Google DeepMind’s WeatherNext 3 learns from live satellite data and powers Search and Maps
See how this story connectsGoogle DeepMind and Google Research released WeatherNext 3, a weather model that learns from live satellite observations as well as physics simulations. It gives hourly forecasts at up to 5km resolution, about five times sharper than WeatherNext 2, and adds 100m wind, solar radiation and cloud cover for energy planning. Google reports precipitation forecasts up to 50% more accurate a day or more out, with the largest gains where forecasts have been weakest, and cites Brightband’s live evaluations as ranking it the most accurate global model. From 3 September it powers weather in Google Search, the Gemini app, Google Maps, the Maps Platform Weather API and Earth Engine, and the data can be queried in BigQuery or downloaded from Cloud Storage.
Why it matters
The model behind weather in Google Search, Maps and the Gemini app now learns from satellite data, and its outputs are open to researchers and grid operators.
- When
- 3 Sep 2026
- ID
WTA-N-2026-0260- Where
- United States, International
- Who
- Google DeepMind, Google
Summary by wheresthe.ai, from Google. Checked against the source on 12 Oct 2026.
Source copy: download the page as saved on 18 Oct 2026 (PDF). Also held by the Internet Archive.
Cite this story
WTA-N-2026-0260: “Google DeepMind’s WeatherNext 3 learns from live satellite data and powers Search and Maps.” wheresthe.ai, 3 Sep 2026. https://wheresthe.ai/d/google-weathernext-3-2026-09/ (source: Google).
Spotted an error? Email [email protected].