups British Columbia coastal rainfall records, linking clusters to El Niño and La Niña patterns.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-wcc.567","title":"S2S reboot: An argument for greater inclusion of machine learning in subseasonal to seasonal forecasts","authors":["Judah Cohen","Dim Coumou","Jessica Hwang","Lester Mackey","Paulo Orenstein","Sonja Totz","Eli Tziperman"],"date":"2018-12-18","year":2018,"venue":"WIREs Climate Change","venue_type":"journal","ids":{"doi":"10.1002/wcc.567","openalex":"W2903758338"},"links":{"paper":"https://doi.org/10.1002/wcc.567"},"orgs":["microsoft-research","mit","pik","stanford"],"topic":"s2s-seasonal","topics":[],"type":"position","method":["classical-ml"],"timescale":["s2s","seasonal"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"Opinion article arguing machine learning should be adopted for S2S forecasting, showing statistical methods beat dynamical models on a polar vortex case.","significance":4,"cited_by":112,"score":61,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2018jd028675","title":"Exploring How Eruption Source Parameters Affect Volcanic Radiative Forcing Using Statistical Emulation","authors":["Lauren Marshall","Jill S. Johnson","Graham W. Mann","Lindsay A. Lee","Sandip S Dhomse","Leighton A. Regayre","Masaru Yoshioka","K. S. Carslaw","Anja Schmidt"],"date":"2018-12-17","year":2018,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2018jd028675","openalex":"W2903710715"},"links":{"paper":"https://doi.org/10.1029/2018jd028675","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018JD028675"},"orgs":["university-of-cambridge"],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Statistical emulators trained on 30 GCM runs map eruption parameters to volcanic aerosol forcing, producing response surfaces for thousands of eruptions.","significance":2,"cited_by":118,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.24215-16666038.18.e21","title":"Short term cloud nowcasting for a solar power plant based on irradiance historical data","authors":["Rafael Caballero","Luis Fernando Zarzalejo","Álvaro Otero","Luís Piñuel","Stefan Wilbert"],"date":"2018-12-12","year":2018,"venue":"Journal of Computer Science and Technology","venue_type":"journal","ids":{"doi":"10.24215/16666038.18.e21","openalex":"W2904583180"},"links":{"paper":"https://doi.org/10.24215/16666038.18.e21","pdf":"https://journal.info.unlp.edu.ar/JCST/article/download/1112/906"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"An LSTM forecasts 5-minute solar irradiance minutes ahead from one year of plant radiometer data, beating standard time-series baselines.","significance":2,"cited_by":6,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1812.04951","title":"The FLUXCOM ensemble of global land-atmosphere energy fluxes","authors":["Martin Jung","Sujan Koirala","Ulrich Weber","Kazuhito Ichii","Fabian Gans","Gustau-Camps-Valls","Dario Papale","Christopher Schwalm","Gianluca Tramontana","Markus Reichstein"],"date":"2018-12-11","year":2018,"venue_type":"preprint","ids":{"arxiv":"1812.04951"},"links":{"paper":"https://arxiv.org/abs/1812.04951","pdf":"https://arxiv.org/pdf/1812.04951"},"orgs":[],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"benchmark","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","stations","era5"],"status":"research","summary":"Machine learning merges FLUXNET eddy-covariance towers with remote sensing and meteorological data into a 147-product global land-atmosphere energy flux database with uncertainties.","significance":5,"score":20,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3170892938","title":"Deepti: Deep Learning-Based Tropical Cyclone Intensity Estimation","authors":["Manil Maskey","Rahul Ramachandran","Jeffrey J. Miller","Iksha Gurung","Brian M. Freitag","Drew Bollinger","Daniel Oliveira da Silva","Andrew Molthan","Christopher Hain","Dan Cecil"],"date":"2018-12-10","year":2018,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2020.3011907","openalex":"W3170892938"},"links":{"paper":"https://doi.org/10.1109/jstars.2020.3011907"},"orgs":["nasa"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"operational","method":["cnn"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"operational","summary":"Deep learning model estimates tropical cyclone intensity from satellite data at higher temporal frequency, deployed in a production monitoring system with a portal.","significance":3,"cited_by":83,"score":57,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1812.01943","title":"Prediction of typhoon tracks using a generative adversarial network with observational and meteorological data","authors":["Mario Rüttgers","Sangseung Lee","Donghyun You"],"date":"2018-12-05","year":2018,"venue_type":"preprint","ids":{"arxiv":"1812.01943","openalex":"W2902006725"},"links":{"paper":"https://arxiv.org/abs/1812.01943","pdf":"https://arxiv.org/pdf/1812.01943"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["gan-vae","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"Uses a GAN on satellite images plus reanalysis fields to predict typhoon centre tracks 6 hours ahead, with 67.2 km mean error versus 95.6 km for images alone.","significance":3,"cited_by":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1111-wej.12443","title":"Assessing future rainfall uncertainties of climate change in Taiwan with a bootstrapped neural network‐based downscaling model","authors":["Chi‐Yu Li","Shiu‐Shin Lin","Chia-Min Chuang","Yen‐Li Hu"],"date":"2018-12-02","year":2018,"venue":"Water and Environment Journal","venue_type":"journal","ids":{"doi":"10.1111/wej.12443","openalex":"W2902354098"},"links":{"paper":"https://doi.org/10.1111/wej.12443","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/wej.12443"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"A bootstrapped RBF neural network downscales three GCMs to project Taiwan station rainfall for 2050–2090 with quantified uncertainty.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W4289233296","title":"DYNAMIC BAYESIAN NETWORK FOR WEATHER FORECAST AND EVALUATION OF RENEWABLE RESOURCES AVAILABILITY","authors":["Alina-Alexandra Ciobanu","Florin Munteanu","Ciprian Mircea Nemeș","Mihaela Adochitei"],"date":"2018-12-01","year":2018,"venue":"DOAJ (DOAJ: Directory of Open Access Journals)","venue_type":"preprint","ids":{"openalex":"W4289233296"},"links":{"paper":"https://doaj.org/article/cb20a87cc7684782854038c39139652e"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Bayesian network learned from four years of station data forecasts wind speed and solar irradiance classes for renewable energy resource evaluation.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3173624484","title":"Runway visual range prediction using Convolutional Neural Network with Weather information","authors":["SungKwan Ku","Seungsu Kim","Seokmin Hong"],"date":"2018-12-01","year":2018,"venue":"International Journal of Advanced Culture Technology(IJACT)","venue_type":"journal","ids":{"openalex":"W3173624484"},"links":{"paper":"https://www.earticle.net/Article/A348106"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"CNN trained on past wind, humidity, temperature and visibility predicts runway visual range at a local airport from station time series.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3045416016","title":"Machine Learning techniques to evaluate reproducibility of climate model simulations on hybrid architectures.","authors":["Shreya Mahajan -","Katherine J. Evans","James H. Kennedy"],"date":"2018-12-01","year":2018,"venue":"AGUFM","venue_type":"journal","ids":{"openalex":"W3045416016"},"links":{"paper":"http://ui.adsabs.harvard.edu/abs/2018AGUFMIN13C0687M/abstract"},"orgs":[],"topic":"infra-software","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"AGU abstract-less entry applying machine learning to assess reproducibility of climate model simulations across hybrid HPC architectures.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2999153000","title":"Fast Neural Network Emulation of a Planetary Boundary Layer Parameterization in Weather Research Forecasting Model","authors":["J. Wang","Prasanna Balaprakash","Veerabhadra Rao Kotamarthi"],"date":"2018-12-01","year":2018,"venue":"AGUFM","venue_type":"journal","ids":{"openalex":"W2999153000"},"links":{"paper":"https://ui.adsabs.harvard.edu/abs/2018AGUFM.T31E0368W/abstract"},"orgs":[],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"A neural network emulates a WRF planetary boundary layer scheme to speed up regional weather simulations; abstract-less AGU entry.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.7780-kjrs.2018.34.6.2.10","title":"The Estimation of Arctic Air Temperature in Summer Based on Machine Learning Approaches Using IABP Buoy and AMSR2 Satellite Data","authors":["Daehyeon Han","Young Jun Kim","Jungho Im","Sanggyun Lee","Yeonsu Lee","Hyun‐Cheol Kim"],"date":"2018-12-01","year":2018,"venue":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","venue_type":"preprint","ids":{"doi":"10.7780/kjrs.2018.34.6.2.10","openalex":"W2963498958"},"links":{"paper":"https://doi.org/10.7780/kjrs.2018.34.6.2.10"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"Random forest and SVM estimate summer Arctic air temperature from AMSR2 microwave data and buoys, reaching R² of 0.84–0.88 and RMSE of 1.31–1.53 °C.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1186-s40645-018-0245-y","title":"Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model","authors":["Daisuke Matsuoka","Masuo Nakano","Daisuke Sugiyama","Seiichi Uchida"],"date":"2018-12-01","year":2018,"venue":"Progress in Earth and Planetary Science","venue_type":"journal","ids":{"doi":"10.1186/s40645-018-0245-y","openalex":"W2905387508"},"links":{"paper":"https://doi.org/10.1186/s40645-018-0245-y"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A CNN ensemble detects western North Pacific tropical cyclones and their precursors 2–7 days ahead in cloud-resolving simulations, with 79.9–89.1% detection.","significance":3,"cited_by":104,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2018.11.060","title":"Application of machine learning to an early warning system for very short-term heavy rainfall","authors":["Seung‐Hyun Moon","Yong-Hyuk Kim","Yong Hee Lee","Byung-Ro Moon"],"date":"2018-11-29","year":2018,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2018.11.060","openalex":"W2902735427"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2018.11.060"},"orgs":["kma"],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"research","summary":"Applies machine learning to an early warning system for very short-term heavy rainfall; abstract unavailable, classification based on title only.","significance":2,"cited_by":109,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w10121750","title":"Uncertainty in Rainfall Intensity Duration Frequency Curves of Peninsular Malaysia under Changing Climate Scenarios","authors":["Muhammad Noor","Tarmizi Ismail","‪Eun‐Sung Chung","Shamsuddin Shahid","Jang Hyun Sung"],"date":"2018-11-28","year":2018,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w10121750","openalex":"W2902731828"},"links":{"paper":"https://doi.org/10.3390/w10121750","pdf":"https://www.mdpi.com/2073-4441/10/12/1750/pdf?version=1543399333"},"orgs":[],"topic":"downscaling","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Combines MOS downscaling of GCM rainfall with ANN temporal disaggregation to project IDF curves for Peninsular Malaysia under RCP4.5 and RCP8.5 with uncertainty bounds.","significance":2,"cited_by":79,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1811.09735","title":"A Multi-variable Stacked Long-Short Term Memory Network for Wind Speed Forecasting","authors":["Sisheng Liang","Long Nguyen","Fang Jin"],"date":"2018-11-24","year":2018,"venue_type":"preprint","ids":{"arxiv":"1811.09735"},"links":{"paper":"https://arxiv.org/abs/1811.09735","pdf":"https://arxiv.org/pdf/1811.09735"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Multi-variable stacked LSTM forecasts short-term wind speed at West Texas sites from meteorological inputs, with competitive accuracy versus baselines.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-018-2702-3","title":"Simulation of precipitation time series using tree-rings, earlywood vessel features, and artificial neural network","authors":["Vahid Gholami","Javad Torkaman","Pejman Dalir"],"date":"2018-11-23","year":2018,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-018-2702-3","openalex":"W2900793336"},"links":{"paper":"https://doi.org/10.1007/s00704-018-2702-3"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["other"],"status":"research","summary":"Uses an artificial neural network with tree-ring and earlywood vessel features to simulate precipitation time series; abstract unavailable, classification based on title only.","significance":2,"cited_by":27,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1811.09496","title":"The Error is the Feature: how to Forecast Lightning using a Model Prediction Error","authors":["Christian Schön","Jens Dittrich","Richard Müller"],"date":"2018-11-23","year":2018,"venue_type":"preprint","ids":{"arxiv":"1811.09496","doi":"10.1145/3292500.3330682","openalex":"W4288278953"},"links":{"paper":"https://arxiv.org/abs/1811.09496","pdf":"https://arxiv.org/pdf/1811.09496"},"orgs":["dwd"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Uses optical-flow error from satellite imagery as features for tree and neural classifiers to predict lightning up to five hours ahead, with 96% accuracy at 15 minutes.","significance":3,"cited_by":23,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1111-geb.12836","title":"Climate seasonality as an essential predictor of global fire activity","authors":["Michael V. Saha","Todd M. Scanlon","Paolo D’Odorico"],"date":"2018-11-21","year":2018,"venue":"Global Ecology and Biogeography","venue_type":"journal","ids":{"doi":"10.1111/geb.12836","openalex":"W2901742406"},"links":{"paper":"https://doi.org/10.1111/geb.12836"},"orgs":["uc-berkeley"],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Random forests show that climate seasonality metrics of precipitation and temperature predict 66-87% of global multi-year fire activity variability.","significance":2,"cited_by":26,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00521-018-3874-6","title":"PHURIE: hurricane intensity estimation from infrared satellite imagery using machine learning","authors":["Amina Asif","Muhammad Dawood","Bismillah Jan","Javaid Khurshid","Mark DeMaria","Fayyaz Minhas"],"date":"2018-11-19","year":2018,"venue":"Neural Computing and Applications","venue_type":"journal","ids":{"doi":"10.1007/s00521-018-3874-6","openalex":"W2901210418"},"links":{"paper":"https://doi.org/10.1007/s00521-018-3874-6"},"orgs":["noaa"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"PHURIE uses machine learning on infrared satellite imagery to estimate hurricane intensity; abstract unavailable, classification based on title only.","significance":3,"cited_by":32,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1811.06341","title":"Spatio-temporal Stacked LSTM for Temperature Prediction in Weather Forecasting","authors":["Zahra Karevan","Johan A. K. Suykens"],"date":"2018-11-15","year":2018,"venue_type":"preprint","ids":{"arxiv":"1811.06341"},"links":{"paper":"https://arxiv.org/abs/1811.06341","pdf":"https://arxiv.org/pdf/1811.06341"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Two-layer spatio-temporal stacked LSTM predicts temperature across multiple locations, with spatial information improving accuracy in most cases.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-08839514.2018.1530858","title":"Designing Weather Forecasting Model Using Computational Intelligence Tools","authors":["Bashar Muneer Yahya","Dursun Zafer Şeker"],"date":"2018-11-13","year":2018,"venue":"Applied Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1080/08839514.2018.1530858","openalex":"W2901800528"},"links":{"paper":"https://doi.org/10.1080/08839514.2018.1530858","pdf":"https://www.tandfonline.com/doi/pdf/10.1080/08839514.2018.1530858?needAccess=true&role=button"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural network models (RBF, fuzzy C-means, NARX) forecast weather variables in Nineveh, Iraq, to 2050, with a GUI for decision-makers; no quantitative accuracy given.","significance":2,"cited_by":33,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tste.2018.2880615","title":"Ensemble Machine Learning-Based Wind Forecasting to Combine NWP Output With Data From Weather Station","authors":["Pengwei Du"],"date":"2018-11-12","year":2018,"venue":"IEEE Transactions on Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1109/tste.2018.2880615","openalex":"W2901316757"},"links":{"paper":"https://doi.org/10.1109/tste.2018.2880615"},"orgs":[],"topic":"post-processing","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Ensemble of ANN, SVR and Gaussian process models blends NWP wind forecasts with weather-station data via Bayesian model averaging for wind power forecasting at ERCOT.","significance":3,"cited_by":107,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018gl080704","title":"Toward Data‐Driven Weather and Climate Forecasting: Approximating a Simple General Circulation Model With Deep Learning","authors":["Sebastian Scher"],"date":"2018-11-12","year":2018,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2018gl080704","openalex":"W2900615125"},"links":{"paper":"https://doi.org/10.1029/2018gl080704","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018GL080704"},"orgs":[],"topic":"climate-emulation","topics":["global-medium-range"],"type":"model","method":["other"],"timescale":["climate","medium"],"spatial":["global"],"data":["other"],"status":"research","summary":"Deep network emulates a simple general circulation model, forecasting its states and producing stable climate runs with matching statistics and no long-term drift.","significance":5,"cited_by":303,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-018-2686-z","title":"ANN-based statistical downscaling of climatic parameters using decision tree predictor screening method","authors":["Vahid Nourani","Zahra Razzaghzadeh","Aida Hosseini Baghanam","Amir Molajou"],"date":"2018-11-12","year":2018,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-018-2686-z","openalex":"W2901093259"},"links":{"paper":"https://doi.org/10.1007/s00704-018-2686-z"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","other"],"status":"research","summary":"ANN-based statistical downscaling of climate parameters with decision-tree predictor screening; abstract unavailable, classification based on title only.","significance":2,"cited_by":106,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1811.04817","title":"A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns","authors":["Ashesh Chattopadhyay","Pedram Hassanzadeh","Saba Pasha"],"date":"2018-11-12","year":2018,"venue":"Scientific Reports, 2020","venue_type":"journal","ids":{"arxiv":"1811.04817","doi":"10.1038/s41598-020-57897-9","openalex":"W2899751676"},"links":{"paper":"https://arxiv.org/abs/1811.04817","pdf":"https://arxiv.org/pdf/1811.04817"},"orgs":[],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"model","method":["cnn","classical-ml"],"timescale":[],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Uses unsupervised clustering to auto-label North American weather regimes in climate model output, then trains CNNs to re-identify them, reaching 90–94% accuracy.","significance":3,"cited_by":195,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1371-journal.pone.0206872","title":"Defining heatwave thresholds using an inductive machine learning approach","authors":["Juhyeon Park","Jeongseob Kim"],"date":"2018-11-07","year":2018,"venue":"PLoS ONE","venue_type":"journal","ids":{"doi":"10.1371/journal.pone.0206872","openalex":"W2899564121"},"links":{"paper":"https://doi.org/10.1371/journal.pone.0206872"},"orgs":[],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"MARS regression on Korean emergency visits and meteorological data yields heatwave thresholds, such as 32.58°C maximum temperature for two consecutive days.","significance":3,"cited_by":28,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3233-ica-180589","title":"Determining geostrophic wind direction in a rainfall forecast expert system","authors":["F. S. Buendía-Buendía","Gabriel Buendia","Diego Andina"],"date":"2018-11-06","year":2018,"venue":"Integrated Computer-Aided Engineering","venue_type":"journal","ids":{"doi":"10.3233/ica-180589","openalex":"W2899789612"},"links":{"paper":"https://doi.org/10.3233/ica-180589","pdf":"https://content.iospress.com:443/download/integrated-computer-aided-engineering/ica180589?id=integrated-computer-aided-engineering%2Fica180589"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural-network rainfall forecasting expert system estimates local geostrophic wind direction and magnitude from surrounding pressure and temperature observations in Valladolid, Spain.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25126-jitecs.20183258","title":"Prediction of Rainfall using Simplified Deep Learning based Extreme Learning Machines","authors":["Imam Cholissodin","Sutrisno Sutrisno"],"date":"2018-11-05","year":2018,"venue":"Journal of Information Technology and Computer Science","venue_type":"journal","ids":{"doi":"10.25126/jitecs.20183258","openalex":"W2900229525"},"links":{"paper":"https://doi.org/10.25126/jitecs.20183258","pdf":"https://jitecs.ub.ac.id/index.php/jitecs/article/download/58/42"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Simplified deep extreme learning machines are proposed for Indonesian rainfall prediction to support planting calendars; no quantitative accuracy is reported in the abstract.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2018.2874950","title":"Estimating Summertime Precipitation from Himawari-8 and Global Forecast System Based on Machine Learning","authors":["Min Min","Chen Bai","Jianping Guo","Fenglin Sun","Chao Liu","Fu Wang","Hui Xu","Shihao Tang","Bo Li","Di Di","Lixin Dong","Jun Li"],"date":"2018-11-05","year":2018,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2018.2874950","openalex":"W2900303043"},"links":{"paper":"https://doi.org/10.1109/tgrs.2018.2874950"},"orgs":["nuist","cma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Random forest estimates summertime precipitation from Himawari-8 infrared brightness temperatures plus GFS predictors, reaching 0.87 classification accuracy and 2.0 mm/h RMSE against GPM.","significance":3,"cited_by":153,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3045379863","title":"Statistical post-processing of a numerical weather prediction model with neural networks / by Matthias Göbel","authors":["Matthias Göbel"],"date":"2018-11-01","year":2018,"venue_type":"other","ids":{"openalex":"W3045379863"},"links":{"paper":"https://diglib.uibk.ac.at/urn:nbn:at:at-ubi:1-31230"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Thesis applying neural networks to statistically post-process numerical weather prediction output; abstract unavailable, so significance is judged from title only.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.26438-ijsrcse-v6i5.2024","title":"Weather Prediction through Sliding Window Algorithm and Deep Learning","authors":["Shubham Billus","Shivam Billus","Rishab Behl"],"date":"2018-10-31","year":2018,"venue":"International Journal of Scientific Research in Computer Sciences and Engineering","venue_type":"journal","ids":{"doi":"10.26438/ijsrcse/v6i5.2024","openalex":"W2907282955"},"links":{"paper":"https://doi.org/10.26438/ijsrcse/v6i5.2024","pdf":"http://www.isroset.org/pub_paper/IJSRCSE/5-IJSRCSE-01217.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Title describes deep-learning weather prediction with a sliding-window method, but the abstract is boilerplate and reports no method details or results.","significance":0,"cited_by":0,"score":0,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5281-ijrset.v2i10.196","title":"Climatic Prognosticate Identification using Soft Computing Techniques and Algorithmic Concepts","authors":["MALARKODI P","BARANIDHARAN N","ARUNACHALAM S"],"date":"2018-10-30","year":2018,"venue":"International Journal for Research in Science Engineering & Technology","venue_type":"journal","ids":{"doi":"10.5281/ijrset.v2i10.196","openalex":"W7215043424"},"links":{"paper":"https://doi.org/10.5281/ijrset.v2i10.196","pdf":"https://ijrset.in/index.php/ijrset/article/download/196/167"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"ANFIS and multiple linear regression predict monthly station temperature, humidity, wind and pressure from 2008–2012 data; ANFIS gives lower RMSE.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018jd028375","title":"Short‐Term Precipitation Forecast Based on the PERSIANN System and LSTM Recurrent Neural Networks","authors":["Ata Akbari Asanjan","Tiantian Yang","Kuolin Hsu","Soroosh Sorooshian","Junqiang Lin","Qidong Peng"],"date":"2018-10-29","year":2018,"venue":"Journal of Geophysical Research Atmospheres","venue_type":"journal","ids":{"doi":"10.1029/2018jd028375","openalex":"W2898796705"},"links":{"paper":"https://doi.org/10.1029/2018jd028375","pdf":"https://agupubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018JD028375"},"orgs":["university-of-oklahoma"],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"An LSTM extrapolates cloud-top brightness temperature, then PERSIANN retrieves 0–6 h rainfall, beating RNN, optical flow and RAP over three US regions.","significance":3,"cited_by":206,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-aae159","title":"Machine learning methods for crop yield prediction and climate change impact assessment in agriculture","authors":["Andrew Crane-Droesch"],"date":"2018-10-26","year":2018,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/aae159","openalex":"W2891765392"},"links":{"paper":"https://doi.org/10.1088/1748-9326/aae159"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Reviews machine learning for crop yield prediction and climate impact on agriculture, with crops rather than the climate system as the main target.","significance":2,"cited_by":494,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1810.10485","title":"Precipitation Nowcasting: Leveraging bidirectional LSTM and 1D CNN","authors":["Maitreya Patel","Anery Patel","Ranendu Ghosh"],"date":"2018-10-24","year":2018,"venue_type":"preprint","ids":{"arxiv":"1810.10485","openalex":"W2896555060"},"links":{"paper":"http://arxiv.org/abs/1810.10485","pdf":"https://arxiv.org/pdf/1810.10485"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":[],"data":["other"],"status":"research","summary":"Bidirectional LSTM is compared with a 1D CNN for multivariate precipitation nowcasting, with sequence models favoured over feed-forward networks; no quantitative results are given.","significance":2,"cited_by":11,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1810.10286","title":"Learning color space adaptation from synthetic to real images of cirrus clouds","authors":["Qing Lyu","Minghao Chen","Xiang Chen"],"date":"2018-10-24","year":2018,"venue_type":"preprint","ids":{"arxiv":"1810.10286"},"links":{"paper":"https://arxiv.org/abs/1810.10286","pdf":"https://arxiv.org/pdf/1810.10286"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["gan-vae"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Adversarial color-space adaptation from synthetic to real cirrus cloud images, improving cloud segmentation by 6.59% for climate-related image analysis.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijhst.2019.10016868","title":"Climate modeling using ANN","authors":["Manzoor Ahmad Ahanger","Mehnaza Akhter"],"date":"2018-10-15","year":2018,"venue":"International Journal of Hydrology Science and Technology","venue_type":"journal","ids":{"doi":"10.1504/ijhst.2019.10016868","openalex":"W3101871812"},"links":{"paper":"https://doi.org/10.1504/ijhst.2019.10016868"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"An ANN downscales GCM predictors to four Jhelum basin stations, projecting 1.4–1.6°C warming and 31–35% precipitation decline by 2100.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1905.08736","title":"Identification of synoptic weather types over Taiwan area with multiple classifiers","authors":["Shih‐Hao Su","Jung‐Lien Chu","Ting‐Shuo Yo","Lee‐Yaw Lin"],"date":"2018-10-15","year":2018,"venue":"Atmospheric Science Letters","venue_type":"journal","ids":{"arxiv":"1905.08736","doi":"10.1002/asl.861","openalex":"W2897629863"},"links":{"paper":"https://doi.org/10.1002/asl.861","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asl.861"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5"],"status":"research","summary":"Three classifiers, with SVM best, identify synoptic weather types over Taiwan from reanalysis with 52–83% hit rates.","significance":2,"cited_by":22,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1810.06327","title":"Deep Photovoltaic Nowcasting","authors":["Jinsong Zhang","Rodrigo Verschae","Shohei Nobuhara","Jean-François Lalonde"],"date":"2018-10-15","year":2018,"venue":"Solar Energy","venue_type":"journal","ids":{"arxiv":"1810.06327","doi":"10.1016/j.solener.2018.10.024","openalex":"W2963986342"},"links":{"paper":"https://arxiv.org/abs/1810.06327","pdf":"https://arxiv.org/pdf/1810.06327"},"orgs":[],"topic":"applications-impacts","topics":["nowcasting"],"type":"application","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["local"],"data":["other"],"status":"pre-operational","summary":"Compares MLP, CNN and LSTM models using sky images to nowcast one-minute photovoltaic output; LSTM gives a 21% RMSE skill gain over persistence.","significance":3,"cited_by":205,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-jstars.2018.2873257","title":"High Winds From Combined Active and Passive Measurements of HY-2A Satellite","authors":["Xingou Xu","Xiaolong Dong","Di Zhu","Shuyan Lang"],"date":"2018-10-12","year":2018,"venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/jstars.2018.2873257","openalex":"W2897345032"},"links":{"paper":"https://doi.org/10.1109/jstars.2018.2873257"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"An ANN fuses HY-2A radiometer and scatterometer data to retrieve typhoon wind fields, outperforming operational HSCAT winds against GRAPES and H*Wind references.","significance":2,"cited_by":19,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.rse.2018.10.006","title":"Prediction of drought-induced reduction of agricultural productivity in Chile from MODIS, rainfall estimates, and climate oscillation indices","authors":["Francisco Zambrano","Anton Vrieling","Andy D. Nelson","Michele Meroni","Tsegaye Tadesse"],"date":"2018-10-09","year":2018,"venue":"Remote Sensing of Environment","venue_type":"journal","ids":{"doi":"10.1016/j.rse.2018.10.006","openalex":"W2897401543"},"links":{"paper":"https://doi.org/10.1016/j.rse.2018.10.006","pdf":"https://www.sciencedirect.com/science/article/pii/S0034425718304541/pdf"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","other"],"status":"research","summary":"Linear regression and a feedforward network predict Chilean agricultural productivity drought anomalies 1–6 months ahead using MODIS, rainfall and ENSO indices.","significance":2,"cited_by":105,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-s18103350","title":"A Novel Wind Speed Estimation Based on the Integration of an Artificial Neural Network and a Particle Filter Using BeiDou GEO Reflectometry","authors":["Kittipong Kasantikul","Dongkai Yang","Qiang Wang","Aung Lwin"],"date":"2018-10-08","year":2018,"venue":"Sensors","venue_type":"journal","ids":{"doi":"10.3390/s18103350","openalex":"W2896302886"},"links":{"paper":"https://doi.org/10.3390/s18103350","pdf":"https://www.mdpi.com/1424-8220/18/10/3350/pdf?version=1538977146"},"orgs":[],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","stations"],"status":"research","summary":"An ANN combined with a particle filter retrieves ocean surface wind speed from BeiDou GEO GNSS reflections, reaching about 1.9 m/s RMSE against buoys.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.5880","title":"Climatological representation of mesoscale convective systems in a dynamically downscaled climate simulation","authors":["Alex M. Haberlie","Walker S. Ashley"],"date":"2018-10-06","year":2018,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.5880","openalex":"W2894611832"},"links":{"paper":"https://doi.org/10.1002/joc.5880"},"orgs":[],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"evaluation","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["km-scale-sim","radar"],"status":"research","summary":"A CNN stratifies convection-permitting climate runs and finds too few quasi-linear convective systems in the Midwest, with future declines not spatially significant.","significance":3,"cited_by":38,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4018-ijamc.2019010102","title":"Analysis of Precipitation Variability using Memory Based Artificial Neural Networks","authors":["Shyama Debbarma","Parthasarathi Choudhury","Parthajit Roy","Ram Kumar"],"date":"2018-10-03","year":2018,"venue":"International Journal of Applied Metaheuristic Computing","venue_type":"journal","ids":{"doi":"10.4018/ijamc.2019010102","openalex":"W2894990022"},"links":{"paper":"https://doi.org/10.4018/ijamc.2019010102"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["rnn","classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["era5","cmip"],"status":"research","summary":"Gamma memory neural networks, with and without GA optimization, downscale daily precipitation for the Barak basin, with GMNN-GA matching the standard SDSM model.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1810.01993","title":"Exascale Deep Learning for Climate Analytics","authors":["Thorsten Kurth","Sean Treichler","Joshua Romero","Mayur Mudigonda","Nathan Luehr","Everett Phillips","Ankur Mahesh","Michael Matheson","Jack Deslippe","Massimiliano Fatica","Prabhat","Michael Houston"],"date":"2018-10-03","year":2018,"venue":"SC18: International Conference for High Performance Computing, Networking, Storage and Analysis","venue_type":"preprint","ids":{"arxiv":"1810.01993","doi":"10.1109/sc.2018.00054","openalex":"W2952046647"},"links":{"paper":"https://arxiv.org/abs/1810.01993","pdf":"https://arxiv.org/pdf/1810.01993"},"orgs":["lbnl-nersc","nvidia","ornl"],"topic":"infra-software","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Tiramisu and DeepLabv3+ segment extreme weather patterns and scale to 27,360 V100 GPUs at 325.8 PF/s sustained throughput.","significance":5,"cited_by":297,"score":65,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5194-gmd-11-3999-2018","title":"Challenges and design choices for global weather and climate models based on machine learning","authors":["Peter D. Dueben","Peter Bauer"],"date":"2018-10-01","year":2018,"venue":"Geoscientific Model Development","venue_type":"journal","ids":{"doi":"10.5194/gmd-11-3999-2018","openalex":"W2809789958"},"links":{"paper":"https://doi.org/10.5194/gmd-11-3999-2018"},"orgs":["ecmwf"],"topic":"global-medium-range","topics":[],"type":"position","method":["other"],"timescale":["medium"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Discusses challenges and design choices for deep-learning global weather forecasting, illustrated with a toy global neural forecast model.","significance":6,"cited_by":398,"score":69,"highlight":true,"highlight_reason":"Early ECMWF perspective on the challenges of fully data-driven global weather models, with a toy model; a frequently cited framing paper.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1029-2018wr023830","title":"Exploring Deep Neural Networks to Retrieve Rain and Snow in High Latitudes Using Multisensor and Reanalysis Data","authors":["Guoqiang Tang","Di Long","Ali Behrangi","Cunguang Wang","Yang E. Hong"],"date":"2018-10-01","year":2018,"venue":"Water Resources Research","venue_type":"journal","ids":{"doi":"10.1029/2018wr023830","openalex":"W2897265228"},"links":{"paper":"https://doi.org/10.1029/2018wr023830","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2018WR023830"},"orgs":["nasa","caltech","tsinghua-university","ucla","university-of-oklahoma"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"A deep neural network retrieves high-latitude rain and snow from GMI and MODIS data, largely outperforming GPROF on snowfall and reducing rain underestimation.","significance":3,"cited_by":76,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.3410","title":"Predicting weather forecast uncertainty with machine learning","authors":["Sebastian Scher","Gabriele Messori"],"date":"2018-10-01","year":2018,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.3410","openalex":"W2896006105"},"links":{"paper":"https://doi.org/10.1002/qj.3410"},"orgs":[],"topic":"probabilistic-ensembles","topics":["post-processing"],"type":"model","method":["cnn"],"timescale":["medium"],"spatial":["global"],"data":["nwp-analysis"],"status":"research","summary":"A CNN trained on past forecasts assigns a confidence score to medium-range forecasts without running an ensemble; it is cheaper but less skilful than ensembles.","significance":4,"cited_by":223,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.5848","title":"Seasonal prediction of high‐resolution temperature at 2‐m height over Mongolia during boreal winter using both coupled general circulation model and artificial neural network","authors":["Gerelchuluun Bayasgalan","Joong‐Bae Ahn"],"date":"2018-09-21","year":2018,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.5848","openalex":"W2893731329"},"links":{"paper":"https://doi.org/10.1002/joc.5848","pdf":"https://rmets.onlinelibrary.wiley.com/doi/pdfdirect/10.1002/joc.5848"},"orgs":[],"topic":"s2s-seasonal","topics":["post-processing","downscaling"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Neural networks post-process PNU CGCM seasonal hindcasts with sea-ice and SST indices to downscale winter 2-m temperature over Mongolia to 20 km, with improved skill.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1088-1748-9326-aae2be","title":"Using machine learning to build temperature-based ozone parameterizations for climate sensitivity simulations","authors":["Peer Johannes Nowack","Peter Braesicke","Joanna D. Haigh","Nathan Luke Abraham","John Adrian Pyle","Apostolos Voulgarakis"],"date":"2018-09-20","year":2018,"venue":"Environmental Research Letters","venue_type":"journal","ids":{"doi":"10.1088/1748-9326/aae2be","openalex":"W2890476809"},"links":{"paper":"https://doi.org/10.1088/1748-9326/aae2be","pdf":"https://iopscience.iop.org/article/10.1088/1748-9326/aae2be/pdf"},"orgs":["university-of-cambridge","kit"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Linear ML regression predicts 3D ozone from temperature alone, improving stratospheric ozone variability over fixed climatology for preindustrial and 4xCO2 climate sensitivity runs.","significance":4,"cited_by":83,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2887686287","title":"Fused Deep Learning for Hurricane Track Forecast from Reanalysis Data","authors":["Sophie Giffard‐Roisin","Mo Yuan Yang","Guillaume Charpiat","Balázs Kégl","Claire Monteleoni"],"date":"2018-09-19","year":2018,"venue":"HAL (Le Centre pour la Communication Scientifique Directe)","venue_type":"preprint","ids":{"openalex":"W2887686287"},"links":{"paper":"https://hal.archives-ouvertes.fr/hal-01851001"},"orgs":[],"topic":"extremes-hazards","topics":["global-medium-range"],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Fused deep learning model forecasts hurricane tracks from reanalysis data; abstract unavailable, so classification is based on the title only.","significance":3,"cited_by":12,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1809.07394","title":"Improving Subseasonal Forecasting in the Western U.S. with Machine Learning","authors":["Jessica Hwang","Paulo Orenstein","Judah Cohen","Karl Pfeiffer","Lester Mackey"],"date":"2018-09-19","year":2018,"venue":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &amp; Data Mining","venue_type":"preprint","ids":{"arxiv":"1809.07394","doi":"10.1145/3292500.3330674","openalex":"W2964178568"},"links":{"paper":"https://arxiv.org/abs/1809.07394","pdf":"https://arxiv.org/pdf/1809.07394"},"orgs":["microsoft-research","stanford"],"topic":"s2s-seasonal","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Ensemble of regression models with the SubseasonalRodeo dataset beats the top Rodeo entry and improves debiased CFSv2 precipitation skill by 129-169%.","significance":5,"cited_by":84,"score":55,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3390-w10091260","title":"Future Predictions of Rainfall and Temperature Using GCM and ANN for Arid Regions: A Case Study for the Qassim Region, Saudi Arabia","authors":["Khalid Alotaibi","Abdul Razzaq Ghumman","Husnain Haider","Yousry Mahmoud Ghazaw","Md. Shafiquzzaman"],"date":"2018-09-15","year":2018,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w10091260","openalex":"W2890965385"},"links":{"paper":"https://doi.org/10.3390/w10091260","pdf":"https://www.mdpi.com/2073-4441/10/9/1260/pdf?version=1537003549"},"orgs":[],"topic":"downscaling","topics":["climate-analysis-attribution"],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Combines GCMs, a weather generator and ANN/ANFIS models to project Qassim rainfall and temperature; ANNs outperformed ANFIS for long-term predictions.","significance":3,"cited_by":66,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1702.04018","title":"Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation","authors":["Thomas Vandal","Evan Kodra","Auroop Ratan Ganguly"],"date":"2018-09-08","year":2018,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"arxiv":"1702.04018","doi":"10.1007/s00704-018-2613-3","openalex":"W2889852608"},"links":{"paper":"https://doi.org/10.1007/s00704-018-2613-3","pdf":"https://arxiv.org/pdf/1702.04018"},"orgs":[],"topic":"downscaling","topics":["benchmarks-data-eval"],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Intercomparison of machine learning methods for statistical downscaling of daily and extreme precipitation; abstract unavailable, classification based on title.","significance":3,"cited_by":202,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-a11090132","title":"Study of Precipitation Forecast Based on Deep Belief Networks","authors":["Du Jinglin","Yayun Liu","Zhijun Liu"],"date":"2018-09-04","year":2018,"venue":"Algorithms","venue_type":"journal","ids":{"doi":"10.3390/a11090132","openalex":"W2889283791"},"links":{"paper":"https://doi.org/10.3390/a11090132","pdf":"https://www.mdpi.com/1999-4893/11/9/132/pdf?version=1536032139"},"orgs":["nuist"],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Applies deep belief networks to precipitation forecasting, claiming better results than conventional forecasting methods; quantitative results are not given in the abstract.","significance":2,"cited_by":29,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2018.191","title":"Evaluation of data-driven models to downscale rainfall parameters from global climate models outputs: the case study of Latyan watershed","authors":["Reza Hosseini","Saeed Golian","Jafar Yazdi"],"date":"2018-09-03","year":2018,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2018.191","openalex":"W2894796079"},"links":{"paper":"https://doi.org/10.2166/wcc.2018.191","pdf":"https://iwaponline.com/jwcc/article-pdf/11/1/200/677617/jwc0110200.pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Compares ANN, K-nearest-neighbour and ANFIS for downscaling GCM precipitation at a Latyan basin station; KNN performed best monthly.","significance":2,"cited_by":13,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.5707","title":"On the classification of different flavours of Indian Ocean Dipole events","authors":["Danielle C. Verdon‐Kidd"],"date":"2018-09-03","year":2018,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.5707","openalex":"W2890262152"},"links":{"paper":"https://doi.org/10.1002/joc.5707"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["other"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural-network-based self-organizing map clustering of Indian Ocean SST reveals ten IOD patterns, showing pseudo-dipoles with distinct rainfall teleconnections over 130 years.","significance":4,"cited_by":25,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.jhydrol.2018.08.049","title":"Data-driven ensemble model to statistically downscale rainfall using nonlinear predictor screening approach","authors":["Vahid Nourani","Aida Hosseini Baghanam","Hüseyin Gökçekuş"],"date":"2018-08-29","year":2018,"venue":"Journal of Hydrology","venue_type":"journal","ids":{"doi":"10.1016/j.jhydrol.2018.08.049","openalex":"W2889498855"},"links":{"paper":"https://doi.org/10.1016/j.jhydrol.2018.08.049"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Ensemble statistical downscaling of rainfall using nonlinear predictor screening to select inputs; the abstract is missing, so details are inferred from the title.","significance":2,"cited_by":65,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.scitotenv.2018.08.369","title":"Data-driven mapping of the spatial distribution and potential changes of frozen ground over the Tibetan Plateau","authors":["Taihua Wang","Dawen Yang","Beijing Fang","Wencong Yang","Yue Qin","Yuhan Wang"],"date":"2018-08-28","year":2018,"venue":"The Science of The Total Environment","venue_type":"journal","ids":{"doi":"10.1016/j.scitotenv.2018.08.369","openalex":"W2889534203"},"links":{"paper":"https://doi.org/10.1016/j.scitotenv.2018.08.369"},"orgs":["tsinghua-university"],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Maps Tibetan Plateau permafrost at 1 km using logistic regression, SVM and random forest, projecting 25.9% to 43.9% permafrost loss by the 2040s and 2090s under RCP4.5.","significance":3,"cited_by":86,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1809.00027","title":"Dimensionality-Reduction of Climate Data using Deep Autoencoders","authors":["J. A. Saenz","N. Lubbers","N. M. Urban"],"date":"2018-08-27","year":2018,"venue_type":"preprint","ids":{"arxiv":"1809.00027","doi":"10.5065/d6k072n6","openalex":"W3122272089"},"links":{"paper":"https://arxiv.org/abs/1809.00027","pdf":"https://arxiv.org/pdf/1809.00027"},"orgs":[],"topic":"climate-emulation","topics":["infra-software"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Convolutional autoencoders compress CMIP5 pre-industrial surface temperature fields and beat PCA in reconstruction error at 40 dimensions, suggesting surrogate climate model use.","significance":3,"cited_by":6,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1808.10854","title":"Forecasting solar radiation during dust storms using deep learning","authors":["B. Ravindra"],"date":"2018-08-25","year":2018,"venue_type":"preprint","ids":{"arxiv":"1808.10854"},"links":{"paper":"https://arxiv.org/abs/1808.10854","pdf":"https://arxiv.org/pdf/1808.10854"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Deep learning forecasts solar radiation and PV output during dust storms, capturing aerosol-driven diffuse irradiance effects that degrade standard forecasts.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2018.08.018","title":"A tropical cyclone similarity search algorithm based on deep learning method","authors":["Yu Wang","Lei Han","Yin-Jing Lin","Yue Guo Shen","Wei Zhang"],"date":"2018-08-24","year":2018,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2018.08.018","openalex":"W2889096034"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2018.08.018"},"orgs":["cma"],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Deep learning similarity search to retrieve historical tropical cyclones matching a query storm; abstract missing, so details are inferred from the title.","significance":3,"cited_by":19,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-018-2598-y","title":"Application of multivariate recursive nesting bias correction, multiscale wavelet entropy and AI-based models to improve future precipitation projection in upstream of the Heihe River, Northwest China","authors":["Linshan Yang","Qi Feng","Zhenliang Yin","Xiaohu Wen","Ravinesh Chand Deo","Jianhua Si","Changbin Li"],"date":"2018-08-23","year":2018,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-018-2598-y","openalex":"W2888502159"},"links":{"paper":"https://doi.org/10.1007/s00704-018-2598-y"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"Combines multivariate recursive nesting bias correction with AI-based models to improve future precipitation projections over the Heihe River upstream; abstract missing.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2902319235","title":"Detection of Precursors of Tropical Cyclone from Cloud-Resolving Atmospheric Simulation Data using Deep Learning","authors":["Daisuke Matsuoka","Masuo Nakano","Daisuke Sugiyama","Uchida Seiichi"],"date":"2018-08-20","year":2018,"venue":"IEICE Technical Report; IEICE Tech. Rep.","venue_type":"journal","ids":{"openalex":"W2902319235"},"links":{"paper":"https://www.ieice.org/ken/paper/201808279156/eng/"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":[],"data":["km-scale-sim"],"status":"research","summary":"Applies deep learning to cloud-resolving simulations to detect tropical cyclone precursors; abstract missing, so details are inferred from the title.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.neunet.2018.08.004","title":"Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning","authors":["Andres Schmidt","Whitney Creason","Beverly Elizabeth Law"],"date":"2018-08-16","year":2018,"venue":"Neural Networks","venue_type":"journal","ids":{"doi":"10.1016/j.neunet.2018.08.004","openalex":"W2887800388"},"links":{"paper":"https://doi.org/10.1016/j.neunet.2018.08.004"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Uses time-delay neural networks with Bayesian regularization to estimate regional effects of climate change and land use on biosphere carbon fluxes.","significance":2,"cited_by":25,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1808.05382","title":"Typhoon track prediction using satellite images in a Generative Adversarial Network","authors":["Mario Rüttgers","Sangseung Lee","Donghyun You"],"date":"2018-08-16","year":2018,"venue":"Scientific Reports","venue_type":"journal","ids":{"arxiv":"1808.05382","doi":"10.1038/s41598-019-42339-y","openalex":"W2937449040"},"links":{"paper":"https://doi.org/10.1038/s41598-019-42339-y","pdf":"https://arxiv.org/pdf/1808.05382"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["gan-vae"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"A GAN predicts one-step-ahead typhoon centres and cloud structure from 6-hourly satellite images, with 42% of centre errors under 80 km.","significance":3,"cited_by":168,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1808.05264","title":"DeepDownscale: a Deep Learning Strategy for High-Resolution Weather Forecast","authors":["Eduardo R. Rodrigues","Igor Oliveira","Renato L. F. Cunha","Marco A. S. Netto"],"date":"2018-08-15","year":2018,"venue_type":"preprint","ids":{"arxiv":"1808.05264"},"links":{"paper":"https://arxiv.org/abs/1808.05264","pdf":"https://arxiv.org/pdf/1808.05264"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"DeepDownscale learns high-resolution weather forecast fields from low-resolution model output with a lightweight deep network, improving on interpolation and ensembles.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-11-4627-2018","title":"A neural network approach to estimating a posteriori distributions of Bayesian retrieval problems","authors":["Simon Pfreundschuh","Patrick Eriksson","David Duncan","Bengt Rydberg","Nina Håkansson","Anke Thoss"],"date":"2018-08-09","year":2018,"venue":"Atmospheric Measurement Techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-11-4627-2018","openalex":"W2795114264"},"links":{"paper":"https://doi.org/10.5194/amt-11-4627-2018"},"orgs":[],"topic":"observations-remote-sensing","topics":["xai-uq-physics"],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Quantile regression neural networks give case-specific posterior uncertainty for Bayesian retrievals, applied to MODIS cloud top pressure with consistent uncertainty; code released.","significance":4,"cited_by":62,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.5923-s.ajee.201601.14","title":"Kinetic Studies of Fenton Oxidation Reaction by UV-VIS Spectroscopy","authors":["Zhongde Dai","Gøril Flatberg","Heinz A. Preisig","Liyuan Deng"],"date":"2018-08-01","year":2018,"venue":"Journal of Laboratory Chemical Education","venue_type":"journal","ids":{"doi":"10.5923/s.ajee.201601.14","openalex":"W4237364183"},"links":{"paper":"https://doi.org/10.5923/s.ajee.201601.14","pdf":"http://www.sapub.org/global/showpaperpdf.aspx?doi=10.5923/s.ajee.201601.14"},"orgs":[],"topic":"s2s-seasonal","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"A neural network tuned by a meta-heuristic predicts monthly and seasonal precipitation in southern Brazil; the abstract does not match the title.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1808.00588","title":"Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks","authors":["Jose Carlos Villarreal Guerra","Zeba Khanam","Shoaib Ehsan","Rustam Stolkin","Klaus McDonald-Maier"],"date":"2018-08-01","year":2018,"venue_type":"preprint","ids":{"arxiv":"1808.00588"},"links":{"paper":"https://arxiv.org/abs/1808.00588","pdf":"https://arxiv.org/pdf/1808.00588"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"benchmark","method":["cnn"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"New open dataset of rain, snow and fog images with a super-pixel augmentation method, benchmarking ten CNN architectures for camera-based weather classification.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-asr-15-159-2018","title":"Current gust forecasting techniques, developments and challenges","authors":["Peter F. Sheridan"],"date":"2018-07-31","year":2018,"venue":"Advances in science and research","venue_type":"journal","ids":{"doi":"10.5194/asr-15-159-2018","openalex":"W2885611555"},"links":{"paper":"https://doi.org/10.5194/asr-15-159-2018","pdf":"https://asr.copernicus.org/articles/15/159/2018/asr-15-159-2018.pdf"},"orgs":["met-office"],"topic":"extremes-hazards","topics":["post-processing"],"type":"review","method":["classical-ml","physics-constrained"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Review of gust forecasting methods, comparing physical boundary-layer parametrizations on NWP fields with statistical and machine learning approaches trained on observations, and outlining challenges from higher resolution.","significance":3,"cited_by":47,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en11081975","title":"Multi-Step Ahead Wind Power Generation Prediction Based on Hybrid Machine Learning Techniques","authors":["Wei Dong","Qiang Yang","Xinli Fang"],"date":"2018-07-30","year":2018,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en11081975","openalex":"W2887747362"},"links":{"paper":"https://doi.org/10.3390/en11081975","pdf":"https://www.mdpi.com/1996-1073/11/8/1975/pdf?version=1532946147"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","other"],"status":"research","summary":"Hybrid PSR, mRMR, K-means and ANFIS-PSO model combines NWP inputs for multi-step wind farm power prediction, with improved accuracy reported on two real wind farms.","significance":3,"cited_by":32,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3041917144","title":"Towards a topological pattern detection in fluid and climate simulation data","authors":["Grzegorz Muszyński","Karthik Kashinath","Kurlin","Michael F. Wehner","Prabhat"],"date":"2018-07-27","year":2018,"venue_type":"other","ids":{"openalex":"W3041917144"},"links":{"paper":"https://livrepository.liverpool.ac.uk/3026927/"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["km-scale-sim","other"],"status":"research","summary":"Proposes combining manifold learning and persistent homology to detect and characterise weather and climate patterns in fluid and climate simulation data.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-joc.5705","title":"Using multi‐model ensembles of CMIP5 global climate models to reproduce observed monthly rainfall and temperature with machine learning methods in Australia","authors":["Bin Wang","Lihong Zheng","De Li Liu","Fei Ji","Anthony Clark","Qiang Yu"],"date":"2018-07-27","year":2018,"venue":"International Journal of Climatology","venue_type":"journal","ids":{"doi":"10.1002/joc.5705","openalex":"W2884721255"},"links":{"paper":"https://doi.org/10.1002/joc.5705"},"orgs":[],"topic":"post-processing","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["cmip","stations"],"status":"research","summary":"Random forest and SVM multi-model ensembles outperform simple averaging and Bayesian averaging in reproducing observed Australian monthly rainfall and temperature from CMIP5 GCMs.","significance":3,"cited_by":170,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2018-6231745","title":"Multistep Wind Speed and Wind Power Prediction Based on a Predictive Deep Belief Network and an Optimized Random Forest","authors":["Zexian Sun","Hexu Sun","Jingxuan Zhang"],"date":"2018-07-24","year":2018,"venue":"Mathematical Problems in Engineering","venue_type":"journal","ids":{"doi":"10.1155/2018/6231745","openalex":"W2884421387"},"links":{"paper":"https://doi.org/10.1155/2018/6231745","pdf":"http://downloads.hindawi.com/journals/mpe/2018/6231745.pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Predictive deep belief network feeds wind speed forecasts into an optimised random forest for wind power prediction at 15 min to 24 h horizons.","significance":2,"cited_by":46,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-info9070177","title":"A Hybrid Model for Monthly Precipitation Time Series Forecasting Based on Variational Mode Decomposition with Extreme Learning Machine","authors":["Guohui Li","Xiao Ma","Hong Yang"],"date":"2018-07-20","year":2018,"venue":"Information","venue_type":"journal","ids":{"doi":"10.3390/info9070177","openalex":"W2883615841"},"links":{"paper":"https://doi.org/10.3390/info9070177","pdf":"https://www.mdpi.com/2078-2489/9/7/177/pdf?version=1532069693"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"VMD decomposition with per-component extreme learning machines forecasts 60 years of monthly precipitation at two Shaanxi sites, outperforming BP, Elman and EMD-ELM baselines.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-adgeo-45-13-2018","title":"Probabilistic short term wind power forecasts using deep neural networks with discrete target classes","authors":["Martin Felder","Frank Sehnke","Kay Ohnmeiß","Leon Schröder","Constantin Junk","Anton K. Kaifel"],"date":"2018-07-19","year":2018,"venue":"Advances in geosciences","venue_type":"journal","ids":{"doi":"10.5194/adgeo-45-13-2018","openalex":"W2883020093"},"links":{"paper":"https://doi.org/10.5194/adgeo-45-13-2018","pdf":"https://www.adv-geosci.net/45/13/2018/adgeo-45-13-2018.pdf"},"orgs":[],"topic":"applications-impacts","topics":["probabilistic-ensembles"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional","local"],"data":["nwp-analysis","other"],"status":"research","summary":"Neural network predicts probability distributions over discretised power bins for wind farm forecasts, matching deterministic MAE with lower CRPS and avoiding costly NWP ensembles.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.20965-jaciii.2018.p0465","title":"Time Series Prediction of Tropical Storm Trajectory Using Self-Organizing Incremental Neural Networks and Error Evaluation","authors":["Wonjik Kim","Osamu Hasegawa"],"date":"2018-07-19","year":2018,"venue":"Journal of Advanced Computational Intelligence and Intelligent Informatics","venue_type":"journal","ids":{"doi":"10.20965/jaciii.2018.p0465","openalex":"W2884811896"},"links":{"paper":"https://doi.org/10.20965/jaciii.2018.p0465"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Self-organising incremental neural network predicts tropical storm tracks from centre latitude, longitude and pressure over East Asia, with low computational cost.","significance":1,"cited_by":12,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.11113-mjce.v27.15966","title":"PERFORMANCE ASSESSMENT OF DIFFERENT BIAS CORRECTION METHODS IN STATISTICAL DOWNSCALING OF PRECIPITATION","authors":["Kamal Ahmed","Shamsuddin Shahid","Sobri B. Harun","Nadeem Nawaz"],"date":"2018-07-15","year":2018,"venue":"Malaysian Journal of Civil Engineering","venue_type":"journal","ids":{"doi":"10.11113/mjce.v27.15966","openalex":"W4401192650"},"links":{"paper":"https://doi.org/10.11113/mjce.v27.15966","pdf":"https://journals.utm.my/mjce/article/download/15966/7445"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"evaluation","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["era5","stations"],"status":"research","summary":"An MLP downscales arid-region monthly precipitation, and four bias correction methods are compared, with power transformation found most reliable.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00704-018-2552-z","title":"Downscaling of daily extreme temperatures in the Yarlung Zangbo River Basin using machine learning techniques","authors":["Meifang Ren","Bo Pang","Zongxue Xu","Jiajia Yue","Rong Zhang"],"date":"2018-07-11","year":2018,"venue":"Theoretical and Applied Climatology","venue_type":"journal","ids":{"doi":"10.1007/s00704-018-2552-z","openalex":"W2825868284"},"links":{"paper":"https://doi.org/10.1007/s00704-018-2552-z"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["other"],"timescale":["climate"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies machine learning to downscale daily extreme temperatures in the Yarlung Zangbo River Basin; abstract not available, so details are limited.","significance":2,"cited_by":15,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1807.03456","title":"Predicting property damage from tornadoes with zero-inflated neural networks","authors":["Jeremy Diaz","Maxwell Joseph"],"date":"2018-07-10","year":2018,"venue_type":"preprint","ids":{"arxiv":"1807.03456"},"links":{"paper":"https://arxiv.org/abs/1807.03456","pdf":"https://arxiv.org/pdf/1807.03456"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Zero-inflated neural networks predict tornado property damage occurrence (AUROC 0.872) and amount (R² 0.432), producing gridded monthly damage probability maps.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.future.2018.06.052","title":"Dynamic fine-tuning stacked auto-encoder neural network for weather forecast","authors":["Szu‐Yin Lin","Chi-Chun Chiang","Jung-Bin Li","Zih-Siang Hung","Kuo‐Ming Chao"],"date":"2018-07-07","year":2018,"venue":"Future Generation Computer Systems","venue_type":"journal","ids":{"doi":"10.1016/j.future.2018.06.052","openalex":"W2849449027"},"links":{"paper":"https://doi.org/10.1016/j.future.2018.06.052","pdf":"https://www.sciencedirect.com/science/article/pii/S0167739X17329801"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Stacked auto-encoder with dynamic fine-tuning for weather forecasting; no abstract was provided, so the scope and scale are judged from the title only.","significance":2,"cited_by":29,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-17-0290.1","title":"Comparing Area Probability Forecasts of (Extreme) Local Precipitation Using Parametric and Machine Learning Statistical Postprocessing Methods","authors":["Kirien Whan","Maurice J. Schmeits"],"date":"2018-07-06","year":2018,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-17-0290.1","openalex":"W2830616863"},"links":{"paper":"https://doi.org/10.1175/mwr-d-17-0290.1"},"orgs":["knmi"],"topic":"post-processing","topics":["extremes-hazards"],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Compares ELR, ZAGA and quantile regression forests for postprocessing HARMONIE-AROME hourly precipitation; QRF is most skillful for high thresholds.","significance":4,"cited_by":48,"score":51,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1177-0309524x18780381","title":"24-hours wind speed forecasting and wind power generation in La Serena (Chile)","authors":["Ignacio Salfate","Carlos Hugo López-Caraballo","Carolina Sabín-Sanjulián","Juan A. Lazzús","Pedro Vega","Fernando Cuturrufo","Julio César Marín"],"date":"2018-07-02","year":2018,"venue":"Wind Engineering","venue_type":"journal","ids":{"doi":"10.1177/0309524x18780381","openalex":"W2810254207"},"links":{"paper":"https://doi.org/10.1177/0309524x18780381"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Backpropagation neural network forecasts 12 and 24 h wind speed at La Serena, Chile, with RMSE about 0.7 m/s, and links it to wind turbine power output.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.54302-mausam.v69i3.330","title":"Artificial neural network model for downscaling of temperature forecast over Western Himalaya","authors":["Piyush Joshi","M. S. Shekhar","Jitender Kumar Quamara","Ajay Kumar"],"date":"2018-07-01","year":2018,"venue":"MAUSAM","venue_type":"journal","ids":{"doi":"10.54302/mausam.v69i3.330","openalex":"W3152845680"},"links":{"paper":"https://doi.org/10.54302/mausam.v69i3.330","pdf":"https://mausamjournal.imd.gov.in/index.php/MAUSAM/article/download/330/252"},"orgs":[],"topic":"post-processing","topics":["downscaling"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Artificial neural network statistically downscales MM5 temperature forecasts at three Western Himalaya stations, reducing RMSE to about 2 °C for day-2 forecasts.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1134-s1054661818030069","title":"Neural Network Forecasting of Precipitation Volumes Using Patterns","authors":["Andrey Konstantinovich Gorshenin","Victor Yu. Kuzmin"],"date":"2018-07-01","year":2018,"venue":"Pattern Recognition and Image Analysis","venue_type":"journal","ids":{"doi":"10.1134/s1054661818030069","openalex":"W2892239877"},"links":{"paper":"https://doi.org/10.1134/s1054661818030069"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Neural networks trained on pattern-based meteorological data forecast precipitation volumes, reporting up to 97% success for one-day and 90% for two-day forecasts.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.18280-eesrj.050201","title":"Monthly rainfall prediction using artificial neural network: A case study of Kano, Nigeria","authors":["Ahmad Bello","Mustapha Mamman"],"date":"2018-06-30","year":2018,"venue":"Environmental and Earth Sciences Research Journal","venue_type":"journal","ids":{"doi":"10.18280/eesrj.050201","openalex":"W2918919013"},"links":{"paper":"https://doi.org/10.18280/eesrj.050201","pdf":"http://www.iieta.org/download/file/fid/5273"},"orgs":[],"topic":"local-forecasting","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Artificial neural network predicts monthly rainfall in Kano, Nigeria from lagged ENSO indices, achieving correlation 0.73 versus 0.70 for a linear model.","significance":1,"cited_by":15,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s40808-018-0495-0","title":"Tollgate neural networks (TNN) model with time bound learning methodology for futuristic approach in climatic data analysis","authors":["A. Stanley Raj","J. Viswanath","D. Hudson Oliver","Y. Srinivas"],"date":"2018-06-30","year":2018,"venue":"Modeling Earth Systems and Environment","venue_type":"journal","ids":{"doi":"10.1007/s40808-018-0495-0","openalex":"W2810101016"},"links":{"paper":"https://doi.org/10.1007/s40808-018-0495-0"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":[],"data":["other"],"status":"research","summary":"Proposes a Tollgate neural network with time-bound learning for climatic data analysis; the abstract is missing, so scope and results are unclear.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.33260-zictjournal.v2i1.46","title":"Forecasting Seasonal Rainfall in Zambia – An Artificial Neural Network Approach","authors":["Lillian Mzyece","Mayumbo Nyirenda","Monde M.K Kabemba","Grey Chibawe"],"date":"2018-06-29","year":2018,"venue":"Zambia ICT Journal","venue_type":"journal","ids":{"doi":"10.33260/zictjournal.v2i1.46","openalex":"W2905629415"},"links":{"paper":"https://doi.org/10.33260/zictjournal.v2i1.46","pdf":"http://ictjournal.icict.org.zm/index.php/zictjournal/article/download/46/20"},"orgs":[],"topic":"s2s-seasonal","topics":["applications-impacts"],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Artificial neural networks replace expert steps in a seasonal rainfall forecasting workflow for Zambia, with results reported only qualitatively.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1111-cgf.13453","title":"Visualization of Neural Network Predictions for Weather Forecasting","authors":["Isabelle Roesch","Tobias Günther"],"date":"2018-06-29","year":2018,"venue":"Computer Graphics Forum","venue_type":"journal","ids":{"doi":"10.1111/cgf.13453","openalex":"W2809710708"},"links":{"paper":"https://doi.org/10.1111/cgf.13453"},"orgs":["eth-zurich"],"topic":"xai-uq-physics","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["short"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Interactive visualization system helps users inspect recurrent convolutional network forecasts of temperature, pressure and wind trained on 25 years of climate data.","significance":2,"cited_by":28,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1806.11037","title":"Using machine learning to parameterize moist convection: potential for modeling of climate, climate change and extreme events","authors":["Paul A. O'Gorman","John G. Dwyer"],"date":"2018-06-28","year":2018,"venue":"Journal of Advances in Modeling Earth Systems, 10, 2548-2563, 2018","venue_type":"journal","ids":{"arxiv":"1806.11037","doi":"10.1029/2018ms001351","openalex":"W2811423591"},"links":{"paper":"https://arxiv.org/abs/1806.11037","pdf":"https://arxiv.org/pdf/1806.11037"},"orgs":["mit"],"topic":"hybrid-parameterization","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"A random forest moist convection parameterization trained on high-resolution output runs stably in a GCM, capturing precipitation extremes and climate change when trained on warm-climate samples.","significance":4,"cited_by":374,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.3233-ida-173427","title":"A deep belief network based precipitation forecast approach using multiple environmental factors","authors":["Pengcheng Zhang","Yangyang Jia","Lei Zhang","Jerry Zeyu Gao","HARETON K. N. LEUNG"],"date":"2018-06-27","year":2018,"venue":"Intelligent Data Analysis","venue_type":"journal","ids":{"doi":"10.3233/ida-173427","openalex":"W2810006455"},"links":{"paper":"https://doi.org/10.3233/ida-173427"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Deep belief network forecasts next-24-hour precipitation at four Chinese regions from environmental factors, outperforming traditional machine-learning baselines in accuracy.","significance":2,"cited_by":14,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1806.09244","title":"A Scalable Machine Learning System for Pre-Season Agriculture Yield Forecast","authors":["Igor Oliveira","Renato L. F. Cunha","Bruno Silva","Marco A. S. Netto"],"date":"2018-06-25","year":2018,"venue_type":"preprint","ids":{"arxiv":"1806.09244"},"links":{"paper":"https://arxiv.org/abs/1806.09244","pdf":"https://arxiv.org/pdf/1806.09244"},"orgs":[],"topic":"applications-impacts","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Pre-season soybean and maize yield forecasts use satellite precipitation and seasonal climate forecasts instead of NDVI, with errors comparable to in-season systems.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22266-ijies2018.0831.17","title":"Deep Learning Based Weighted SOM to Forecast Weather and Crop Prediction for Agriculture Application","authors":["Pushpa Mohan","Kiran Kumari Patil"],"date":"2018-06-24","year":2018,"venue":"International journal of intelligent engineering and systems","venue_type":"journal","ids":{"doi":"10.22266/ijies2018.0831.17","openalex":"W2810857113"},"links":{"paper":"https://doi.org/10.22266/ijies2018.0831.17","pdf":"https://doi.org/10.22266/ijies2018.0831.17"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["other"],"timescale":["seasonal"],"spatial":["regional"],"data":["other"],"status":"research","summary":"SOM and LDA dimensionality reduction with a DNN classifier claims 7-23% accuracy gains for weather and crop prediction; methodology is weakly described.","significance":1,"cited_by":46,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018gl078510","title":"Prognostic Validation of a Neural Network Unified Physics Parameterization","authors":["N. D. Brenowitz","C. S. Bretherton"],"date":"2018-06-22","year":2018,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2018gl078510","openalex":"W2808400960"},"links":{"paper":"https://doi.org/10.1029/2018gl078510"},"orgs":["university-of-washington"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Neural network unified physics parameterization trained on 4-km aquaplanet data gives stable prognostic single-column tests better than CAM's scheme.","significance":4,"cited_by":353,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1016-j.compeleceng.2018.06.004","title":"Rainfall prediction for the Kerala state of India using artificial intelligence approaches","authors":["Yajnaseni Dash","Saroj K. Mishra","Bijaya Ketan Panigrahi"],"date":"2018-06-20","year":2018,"venue":"Computers & Electrical Engineering","venue_type":"journal","ids":{"doi":"10.1016/j.compeleceng.2018.06.004","openalex":"W2809195970"},"links":{"paper":"https://doi.org/10.1016/j.compeleceng.2018.06.004"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies artificial intelligence approaches to rainfall prediction in Kerala, India; the abstract is missing, so methods and results cannot be confirmed.","significance":1,"cited_by":125,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-w10060788","title":"Drought Prediction for Areas with Sparse Monitoring Networks: A Case Study for Fiji","authors":["Jinyoung Rhee","Hongwei Yang"],"date":"2018-06-14","year":2018,"venue":"Water","venue_type":"journal","ids":{"doi":"10.3390/w10060788","openalex":"W2808053342"},"links":{"paper":"https://doi.org/10.3390/w10060788","pdf":"https://www.mdpi.com/2073-4441/10/6/788/pdf?version=1528971076"},"orgs":[],"topic":"post-processing","topics":["s2s-seasonal"],"type":"application","method":["classical-ml"],"timescale":["seasonal"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Extra-Trees and AdaBoost correct seasonal forecasts and WRF downscaling to predict 6-month drought (SPI) in data-sparse Fiji, outperforming bias-corrected forecasts.","significance":2,"cited_by":20,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-rs10060939","title":"Satellite-Based Rainfall Retrieval: From Generalized Linear Models to Artificial Neural Networks","authors":["Lea Beusch","Loris Foresti","Marco Gabella","Ulrich Hamann"],"date":"2018-06-13","year":2018,"venue":"Remote Sensing","venue_type":"journal","ids":{"doi":"10.3390/rs10060939","openalex":"W2808135056"},"links":{"paper":"https://doi.org/10.3390/rs10060939","pdf":"https://www.mdpi.com/2072-4292/10/6/939/pdf?version=1528965613"},"orgs":["meteoswiss"],"topic":"observations-remote-sensing","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","radar","nwp-analysis"],"status":"research","summary":"Compares generalized linear models and neural networks for rainfall retrieval from geostationary IR data, using OPERA radar as truth; neural networks reduce false alarms.","significance":3,"cited_by":31,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018gl078202","title":"Could Machine Learning Break the Convection Parameterization Deadlock?","authors":["P. Gentine","M. Pritchard","S. Rasp","G. Reinaudi","G. Yacalis"],"date":"2018-06-12","year":2018,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2018gl078202","openalex":"W2804943168"},"links":{"paper":"https://doi.org/10.1029/2018gl078202"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"CBRAIN, a deep network trained on superparameterization output, skillfully emulates convective heating and moistening in an aquaplanet, a proof of concept for ML convection schemes.","significance":7,"cited_by":497,"score":48,"highlight":false,"classic":false,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1806.04731","title":"Deep learning to represent sub-grid processes in climate models","authors":["Stephan Rasp","Michael S. Pritchard","Pierre Gentine"],"date":"2018-06-12","year":2018,"venue":"Proceedings of the National Academy of Sciences Sep 2018, 201810286; DOI: 10.1073/pnas.1810286115","venue_type":"journal","ids":{"arxiv":"1806.04731","doi":"10.1073/pnas.1810286115","openalex":"W2808559252"},"links":{"paper":"https://arxiv.org/abs/1806.04731","pdf":"https://arxiv.org/pdf/1806.04731"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"A neural network trained on cloud-resolving output replaces subgrid convection in a global climate model, giving stable multi-year runs that capture precipitation extremes and approximately conserve energy.","significance":8,"cited_by":1044,"score":62,"highlight":true,"highlight_reason":"Landmark demonstration of a deep-learning sub-grid parameterization running stably in a coupled GCM for multi-year simulations; foundational for ML climate emulation.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.11113-mjce.v21.15826","title":"GEOSTATIONARY METEOROLOGICAL SATELLITE-BASED QUANTITATIVE RAINFALL ESTIMATION (GMS-RAIN) FOR FLOOD FORECASTING","authors":["Wardah Tahir","Zaidah Ibrahim","Suzana Ramli"],"date":"2018-06-10","year":2018,"venue":"Malaysian Journal of Civil Engineering","venue_type":"journal","ids":{"doi":"10.11113/mjce.v21.15826","openalex":"W2133250687"},"links":{"paper":"https://doi.org/10.11113/mjce.v21.15826"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite","nwp-analysis","stations"],"status":"research","summary":"Estimates convective rainfall from GMS-5 infrared images and NWP products with an artificial neural network, validated against gauges (r=0.63 hourly) and gaining about 2 h lead time for flood forecasting.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1806.02543","title":"Grouped Gaussian Processes for Solar Power Prediction","authors":["Astrid Dahl","Edwin V. Bonilla"],"date":"2018-06-07","year":2018,"venue_type":"preprint","ids":{"arxiv":"1806.02543"},"links":{"paper":"https://arxiv.org/abs/1806.02543","pdf":"https://arxiv.org/pdf/1806.02543"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local","regional"],"data":["stations"],"status":"research","summary":"Coupled Gaussian process priors improve multi-site solar power and wind speed forecasts, matching or beating benchmarks with better uncertainty quantification.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1806.02654","title":"New Hybrid Neuro-Evolutionary Algorithms for Renewable Energy and Facilities Management Problems","authors":["L. Cornejo-Bueno"],"date":"2018-06-05","year":2018,"venue_type":"preprint","ids":{"arxiv":"1806.02654"},"links":{"paper":"https://arxiv.org/abs/1806.02654","pdf":"https://arxiv.org/pdf/1806.02654"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Thesis applies hybrid neuro-evolutionary methods to predict solar radiation, wind-farm power variations, wave height and airport low-visibility events for renewable energy and facilities.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-11-2033-2018","title":"Cluster-based analysis of multi-model climate ensembles","authors":["Richard Hyde","Ryan Hossaini","Amber Alexandra Leeson"],"date":"2018-06-04","year":2018,"venue":"Geoscientific model development","venue_type":"journal","ids":{"doi":"10.5194/gmd-11-2033-2018","openalex":"W2806980816"},"links":{"paper":"https://doi.org/10.5194/gmd-11-2033-2018","pdf":"https://gmd.copernicus.org/articles/11/2033/2018/gmd-11-2033-2018.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":["benchmarks-data-eval"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Applies density-based clustering to choose grid-cell model subsets for multi-model means of tropospheric ozone, improving agreement with satellite climatology in chemistry-climate models.","significance":2,"cited_by":7,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-11-3177-2018","title":"Neural network cloud top pressure and height for MODIS","authors":["Nina Håkansson","Claudia Adok","Anke Thoss","Ronald Scheirer","Sara Hörnquist"],"date":"2018-06-01","year":2018,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-11-3177-2018","openalex":"W2787809105"},"links":{"paper":"https://doi.org/10.5194/amt-11-3177-2018","pdf":"https://amt.copernicus.org/articles/11/3177/2018/amt-11-3177-2018.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Neural networks retrieve MODIS cloud-top height using CALIOP training labels, cutting mean absolute error by at least 33% against operational algorithms.","significance":3,"cited_by":79,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5812-jhealthscope.57786","title":"Simulation of Climate Change Impact on Emergency Medical Services Clients Caused by Air Pollution","authors":["Hamed Mohammadi","Ali Ardalan","Ali Reza Massah Bavani","Kazem Naddafi","Mohammad Taghi Talebian"],"date":"2018-05-27","year":2018,"venue":"Health Scope","venue_type":"journal","ids":{"doi":"10.5812/jhealthscope.57786","openalex":"W2809339527"},"links":{"paper":"https://doi.org/10.5812/jhealthscope.57786","pdf":"https://healthscope.kowsarpub.com/cdn/dl/4344c7e0-7dea-11e8-ace8-43b6e24d2343"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"Projects 2020–2050 emergency medical visits in Tehran under RCP scenarios by linking downscaled GCM climate and air pollution to health via an ANN.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.atmosres.2018.05.022","title":"Statistical downscaling of precipitation using machine learning techniques","authors":["Dhanapala Arachchige Sachindra","Kamal Ahmed","Md. Mamunur Rashid","Shamsuddin Shahid","B. J. C. Perera"],"date":"2018-05-27","year":2018,"venue":"Atmospheric Research","venue_type":"journal","ids":{"doi":"10.1016/j.atmosres.2018.05.022","openalex":"W2807107999"},"links":{"paper":"https://doi.org/10.1016/j.atmosres.2018.05.022"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Applies machine learning techniques to statistically downscale precipitation; no abstract was available, so skill and data specifics are unconfirmed.","significance":2,"cited_by":373,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1805.09091","title":"Neural networks for post-processing ensemble weather forecasts","authors":["Stephan Rasp","Sebastian Lerch"],"date":"2018-05-23","year":2018,"venue":"Monthly Weather Review 2018, 146, 3885-3900","venue_type":"journal","ids":{"arxiv":"1805.09091","doi":"10.1175/mwr-d-18-0187.1","openalex":"W2803408063"},"links":{"paper":"https://arxiv.org/abs/1805.09091","pdf":"https://arxiv.org/pdf/1805.09091"},"orgs":["kit"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["stations","nwp-analysis"],"status":"research","summary":"Neural networks for ensemble post-processing outperform benchmark distributional regression for 2-m temperature at German stations, using embeddings and auxiliary predictors.","significance":7,"cited_by":513,"score":58,"highlight":true,"highlight_reason":"Influential neural network ensemble post-processing with embeddings that beat EMOS benchmarks; became a standard baseline for ML post-processing.","classic":false,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1007-s00382-018-4252-x","title":"Rainfall prediction methodology with binary multilayer perceptron neural networks","authors":["João Trevizoli Esteves","Glauco de Souza Rolim","Antônio Sérgio Ferraudo"],"date":"2018-05-21","year":2018,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-018-4252-x","openalex":"W2803604456"},"links":{"paper":"https://doi.org/10.1007/s00382-018-4252-x"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Proposes a binary multilayer perceptron method for rainfall prediction; no abstract was available, so reported skill is unconfirmed.","significance":2,"cited_by":67,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1805.07897","title":"Predicting Electricity Outages Caused by Convective Storms","authors":["Roope Tervo","Joonas Karjalainen","Alexander Jung"],"date":"2018-05-21","year":2018,"venue_type":"preprint","ids":{"arxiv":"1805.07897"},"links":{"paper":"https://arxiv.org/abs/1805.07897","pdf":"https://arxiv.org/pdf/1805.07897"},"orgs":[],"topic":"applications-impacts","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["radar"],"status":"research","summary":"Random forests and neural networks predict grid power outage damage from convective storm cells, using SMOTE to handle rare extreme events.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos9050194","title":"Multivariate Interpolation of Wind Field Based on Gaussian Process Regression","authors":["Miao Feng","Weimin Zhang","Xiangru Zhu","Boheng Duan","Mengbin Zhu","De Xing"],"date":"2018-05-17","year":2018,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos9050194","openalex":"W2804165808"},"links":{"paper":"https://doi.org/10.3390/atmos9050194","pdf":"https://www.mdpi.com/2073-4433/9/5/194/pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Gaussian process regression with a multi-scale anisotropic kernel interpolates NWP 10 m wind fields, cutting RMSE by up to 95% versus neural networks in cyclone cases.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tgrs.2018.2830123","title":"Bottleneck Channels Algorithm for Satellite Data Dimension Reduction: A Case Study for IASI","authors":["Victor Pellet","Filipe Aires"],"date":"2018-05-17","year":2018,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"doi":"10.1109/tgrs.2018.2830123","openalex":"W2803965377"},"links":{"paper":"https://doi.org/10.1109/tgrs.2018.2830123"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["other"],"timescale":[],"spatial":["global"],"data":["satellite"],"status":"research","summary":"Bottleneck-channel neural compression of 8461 IASI channels matches NAPCA for temperature, water vapor and ozone retrievals while preserving physical meaning.","significance":3,"cited_by":19,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018jc013847","title":"Retrieval of Barometric Pressure from Satellite Passive Microwave Observations over the Oceans","authors":["Zijin Zhang","Xiaolong Dong","Liling Liu","Jieying He"],"date":"2018-05-16","year":2018,"venue":"Journal of Geophysical Research Oceans","venue_type":"journal","ids":{"doi":"10.1029/2018jc013847","openalex":"W2803600826"},"links":{"paper":"https://doi.org/10.1029/2018jc013847"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["satellite","stations","era5"],"status":"research","summary":"Back-propagation network retrieves sea surface pressure from ATMS microwave radiances with 2–3.5 hPa RMSE across clear, cloudy and rainy skies.","significance":3,"cited_by":10,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1117-1.jrs.12.026015","title":"Ingesting microwave sounder radiances for improvement in track forecast of cyclone Vardah","authors":["Krishnamoorthy Chandramouli","Chakravarthy Balaji"],"date":"2018-05-14","year":2018,"venue":"Journal of Applied Remote Sensing","venue_type":"journal","ids":{"doi":"10.1117/1.jrs.12.026015","openalex":"W2804513542"},"links":{"paper":"https://doi.org/10.1117/1.jrs.12.026015"},"orgs":[],"topic":"data-assimilation","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["satellite","nwp-analysis"],"status":"research","summary":"Assimilating SAPHIR microwave radiances into WRF with an ANN radiative transfer surrogate improves 72-hour track forecasts of cyclone Vardah.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1805.04907","title":"A Computational Framework for Modelling and Analyzing Ice Storms","authors":["Ranjini Swaminathan","Mohan Sridharan","Katharine Hayhoe"],"date":"2018-05-13","year":2018,"venue_type":"preprint","ids":{"arxiv":"1805.04907","openalex":"W2801012970"},"links":{"paper":"https://arxiv.org/abs/1805.04907","pdf":"https://arxiv.org/pdf/1805.04907"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional"],"data":["era5","cmip"],"status":"research","summary":"Framework learns ice storm occurrence from atmospheric variables with weak labels, evaluated on reanalysis and GCM data under future climate scenarios.","significance":3,"cited_by":8,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.enconman.2018.04.099","title":"Ensemble empirical mode decomposition based adaptive wavelet neural network method for wind speed prediction","authors":["Santhosh Madasthu","Chintham Venkaiah","D. M. Vinod Kumar"],"date":"2018-05-12","year":2018,"venue":"Energy Conversion and Management","venue_type":"journal","ids":{"doi":"10.1016/j.enconman.2018.04.099","openalex":"W2801076518"},"links":{"paper":"https://doi.org/10.1016/j.enconman.2018.04.099"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Hybrid EEMD and wavelet neural network for wind speed prediction; abstract not available, classified from title.","significance":2,"cited_by":214,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1805.04193","title":"An Unsupervised Clustering-Based Short-Term Solar Forecasting Methodology Using Multi-Model Machine Learning Blending","authors":["Cong Feng","Mingjian Cui","Bri-Mathias Hodge","Siyuan Lu","Hendrik F. Hamann","Jie Zhang"],"date":"2018-05-10","year":2018,"venue_type":"preprint","ids":{"arxiv":"1805.04193"},"links":{"paper":"https://arxiv.org/abs/1805.04193","pdf":"https://arxiv.org/pdf/1805.04193"},"orgs":[],"topic":"local-forecasting","topics":["applications-impacts"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Clustering-based multi-model machine learning forecasts one-hour-ahead solar irradiance, outperforming single-model baselines by about 20%.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.rse.2018.05.003","title":"Self-adaptive differential evolutionary extreme learning machines for long-term solar radiation prediction with remotely-sensed MODIS satellite and Reanalysis atmospheric products in solar-rich cities","authors":["Sujan Ghimire","Ravinesh Chand Deo","Nathan James Downs","Nawin Raj"],"date":"2018-05-08","year":2018,"venue":"Remote Sensing of Environment","venue_type":"journal","ids":{"doi":"10.1016/j.rse.2018.05.003","openalex":"W2799674728"},"links":{"paper":"https://doi.org/10.1016/j.rse.2018.05.003"},"orgs":[],"topic":"applications-impacts","topics":["local-forecasting"],"type":"model","method":["classical-ml"],"timescale":["seasonal"],"spatial":["local"],"data":["satellite","era5"],"status":"research","summary":"Self-adaptive differential evolution tuned extreme learning machines predict long-term solar radiation in solar-rich cities using MODIS and reanalysis predictors.","significance":2,"cited_by":90,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1805.01950","title":"A Data-driven Approach to Detecting Precipitation from Meteorological Sensor Data","authors":["Shilpa Manandhar","Soumyabrata Dev","Yee Hui Lee","Yu Song Meng","Stefan Winkler"],"date":"2018-05-04","year":2018,"venue_type":"preprint","ids":{"arxiv":"1805.01950"},"links":{"paper":"https://arxiv.org/abs/1805.01950","pdf":"https://arxiv.org/pdf/1805.01950"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine-learning detection of rainfall from meteorological sensor data reaches an 87.4% true detection rate with a 32.2% false alarm rate.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1186-s40645-018-0185-6","title":"Coupling dynamical and statistical downscaling for high-resolution rainfall forecasting: case study of the Red River Delta, Vietnam","authors":["Quan Tran-Anh","Kenji Taniguchi"],"date":"2018-05-03","year":2018,"venue":"Progress in Earth and Planetary Science","venue_type":"journal","ids":{"doi":"10.1186/s40645-018-0185-6","openalex":"W2805053906"},"links":{"paper":"https://doi.org/10.1186/s40645-018-0185-6","pdf":"https://progearthplanetsci.springeropen.com/track/pdf/10.1186/s40645-018-0185-6"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["era5","km-scale-sim"],"status":"research","summary":"Hybrid RCM and neural-network downscaling reproduces 6-km Red River Delta rainfall (r>0.9) at an 89% reduction in computing power.","significance":3,"cited_by":28,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-info9050106","title":"Precipitation Data Assimilation System Based on a Neural Network and Case-Based Reasoning System","authors":["Jing Lu","Wei Hu","Xiakun Zhang"],"date":"2018-05-02","year":2018,"venue":"Information","venue_type":"journal","ids":{"doi":"10.3390/info9050106","openalex":"W2800044770"},"links":{"paper":"https://doi.org/10.3390/info9050106","pdf":"https://www.mdpi.com/2078-2489/9/5/106/pdf?version=1525350520"},"orgs":[],"topic":"data-assimilation","topics":["global-medium-range"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Integrates neural network and case-based reasoning into a precipitation data assimilation system to improve weather forecasts; results reported as effective.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s13131-018-1219-z","title":"A nowcasting model for the prediction of typhoon tracks based on a long short term memory neural network","authors":["Song Gao","Peng Zhao","Bin Pan","Yaru Li","Min Zhou","Jiangling Xu","Shan Zhong","Zhenwei Shi"],"date":"2018-05-01","year":2018,"venue":"Acta Oceanologica Sinica","venue_type":"journal","ids":{"doi":"10.1007/s13131-018-1219-z","openalex":"W2799572365"},"links":{"paper":"https://doi.org/10.1007/s13131-018-1219-z"},"orgs":[],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["rnn"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"LSTM neural network model for typhoon track nowcasting; abstract not available, classified from title.","significance":3,"cited_by":121,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W7218152603","title":"Felhőalap és felhőborítottság rövid távú előrejelzése neurális hálózat segítségével","authors":["Anikó Várkonyi","Péter Kardos"],"date":"2018-04-30","year":2018,"venue":"Repüléstudományi Közlemények","venue_type":"journal","ids":{"openalex":"W7218152603"},"links":{"paper":"https://folyoirat.ludovika.hu/index.php/reptudkoz/article/view/4270","pdf":"https://folyoirat.ludovika.hu/index.php/reptudkoz/article/download/4270/3496"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Neural network post-processing of three years of WRF output improves short-term cloud ceiling and cover forecasts for aviation use.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-app8050689","title":"A Short-Term Photovoltaic Power Prediction Model Based on the Gradient Boost Decision Tree","authors":["Jidong Wang","Peng Li","Ran Ran","Yanbo Che","Yue Zhou"],"date":"2018-04-28","year":2018,"venue":"Applied Sciences","venue_type":"journal","ids":{"doi":"10.3390/app8050689","openalex":"W2801596954"},"links":{"paper":"https://doi.org/10.3390/app8050689","pdf":"https://www.mdpi.com/2076-3417/8/5/689/pdf"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Gradient boosted decision trees predict short-term photovoltaic power from historical weather and weather forecast inputs for grid operation.","significance":2,"cited_by":246,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos9050164","title":"Development of an Urban High-Resolution Air Temperature Forecast System for Local Weather Information Services Based on Statistical Downscaling","authors":["Chaeyeon Yi","Yire Shin","Joon‐Woo Roh"],"date":"2018-04-26","year":2018,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos9050164","openalex":"W2801668212"},"links":{"paper":"https://doi.org/10.3390/atmos9050164"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"Statistical and machine-learning downscaling produces 25 m urban air temperature maps for Seoul, improving on the 1.5 km UM-LDAPS model.","significance":2,"cited_by":41,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-wcc.2018.136","title":"Bat optimisation neural networks for rainfall forecasting: case study for Kuching city","authors":["King Kuok Kuok","Sze Miang Kueh","Po Chan Chiu"],"date":"2018-04-25","year":2018,"venue":"Journal of Water and Climate Change","venue_type":"journal","ids":{"doi":"10.2166/wcc.2018.136","openalex":"W2802523594"},"links":{"paper":"https://doi.org/10.2166/wcc.2018.136","pdf":"https://iwaponline.com/jwcc/article-pdf/10/3/569/598286/jwc0100569.pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["local"],"data":["cmip","stations"],"status":"research","summary":"A metaheuristic bat-optimised neural network downscales climate model predictors to Kuching station precipitation, reporting average r of 0.96 across three GCMs.","significance":2,"cited_by":17,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2921228239","title":"Weather Forecasting using Neural Network","authors":["Priyanka Mahajan","Chhaya Nawale","Siddheshwar Kini","Krishnanjali Shinde"],"date":"2018-04-24","year":2018,"venue_type":"other","ids":{"openalex":"W2921228239"},"links":{"paper":"https://www.ijert.org/research/weather-forecasting-using-neural-network-IJERTCONV5IS01197.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Neural network weather forecasting study; the abstract is unavailable, so scope and results are unclear.","significance":1,"cited_by":5,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018gl077049","title":"Machine Learning Predictions of a Multiresolution Climate Model Ensemble","authors":["Gemma J. Anderson","Donald D. Lucas"],"date":"2018-04-19","year":2018,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1029/2018gl077049","openalex":"W2801390916"},"links":{"paper":"https://doi.org/10.1029/2018gl077049","pdf":"https://www.osti.gov/servlets/purl/1488815"},"orgs":[],"topic":"climate-emulation","topics":["benchmarks-data-eval"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Random forests trained on a multiresolution perturbed-parameter GCM ensemble predict high-resolution TOA flux and precipitation using few high-resolution runs, cutting simulation cost.","significance":4,"cited_by":60,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2906246796","title":"Analyzing el nino southern oscillation predictions from long-short-merm-memory models","authors":["Andrew Huang"],"date":"2018-04-18","year":2018,"venue":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","venue_type":"preprint","ids":{"openalex":"W2906246796"},"links":{"paper":"http://hdl.handle.net/2142/101011","pdf":"http://hdl.handle.net/2142/101011"},"orgs":[],"topic":"s2s-seasonal","topics":[],"type":"evaluation","method":["rnn"],"timescale":["seasonal"],"spatial":["global"],"data":["other"],"status":"research","summary":"LSTM networks compared with linear regression for ENSO prediction across 11 leads; LSTM gains skill over regression only with daily SST predictors at longer leads.","significance":3,"cited_by":0,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-mwr-d-17-0250.1","title":"Money Doesn't Grow on Trees, but Forecasts Do: Forecasting Extreme Precipitation with Random Forests","authors":["Gregory R. Herman","Russ S. Schumacher"],"date":"2018-04-18","year":2018,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-17-0250.1","openalex":"W2801493395"},"links":{"paper":"https://doi.org/10.1175/mwr-d-17-0250.1"},"orgs":["colorado-state-university"],"topic":"post-processing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["short","medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Random forests trained on 11 years of GEFS reforecasts give better CONUS extreme precipitation exceedance forecasts than raw ensembles and ECMWF.","significance":4,"cited_by":142,"score":36,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2803678489","title":"Tropical Cyclone Intensity Estimation Using Deep Convolutional Neural Networks","authors":["Manil Maskey","Dan Cecil","Rahul Ramachandran","Jeffrey J. Miller"],"date":"2018-04-16","year":2018,"venue":"NASA STI Repository (National Aeronautics and Space Administration)","venue_type":"preprint","ids":{"openalex":"W2803678489"},"links":{"paper":"http://hdl.handle.net/2060/20180002609","pdf":"http://hdl.handle.net/2060/20180002609"},"orgs":["nasa"],"topic":"extremes-hazards","topics":["observations-remote-sensing"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Deep CNNs estimate tropical cyclone intensity directly from infrared satellite imagery as an objective alternative to subjective Dvorak analysis.","significance":3,"cited_by":1,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00382-018-4205-4","title":"Multi-level emulation of complex climate model responses to boundary forcing data","authors":["Giang Tran","K. I. C. Oliver","Philip B. Holden","Neil Robert Edwards","András Sóbester","Peter Challenor"],"date":"2018-04-16","year":2018,"venue":"Climate Dynamics","venue_type":"journal","ids":{"doi":"10.1007/s00382-018-4205-4","openalex":"W2800266007"},"links":{"paper":"https://doi.org/10.1007/s00382-018-4205-4"},"orgs":[],"topic":"climate-emulation","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Multi-level statistical emulation of climate model responses to boundary forcing; abstract missing, so ML role is inferred from emulator-style methods and is weakly evidenced.","significance":3,"cited_by":18,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.7809-b-e.00304","title":"Predictability of daily precipitation using data from newly established automated weather stations over Notwane catchment in Botswana","authors":["Ditiro B. Moalafhi","Piet Kebuang Kenabatho","Bhagabat Prasad Parida","Botlhe Matlhodi"],"date":"2018-04-14","year":2018,"venue":"Biodiversity & Ecology","venue_type":"journal","ids":{"doi":"10.7809/b-e.00304","openalex":"W2808055227"},"links":{"paper":"https://doi.org/10.7809/b-e.00304","pdf":"http://www.biodiversity-plants.de/biodivers_ecol/publishing/b-e.00304.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Artificial neural networks using new Botswana automated weather station data predict daily precipitation at four stations, but struggle with extreme events.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-atmos9040141","title":"Regional Forecasting of Wind Speeds during Typhoon Landfall in Taiwan: A Case Study of Westward-Moving Typhoons","authors":["Chih‐Chiang Wei","Po-Chun Peng","Cheng‐Han Tsai","Chien‐Lin Huang"],"date":"2018-04-10","year":2018,"venue":"Atmosphere","venue_type":"journal","ids":{"doi":"10.3390/atmos9040141","openalex":"W2797869508"},"links":{"paper":"https://doi.org/10.3390/atmos9040141","pdf":"https://www.mdpi.com/2073-4433/9/4/141/pdf?version=1525347867"},"orgs":["ucla"],"topic":"local-forecasting","topics":["extremes-hazards"],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Backpropagation neural networks forecast typhoon wind speeds at three western Taiwan stations, outperforming linear regression across different typhoon tracks.","significance":2,"cited_by":10,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1804.04601","title":"Expressway visibility estimation based on image entropy and piecewise stationary time series analysis","authors":["Xiaogang Cheng","Guoqing Liu","Anders Hedman","Kun Wang","Haibo Li"],"date":"2018-04-08","year":2018,"venue_type":"preprint","ids":{"arxiv":"1804.04601"},"links":{"paper":"https://arxiv.org/abs/1804.04601","pdf":"https://arxiv.org/pdf/1804.04601"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Gaussian image entropy with piecewise stationary time series estimates expressway visibility from video, reaching 99.14% of relative errors under 10%.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3116551537","title":"Data-mining analysis of the global distribution of soil carbon in observational databases and Earth system models","authors":["Shoji Hashimoto","Kazuki Nanko","Boris Ťupek","Aleksi Lehtonen"],"date":"2018-04-01","year":2018,"venue":"Jukuri (Natural Resources Institute Finland (Luke))","venue_type":"preprint","ids":{"openalex":"W3116551537"},"links":{"paper":"http://jukuri.luke.fi/handle/10024/538957"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"evaluation","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip","other"],"status":"research","summary":"Boosted regression trees identify drivers of global soil organic carbon in observations and CMIP5 Earth system models, revealing key mismatches such as clay content and temperature.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3024029187","title":"Topological Data Analysis and Machine Learning for Classifying Atmospheric River Patterns in Large Climate Datasets","authors":["Grzegorz Muszyński","Vitaliy A. Kurlin","Karthik Kashinath","Michael F. Wehner","Prabhat"],"date":"2018-04-01","year":2018,"venue":"EGUGA","venue_type":"journal","ids":{"doi":"10.5194/gmd-12-613-2019","openalex":"W3024029187"},"links":{"paper":"https://ui.adsabs.harvard.edu/abs/2018EGUGA..2010825M/abstract"},"orgs":["lbnl-nersc"],"topic":"climate-analysis-attribution","topics":["extremes-hazards"],"type":"model","method":["classical-ml","other"],"timescale":[],"spatial":["global"],"data":[],"status":"research","summary":"Abstract missing; applies topological data analysis with machine learning to classify atmospheric river patterns in large climate datasets.","significance":3,"cited_by":67,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2994363772","title":"\"Dark magic\" wind power nowcasting/forecasting for semi-complex terrain using an artificial neural network and data mining framework","authors":["Irene Schicker","Petrina Papazek","Alexander Kann"],"date":"2018-04-01","year":2018,"venue":"EGUGA","venue_type":"journal","ids":{"openalex":"W2994363772"},"links":{"paper":"https://ui.adsabs.harvard.edu/abs/2018EGUGA..2012993S/abstract"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Neural network and data-mining framework for wind power nowcasting and forecasting in semi-complex terrain; abstract not available.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1803.10705","title":"Semi-supervised learning for structured regression on partially observed attributed graphs","authors":["Jelena Stojanovic","Milos Jovanovic","Djordje Gligorijevic","Zoran Obradovic"],"date":"2018-03-28","year":2018,"venue_type":"preprint","ids":{"arxiv":"1803.10705"},"links":{"paper":"https://arxiv.org/abs/1803.10705","pdf":"https://arxiv.org/pdf/1803.10705"},"orgs":[],"topic":"local-forecasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["stations","other"],"status":"research","summary":"Marginalized Gaussian CRF predicts continental US precipitation from partially observed climate-variable graphs and identifies weather stations to cut data-collection costs.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1803.10076","title":"Using Network Theory and Machine Learning to predict El Niño","authors":["Peter D. Nooteboom","Qing Yi Feng","Cristóbal López","Emilio Hernández-García","Henk A. Dijkstra"],"date":"2018-03-27","year":2018,"venue":"Earth System Dynamics 9, 969-983 (2018)","venue_type":"journal","ids":{"arxiv":"1803.10076","doi":"10.5194/esd-9-969-2018","openalex":"W2963547740"},"links":{"paper":"https://arxiv.org/abs/1803.10076","pdf":"https://arxiv.org/pdf/1803.10076"},"orgs":[],"topic":"s2s-seasonal","topics":["climate-analysis-attribution"],"type":"model","method":["classical-ml"],"timescale":["s2s","seasonal"],"spatial":["global"],"data":["other","nwp-analysis"],"status":"research","summary":"Hybrid ARIMA and neural network using climate-network topological features extends El Niño prediction to a 12-month lead, matching CFSv2 skill up to six months.","significance":4,"cited_by":89,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-2018gl077004","title":"A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon‐Ocean Feedback in Typhoon Forecast Models","authors":["Guoqing Jiang","Jing Xin Xu","Jun Wei"],"date":"2018-03-26","year":2018,"venue":"Geophysical Research Letters","venue_type":"journal","ids":{"doi":"10.1002/2018gl077004","openalex":"W2792413338"},"links":{"paper":"https://doi.org/10.1002/2018gl077004","pdf":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/2018GL077004"},"orgs":["mit","cma"],"topic":"hybrid-parameterization","topics":["extremes-hazards"],"type":"model","method":["other"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","km-scale-sim"],"status":"research","summary":"Neural network parameterizations of typhoon-induced sea surface cooling reduce maximum wind intensity errors by 60–70% in four atmosphere-only typhoon forecast cases.","significance":3,"cited_by":127,"score":32,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1803.11259","title":"The Classification of Cropping Patterns Based on Regional Climate Classification Using Decision Tree Approach","authors":["T. A. Munandar","Sumiati"],"date":"2018-03-26","year":2018,"venue":"Journal of Computer Science 2017, 13 (9): 408.415","venue_type":"journal","ids":{"arxiv":"1803.11259","doi":"10.3844/jcssp.2017.408.415"},"links":{"paper":"https://arxiv.org/abs/1803.11259","pdf":"https://arxiv.org/pdf/1803.11259"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Decision trees classify rice and CGPRT cropping patterns from regional rainfall patterns in Indonesia, with J48 reaching 48% accuracy.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1029-2018eo093857","title":"Next-Generation Climate Models Could Learn, Improve on the Fly","authors":["Sarah Stanley"],"date":"2018-03-21","year":2018,"venue":"Eos","venue_type":"journal","ids":{"doi":"10.1029/2018eo093857","openalex":"W2790419979"},"links":{"paper":"https://doi.org/10.1029/2018eo093857"},"orgs":[],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"position","method":["other"],"timescale":["climate"],"spatial":["global"],"data":[],"status":"research","summary":"Eos news piece proposing that climate models learn and adapt on the fly with machine learning to reduce prediction uncertainty.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2166-nh.2018.169","title":"Conjunction of wavelet-entropy and SOM clustering for multi-GCM statistical downscaling","authors":["Aida Hosseini Baghanam","Vahid Nourani","Mohammad-Ali Keynejad","Hassan Taghipour","Mohammad Taghi Aalami"],"date":"2018-03-20","year":2018,"venue":"Hydrology research","venue_type":"journal","ids":{"doi":"10.2166/nh.2018.169","openalex":"W2789274210"},"links":{"paper":"https://doi.org/10.2166/nh.2018.169","pdf":"https://iwaponline.com/hr/article-pdf/50/1/1/524510/nh0500001.pdf"},"orgs":[],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip","era5"],"status":"research","summary":"Wavelet-entropy and SOM predictor selection with ANN downscales multi-GCM station rainfall, projecting a 21–29% rainfall decrease for 2017–2050.","significance":2,"cited_by":32,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.31223-osf.io-hv95e","title":"Could machine learning break the convection parametrization deadlock?","authors":["Pierre Gentine","Mike Pritchard","Stephan Rasp","Gael Reinaudi","Galen Yacalis"],"date":"2018-03-16","year":2018,"venue_type":"other","ids":{"doi":"10.31223/osf.io/hv95e","openalex":"W4239236185"},"links":{"paper":"https://doi.org/10.31223/osf.io/hv95e","pdf":"https://eartharxiv.org/repository/object/1405/download/3159/"},"orgs":["columbia-leap"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"CBRAIN, a neural network trained on superparameterized aquaplanet data, replaces convection parameterization and reproduces its features with reduced stochasticity.","significance":5,"cited_by":2,"score":30,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-waf-d-17-0006.1","title":"Improvements in Hurricane Intensity Forecasts from a Multimodel Superensemble Utilizing a Generalized Neural Network Technique","authors":["Tirthankar Ghosh","T. N. Krishnamurti"],"date":"2018-03-16","year":2018,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-17-0006.1","openalex":"W2790650423"},"links":{"paper":"https://doi.org/10.1175/waf-d-17-0006.1","pdf":"https://journals.ametsoc.org/downloadpdf/journals/wefo/33/3/waf-d-17-0006_1.pdf"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short","medium"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Generalized regression neural network consensus of dynamical models improves Atlantic tropical storm intensity forecasts over 2012–16, outperforming individual models and the ensemble mean.","significance":3,"cited_by":17,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3027231904","title":"Deep Learning Approach for Detecting Precursors of Tropical Cyclone Simulated by a Global Nonhydrostatic Atmospheric Model","authors":["Daisuke Matsuoka","Masuo Nakano","Daisuke Sugiyama","Seiichi Uchida"],"date":"2018-03-14","year":2018,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W3027231904"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2018/subject/AAS03-08/detail"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["cnn"],"timescale":["short"],"spatial":["global"],"data":["km-scale-sim"],"status":"research","summary":"Conference abstract applying deep learning to detect tropical cyclone precursors in a global nonhydrostatic atmospheric model simulation.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3026855470","title":"Developping New Nowcasting Method by Using Convolution Neural Network","authors":["Taku Suezawa","Tomoaki Mega","Hiroshi Kikuchi","Syo YOSHIDA","Fumihiko Mizutani","Kazuhiro Yoshimi","Tomoo Ushio"],"date":"2018-03-14","year":2018,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W3026855470"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2018/subject/MIS19-05/detail"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":[],"data":[],"status":"research","summary":"Conference abstract proposing a convolutional neural network approach to weather nowcasting; no quantitative results are available.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2922437927","title":"Scientific Visualization of Climate Simulation Data for Deep Convolutional Neural Network","authors":["Daisuke Matsuoka"],"date":"2018-03-14","year":2018,"venue":"Japan Geoscience Union","venue_type":"journal","ids":{"openalex":"W2922437927"},"links":{"paper":"https://confit.atlas.jp/guide/event/jpgu2018/subject/MAG32-04/detail"},"orgs":[],"topic":"benchmarks-data-eval","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":[],"data":["km-scale-sim"],"status":"research","summary":"Conference abstract on visualizing climate simulation data as input for deep convolutional networks; no abstract details or results are given.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.22266-ijies2018.0430.21","title":"Weather and Crop Prediction Using Modified Self Organizing Map for Mysore Region","authors":["Pushpa Mohan","Kiran Kumari Patil"],"date":"2018-03-06","year":2018,"venue":"International journal of intelligent engineering and systems","venue_type":"journal","ids":{"doi":"10.22266/ijies2018.0430.21","openalex":"W2791506542"},"links":{"paper":"https://doi.org/10.22266/ijies2018.0430.21","pdf":"https://doi.org/10.22266/ijies2018.0430.21"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":[],"status":"research","summary":"Weighted self-organizing map predicts weather and suitable crops for the Mysore region, reporting 0.5–2% accuracy gains over SOM, KNN and ensemble networks.","significance":1,"cited_by":12,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3929-ethz-b-000258243","title":"Deep Learning for Analyzing Atmospheric Clouds","authors":["Georgios Touloupas"],"date":"2018-03-01","year":2018,"venue":"Repository for Publications and Research Data (ETH Zurich)","venue_type":"preprint","ids":{"doi":"10.3929/ethz-b-000258243","openalex":"W2914437713"},"links":{"paper":"https://doi.org/10.3929/ethz-b-000258243","pdf":"http://hdl.handle.net/20.500.11850/258243"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"Deep learning classifies cloud particle images from digital in-line holography to enable labeling of large datasets on precipitation initiation.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.3390-en11030528","title":"Ultra-Short-Term Forecast of Photovoltaic Output Power under Fog and Haze Weather","authors":["Weiliang Liu","Changliang Liu","Yongjun Lin","Liangyu Ma","Feng Xiong","Jintuo Li"],"date":"2018-02-28","year":2018,"venue":"Energies","venue_type":"journal","ids":{"doi":"10.3390/en11030528","openalex":"W2789711100"},"links":{"paper":"https://doi.org/10.3390/en11030528","pdf":"https://www.mdpi.com/1996-1073/11/3/528/pdf?version=1519959687"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning maps PM concentration to aerosol optical depth, and a dust model is combined with weather forecasts to predict ultra-short-term PV output under fog and haze.","significance":2,"cited_by":32,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.21086-ksles.2018.02.25.1.119","title":"Improvement for Forecasting of Photovoltaic Power Output using Real Time Weather Data based on Machine Learning","authors":["Jin-Hwa Jeong","Young-Tae Chae"],"date":"2018-02-28","year":2018,"venue":"한국생활환경학회지","venue_type":"journal","ids":{"doi":"10.21086/ksles.2018.02.25.1.119","openalex":"W2808443909"},"links":{"paper":"https://doi.org/10.21086/ksles.2018.02.25.1.119"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Random Forest, ANN and SVM forecast photovoltaic output from forecast weather and predicted solar radiation, with Random Forest performing best.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1802.08937","title":"Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion","authors":["Xinye Zheng","Jianbo Ye","Yukun Chen","Stephen Wistar","Jia Li","Jose A. Piedra-Fernández","Michael A. Steinberg","James Z. Wang"],"date":"2018-02-25","year":2018,"venue":"IEEE Transactions on Geoscience and Remote Sensing","venue_type":"journal","ids":{"arxiv":"1802.08937","doi":"10.1109/tgrs.2018.2887206","openalex":"W2788309473"},"links":{"paper":"https://doi.org/10.1109/tgrs.2018.2887206","pdf":"https://arxiv.org/pdf/1802.08937"},"orgs":["amazon"],"topic":"observations-remote-sensing","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Shape and motion features with a trained classifier detect comma-shaped cyclone-associated cloud patterns in satellite imagery to support severe weather forecasting.","significance":2,"cited_by":20,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1802.08055","title":"A Learning Based Approach for Uncertainty Analysis in Numerical Weather Prediction Models","authors":["Azam Moosavi","Vishwas Rao","Adrian Sandu"],"date":"2018-02-20","year":2018,"venue_type":"preprint","ids":{"arxiv":"1802.08055"},"links":{"paper":"https://arxiv.org/abs/1802.08055","pdf":"https://arxiv.org/pdf/1802.08055"},"orgs":[],"topic":"xai-uq-physics","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["other"],"status":"research","summary":"Machine learning learns WRF precipitation errors from past observations to correct systematic bias and identify which physics schemes drive forecast uncertainty.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1802.04742","title":"Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning","authors":["Thomas Vandal","Evan Kodra","Jennifer Dy","Sangram Ganguly","Ramakrishna Nemani","Auroop R. Ganguly"],"date":"2018-02-13","year":2018,"venue":"The 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, August 19--23, 2018, London, United Kingdom","venue_type":"journal","ids":{"arxiv":"1802.04742","doi":"10.1145/3219819.3219996"},"links":{"paper":"https://arxiv.org/abs/1802.04742","pdf":"https://arxiv.org/pdf/1802.04742"},"orgs":[],"topic":"downscaling","topics":["xai-uq-physics"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Discrete-continuous Bayesian deep learning with lognormal likelihood gives calibrated aleatoric and epistemic uncertainty for DeepSD precipitation downscaling, especially at extremes.","significance":4,"score":16,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.12783-dtcse-aiie2017-18223","title":"Short-term Precipitation Prediction Based on a Neural Network Method from Radar Observations","authors":["Yan Ji"],"date":"2018-02-12","year":2018,"venue":"DEStech Transactions on Computer Science and Engineering","venue_type":"journal","ids":{"doi":"10.12783/dtcse/aiie2017/18223","openalex":"W2791404987"},"links":{"paper":"https://doi.org/10.12783/dtcse/aiie2017/18223"},"orgs":[],"topic":"nowcasting","topics":["observations-remote-sensing"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["radar","stations"],"status":"research","summary":"Neural networks trained on CINRAD radar reflectivity and gauges nowcast Wuhan rain intensity, reaching over 50% accuracy at 36-minute lead for 5 dBZ.","significance":2,"cited_by":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-qj.3247","title":"Local improvements in numerical forecasts of relative humidity using polynomial solutions of general differential equations","authors":["Ladislav Zjavka","Zbyněk Sokol"],"date":"2018-02-09","year":2018,"venue":"Quarterly Journal of the Royal Meteorological Society","venue_type":"journal","ids":{"doi":"10.1002/qj.3247","openalex":"W2791696131"},"links":{"paper":"https://doi.org/10.1002/qj.3247"},"orgs":[],"topic":"post-processing","topics":["local-forecasting"],"type":"model","method":["other"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"research","summary":"A differential polynomial network corrects 24-hour numerical relative humidity forecasts using local observations, improving forecasts in most cases.","significance":2,"cited_by":12,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1016-j.energy.2018.01.177","title":"Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM","authors":["Xiangyun Qing","Yugang Niu"],"date":"2018-02-03","year":2018,"venue":"Energy","venue_type":"journal","ids":{"doi":"10.1016/j.energy.2018.01.177","openalex":"W2792326773"},"links":{"paper":"https://doi.org/10.1016/j.energy.2018.01.177"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"LSTM produces hourly day-ahead solar irradiance forecasts from weather forecast inputs for solar energy planning; abstract unavailable, so judged from title.","significance":2,"cited_by":953,"score":28,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-amt-11-611-2018","title":"Retrieval of an ice water path over the ocean from ISMAR and MARSS millimeter and submillimeter brightness temperatures","authors":["Manfred Brath","Stuart Fox","Patrick Eriksson","Chawn Harlow","Martin Jörg Burgdorf","Stefan A. Buehler"],"date":"2018-02-01","year":2018,"venue":"Atmospheric measurement techniques","venue_type":"journal","ids":{"doi":"10.5194/amt-11-611-2018","openalex":"W2694869475"},"links":{"paper":"https://doi.org/10.5194/amt-11-611-2018","pdf":"https://www.atmos-meas-tech.net/11/611/2018/amt-11-611-2018.pdf"},"orgs":["met-office"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["other"],"status":"research","summary":"Neural network retrieves snow and liquid water path and water vapour from airborne millimetre radiometer data; submillimetre channels halve snow retrieval error.","significance":3,"cited_by":69,"score":47,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1802.02548","title":"Predicting Hurricane Trajectories using a Recurrent Neural Network","authors":["Sheila Alemany","Jonathan Beltran","Adrian Perez","Sam Ganzfried"],"date":"2018-02-01","year":2018,"venue_type":"preprint","ids":{"arxiv":"1802.02548"},"links":{"paper":"https://arxiv.org/abs/1802.02548","pdf":"https://arxiv.org/pdf/1802.02548"},"orgs":[],"topic":"extremes-hazards","topics":[],"type":"model","method":["rnn"],"timescale":["short","medium"],"spatial":["regional"],"data":["other"],"status":"research","summary":"A fully connected RNN predicts hurricane tracks from NHC best-track latitude, longitude, wind and pressure, forecasting about 120 hours ahead at 6-hour steps, competitive with NHC methods.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1007-s00376-017-6334-9","title":"Three-dimensional fusion of spaceborne and ground radar reflectivity data using a neural network-based approach","authors":["Leilei Kou","Zhuihui Wang","Fen Xu"],"date":"2018-01-26","year":2018,"venue":"Advances in Atmospheric Sciences","venue_type":"journal","ids":{"doi":"10.1007/s00376-017-6334-9","openalex":"W2791568593"},"links":{"paper":"https://doi.org/10.1007/s00376-017-6334-9"},"orgs":["nuist"],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["radar","satellite"],"status":"research","summary":"A neural network method fuses spaceborne and ground radar reflectivity into three-dimensional fields. The abstract is missing, so the assessment relies on the title.","significance":2,"cited_by":18,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1801.08267","title":"Visual Weather Temperature Prediction","authors":["Wei-Ta Chu","Kai-Chia Ho","Ali Borji"],"date":"2018-01-25","year":2018,"venue_type":"preprint","ids":{"arxiv":"1801.08267"},"links":{"paper":"https://arxiv.org/abs/1801.08267","pdf":"https://arxiv.org/pdf/1801.08267"},"orgs":[],"topic":"observations-remote-sensing","topics":["local-forecasting"],"type":"model","method":["cnn","rnn"],"timescale":[],"spatial":["local"],"data":["other"],"status":"research","summary":"CNN and RNN models estimate ambient air temperature from outdoor images alone, with the RNN outperforming prior methods on image sequences.","significance":2,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4314-jfas.v9i3s.38","title":"Prediction of rainfall based on weather parameter using artificial neural network","authors":["Fakroul Ridzuan Hashim","N.G. Nik Daud","K.A. Ahmad","Ja’afar Adnan","Zairi Ismael Rizman"],"date":"2018-01-23","year":2018,"venue":"Journal of Fundamental and Applied Sciences","venue_type":"journal","ids":{"doi":"10.4314/jfas.v9i3s.38","openalex":"W2789124470"},"links":{"paper":"https://doi.org/10.4314/jfas.v9i3s.38","pdf":"https://www.ajol.info/index.php/jfas/article/download/165490/154949"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Multilayer perceptron trained with Levenberg-Marquardt predicts whether it will rain from temperature, pressure and humidity, reaching 99.75% accuracy.","significance":1,"cited_by":22,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1002-ep.12856","title":"Statistical downscaling of global climate model outputs to monthly precipitation via extreme learning machine: A case study","authors":["Meysam Alizamir","Mehdi Azhdary Moghadam","Arman Hashemi Monfared","Aliakbar Shamsipour"],"date":"2018-01-22","year":2018,"venue":"Environmental Progress & Sustainable Energy","venue_type":"journal","ids":{"doi":"10.1002/ep.12856","openalex":"W2791703741"},"links":{"paper":"https://doi.org/10.1002/ep.12856"},"orgs":[],"topic":"downscaling","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["era5","stations"],"status":"research","summary":"Extreme learning machine downscales reanalysis predictors to station monthly precipitation in Iran, outperforming ANN, genetic programming and quantile mapping.","significance":2,"cited_by":8,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1080-01431161.2018.1425562","title":"Nowcasting model of low wind profile based on neural network using SODAR data at Guarulhos Airport, Brazil","authors":["Gutemberg Borges França","Manoel Valdonel de Almeida","Suzanna Maria Bonnet","Francisco Leite Albuquerque Neto"],"date":"2018-01-19","year":2018,"venue":"International Journal of Remote Sensing","venue_type":"journal","ids":{"doi":"10.1080/01431161.2018.1425562","openalex":"W2792647419"},"links":{"paper":"https://doi.org/10.1080/01431161.2018.1425562"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["local"],"data":["other","stations"],"status":"research","summary":"Generalized regression neural network nowcasts low-level wind profiles up to 45 minutes ahead at Guarulhos Airport using SODAR data, with near-zero bias.","significance":2,"cited_by":18,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2794994087","title":"Machine Learning Approaches to Reducing Tropical Cyclone Prediction Errors","authors":["Michael B. Richman"],"date":"2018-01-10","year":2018,"venue":"98th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W2794994087"},"links":{"paper":"https://ams.confex.com/ams/98Annual/webprogram/Paper335042.html"},"orgs":["university-of-oklahoma"],"topic":"extremes-hazards","topics":["global-medium-range"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["global"],"data":["other"],"status":"research","summary":"An AMS 2018 conference abstract on applying machine learning to reduce tropical cyclone prediction errors. No abstract is available, so the assessment is low confidence.","significance":2,"cited_by":0,"score":18,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2785722420","title":"Super-Resolution and Deep Learning for Climate Downscaling","authors":["Thomas Vandal"],"date":"2018-01-10","year":2018,"venue":"98th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W2785722420"},"links":{"paper":"https://ams.confex.com/ams/98Annual/webprogram/Paper333682.html"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":[],"data":["other"],"status":"research","summary":"Conference abstract on applying super-resolution deep learning to climate downscaling; no quantitative results are available from the abstract.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2785486008","title":"Opportunities for Machine Learning in Weather Forecasting","authors":["Rachel Prudden"],"date":"2018-01-10","year":2018,"venue":"98th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W2785486008"},"links":{"paper":"https://ams.confex.com/ams/98Annual/webprogram/Paper328573.html"},"orgs":["met-office"],"topic":"global-medium-range","topics":[],"type":"position","method":[],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"AMS conference paper on opportunities for machine learning in weather forecasting; no abstract available, so content is inferred from the title.","significance":2,"cited_by":0,"score":43,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2784565490","title":"Precipitation Nowcasting Leveraging Deep Learning and HPC Systems to Optimize the Data Pipeline","authors":["Alexander Douglas Heye"],"date":"2018-01-10","year":2018,"venue":"98th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W2784565490"},"links":{"paper":"https://ams.confex.com/ams/98Annual/webprogram/Paper327679.html"},"orgs":[],"topic":"nowcasting","topics":["infra-software"],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Deep learning precipitation nowcasting paired with HPC-optimized data pipelines; abstract unavailable, so the contribution is inferred from the title only.","significance":2,"cited_by":1,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.12783-dtcse-csae2017-17544","title":"Convolutional Neural Networks Applied on Weather Radar Echo Extrapolation","authors":["En Shi","Qian Li","Daquan Gu","Zhangming Zhao"],"date":"2018-01-10","year":2018,"venue":"DEStech Transactions on Computer Science and Engineering","venue_type":"journal","ids":{"doi":"10.12783/dtcse/csae2017/17544","openalex":"W2783320027"},"links":{"paper":"https://doi.org/10.12783/dtcse/csae2017/17544"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn","rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Recurrent dynamic convolutional network extrapolates radar echo images for short-term nowcasting on Chinese radar data with higher accuracy than traditional methods.","significance":2,"cited_by":4,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2788147514","title":"Machine Learning with Numerical Weather Prediction Cloud Forecasts for Optical Communications Support","authors":["Alexandria M. Russell"],"date":"2018-01-09","year":2018,"venue":"98th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W2788147514"},"links":{"paper":"https://ams.confex.com/ams/98Annual/webprogram/Paper327137.html"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":[],"data":["nwp-analysis"],"status":"research","summary":"Applies machine learning to NWP cloud forecasts to support optical communication links; abstract unavailable, so scope is inferred from the title.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2787184278","title":"A Machine Learning Approach to Severe Weather Nowcasting using Weather Radar Data","authors":["César Beneti"],"date":"2018-01-09","year":2018,"venue":"98th American Meteorological Society Annual Meeting","venue_type":"journal","ids":{"openalex":"W2787184278"},"links":{"paper":"https://ams.confex.com/ams/98Annual/webprogram/Paper333598.html"},"orgs":[],"topic":"nowcasting","topics":["extremes-hazards"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"Machine learning applied to weather radar data for severe weather nowcasting; abstract unavailable, so details are inferred from the title only.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1109-tsmc.2017.2783681","title":"A Decision Support System for Wind Power Production","authors":["Ruggero Donida Labati","Angelo Genovese","Vincenzo Piuri","Fabio Scotti","Gianluca Sforza"],"date":"2018-01-09","year":2018,"venue":"IEEE Transactions on Systems Man and Cybernetics Systems","venue_type":"journal","ids":{"doi":"10.1109/tsmc.2017.2783681","openalex":"W2784195648"},"links":{"paper":"https://doi.org/10.1109/tsmc.2017.2783681"},"orgs":[],"topic":"applications-impacts","topics":["post-processing"],"type":"application","method":["classical-ml"],"timescale":["medium"],"spatial":["local"],"data":["nwp-analysis","stations"],"status":"pre-operational","summary":"Neural-network decision support system calibrates weather forecasts for wind farm orography and predicts power output, improving prediction at ten real wind farms.","significance":3,"cited_by":35,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-jtech-d-17-0096.1","title":"Smartphone Pressure Collection and Bias Correction Using Machine Learning","authors":["Callie McNicholas","Clifford F. Mass"],"date":"2018-01-04","year":2018,"venue":"Journal of Atmospheric and Oceanic Technology","venue_type":"journal","ids":{"doi":"10.1175/jtech-d-17-0096.1","openalex":"W2782459188"},"links":{"paper":"https://doi.org/10.1175/jtech-d-17-0096.1"},"orgs":["university-of-washington"],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["stations","other"],"status":"research","summary":"Machine learning corrects smartphone barometer biases using ancillary sensor data, cutting average pressure bias by 82% and supporting use in NWP.","significance":4,"cited_by":30,"score":26,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.5194-gmd-2017-276","title":"The Climate Generator: Stochastic climate representation for glacial cycle integration","authors":["Mohammad Hizbul Bahar Arif","Lev Tarasov","Tristan Hauser"],"date":"2018-01-02","year":2018,"venue_type":"other","ids":{"doi":"10.5194/gmd-2017-276","openalex":"W2781976050"},"links":{"paper":"https://doi.org/10.5194/gmd-2017-276","pdf":"https://www.geosci-model-dev-discuss.net/gmd-2017-276/gmd-2017-276.pdf"},"orgs":[],"topic":"climate-emulation","topics":["downscaling"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Bayesian neural networks emulate GCM monthly temperature and precipitation for glacial cycles, adding calibrated noise to mimic internal variability from 22 to 120 ka.","significance":3,"cited_by":1,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1801.00548","title":"A Machine Learning Approach to Adaptive Covariance Localization","authors":["Azam Moosavi","Ahmed Attia","Adrian Sandu"],"date":"2018-01-02","year":2018,"venue_type":"preprint","ids":{"arxiv":"1801.00548","openalex":"W2781882867"},"links":{"paper":"https://arxiv.org/abs/1801.00548","pdf":"https://arxiv.org/pdf/1801.00548"},"orgs":["argonne"],"topic":"data-assimilation","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Proposes machine-learning-based adaptive covariance localization for ensemble Kalman filters, tuning the localization radius in time and space to counter sampling errors.","significance":3,"cited_by":8,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3214373124","title":"Artificial neural network and data mining approaches for short-range wind speed forecasts","authors":["Petrina Papazek"],"date":"2018-01-01","year":2018,"venue_type":"other","ids":{"openalex":"W3214373124"},"links":{"paper":"https://othes.univie.ac.at/54339/"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Ensemble data-mining framework of ANNs, random forests and SVMs forecasts 10 m wind speed for Austria from 1 to 48 hours using station observations.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3093337440","title":"Weather forecasting with back propagation of neural network utilizing MATLAB","authors":["K. Geetha","B. Sarojamma","B. Hari Mallikarjuna Reddy"],"date":"2018-01-01","year":2018,"venue":"International Journal of Statistics and Applied Mathematics","venue_type":"journal","ids":{"openalex":"W3093337440"},"links":{"paper":"https://www.mathsjournal.com/pdf/2018/vol3issue2/PartD/3-2-13-782.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"MATLAB back-propagation neural network applied to one month of weather data; a small, basic application with limited novelty.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W3026400139","title":"Deep neural networks for statistical downscaling of climate change projections","authors":["Jorge Baño‐Medina","José Manuel Gutiérrez","Sixto Herrera"],"date":"2018-01-01","year":2018,"venue":"Dialnet (Universidad de la Rioja)","venue_type":"preprint","ids":{"openalex":"W3026400139"},"links":{"paper":"https://dialnet.unirioja.es/servlet/articulo?codigo=7374009"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":[],"timescale":["climate"],"spatial":[],"data":["cmip"],"status":"research","summary":"Deep neural networks are applied to statistically downscale climate change projections; no abstract or quantitative results are available.","significance":1,"cited_by":2,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2989799212","title":"RAINFALL PREDICTION WITH TSUKAMOTO FUZZY INFERENCE SYSTEM","authors":["Rosyana Fitria Purnomo","Matheace Ramaputra","Riko Herwanto"],"date":"2018-01-01","year":2018,"venue_type":"other","ids":{"openalex":"W2989799212"},"links":{"paper":"http://repo.darmajaya.ac.id/232/"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["stations"],"status":"research","summary":"Tsukamoto fuzzy inference system predicts rainfall in South Lampung, Indonesia from ten years of data to support agricultural planning.","significance":1,"cited_by":0,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2896943695","title":"Determining Cloud Cover with Machine Learning","authors":["Sarah Sesek"],"date":"2018-01-01","year":2018,"venue":"EngagedScholarship @ Cleveland State University (Cleveland State University)","venue_type":"preprint","ids":{"openalex":"W2896943695"},"links":{"paper":"https://engagedscholarship.csuohio.edu/u_poster_2018/40","pdf":"https://engagedscholarship.csuohio.edu/cgi/viewcontent.cgi?article=1039&context=u_poster_2018"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["cnn"],"timescale":[],"spatial":["local"],"data":["other","km-scale-sim"],"status":"research","summary":"A DeepLab-based CNN trained on large-eddy simulation fields segments cloud base from total sky imager images to improve boundary-layer cloud cover measurement.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"openalex-W2809531261","title":"Precipitation Nowcasting using Residual Networks","authors":["Emilio Vega Ezpeleta"],"date":"2018-01-01","year":2018,"venue_type":"other","ids":{"openalex":"W2809531261"},"links":{"paper":"http://www.diva-portal.org/smash/record.jsf?pid=diva2:1216196"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":[],"status":"research","summary":"Residual convolutional networks are applied to spatiotemporal inputs to investigate deep-learning precipitation nowcasting; abstract is truncated, so results are unknown.","significance":2,"cited_by":0,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4236-cweee.2018.73009","title":"Analysis of Global Warming Using Machine Learning","authors":["Harvey Zheng"],"date":"2018-01-01","year":2018,"venue":"Computational Water Energy and Environmental Engineering","venue_type":"journal","ids":{"doi":"10.4236/cweee.2018.73009","openalex":"W2886054132"},"links":{"paper":"https://doi.org/10.4236/cweee.2018.73009","pdf":"http://www.scirp.org/journal/PaperDownload.aspx?paperID=86337"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"application","method":["classical-ml"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"Random forest on 800,000 years of ice-core data finds CO2 the largest driver of temperature change, followed by CH4 and N2O.","significance":2,"cited_by":21,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.4172-2157-7617.1000475","title":"Comparison of MLP-ANN Scheme and SDSM as Tools for Providing Downscaled Precipitation for Impact Studies at Daily Time Scale","authors":["Rahman Hashmi MZU","Asaad Yahia Shamseldin","BW Melville"],"date":"2018-01-01","year":2018,"venue":"Journal of Earth Science & Climatic Change","venue_type":"journal","ids":{"doi":"10.4172/2157-7617.1000475","openalex":"W2856856245"},"links":{"paper":"https://doi.org/10.4172/2157-7617.1000475"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional","local"],"data":["stations","other"],"status":"research","summary":"An MLP-ANN downscaling scheme for daily precipitation in the Clutha watershed, New Zealand, is shown to outperform the standard SDSM regression model.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.30638-eemj.2018.127","title":"FORECASTING LONG TERM PRECIPITATION USING CUCKOO SEARCH OPTIMIZATION NEURAL NETWORK MODELS","authors":["Sze Miang Kueh","King Kuok Kuok"],"date":"2018-01-01","year":2018,"venue":"Environmental Engineering and Management Journal","venue_type":"journal","ids":{"doi":"10.30638/eemj.2018.127","openalex":"W2835358689"},"links":{"paper":"https://doi.org/10.30638/eemj.2018.127"},"orgs":[],"topic":"downscaling","topics":[],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["local"],"data":["cmip"],"status":"research","summary":"Cuckoo search-trained feedforward and recurrent networks downscale GCM output to project long-term precipitation, forecasting a 6–7% rise by 2071–2100.","significance":2,"cited_by":14,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.26808-rs.ca.i8v1.07","title":"Nonlinear Autoregression Neural Network for Meteorological Parameters Forecasting to Evaluate the Behavior of Radioactive Material Release from Nuclear Power Plants","authors":["Eman Sarwat"],"date":"2018-01-01","year":2018,"venue":"INTERNATIONAL JOURNAL OF COMPUTER APPLICATION","venue_type":"journal","ids":{"doi":"10.26808/rs.ca.i8v1.07","openalex":"W2790118068"},"links":{"paper":"https://doi.org/10.26808/rs.ca.i8v1.07","pdf":"https://doi.org/10.26808/rs.ca.i8v1.07"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["rnn"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"NARX recurrent network forecasts temperature and wind speed with MAPE under 20%, applied to meteorology for nuclear release assessment.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.25675-3.020697","title":"A new post-processing paradigm? Improving high-impact weather forecasts with machine learning","authors":["Gregory R. Herman","Schumacher, Russ S.","Barnes, Elizabeth A.","van den Heever, Susan C.","Cooley, Daniel S.","Hamill, Thomas M."],"date":"2018-01-01","year":2018,"venue":"Digital Collections of Colorado (Colorado State University)","venue_type":"preprint","ids":{"doi":"10.25675/3.020697","openalex":"W2976493830"},"links":{"paper":"https://doi.org/10.25675/3.020697"},"orgs":[],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis"],"status":"research","summary":"Machine-learning post-processing gives calibrated probabilistic forecasts of flash floods, extreme rain, tornadoes, hail and convective winds across the US.","significance":3,"score":12,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.2151-sola.2018-023","title":"Contrail Recognition with Convolutional Neural Network and Contrail Parameterizations Evaluation","authors":["Guoyu Zhang","Jinglin Zhang","Jian Shang"],"date":"2018-01-01","year":2018,"venue":"SOLA","venue_type":"journal","ids":{"doi":"10.2151/sola.2018-023","openalex":"W2892351121"},"links":{"paper":"https://doi.org/10.2151/sola.2018-023","pdf":"https://www.jstage.jst.go.jp/article/sola/14/0/14_2018-023/_pdf"},"orgs":["nuist"],"topic":"observations-remote-sensing","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["regional"],"data":["satellite","era5"],"status":"research","summary":"ContrailMod, a CNN applied to Himawari-8 imagery, outperforms a conventional contrail detection algorithm and is used to evaluate potential contrail coverage from ERA-Interim over South China.","significance":3,"cited_by":21,"score":22,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.18488-journal.2.2018.81.1.12","title":"Weather Forecasting Models Using Neural Networks and Adaptive Neuro Fuzzy Inference for Two Case Studies at Huoston, Texas and Dallas States","authors":["Chelang Akrem Arslan","Enas Kayis"],"date":"2018-01-01","year":2018,"venue":"Journal of Asian Scientific Research","venue_type":"journal","ids":{"doi":"10.18488/journal.2.2018.81.1.12","openalex":"W2782045358"},"links":{"paper":"https://doi.org/10.18488/journal.2.2018.81.1.12"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"application","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Backpropagation neural network and ANFIS models forecast daily precipitation for two Texas cities using weather variables and lagged precipitation values.","significance":1,"cited_by":1,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijgw.2018.091508","title":"Integrating metaheuristics and artificial neural network for weather forecasting","authors":["Mustafa Göçken","Aslı Boru","Ayşe Tuğba Dosdoğru","Mehmet Özçalıcı"],"date":"2018-01-01","year":2018,"venue":"International Journal of Global Warming","venue_type":"journal","ids":{"doi":"10.1504/ijgw.2018.091508","openalex":"W4254299413"},"links":{"paper":"https://doi.org/10.1504/ijgw.2018.091508"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Genetic algorithm and harmony search tune neural networks to forecast daily mean temperature in six Turkish cities, improving on plain ANN baselines.","significance":2,"cited_by":5,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1504-ijes.2018.10016095","title":"A survey of rainfall forecasting using artificial neural network","authors":["Nigel Linge","Xiaodong Liu","Qi Liu","Yanyun Zou"],"date":"2018-01-01","year":2018,"venue":"International Journal of Embedded Systems","venue_type":"journal","ids":{"doi":"10.1504/ijes.2018.10016095","openalex":"W2891320863"},"links":{"paper":"https://doi.org/10.1504/ijes.2018.10016095","pdf":"https://www.inderscienceonline.com/doi/epdf/10.1504/IJES.2019.098300"},"orgs":["nuist"],"topic":"local-forecasting","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":[],"data":[],"status":"research","summary":"Survey of artificial neural network methods for rainfall prediction, arguing they outperform NWP and statistical models for nonlinear precipitation dynamics.","significance":1,"cited_by":6,"score":14,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14569-ijacsa.2018.090859","title":"Artificial Neural Network based Weather Prediction using Back Propagation Technique","authors":["Saboor Ahmed Kakar","Naveed Sheikh","Adnan Naseem","Saleem Iqbal","Abdul Rehman","Aziz Ullah","Bilal Ahmad","Hazrat Ali","Bilal  Alam Khan"],"date":"2018-01-01","year":2018,"venue":"International Journal of Advanced Computer Science and Applications","venue_type":"journal","ids":{"doi":"10.14569/ijacsa.2018.090859","openalex":"W2891610319"},"links":{"paper":"https://doi.org/10.14569/ijacsa.2018.090859","pdf":"http://thesai.org/Downloads/Volume9No8/Paper_59-Artificial_Neural_Network.pdf"},"orgs":[],"topic":"local-forecasting","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["stations"],"status":"research","summary":"Backpropagation neural network predicts daily maximum temperature and classifies weather types from 1997-2015 records; a basic application study.","significance":1,"cited_by":19,"score":4,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.14569-ijacsa.2018.090208","title":"Detection of Climate Crashes using Fuzzy Neural Networks","authors":["H. Rahib","Mohammed Azad","Boran Şekeroğlu"],"date":"2018-01-01","year":2018,"venue":"International Journal of Advanced Computer Science and Applications","venue_type":"journal","ids":{"doi":"10.14569/ijacsa.2018.090208","openalex":"W2788289703"},"links":{"paper":"https://doi.org/10.14569/ijacsa.2018.090208","pdf":"http://thesai.org/Downloads/Volume9No2/Paper_8-Detection_of_Climate_Crashes_using_Fuzzy_Neural.pdf"},"orgs":[],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Takagi-Sugeno fuzzy neural network detects failures ('crashes') in climate model simulations, reaching 97.96% accuracy versus 94.4% for SVM.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.12677-jisp.2018.74023","title":"3D Convolutional Neural Network for Regional Precipitation Nowcasting","authors":["昆 吴"],"date":"2018-01-01","year":2018,"venue":"Journal of Image and Signal Processing","venue_type":"journal","ids":{"doi":"10.12677/jisp.2018.74023","openalex":"W3135367079"},"links":{"paper":"https://doi.org/10.12677/jisp.2018.74023"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["other"],"status":"research","summary":"3D convolutional network for regional precipitation nowcasting; abstract missing, so details are limited to the title.","significance":2,"cited_by":36,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1155-2018-7210137","title":"Error Correction of Meteorological Data Obtained with Mini-AWSs Based on Machine Learning","authors":["Ji-Hun Ha","Yong-Hyuk Kim","Hyo-Hyuc Im","Nayoung Kim","Sangjin Sim","Yourim Yoon"],"date":"2018-01-01","year":2018,"venue":"Advances in Meteorology","venue_type":"journal","ids":{"doi":"10.1155/2018/7210137","openalex":"W2800754400"},"links":{"paper":"https://doi.org/10.1155/2018/7210137","pdf":"http://downloads.hindawi.com/journals/amete/2018/7210137.pdf"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["local"],"data":["stations"],"status":"research","summary":"Machine learning error correction makes low-cost Mini-AWS pressure readings meet WMO ±0.1 hPa accuracy, offering a cheap complement to automatic weather stations.","significance":2,"cited_by":16,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"arxiv-1812.09467","title":"Deep Uncertainty Learning: A Machine Learning Approach for Weather Forecasting.","authors":["Bin Wang","Zheng Yan","Huaishao Luo","Tianrui Li","Jie Lu B","Guangquan Zhang"],"date":"2018-01-01","year":2018,"venue_type":"preprint","ids":{"arxiv":"1812.09467","openalex":"W2906239890"},"links":{"paper":"https://arxiv.org/pdf/1812.09467.pdf"},"orgs":[],"topic":"probabilistic-ensembles","topics":[],"type":"model","method":["other"],"timescale":["short"],"spatial":[],"data":["other"],"status":"research","summary":"Deep learning framework for quantifying uncertainty in weather forecasts; abstract unavailable, so only the title is available.","significance":2,"cited_by":3,"score":8,"highlight":false,"classic":false,"added":"2026-10-22","source":"backfill"},{"id":"doi-10.1175-bams-d-16-0123.1","title":"Using Artificial Intelligence to Improve Real-Time Decision-Making for High-Impact Weather","authors":["Amy McGovern","Kimberly L. Elmore","David John Gagne","Sue Ellen Haupt","Christopher D. Karstens","Ryan Lagerquist","Travis Smith","John K. Williams"],"date":"2017-10-01","year":2017,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/bams-d-16-0123.1","openalex":"W2601923741"},"links":{"paper":"https://doi.org/10.1175/bams-d-16-0123.1"},"orgs":["ncar","noaa","university-of-oklahoma"],"topic":"extremes-hazards","topics":["applications-impacts"],"type":"review","method":["classical-ml"],"timescale":["nowcast","short"],"spatial":["regional"],"data":["nwp-analysis","radar","stations"],"status":"research","summary":"Shows AI methods, combined with physical understanding, improve forecasts of storm duration, severe wind and hail, precipitation type, renewable energy and aviation turbulence.","significance":4,"cited_by":444,"score":61,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-waf-d-17-0010.1","title":"Storm-Based Probabilistic Hail Forecasting with Machine Learning Applied to Convection-Allowing Ensembles","authors":["David John Gagne","Amy McGovern","Sue Ellen Haupt","Ryan A. Sobash","John K. Williams","Ming Xue"],"date":"2017-09-22","year":2017,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/waf-d-17-0010.1","openalex":"W2743153755"},"links":{"paper":"https://doi.org/10.1175/waf-d-17-0010.1"},"orgs":["ncar","university-of-oklahoma"],"topic":"extremes-hazards","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","radar"],"status":"research","summary":"Storm-based machine learning produces calibrated probabilistic severe hail forecasts from convection-allowing ensembles, achieving higher critical success index than existing hail forecasting methods.","significance":5,"cited_by":169,"score":65,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1709.00037","title":"Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations","authors":["Tapio Schneider","Shiwei Lan","Andrew Stuart","João Teixeira"],"date":"2017-08-31","year":2017,"venue":"Geophysical Research Letters 2017","venue_type":"journal","ids":{"arxiv":"1709.00037","doi":"10.1002/2017gl076101","openalex":"W2750605337"},"links":{"paper":"https://arxiv.org/abs/1709.00037","pdf":"https://arxiv.org/pdf/1709.00037"},"orgs":["caltech","nasa"],"topic":"hybrid-parameterization","topics":["data-assimilation"],"type":"position","method":["other"],"timescale":["climate"],"spatial":["global"],"data":["other"],"status":"research","summary":"A blueprint proposes Earth system models that learn parameterizations from observations and high-resolution simulations via data assimilation and machine learning, illustrated on a toy system.","significance":6,"cited_by":391,"score":69,"highlight":true,"highlight_reason":"Influential blueprint for ESMs learning parameterizations from observations and high-resolution simulations; shaped hybrid climate modeling agenda.","classic":true,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1706.03458","title":"Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model","authors":["Xingjian Shi","Zhihan Gao","Leonard Lausen","Hao Wang","Dit-Yan Yeung","Wai-kin Wong","Wang-chun Woo"],"date":"2017-06-12","year":2017,"venue_type":"preprint","ids":{"arxiv":"1706.03458","openalex":"W2625614184"},"links":{"paper":"https://arxiv.org/abs/1706.03458","pdf":"https://arxiv.org/pdf/1706.03458"},"orgs":[],"topic":"nowcasting","topics":["benchmarks-data-eval"],"type":"model","method":["rnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"TrajGRU learns location-variant recurrent connections for radar nowcasting and is benchmarked on a Hong Kong Observatory dataset, outperforming ConvLSTM.","significance":6,"cited_by":829,"score":44,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1016-j.renene.2016.12.095","title":"Machine learning methods for solar radiation forecasting: A review","authors":["Cyril Voyant","Gilles Notton","Soteris Kalogirou","Marie-Laure Nivet","Christophe Paoli","Fabrice Motte","Alexis Fouilloy"],"date":"2017-05-01","year":2017,"venue":"Renewable Energy","venue_type":"journal","ids":{"doi":"10.1016/j.renene.2016.12.095","openalex":"W2569349941"},"links":{"paper":"https://doi.org/10.1016/j.renene.2016.12.095"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"review","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Reviews machine learning for solar radiation forecasting, a renewable energy application rather than atmospheric science.","significance":2,"cited_by":1829,"score":28,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1703.03126","title":"DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution","authors":["Thomas Vandal","Evan Kodra","Sangram Ganguly","Andrew Michaelis","Ramakrishna Nemani","Auroop R Ganguly"],"date":"2017-03-09","year":2017,"venue":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","venue_type":"preprint","ids":{"arxiv":"1703.03126","doi":"10.1145/3097983.3098004","openalex":"W2604521289"},"links":{"paper":"https://arxiv.org/abs/1703.03126","pdf":"https://arxiv.org/pdf/1703.03126"},"orgs":["nasa"],"topic":"downscaling","topics":[],"type":"model","method":["cnn"],"timescale":["climate"],"spatial":["regional"],"data":["cmip"],"status":"research","summary":"DeepSD applies a multi-scale stacked super-resolution CNN to downscale daily precipitation from 1 degree to 1/8 degree over the continental US for climate projections.","significance":5,"cited_by":281,"score":65,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1609-aaai.v31i1.11172","title":"Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data","authors":["Jiaxuan You","Xiaocheng Li","Melvin Low","David Lobell","Stefano Ermon"],"date":"2017-02-12","year":2017,"venue":"Proceedings of the AAAI Conference on Artificial Intelligence","venue_type":"journal","ids":{"doi":"10.1609/aaai.v31i1.11172","openalex":"W2604645045"},"links":{"paper":"https://doi.org/10.1609/aaai.v31i1.11172"},"orgs":["stanford"],"topic":"applications-impacts","topics":[],"type":"model","method":["cnn","rnn","gan-vae","classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Deep Gaussian process with CNN or LSTM features predicts county-level crop yields from remote sensing; the target is agriculture, not weather or climate.","significance":1,"cited_by":598,"score":34,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1612.02095","title":"ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events","authors":["Evan Racah","Christopher Beckham","Tegan Maharaj","Samira Ebrahimi Kahou","Prabhat","Christopher Pal"],"date":"2016-12-07","year":2016,"venue_type":"preprint","ids":{"arxiv":"1612.02095","openalex":"W2752848290"},"links":{"paper":"https://arxiv.org/abs/1612.02095","pdf":"https://arxiv.org/pdf/1612.02095","code":"https://github.com/eracah/hur-detect"},"orgs":["lbnl-nersc"],"topic":"extremes-hazards","topics":[],"type":"benchmark","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"Introduces ExtremeWeather, a labeled climate dataset and semi-supervised spatiotemporal CNN for localizing hurricanes, extratropical cyclones and fronts in simulations.","significance":5,"cited_by":184,"score":50,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1109-smc.2016.7844673","title":"Deep Learning for solar power forecasting — An approach using AutoEncoder and LSTM Neural Networks","authors":["André Gensler","Janosch Henze","Bernhard Sick","Nils Raabe"],"date":"2016-10-01","year":2016,"venue":"2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","venue_type":"conference","ids":{"arxiv":"2016.78446","doi":"10.1109/smc.2016.7844673","openalex":"W2587586954"},"links":{"paper":"https://doi.org/10.1109/smc.2016.7844673"},"orgs":[],"topic":"applications-impacts","topics":[],"type":"model","method":["rnn","gan-vae"],"timescale":["short"],"spatial":["local"],"data":["other"],"status":"research","summary":"Applies an autoencoder with LSTM to solar power forecasting; the energy target is not an atmospheric target, so it is out of scope.","significance":2,"cited_by":664,"score":28,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-mwr-d-15-0260.1","title":"Calibrated Ensemble Forecasts Using Quantile Regression Forests and Ensemble Model Output Statistics","authors":["Maxime Taillardat","Olivier Mestre","Michaël Zamo","Philippe Naveau"],"date":"2016-06-10","year":2016,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr-d-15-0260.1","openalex":"W2296277783"},"links":{"paper":"https://doi.org/10.1175/mwr-d-15-0260.1"},"orgs":["meteo-france"],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["regional"],"data":["nwp-analysis","stations"],"status":"research","summary":"Quantile regression forests calibrate Météo-France ensemble temperature and wind forecasts, outperforming EMOS and giving better-calibrated, sharper probabilistic forecasts from 3 to 54 h.","significance":4,"cited_by":245,"score":61,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-jcli-d-15-0654.1","title":"Using Causal Effect Networks to Analyze Different Arctic Drivers of Midlatitude Winter Circulation","authors":["Marlene Kretschmer","Dim Coumou","Jonathan F. Donges","Jakob Runge"],"date":"2016-06-01","year":2016,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-15-0654.1","openalex":"W2288320689"},"links":{"paper":"https://doi.org/10.1175/jcli-d-15-0654.1"},"orgs":["pik"],"topic":"climate-analysis-attribution","topics":[],"type":"model","method":["classical-ml"],"timescale":["s2s"],"spatial":["global"],"data":["era5"],"status":"research","summary":"Causal effect networks identify Barents and Kara sea ice and Eurasian snow cover as drivers of winter Arctic Oscillation and midlatitude circulation.","significance":4,"cited_by":311,"score":36,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1605.01156","title":"Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets","authors":["Yunjie Liu","Evan Racah","Prabhat","Joaquin Correa","Amir Khosrowshahi","David Lavers","Kenneth Kunkel","Michael Wehner","William Collins"],"date":"2016-05-04","year":2016,"venue_type":"preprint","ids":{"arxiv":"1605.01156","openalex":"W2345707736"},"links":{"paper":"https://arxiv.org/abs/1605.01156","pdf":"https://arxiv.org/pdf/1605.01156"},"orgs":[],"topic":"extremes-hazards","topics":["climate-analysis-attribution"],"type":"model","method":["cnn"],"timescale":[],"spatial":["global"],"data":["cmip"],"status":"research","summary":"First deep CNN application to detect tropical cyclones, atmospheric rivers and weather fronts in climate datasets, reaching 89-99% accuracy.","significance":4,"cited_by":300,"score":26,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-jhm-d-15-0075.1","title":"A Deep Neural Network Modeling Framework to Reduce Bias in Satellite Precipitation Products","authors":["Yumeng Tao","Xiaogang Gao","Kuolin Hsu","Soroosh Sorooshian","Alexander Ihler"],"date":"2016-03-02","year":2016,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/jhm-d-15-0075.1","openalex":"W2232647241"},"links":{"paper":"https://doi.org/10.1175/jhm-d-15-0075.1"},"orgs":[],"topic":"observations-remote-sensing","topics":["post-processing"],"type":"model","method":["other"],"timescale":[],"spatial":["regional"],"data":["satellite","radar"],"status":"research","summary":"A stacked denoising autoencoder bias-corrects PERSIANN-CCS satellite rainfall, cutting precipitation-rate bias by 78–98% and false alarms by 33–43%.","significance":4,"cited_by":159,"score":26,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"arxiv-1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","authors":["Xingjian Shi","Zhourong Chen","Hao Wang","Dit-Yan Yeung","Wai-kin Wong","Wang-chun Woo"],"date":"2015-06-13","year":2015,"venue_type":"preprint","ids":{"arxiv":"1506.04214","openalex":"W1485009520"},"links":{"paper":"https://arxiv.org/abs/1506.04214","pdf":"https://arxiv.org/pdf/1506.04214"},"orgs":[],"topic":"nowcasting","topics":[],"type":"model","method":["rnn","cnn"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"ConvLSTM recasts precipitation nowcasting as spatiotemporal sequence prediction, outperforming FC-LSTM and the operational ROVER algorithm on radar rainfall data.","significance":8,"cited_by":7706,"score":52,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-jcli-d-11-00387.1","title":"Causal Discovery for Climate Research Using Graphical Models","authors":["Imme Ebert-Uphoff","Yi Deng"],"date":"2012-03-02","year":2012,"venue":"Journal of Climate","venue_type":"journal","ids":{"doi":"10.1175/jcli-d-11-00387.1","openalex":"W2071312622"},"links":{"paper":"https://doi.org/10.1175/jcli-d-11-00387.1"},"orgs":["colorado-state-university"],"topic":"climate-analysis-attribution","topics":[],"type":"review","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["era5"],"status":"research","summary":"Accessible introduction to constraint-based causal discovery for climate scientists, illustrated on boreal winter atmospheric low-frequency modes.","significance":4,"cited_by":186,"score":36,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-2008jhm960.1","title":"Probabilistic Multisite Precipitation Downscaling by an Expanded Bernoulli–Gamma Density Network","authors":["Alex J. Cannon"],"date":"2008-12-01","year":2008,"venue":"Journal of Hydrometeorology","venue_type":"journal","ids":{"doi":"10.1175/2008jhm960.1","openalex":"W1995797217"},"links":{"paper":"https://doi.org/10.1175/2008jhm960.1"},"orgs":["eccc"],"topic":"downscaling","topics":["post-processing"],"type":"model","method":["classical-ml"],"timescale":["climate"],"spatial":["regional","local"],"data":["stations"],"status":"research","summary":"An expanded Bernoulli-gamma neural density network downscales multisite daily precipitation from synoptic predictors, reproducing spatial covariances and generating realistic synthetic series in coastal British Columbia.","significance":3,"cited_by":140,"score":32,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1016-j.neunet.2006.01.002","title":"Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction","authors":["Vladimir M. Krasnopolsky","Michael S. Fox-Rabinovitz"],"date":"2006-03-01","year":2006,"venue":"Neural Networks","venue_type":"journal","ids":{"doi":"10.1016/j.neunet.2006.01.002","openalex":"W2083307976"},"links":{"paper":"https://doi.org/10.1016/j.neunet.2006.01.002"},"orgs":["noaa"],"topic":"hybrid-parameterization","topics":["global-medium-range"],"type":"position","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Discusses hybrid models combining deterministic physics and machine learning components for climate modeling and weather prediction; abstract unavailable.","significance":4,"cited_by":179,"score":61,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-mwr2923.1","title":"New Approach to Calculation of Atmospheric Model Physics: Accurate and Fast Neural Network Emulation of Longwave Radiation in a Climate Model","authors":["Vladimir M. Krasnopolsky","Michael S. Fox-Rabinovitz","Dmitry V. Chalikov"],"date":"2005-05-01","year":2005,"venue":"Monthly Weather Review","venue_type":"journal","ids":{"doi":"10.1175/mwr2923.1","openalex":"W2047421660"},"links":{"paper":"https://doi.org/10.1175/mwr2923.1"},"orgs":["noaa"],"topic":"hybrid-parameterization","topics":["climate-emulation"],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Neural network emulates CAM longwave radiation 50-80 times faster with near-identical 10-year climate simulations, an early ML physics emulation.","significance":6,"cited_by":197,"score":69,"highlight":true,"highlight_reason":"Seminal NN emulation of CAM longwave radiation, 50-80x speedup with stable climate runs; foundational for ML physics emulation.","classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-1520-0434-1998-013-1194-lpffan-2.0.co-2","title":"Localized Precipitation Forecasts from a Numerical Weather Prediction Model Using Artificial Neural Networks","authors":["Robert J. Kuligowski","Ana P. Barros"],"date":"1998-12-01","year":1998,"venue":"Weather and Forecasting","venue_type":"journal","ids":{"doi":"10.1175/1520-0434(1998)013<1194:lpffan>2.0.co;2","openalex":"W2160203977"},"links":{"paper":"https://doi.org/10.1175/1520-0434(1998)013<1194:lpffan>2.0.co;2"},"orgs":[],"topic":"post-processing","topics":[],"type":"model","method":["classical-ml"],"timescale":["short"],"spatial":["local"],"data":["nwp-analysis"],"status":"research","summary":"Early work using artificial neural networks to produce localized precipitation forecasts from NWP model output. Abstract not available; classification based on title.","significance":2,"cited_by":166,"score":18,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-1520-0450-1998-037-1385-annafa-2.0.co-2","title":"A Neural Network Approach for a Fast and Accurate Computation of a Longwave Radiative Budget","authors":["F. Chevallier","F. Chéruy","N. A. Scott","A. Chédin"],"date":"1998-11-01","year":1998,"venue":"Journal of Applied Meteorology","venue_type":"journal","ids":{"doi":"10.1175/1520-0450(1998)037<1385:annafa>2.0.co;2","openalex":"W2176178328"},"links":{"paper":"https://doi.org/10.1175/1520-0450(1998)037<1385:annafa>2.0.co;2"},"orgs":["ecmwf"],"topic":"hybrid-parameterization","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["global"],"data":["other"],"status":"research","summary":"Early neural network approach computes longwave radiative budgets quickly and accurately for atmospheric models; abstract unavailable.","significance":5,"cited_by":362,"score":65,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-1520-0477-1998-079-1855-annmtp-2.0.co-2","title":"Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography","authors":["William W. Hsieh","Benyang Tang"],"date":"1998-09-01","year":1998,"venue":"Bulletin of the American Meteorological Society","venue_type":"journal","ids":{"doi":"10.1175/1520-0477(1998)079<1855:annmtp>2.0.co;2","openalex":"W2084547407"},"links":{"paper":"https://doi.org/10.1175/1520-0477(1998)079<1855:annmtp>2.0.co;2"},"orgs":[],"topic":"global-medium-range","topics":["climate-analysis-attribution"],"type":"review","method":["classical-ml"],"timescale":["short","seasonal"],"spatial":["regional","global"],"data":["other"],"status":"research","summary":"Early review of neural network applications to meteorological and oceanographic prediction and data analysis, from the pre-deep-learning era.","significance":3,"cited_by":418,"score":22,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-1520-0450-1997-036-1176-pefrsi-2.0.co-2","title":"Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks","authors":["Kou-lin Hsu","Xiaogang Gao","Soroosh Sorooshian","Hoshin V. Gupta"],"date":"1997-09-01","year":1997,"venue":"Journal of Applied Meteorology","venue_type":"journal","ids":{"doi":"10.1175/1520-0450(1997)036<1176:pefrsi>2.0.co;2","openalex":"W2094653192"},"links":{"paper":"https://doi.org/10.1175/1520-0450(1997)036<1176:pefrsi>2.0.co;2"},"orgs":[],"topic":"observations-remote-sensing","topics":[],"type":"model","method":["classical-ml"],"timescale":[],"spatial":["regional"],"data":["satellite"],"status":"research","summary":"Early neural network method that estimates precipitation rates from remotely sensed satellite cloud and infrared information.","significance":4,"cited_by":1098,"score":36,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"},{"id":"doi-10.1175-1520-0450-1996-035-0617-annftp-2.0.co-2","title":"A Neural Network for Tornado Prediction Based on Doppler Radar-Derived Attributes","authors":["Caren Marzban","Gregory J. Stumpf"],"date":"1996-05-01","year":1996,"venue":"Journal of Applied Meteorology","venue_type":"journal","ids":{"doi":"10.1175/1520-0450(1996)035<0617:annftp>2.0.co;2","openalex":"W2031580446"},"links":{"paper":"https://doi.org/10.1175/1520-0450(1996)035<0617:annftp>2.0.co;2"},"orgs":["noaa","university-of-oklahoma"],"topic":"extremes-hazards","topics":["nowcasting"],"type":"model","method":["classical-ml"],"timescale":["nowcast"],"spatial":["regional"],"data":["radar"],"status":"research","summary":"An early neural network predicts tornadoes from Doppler radar-derived storm attributes. Abstract not available; classification based on title.","significance":4,"cited_by":175,"score":61,"highlight":false,"classic":true,"added":"2026-10-22","source":"seed"}]