A new artificial intelligence weather forecasting model developed by researchers at a leading technology institute has demonstrated superior accuracy compared to conventional physics-based models in global medium-range weather predictions. The AI system, trained on decades of historical atmospheric data, can generate a 10-day forecast in under a minute on a single high-performance computer server, a task that typically requires hours of computation on supercomputers using traditional numerical weather prediction methods. Initial tests over a three-month period showed the AI model outperformed the world’s leading operational system, the European Centre for Medium-Range Weather Forecasts (ECMWF), on over 90% of key weather variables. While promising, meteorologists caution that AI models must still prove their reliability in predicting extreme weather events and require integration with established physical models for operational use. Read the full article at: https://technologyreview.com/ai-weather-model-forecast