WeatherNext 3

AI weather forecasting model

dataadvanced

Overview

WeatherNext 3 adds hourly refreshes, higher resolution, precise precipitation forecasting, and clean-energy variables. The launch is clearly focused on predictive analytics rather than a user-facing weather app. It is most relevant for teams building weather-sensitive planning or energy applications.

Best For

+data teams
+energy

News & Updates

Google's WeatherNext 3 Ditches Physics, Learns from Live Satellite Data at 5km Resolution

Google Research and DeepMind are releasing WeatherNext 3, a weather model that skips traditional physics simulations and learns directly from real-time satellite data. It produces hourly forecasts at up to five-kilometer resolution, five times more detailed than its predecessor. Google says regions in Africa, Latin America, and the Asia-Pacific that have lacked accurate forecasts should see the biggest gains. This shift from physics-based to data-driven modeling could make forecasts faster and more accurate, especially in data-sparse regions.

breakthroughs9/6/2026

Google's WeatherNext 3 AI Model Powers Search, Maps, and Gemini Forecasts

Google has unveiled WeatherNext 3, a deep learning-based weather model that will soon feed forecasts into Google Search, Google Maps, and Gemini. The model represents a significant leap in meteorological accuracy, leveraging advanced neural networks to predict weather patterns with greater precision than traditional numerical models. Google says WeatherNext 3 will provide hyper-local, real-time updates, making it easier for users to plan around rain or sunshine. This integration marks a major shift in how weather data is delivered to billions of users daily.

breakthroughs9/3/2026