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 model, named GraphCast, utilizes machine learning trained on decades of historical weather data to predict hundreds of weather variables up to 10 days in advance. In a comprehensive evaluation, GraphCast significantly outperformed the world’s leading numerical weather prediction system, the European Centre for Medium-Range Weather Forecasts’ (ECMWF) High RESolution forecast (HRES), on over 90% of 1,380 test variables. The AI system showed particular strength in predicting severe weather events, providing more accurate forecasts for tropical cyclones, atmospheric rivers, and extreme temperatures. Researchers note that while AI models like GraphCast are faster and less computationally expensive than conventional models, they are best used in conjunction with traditional systems rather than as replacements. The development marks a significant advancement in the application of machine learning to complex Earth system science challenges. For the full article, visit: https://www.example.com/full-article