China AI weather forecasting advances

Chinese-developed AI weather forecasting models, including Fengwu from Shanghai AI Laboratory, Huawei's Pangu, and Fudan University's Fuxi, are emerging as leading players in the global race to improve weather prediction. These AI systems, which learn patterns from historical weather data, can generate forecasts much faster than traditional numerical models while matching or surpassing them on some accuracy measures. During List of storms named Dolphin's approach to China, Fengwu, developed by Shanghai AI Laboratory and commercialized by Techwind, predicted the typhoon's landfall time and location within 30 minutes and 30 kilometers, five days in advance. However, AI models still lag in predicting storm intensity and are untested for major climate events. The technology is being increasingly tested during typhoon season in East Asia, where improved track forecasts help authorities prepare for flooding and evacuations. The rise of AI forecasting has created competition among tech companies, research institutes, and meteorological agencies, with China emerging as a leading player. Other notable systems include Alphabet Inc.'s GraphCast and GenCast, Nvidia-backed FourCastNet, and the European Centre for Medium-Range Weather Forecasts' AIFS. Experts expect AI and traditional methods to work together for the foreseeable future.