Consensus forecast technology for tropical cyclone tracks by integrating AI weather prediction models

WANG Xuan; QI Liangbo

doi:10.19513/j.cnki.hyqxxb.20250310002

Abstract：To improve the consensus forecast of tropical cyclone(TC)tracks over western North Pacific,this study constructs 6 consensus schemes by combining three artificial intelligence(AI)weather prediction models(Pangu,FuXi and FengWu)with numerical weather prediction(NWP)models(including deterministic and ensemble forecasts)using three consensus methods:simple multi-model average(AVG),selective ensemble average(SEAV)and selective ensemble change-weighted average(SECW).These schemes are evaluated for their 120-h TC track forecasts from 2023 to 2024.The results are as follows.(1)Individual AI models exhibit clear advantages over NWP in TC track forecast(most notably at longer lead times).Compared to the ECMWF ensemble mean,FengWu shows comprehensive superiority,while the other two AI models perform worse at 24 h and 48 h,but better at 72-120 h.Against pure NWP consensus forecasts,FengWu has slightly higher errors at 24-72 h,but significant advantages at 96 h and 120 h.(2)The integrated schemes combining AI and NWP leverage the strengths of both approaches,substantially outperforming the ECMWF-EPS ensemble mean.They generally surpass both individual AI models and pure NWP consensus forecasts,and exceed pure AI consensus forecasts within 72 h.At 96 h and 120 h,however,the pure AI consensus forecasts show the most significant advantages.(3)Compared to the operational consensus forecasts from the Shanghai Typhoon Institute,the three proposed integrated schemes—incorporating additional ensemble and AI model members—significantly reduce track errors and enhance forecast stability,with the AI+NWP_SECW scheme performing the best.This study demonstrates that AI models have promising application potential in TC track consensus forecast.