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 GraphCast model, detailed in a study published in Science, uses machine learning to analyze decades of historical weather data, learning complex atmospheric patterns to generate 10-day forecasts in under a minute on a single computer. In head-to-head comparisons with the European Centre for Medium-Range Weather Forecasts’ high-resolution system (HRES), GraphCast was more accurate in over 90% of 1,380 test variables, including critical metrics for tracking severe weather events. The AI model showed particular strength in predicting extreme temperatures and atmospheric river events days in advance, though researchers note it should complement rather than replace existing systems due to limitations in predicting rare events and the continued need for human expertise. The model’s efficiency and open-source nature could democratize access to high-quality weather forecasting globally. Read the full article at: https://sciencedaily.com/releases/2023/11/231114143453.htm