WeatherNext AI Model Achieves Breakthrough in Forecasting Cyclones with Extra Day of Warning

Google DeepMind's WeatherNext AI model has made a breakthrough in forecasting cyclones, providing accurate predictions that give forecasters an extra day of warning. According to a paper published in Nature, the model achieved state-of-the-art accuracy in predicting a cyclone's track, intensity, and wind structure.

The team behind WeatherNext worked with expert forecasters at the National Hurricane Center (NHC), the Cooperative Institute for Research in the Atmosphere (CIRA), the UK Met Office, and weather agencies around the world. The model was co-trained on two distinct data modalities: global weather dynamics and expert-curated historical cyclone observations.

WeatherNext uses Functional Generative Networks (FGNs) to efficiently produce ensembles of different predictions, which captures the inherent uncertainty of the weather. The team claims that this improvement is equivalent to a decade's worth of meteorological progress. The model has already had real-world impact, helping the NHC make a historic forecast for Hurricane Melissa in 2025.

The WeatherNext model is now open-sourced, allowing researchers and meteorological agencies to build on its technology. This includes academic research, operational forecasting, or developing more specialized, localized models.