A new artificial intelligence weather forecasting model developed by researchers has demonstrated superior performance compared to conventional physics-based systems in global weather prediction. The AI model, trained on decades of historical weather data, can generate accurate 10-day forecasts in minutes on a single computer, while traditional supercomputer-based models take hours. Initial tests show the AI system matches or exceeds the accuracy of leading global forecasting models, particularly in predicting extreme weather events like hurricanes and heatwaves. The technology represents a significant shift toward data-driven climate modeling, though researchers note it should complement rather than replace existing physics-based approaches. Read the full article at https://technologyreview.com/ai-weather-model-outperforms-traditional-systems.