A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior accuracy compared to conventional physics-based systems in global medium-range weather predictions. The GraphCast model, detailed in a Science journal study, leverages machine learning trained on decades of historical weather data to predict hundreds of key atmospheric variables. In head-to-head tests against the European Centre for Medium-Range Weather Forecasts’ high-resolution system (HRES), GraphCast provided more accurate forecasts for over 90% of 1,380 test variables. The AI system excels at predicting severe weather events earlier, including tropical cyclones and extreme temperatures, while running in under a minute on a single machine. Researchers emphasize that AI models like GraphCast are designed to complement, not replace, traditional methods, offering a new tool for meteorologists. The full findings are published in the peer-reviewed journal Science. Read the full article at https://sciencedaily.com/releases/2023/11/231114155022.htm