Nowcasting
Forecasts from minutes to about 6 hours, mostly precipitation and convection, learned from radar, satellite or station data.
297 papers · 5 ★
Topics
Every paper has one primary topic and up to two secondary topics.
Forecasting
Global medium-range NWP
Data-driven global weather models for 1 to 15 days, usually trained on reanalysis (ERA5), deterministic or with a single best estimate.
63 papers · 10 ★
Probabilistic & ensemble forecasting
ML models that produce ensembles or full forecast distributions: generative models (diffusion, flow matching), CRPS-trained models, learned perturbations.
27 papers · 7 ★
Regional & km-scale models
Limited-area and regional ML weather models, convection-permitting and km-scale emulators, including boundary handling and stretched grids.
17 papers · 2 ★
Local & station forecasting
ML forecasts for a point, station, city or small area, mostly from observed time series (rainfall, temperature, wind, fog, visibility), without a gridded NWP-like model. Use post-processing instead when the model corrects NWP output.
411 papers · 0 ★
Sub-seasonal to seasonal
Forecasts from 2 weeks to about a year: sub-seasonal, seasonal and ENSO/MJO prediction.
180 papers · 5 ★
Climate emulation
Emulators of climate models and long stable rollouts (decades to centuries), scenario emulation, emulators of the coupled climate system.
84 papers · 3 ★
Modelling chain
Hybrid physics-ML & parameterization
ML inside physical models: subgrid parameterizations (convection, clouds, radiation, turbulence, gravity waves), online coupling, differentiable dynamical cores.
182 papers · 7 ★
Data assimilation
ML for data assimilation and state estimation, learned observation operators, and end-to-end models that forecast directly from observations.
77 papers · 4 ★
Downscaling & super-resolution
Statistical and generative downscaling of weather or climate fields to higher resolution, including bias-aware downscaling of climate projections.
282 papers · 2 ★
Post-processing & calibration
Statistical post-processing of NWP or ML forecasts: bias correction, ensemble calibration, distributional regression, station forecasts.
263 papers · 2 ★
Foundation models
Large pretrained models for the atmosphere or Earth system that are fine-tuned for many tasks (forecasting, downscaling, other variables).
12 papers · 2 ★
Hazards & observations
Extremes & hazards
Prediction and detection of extremes: tropical cyclones, heatwaves, heavy rain, severe convection, hail, tornadoes, fire weather, atmospheric rivers, cold spells.
443 papers · 2 ★
Observations & remote sensing
ML on satellite, radar and in-situ observations for weather and climate: retrievals, precipitation estimation, cloud detection, gap filling of observations.
395 papers · 0 ★
Science & cross-cutting
Climate analysis & attribution
ML for climate science questions: causal discovery, teleconnections, pattern detection, detection and attribution, climate model evaluation.
200 papers · 3 ★
Explainability, uncertainty & physics
Explainable AI for weather/climate, uncertainty quantification, and tests of physical consistency, balance, spectra and stability of AI models.
63 papers · 3 ★
Benchmarks, datasets & evaluation
Benchmarks, ML-ready datasets, verification methods and model intercomparisons.
52 papers · 6 ★
Software, scaling & compression
Frameworks, training and inference at scale, HPC, and compression of weather and climate data with ML.
23 papers · 2 ★
Applications & impacts
ML weather or climate models applied to a sector: renewable energy, agriculture, health, insurance, aviation. The ML-for-weather part must be central.
269 papers · 1 ★
LLMs & agents
Language models and agents for weather and climate science: QA, data analysis, model-running agents, multimodal models that read weather fields.
10 papers · 0 ★
Later
Ocean & sea ice
Ocean-only forecasting and emulation, sea-ice prediction.
Coming later: papers are collected but not labeled yet.
Hydrology & floods
Rainfall-runoff, streamflow, flood inundation, land hydrology.
Coming later: papers are collected but not labeled yet.
Atmospheric composition & air quality
Air quality, aerosols and chemistry as the main target.
Coming later: papers are collected but not labeled yet.