Google DeepMind has publicly released SatWeave and PARDIG, the two foundational datasets behind its WeatherNext 3 weather model, both hosted on Google Cloud Storage under CC BY 4.0. PARDIG uses a spherical-grid Transformer with ~10 km spatial and 15-minute temporal resolution, outperforming NASA IMERG-Final by over 30% on hourly light-to-moderate precipitation detection and remaining reliable in regions lacking ground radar.
Toolsslug: pardig
PARDIG
A foundational dataset supporting weather, hydrology, and climate modeling, forming the data base of WeatherNext 3 alongside Sat
Curated Intelligence
IT之家 · 智能时代T2·Open Source
78 pts
Google DeepMindT1·Open Source
72 pts
Google DeepMind's WeatherNext team released SatWeave and PARDIG, two foundational datasets for building weather, hydrology, and climate applications. Both underpin the recently launched WeatherNext 3 model, and their open release lowers the data barrier for researchers worldwide.