Predicting how hurricanes and cyclones develop is a longstanding challenge, and every hour of warning counts. Tropical cyclones are among the most destructive weather events on Earth, and for meteorologists, issuing accurate, timely warnings is a constant race against time.

Today, in a paper published in Nature, Google researchers show that our WeatherNext AI model achieved state-of-the-art accuracy in predicting a cyclone's track, intensity, and wind structure. This represents a massive leap forward — roughly a decade of meteorological progress in one model.

To help build climate resilience worldwide, we are now open-sourcing the WeatherNext 2 model to the global research community. For more information, check the Google DeepMind blog.