Google today announced WeatherNext 3 as its “most advanced and accurate global weather AI model,” with immediate benefits for Search and Gemini.
Other AI weather models (including WeatherNext 2 from November 2025) are “trained on data from numerical weather prediction (NWP) models.”
Although useful, NWP models are complex, supercomputer-driven physics simulations that carry a six-hour data lag. This lag can lead to biases for fast-changing variables like rain or surface temperature.
WeatherNext 3 uses a “mosaic of live, global geostationary satellite data.” This ability to learn “directly from real-time observations” allows for a “continuously updating view of the atmosphere” that results in “timely and more localized predictions for the weather events.” The Google DeepMind and Google Research model can generate “hourly forecasts at multiple spatial resolutions.”
Temperature and moisture at 5-kilometer resolution
