A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior accuracy compared to the world’s leading conventional system in a comprehensive global evaluation. The AI model, named GraphCast, significantly outperformed the European Centre for Medium-Range Weather Forecasts’ (ECMWF) high-resolution forecast (HRES) system across more than 90% of 1,380 test variables and prediction timeframes. The study, published in Science, highlights GraphCast’s ability to provide accurate 10-day forecasts in under one minute on a single Google TPU v4 cloud computer, a task that typically takes the traditional system hours to compute on a supercomputer. Researchers emphasize that the AI system is not intended to replace but to complement existing physics-based models, potentially offering a powerful new tool for meteorologists. The model was trained on decades of historical weather data from ECMWF to learn cause-and-effect relationships within Earth’s weather systems. For the full details and methodology, read the complete article at: https://sciencedaily.com/releases/2023/11/231114143453.htm