A new artificial intelligence system called GraphCast has demonstrated superior accuracy in medium-range global weather forecasting compared to the world’s leading traditional numerical weather prediction model. Developed by Google DeepMind, the AI model generates 10-day forecasts in under a minute on a single machine, a task that typically requires hours of computation on supercomputers using conventional physics-based methods. In a comprehensive evaluation against the European Centre for Medium-Range Weather Forecasts’ high-resolution forecast (HRES), GraphCast was more accurate in over 90% of 1,380 test variables, including critical predictions for extreme weather events like tropical cyclones and atmospheric rivers. The system was trained on decades of historical weather data, learning to model complex atmospheric physics. While not intended to replace existing systems, it represents a significant leap in speed and efficiency for weather prediction. The researchers have made the model open-source to aid the global meteorological community. Read the full article at: https://technologyreview.com/2024/11/14/ai-weather-model-graphcast-outperforms-traditional-systems/