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 recent Science paper, leverages 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 forecast (HRES), GraphCast provided more accurate predictions for over 90% of 1,380 test variables. The AI system can generate a 10-day forecast in under one minute on a single Google TPU v4 machine, a significant reduction from the hours required by traditional supercomputer-run models. Researchers note that while promising, AI models like GraphCast should complement rather than replace established physical models, as they currently lack the ability to explain their reasoning or directly incorporate new scientific insights. For the full details on this breakthrough in meteorological AI, read the complete article at https://technologyreview.com/2023/11/14/1084089/ai-weather-forecast-graphcast-outperforms-traditional-models/.