Abstract: In order to improve the predictive accuracy of the Orseolia oryzae emergency size and control area affected by Orseolia oryzae effectively, an improved Back-propagation Neural Network (BPNN) model named REMCC-BPNN was proposed. REMCC-BPNN optimizes the training model for BPNN based on the minimum correlation coefficient of the absolute value of the K nearest neighbor training samples’ fitting relative error and the K training samples’ time order. This study utilized air temperature and precipitation as influencing factors to forecast pest management independently. The results of two instances (Orseolia oryzae emergency size in Huazhou City and Yongning County of Guangxi Province) indicated that the prediction accuracy of REMCC-BPNN was 94% and 100% respectively, which was better than that of several traditional used models, such as SVR-CAR, MIV-BPNN. REMCC-BPNN has a promising application prospect in the forecast of pest management.