16 papers in the archive · tier-1 watchlist.
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
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.
Software, scaling & compressionCSCS - Swiss National Supercomputing CentreETH ZurichMeteoSwissMassachusetts Institute of Technology (MIT)Max Planck Institute for MeteorologyNSF NCAR / UCARNVIDIAUniversity of Reading
A latent diffusion model for radar precipitation nowcasting gives more diverse, well-calibrated ensembles than DGMR and PySTEPS, with more accurate predictions.
Neural network post-processing of Swiss surface forecasts enforces thermodynamic equations, yielding physically consistent temperature and humidity without losing accuracy, especially with scarce data.
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.
MESMER-X statistical emulator reproduces spatially resolved annual maximum temperatures of Earth system models using global mean temperature as the driver.
MESMER-M extends an Earth system model emulator to monthly local temperatures, emulating 38 CMIP6 models with skewed, spatially correlated variability.
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.
Gradient-boosted nowcasts of reflectivity, lightning and hail-related echo tops show radar is the most useful input and satellite helps across all hazards.
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.
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.
A recurrent stochastic GAN generates ensembles of temporally consistent high-resolution precipitation radar and cloud optical thickness fields from low-resolution sequences.
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
Stacking TrajGRU ensemble members with orographic features via a CNN roughly doubles skill on extreme rain rates, matching Lagrangian persistence on TAASRAD19 radar data.
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.
Compares generalized linear models and neural networks for rainfall retrieval from geostationary IR data, using OPERA radar as truth; neural networks reduce false alarms.
