A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior accuracy and speed compared to current state-of-the-art systems in a comprehensive global evaluation. The model, named GraphCast, uses machine learning to analyze decades of historical weather data, learning the underlying physics of atmospheric dynamics. In head-to-head tests against 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, including critical metrics like temperature, pressure, and wind speed at various altitudes. The AI system generates a 10-day forecast in under a minute on a single Google TPU v4 machine, a task that takes conventional numerical weather prediction models hours to compute on vast supercomputers. Researchers emphasize that the AI model is designed to complement, not replace, traditional physics-based methods, offering a powerful new tool for meteorologists. The findings were published in the peer-reviewed journal Science. Read the full article at: https://sciencedaily.com/releases/2023/11/231114155020.htm