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, described in a Science journal paper, uses machine learning trained on decades of historical weather data to predict hundreds of weather variables up to 10 days in advance. In head-to-head comparisons with the European Centre for Medium-Range Weather Forecasts’ high-resolution forecasting system (HRES), GraphCast provided more accurate predictions for over 90% of 1,380 test variables. The AI system was particularly skilled at predicting severe weather events, correctly anticipating the path of Hurricane Lee’s landfall in Nova Scotia three days earlier than traditional approaches. While meteorologists emphasize that AI models should complement rather than replace existing systems, the technology represents a significant advancement in computational efficiency, generating 10-day forecasts in under one minute on a single Google TPU v4 cloud computer. For the full article, visit https://sciencedaily.com/releases/2023/11/231114155012.htm.