Google DeepMind has released two new datasets, SatWeave and PARDIG, to advance AI-driven weather forecasting. SatWeave offers a unified, hourly view of global cloud and storm development by combining imagery from five geostationary satellites. PARDIG, an AI-based precipitation dataset, provides highly accurate, high-resolution global precipitation maps updated every 15 minutes, outperforming existing baselines like NASA's IMERG-Final. AI
IMPACT Enables researchers to build more advanced AI weather and climate applications, potentially improving forecasting accuracy and lead times.
RANK_REASON Release of datasets by a major AI lab to support research and development in AI weather modeling. [lever_c_demoted from research: ic=1 ai=1.0]
- European Centre for Medium-Range Weather Forecasts
- GOES-East
- GOES-West
- Google DeepMind
- Himawari
- Meteosat 0
- Meteosat Indian Ocean
- NASA Global Precipitation Measurement (GPM) Core Observatory
- NASA's IMERG-Final
- SatWeave
- WeatherNext 3
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →