Google WeatherNext improves cyclone forecasts
DeepMind and Google Research say the AI model gives forecasters about one extra day of lead time.
Why it matters
The results suggest AI weather models can improve high-impact forecasting where additional warning time can affect emergency planning. Google has also published a WeatherNext repository on GitHub, pointing to broader access for researchers and developers.
The key points
- 1.WeatherNext reportedly adds about one day of cyclone forecast lead time.
- 2.The model predicted Hurricane Melissa's Jamaica impact five days before landfall.
- 3.Google has published a WeatherNext repository on GitHub.
Researchers reported in a Nature paper that Google DeepMind and Google Research's WeatherNext AI model can predict cyclones with higher accuracy than existing models cited in the reports. Ars Technica reported that, on average, its three-day predictions match the accuracy of previous models' two-day predictions, giving forecasters about one additional day of lead time. In October 2025, WeatherNext predicted five days before landfall with 80 percent confidence that a Caribbean storm would hit Jamaica as a Category 5 hurricane, according to Ars Technica.
⚡ Try this today
Review the WeatherNext GitHub repository before building cyclone-risk or weather-forecasting workflows.
Sources & original reporting
This brief summarizes and links to reporting from the publishers below.
Enjoyed this brief? Get the next one in your inbox.
More in Research
Startup says cancer AI needs better data
TechCrunch reports a startup argues cancer cures require stronger data, not near-term AI claims.
HarnessRisk benchmark targets agent harness safety
The arXiv benchmark tests safety failures across agent configuration, tools, state and recovery.
Agent Lightning v1.0 targets harnessed agentic RL
The framework connects arbitrary agent harnesses to RL training through an LLM endpoint proxy.