Google DeepMind's WeatherNext AI Achieves Decade of Meteorological Progress, Revolutionizing Cyclone Forecasting
Summary
Google DeepMind's WeatherNext AI delivers a decade's worth of meteorological progress, achieving three-day cyclone forecasts as accurate as previous two-day models, successfully predicting Hurricane Melissa's rapid intensification, and is now being open-sourced to empower researchers and agencies worldwide.
Key Points
- Google DeepMind's WeatherNext AI model achieves a breakthrough in cyclone forecasting, delivering three-day forecasts as accurate as what previous models could only provide for two days, representing roughly a decade of meteorological progress.
- The model successfully predicted Hurricane Melissa's rapid intensification and Jamaica landfall during the 2025 hurricane season, enabling the National Hurricane Center to issue advance warnings, and now generates 1,000 possible cyclone scenarios to support forecasters.
- Google DeepMind is open sourcing WeatherNext 2 and WeatherNext Cyclones, including code and model weights, to empower researchers, meteorological agencies, and nonprofits worldwide to improve weather prediction and protect communities from extreme weather events.