China's AI System Boosts Hurricane Track Forecast Accuracy

Chinese researchers have created an artificial‑intelligence‑based forecasting system that markedly improves the precision of hurricane track predictions. Led by Duan Van To, a researcher at the Institute of Atmospheric Physics of the Chinese Academy of Sciences, and Ly Hao of Fudan University, the system integrates the AI‑driven weather model FuXi with a method that generates realistic initial scenario ensembles for combined forecasts. Tests on 62 tropical cyclones, involving 91 comparative analyses, showed the new system outperformed leading global ensemble forecasting models and could also predict storm speed and direction. The developers say the approach can be extended to other hazardous weather phenomena, offering a more reliable tool for early warning and disaster mitigation.