27 papers in the archive.
DLESyM, a deep learning Earth system model, simulates 1000-year observed climate without drift, matching CMIP6 variability at a fraction of the cost.
Climate emulationInstitute of Atmospheric Physics, Chinese Academy of SciencesUniversity of Washington
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.
LLMs & agentsAllen Institute for AI (Ai2, ACE)University of Washingtoncode
Backpropagation through GraphCast optimizes initial conditions, cutting 10-day Pacific Northwest heatwave errors over 90% and extending predictability to about 23 days.
Explainability, uncertainty & physicsUniversity of Washington
Classical dynamical experiments show Pangu-Weather reproduces Matsuno-Gill responses, polar lows and hurricane development, suggesting it encodes realistic atmospheric physics.
Explainability, uncertainty & physicsUniversity of Washington
A CNN trained on daily precipitation from climate models detects emerging anthropogenic signals in observed rainfall since the mid-2010s.
Climate analysis & attributionNanjing University of Information Science & Technology (NUIST)University of Washington
Describes an AI2ES summer school teaching trustworthy and explainable AI for severe storms, tropical cyclones and space weather to 677 participants.
Explainability, uncertainty & physicsNOAA (incl. GFDL, PSL, GSL, NCEP/EMC)NSF NCAR / UCARUniversity of WashingtonColorado State University (incl. CIRA)University of Oklahoma (AI2ES)
AiBEDO uses the Fluctuation-Dissipation Theorem and 8250 years of Earth system model output to emulate regional climate responses to marine cloud brightening forcing.
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.
Climate analysis & attributionNOAA (incl. GFDL, PSL, GSL, NCEP/EMC)NSF NCAR / UCARUniversity of Washington
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.
Extremes & hazardsUniversity of WashingtonMax Planck Institute for Biogeochemistry
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.
Data assimilationNOAA (incl. GFDL, PSL, GSL, NCEP/EMC)NSF NCAR / UCARUniversity of Washington
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.
Hybrid physics-ML & parameterizationAllen Institute for AI (Ai2, ACE)NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)University of Washington
UWILD random forest classifies ice versus liquid particles in Southern Ocean clouds from 2D-S probe images with 95% accuracy, beating two existing methods.
Machine learning bias correction of billions of smartphone pressure observations cuts errors 43-57% and yields analyses 21-31% better than MADIS networks.
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.
Hybrid physics-ML & parameterizationAllen Institute for AI (Ai2, ACE)NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)University of WashingtonPrinceton University
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.
Sub-seasonal to seasonalMicrosoft Research (AI for Science)University of Washington
Perspective proposing Neural Earth System Modelling, which fuses deep networks and Earth system models into interpretable hybrids that might eventually replace them.
Hybrid physics-ML & parameterizationColorado State University (incl. CIRA)NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)Potsdam Institute for Climate Impact Research (PIK)Princeton UniversityUniversity of Washington
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.
Hybrid physics-ML & parameterizationNOAA (incl. GFDL, PSL, GSL, NCEP/EMC)University of WashingtonUniversity of ReadingColorado State University (incl. CIRA)
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.
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.
Global medium-range NWPMicrosoft Research (AI for Science)University of Washington
Introduces tools to interpret neural convection parameterizations and diagnose gravity-wave instability when coupled to climate models, using SPCAM and cloud-resolving training data.
Hybrid physics-ML & parameterizationAllen Institute for AI (Ai2, ACE)Columbia University (LEAP, Lamont-Doherty)University of Washington
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.
Benchmarks, datasets & evaluationECMWFTechnical University of Munich (TUM)University of Washingtoncode
WeatherBench provides an ERA5-derived benchmark with metrics and baselines for data-driven global medium-range forecasting, enabling direct model comparison.
Benchmarks, datasets & evaluationECMWFUniversity of WashingtonTechnical University of Munich (TUM)code
CNNs forecast 500-hPa geopotential height up to 14 days, beating persistence and barotropic vorticity model but not the operational NWP model.
Global medium-range NWPMicrosoft Research (AI for Science)University of Washington
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.
Hybrid physics-ML & parameterizationUniversity of Washington
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.
Hybrid physics-ML & parameterizationUniversity of Washington
Neural network unified physics parameterization trained on 4-km aquaplanet data gives stable prognostic single-column tests better than CAM's scheme.
Hybrid physics-ML & parameterizationUniversity of Washington
Machine learning corrects smartphone barometer biases using ancillary sensor data, cutting average pressure bias by 82% and supporting use in NWP.
