Abstract:Ensemble weight methods based on the Threat Score (TS), the Brier Score (BS) and the Arithmetic Average (AA) were employed to combine the precipitation prediction of four ensemble numerical prediction systems (CMA, ECMWF, NCEP and JMA) from the TIGGE over the southeast of China and its five sub regions. The results of comparison analysis of the four ensemble numerical prediction systems indicated that the super ensemble based on TS weight always provides more skillful performance in any of the four ensemble numerical prediction systems regionally and shows the best prediction performance of rainfall impacted by typhoon landing or not. The grand ensemble based on BS weight and AA weight also shows the better skillful performance. Moreover, verification of super ensemble method in five sub regions showed that the super ensemble precipitation based on TS weight always has a less mean absolute error (MAE) and higher TS score in most sub regions than that based on BS weight and AA weight. The super ensemble precipitation based on TS weight provides the best performance in the southeast of Guangdong and northern Zhejiang and the secondary performance along the coast of Zhejiang and Fujian and the northwest of Guangdong. The skillful performance based on BS weight and AA weight is provided only in the southeast of Guangdong.