Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Machine learning for weather and climate
Weather and climate ML trains data-driven forecasters and emulators on reanalysis (ERA5) and climate-model output: medium-range global forecasting, long stable climate emulation, statistical downscaling to high resolution, and prediction of extremes and precipitation nowcasting. Evaluation follows meteorological practice: latitude-weighted RMSE and anomaly correlation against analysis for deterministic forecasts, CRPS and spread-skill for ensembles, spectra for blurriness, and categorical scores (CSI, FSS) for precipitation, always against physical baselines (ECMWF IFS, climatology, persistence) on held-out years.