Development of Two Early Forecasting Models for Predicting Incidence of Rice Panicle Blast in China.

Abstract

To develop models for rice panicle blast, the relationship between the seasonal maximum incidence of rice panicle blast (PBx) with the PBx in the preceding crop, weather conditions, altitude, and acreage of susceptible variety in class (SVC) was analyzed. Results revealed that PBx in the preceding crop, SVC, altitude, weather conditions in the period of 120 to 180 days before the PBx date (dbPBx), and in the period of 30 to 90 dbPBx were significantly correlated to PBx. Subsequently, a logistic model and a two-step hurdle model were developed to predict rice panicle blast. The logistic model was developed to predict whether PBx was 0 or not based on the preceding PBx, altitude, acreage of susceptible varieties, the longest stretch of days with soil temperatures between 16°C and 24°C 120 to 150 dbPBx, and the longest stretch of rainy days 120 to 180 dbPBx. The hurdle model predicted if PBx was greater than 0 at the first step, and if the prediction was greater than 0, then predicted PBx based on the preceding PBx, SVC, altitude, and weather data 180 to 30 dbPBx. Validation with the test datasets showed that the logistic model could correctly predict whether PBx was 0 at a mean test accuracy of 78.39%, and the absolute prediction error of the hurdle model was smaller than 6.16% for 90% of the records. The model developed in this study will be helpful in management decision making for rice growers and policy makers.