A new artificial intelligence model developed by researchers has demonstrated superior accuracy in global weather forecasting compared to conventional numerical weather prediction systems. The AI model, trained on decades of historical weather data, can generate high-resolution, 10-day global forecasts in under a minute on a single desktop computer, a task that typically requires hours of computation on supercomputers using traditional physics-based models. While the AI system excels at predicting atmospheric pressure, temperature, and wind patterns, meteorologists note that it currently lacks the ability to forecast certain high-impact phenomena like precipitation extremes with the same reliability. The development signals a potential shift in weather prediction methodology, though operational integration would require rigorous testing and validation. Read the full article at: https://technologyreview.com/2024/05/15/ai-weather-model-outperforms-traditional-systems