A new AI model from Google DeepMind is the world’s most accurate 10-day global weather forecasting system, according to the London-based lab. The model is open sourced, with the code on GitHub.
Named GraphCast, the model promises medium-range weather forecasts of “unprecedented accuracy.” In research published today, GraphCast was found to be more precise and faster than the industry gold standard for weather simulation, the High-Resolution Forecast (HRES).
The system also predicted extreme weather from a more distant future than was previously possible. These insights were analysed by the European Centre for Medium-Range Weather Forecasts (ECMWF), an intergovernmental organisation that produces the HRES.
In tests, the results were impressive. GraphCast significantly outperformed the most accurate operational deterministic systems on 90% of 1,380 test targets.
It’s not perfect though, as it has had issues with predicting the intensity of cyclones, as well as precipitation amounts.
And whilst this is all great and fine, I don’t actually find any mobile app at all that uses these predictions. There is also no mention of ‘whether’ Google’s own weather forecasts are actually using it. So I suppose we have to stay tuned to hear when it really filters into what real end users actually use.
See https://thenextweb.com/news/deepmind-ai-graphcast-weather-forecasting