Google’s WeatherNext 3 improves weather forecasting by combining current raw satellite data with global weather analyses. This allows the model to detect atmospheric changes more quickly and update forecasts hourly instead of every six hours as before. WeatherNext 3 also uses higher spatial resolution and a larger machine-learning architecture. A separate model estimates precipitation based on satellite data.
Google reports an approximately five percent improvement in upper-atmosphere accuracy, equivalent to around six additional hours of reliable forecast lead time. Location-specific temperature calculations can improve accuracy by up to 30%. WeatherNext 3 already provides weather forecasts across Google Search, Gemini, and Maps.