Learn how our latest AI model, developed with Google DeepMind, is helping us better predict the weather ⬇️
Today, we are introducing WeatherNext 2, our most advanced AI-based medium-range weather forecasting model, developed by Google DeepMind and Google Research. The weather affects important decisions and high quality weather forecasting has a significant impact on people, businesses and society. In recent years AI-based modeling has dramatically enhanced what’s possible with weather forecasting and the new WeatherNext 2 models are more accurate, of higher resolution, and more efficient. ✨ Accelerating Speed and Resolution: WeatherNext 2 generates forecasts 8 X faster and at a higher resolution (down to 1-hour intervals) than its predecessor. ✨ Superior Accuracy: Overall, WeatherNext 2 surpasses the previous state-of-the-art WeatherNext model on 99.9% of variables and lead times (0–15 days). ✨ Modeling Uncertainty for Resilience: The model introduces a new approach, the Functional Generative Network (FGN), which predicts hundreds of possible weather outcomes. This is crucial for meteorologists who need to plan for a range of scenarios, especially the most important "worst-case" outcomes. ✨ From Research to Reality: We are making the forecast data available in Earth Engine and BigQuery and launching an early access program on Google Cloud’s Vertex AI platform for custom model inference. The technology is now upgrading forecasts in Search, Gemini, Pixel Weather, and Google Maps Platform’s Weather API, with integration coming soon to Google Maps. WeatherNext 2 represents a significant step in translating breakthrough AI from the lab into high-impact, operational applications. We are making powerful tools available to the global community to accelerate scientific discovery and build a more resilient future. Read more about WeatherNext 2: https://lnkd.in/dfqGShGp Read paper: https://lnkd.in/dC5yTWEP Earth AI: https://lnkd.in/d33UYtae