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 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 system (HRES), GraphCast provided more accurate forecasts for over 90% of 1,380 test variables. The AI system significantly outperformed HRES in predicting severe weather events, including tropical cyclones and atmospheric rivers, while completing forecasts in under a minute on a single machine—far faster than traditional supercomputer-based methods. Researchers emphasize the model is designed to complement rather than replace existing systems, offering a new tool for meteorologists. For the full details, read the complete article at https://technologyreview.com/2023/11/14/1084079/ai-weather-forecasting-graphcast-outperforms-traditional-models/