Google DeepMind published a Nature paper showing its WeatherNext model predicts a tropical cyclone's path, strength and wind field more accurately than existing systems, with three-day forecasts matching what earlier models managed at two days. The code and model weights for WeatherNext Cyclones and WeatherNext 2 are now openly available, including a compact version that runs in a free notebook. Google notes that official warnings still come from national weather agencies.
What changed
Cyclone track and intensity needed separate models, and WeatherNext weights were not publicly available.
What it unlocks
Running Google's cyclone and global weather models locally, including a compact version in a free Colab notebook on a single TPU.
- 24+ hours extra lead time
- 1,000-member ensemble, up from 50
- 15-day forecast in under a minute
- 28x28km input resolution
What you need to act on it
- technical setup to run the models
- compute for full-size versions
- deepmind.google2026-08-06