A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior accuracy to current state-of-the-art systems in global medium-range weather predictions. The model, named GraphCast, outperformed the European Centre for Medium-Range Weather Forecasts’ (ECMWF) high-resolution forecast (HRES) system in over 90% of 1,380 test variables and lead times. GraphCast uses machine learning trained on decades of historical weather data to predict future conditions, generating a 10-day forecast in under one minute on a single Google TPU v4 machine. While traditional numerical weather prediction relies on complex physics calculations, this AI approach learns patterns directly from data. Researchers note the model is particularly skilled at predicting severe weather events, including tropical cyclones and extreme temperatures. The technology represents a significant shift in weather modeling, though experts emphasize it should complement rather than replace existing physics-based systems. For the full details, read the complete article at https://technologyreview.com/2023/11/14/1083729/ai-weather-forecasting-graphcast-outperforms-traditional-models/.