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 a 10-day forecast in under a minute on a single desktop computer, a task that typically requires hours of computation on supercomputers using traditional numerical weather prediction methods. Initial tests show the AI system matches or exceeds the accuracy of leading global forecasting models for predictions up to seven days ahead, particularly in tracking the intensity and path of extreme weather events like hurricanes. While promising, meteorologists emphasize that AI should complement rather than replace current systems, as traditional models still provide crucial detailed physics that AI may not fully capture. The integration of AI could lead to more frequent and accessible high-quality forecasts, especially for regions with limited computational resources. Read the full article at: https://technologyreview.com/2024/05/15/ai-weather-model-forecast-accuracy