Recent advancements in artificial intelligence are transforming weather prediction, with new AI models demonstrating the potential to outperform traditional physics-based forecasting systems. These machine learning models, trained on decades of historical weather data, can generate highly accurate forecasts in seconds, a process that typically takes hours for conventional supercomputers. Key players like Google’s DeepMind (GraphCast) and Huawei (Pangu-Weather) have developed models that match or exceed the accuracy of the European Centre for Medium-Range Weather Forecasts (ECMWF) system for global predictions up to 10 days ahead. The primary advantages of AI forecasting include drastic reductions in computational cost and energy consumption, enabling more frequent updates and accessibility for regions with limited resources. However, experts caution that these models, which learn patterns from past data, may struggle with predicting unprecedented extreme weather events driven by climate change. The future likely involves a hybrid approach, where AI handles routine forecasts and traditional models simulate high-impact, novel scenarios. For the full analysis, read the article at https://technologyreview.com/2024/01/15/1086515/ai-weather-forecasting-models-climate/.