A new artificial intelligence weather forecasting model developed by researchers has demonstrated superior accuracy compared to conventional physics-based systems in global medium-range weather predictions. The AI model, trained on decades of historical weather data, can generate 10-day forecasts in minutes on standard computing hardware, a task that typically requires hours on supercomputers using traditional numerical weather prediction methods. Initial evaluations show the AI system matches or exceeds the accuracy of leading global forecasting models for key atmospheric variables like temperature and humidity at various altitudes. While promising, researchers note the AI model currently focuses on atmospheric conditions and does not fully replace comprehensive systems that also model oceans, sea ice, and land surfaces. The development represents a significant step toward faster, more efficient weather prediction that could improve early warnings for extreme weather events. Read the full article at https://technologyreview.com/ai-weather-model-outperforms-traditional-forecasts