A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior performance compared to the world’s leading traditional systems. The model, named GraphCast, uses machine learning to analyze decades of historical weather data and current atmospheric conditions to generate accurate 10-day forecasts in under a minute. In head-to-head tests, GraphCast outperformed the European Centre for Medium-Range Weather Forecasts’ high-resolution system, the current global gold standard, on over 90% of 1,380 test variables. The AI system showed particular strength in predicting extreme weather events, including tropical cyclones and atmospheric rivers, with greater accuracy and at a fraction of the computational cost of conventional physics-based models. While not intended to replace existing systems, researchers suggest AI models like GraphCast could work alongside them to provide faster, more efficient forecasts, potentially improving early warning systems for severe weather. The model’s code has been made publicly available to support further research in the field. Read the full article at: https://technologyreview.com/2023/11/14/1083729/ai-weather-forecasting-model-graphcast-outperforms-traditional-systems/