Recent advancements in artificial intelligence are transforming weather prediction, with new AI models demonstrating the potential to surpass traditional physics-based forecasting systems in both speed and accuracy. These machine learning systems, trained on decades of historical weather data, can generate high-resolution forecasts in minutes rather than hours. Early results from models like Google’s GraphCast and Huawei’s Pangu-Weather show they can match or exceed the skill of established numerical weather prediction models for global forecasts up to 10 days ahead. While promising, experts note that AI models currently rely on traditional systems for initial data and may struggle with predicting extreme, rare events due to their training on past patterns. Further testing and integration with conventional methods are needed to fully assess their operational reliability. Read the full article at https://technologyreview.com/2024/05/15/ai-weather-forecasting-models.