A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior performance compared to traditional physics-based systems in global medium-range weather predictions. The model, named GraphCast, uses machine learning to analyze decades of historical weather data and current atmospheric conditions to generate accurate 10-day forecasts in under one minute. In head-to-head comparisons with the European Centre for Medium-Range Weather Forecasts’ high-resolution system (HRES), GraphCast provided more accurate predictions for over 90% of 1,380 test variables, including temperature, pressure, wind speed, and humidity. The AI system particularly excelled at predicting extreme weather events like tropical cyclones and atmospheric rivers earlier and with greater precision. Researchers emphasize that AI models like GraphCast complement rather than replace traditional methods, offering faster, more computationally efficient forecasts that could improve early warning systems for severe weather worldwide. For the full analysis and technical details, read the complete article at https://technologyreview.com/2024/03/14/ai-weather-model-graphcast-outperforms-traditional-systems.