A regional artificial intelligence model for skillful typhoon prediction

Abstract

Accurate prediction of tropical cyclones remains a major challenge for both numerical weather prediction and emerging artificial intelligence weather prediction (AIWP) systems. While recent global AI models have demonstrated strong skill in predicting large-scale circulation and tropical cyclone tracks, they often struggle to represent the mesoscale structures critical for tropical cyclone intensity and extreme precipitation. Here we develop the Hybrid Intelligent Typhoon System (HITS), a regional AI forecasting framework for 0–120 h typhoon prediction over the Asia–Pacific region, trained on a newly constructed 9 km high-resolution typhoon reanalysis dataset. The model combines regional autoregressive prediction with large-scale constraints from the state-of-the-art ECMWF Artificial Intelligence Forecasting System (AIFS), allowing it to remain consistent with the evolving large-scale circulation while resolving mesoscale structures. HITS is further extended with a structure-aware perceptual training strategy based on Learned Perceptual Image Patch Similarity (LPIPS), referred to as HITS-LPIPS, which improves the representation of convective and typhoon rainband structures. Experiments show that the hybrid framework substantially improves precipitation structure and typhoon intensity forecasts compared with both purely autoregressive regional AI models and standalone AI downscaling approaches. In particular, HITS-LPIPS reduces intensity errors by up to 48.3% relative to AIFS at a 120 h lead time and produces a near-unbiased wind–pressure relationship for simulated typhoons. These results demonstrate that regional AI systems combining large-scale circulation constraints with high-resolution initial conditions provide a promising pathway for improving natural hazard prediction for typhoons.