Google DeepMind and Google Research released WeatherNext 3 on September 3, 2026, a new AI weather forecasting model that the company says will begin powering weather information across Google Search, Google Maps, and Gemini, as well as being available to users and researchers on Google’s cloud platforms.
WeatherNext 3 has ranked as the most accurate model among leading contenders tested on Operational WeatherBench, a forecasting comparison tool built by the startup Brightband. It outperformed deep-learning models from Google, Microsoft, Nvidia, and the European Centre for Medium-Range Weather Forecasting (ECMWF), as well as traditional forecasts from the U.S. National Weather Service and the ECMWF.
The model addresses three longstanding weaknesses in AI forecasting. It can predict key variables at a resolution of 5km, compared to the 15–25 square km typical of earlier models. Its rain forecasting is 60% improved over its predecessor, WeatherNext 2. And it now produces hourly forecasts rather than the standard six-hour intervals. WeatherNext 3 is also 2.4 times larger in parameters than WeatherNext 2.
Those hourly forecasts are possible because the model ingests real-time satellite data on an hourly basis. Google describes WeatherNext 3 as the first AI model to directly incorporate raw observations for a high-resolution global forecast, though AI weather startup WindBorne says its WeatherMesh 6 model has incorporated raw observations since late 2025. Both models still rely on national weather datasets to perform forecasts.
“This is going to be the first time that some of the core variables feed and power a lot of the Google products,” said Samier Merchant, a Google senior staff engineer.
The broader shift toward AI-based meteorology carries potential consequences beyond consumer apps. European and U.S. weather agencies are already incorporating AI models into their forecast products. DeepMind researcher Ferran Alet noted that higher-resolution forecasts of wind, rain, and cloud cover could make renewable energy projects more dependable, and Bill Gates has cited AI weather forecasting as a tool that could improve crop yields in developing countries.
Source: TechCrunch