22 papers in the archive.
Compares uncertainty quantification methods for Pangu-Weather ensembles over Europe; ML post-hoc UQ gives skill up to 5 days beyond ECMWF ENS.
Explainability, uncertainty & physicsKarlsruhe Institute of Technology (KIT)
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.
Downscaling & super-resolutionKarlsruhe Institute of Technology (KIT)
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.
Foundation modelsIBM ResearchKarlsruhe Institute of Technology (KIT)NASA
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.
Sub-seasonal to seasonalKarlsruhe Institute of Technology (KIT)
Releases EUPPBench, a time-aligned forecast-observation dataset with evaluation methods and a first benchmark of 2 m temperature postprocessing.
Benchmarks, datasets & evaluationDeutscher Wetterdienst (DWD)ECMWFKarlsruhe Institute of Technology (KIT)Met OfficeMétéo-France (incl. CNRM)MeteoSwisscode
CNN post-processing of ECMWF ensemble means yields calibrated global tercile forecasts for weeks 3-6, outperforming recalibrated ECMWF sub-seasonal forecasts.
Post-processing & calibrationKarlsruhe Institute of Technology (KIT)
Proposes a probabilistic clear-sky benchmark and neural post-processing methods for NWP-based solar irradiance forecasts, with proper scoring and calibration checks.
Post-processing & calibrationKarlsruhe Institute of Technology (KIT)
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.
Post-processing & calibrationETH ZurichKarlsruhe Institute of Technology (KIT)
Machine learning post-processing of ECMWF forecasts improves MJO prediction, outperforming multiple linear regression in location and intensity skill.
Post-processing & calibrationECMWFKarlsruhe Institute of Technology (KIT)
Convolutional autoencoders compress spatial NWP fields into features that augment station-based neural post-processing of 2 m temperature ensemble forecasts over Germany.
Post-processing & calibrationKarlsruhe Institute of Technology (KIT)
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.
Climate analysis & attributionKarlsruhe Institute of Technology (KIT)
Applies the CNN warm conveyor belt identifier to reanalyses and ECMWF ensembles, showing CNN and trajectory methods agree on North Atlantic forecast biases.
Climate analysis & attributionKarlsruhe Institute of Technology (KIT)
CNNs predict warm conveyor belt inflow, ascent and outflow footprints from gridded fields, reproducing trajectory-based climatology at much lower computational cost.
Climate analysis & attributionKarlsruhe Institute of Technology (KIT)
Deep-learning postprocessing turns deterministic West-WRF atmospheric river IVT forecasts into reliable probabilistic forecasts that rival calibrated GEFS out to 120 h.
Post-processing & calibrationNSF NCAR / UCARKarlsruhe Institute of Technology (KIT)
Systematic comparison of eight statistical and ML wind gust ensemble postprocessing methods on German convection-permitting ensembles; locally adaptive neural networks perform best.
Post-processing & calibrationKarlsruhe Institute of Technology (KIT)
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.
Post-processing & calibrationThe Alan Turing InstituteKarlsruhe Institute of Technology (KIT)Met OfficeNSF NCAR / UCAR
Random forest and SVM classify polar stratospheric clouds from MIPAS infrared limb spectra, with random forest the most promising and less prone to overfitting.
Observations & remote sensingKarlsruhe Institute of Technology (KIT)Forschungszentrum Jülich / Jülich Supercomputing Centre
Review of statistical postprocessing methods for NWP forecasts and their challenges in big-data settings, with little explicit machine learning focus.
Post-processing & calibrationDeutscher Wetterdienst (DWD)ECMWFKarlsruhe Institute of Technology (KIT)KNMI (Royal Netherlands Meteorological Institute)MET Norway (Norwegian Meteorological Institute)Met OfficeMétéo-France (incl. CNRM)MeteoSwiss
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.
Post-processing & calibrationKarlsruhe Institute of Technology (KIT)
A one-hidden-layer neural network replaces Monin–Obukhov stability functions for surface-layer fluxes, matching the standard method at seven flux sites.
Hybrid physics-ML & parameterizationKarlsruhe Institute of Technology (KIT)Forschungszentrum Jülich / Jülich Supercomputing Centre
Linear ML regression predicts 3D ozone from temperature alone, improving stratospheric ozone variability over fixed climatology for preindustrial and 4xCO2 climate sensitivity runs.
Hybrid physics-ML & parameterizationUniversity of Cambridge (Aardvark)Karlsruhe Institute of Technology (KIT)
Neural networks for ensemble post-processing outperform benchmark distributional regression for 2-m temperature at German stations, using embeddings and auxiliary predictors.
Post-processing & calibrationKarlsruhe Institute of Technology (KIT)
