Google DeepMind opens SatWeave and PARDIG climate datasets
Google DeepMind released SatWeave and PARDIG, the foundational datasets behind WeatherNext 3, with real-time streams and historical archives for climate research and development. SatWeave combines observations from five geostationary satellites into a global imagery mosaic, while PARDIG uses a spherical-grid Transformer architecture for global precipitation reanalysis. Google reported that PARDIG outperformed NASA IMERG-Final in its evaluation, but the supplied reports contain no independent reproduction.
The release gives researchers and developers openly licensed access to the real-time and archival data underpinning WeatherNext 3 for weather, hydrology, climate, and related modeling.
Accurate weather forecasting starts with how clearly we can observe the atmosphere in real-time. 🌍
That’s why we’re releasing PARDIG and SatWeave - the foundational datasets behind WeatherNext 3 - to help researchers and developers build new climate applications 🧵
#Google DeepMind#WeatherNext 3#SatWeave#PARDIG#NASA IMERG-Final#NASA GPM Core Observatory#ECMWF