Google DeepMind's AI Outperforms Traditional Weather Forecasting

GraphCast Uses Neural Networks to Predict Weather Conditions with Unprecedented Accuracy

Google DeepMind's new AI model, GraphCast, can predict weather conditions up to 10 days in advance with unprecedented accuracy, outperforming the current best weather simulation system, the High Resolution Forecast (HRES), used by the European Centre for Medium-Range Weather Forecasts (ECMWF).
GraphCast uses a neural network to learn how the atmosphere evolves over time, trained on 40 years of meteorological data from weather stations, satellite images, and radar records.
The AI model can produce precise forecasts in less than a minute, and has shown it can identify extreme weather events much sooner than traditional forecasts.
GraphCast has been made open source, allowing weather organizations around the world to use it alongside their traditional models.
While the AI model has shown promising results, it is not intended to replace traditional weather forecasting methods, but rather to complement and improve them.