基于全子集回归和BP神经网络的信阳稻瘟病预测模型构建

打开文本图片集

关键词：稻瘟病；发生面积；全子集回归；BP神经网络算法；预测模型；构建；信阳市

中图分类号： S435.111.4+1 ;S431.1 文献标识码：A

文章编号：0439-8114（2025）12-0104-06

DOI：10.14088/j.cnki.issn0439-8114.2025.12.018 开放科学（资源服务）标识码（OSID）：回

Construction of a prediction model for Xinyang rice blast based on all subsets regression and BP neural network

HU Xue-min 1 ，ZHU Zhi-gang²，JIANG Zhao-qin²，JI Xin1，CHENLi-jun ！1 ，SHI Hong-zhongl

College of Agronomy，Xinyang Agricultureand Forestry University，Xinyang 4640oo，Henan，China; 2.Xinyang Agricultural Technology Service Center，Xinyang 464ooo，Henan，China）

Abstract：UsingmeteorologicaldatafromtheXinyangCitybetween2O04and2O21（excluding2020），includingairtemperature，relativehumidity，precipitation，andsunsineduration，fivekefactorsinfluencingriceblastepidemicsereidentiedtroughcoelationanalysis.Thesefactorswere：TheminimumrelativehumidityinlateJune，theminimumrelativehumidityinearlyMaytheminimumtemperatureinearly May，thesunshine duration inmid-June，andthecumulativerainfallinearlyAugust.Bothall-subsetregresionandBPneuralnetworkalgorithms wereemployedtopredicttheincidenceareaofriceblastintheXinyang City.Theresults showed that all-subset regresson model 1 and model 2 achieved back-testing accuracies of 92.49% and 94.43% ，respectively，for the 2004-2021 rice blast incidence area，andboth yieldeda prediction accuracyof 79.68% for the years 2022 and 2O23.Incomparison， BP neural network models 1 and model 2 achieved back-testing accuracies of 82.72% and 83.55% ，respectively，for the 2004——2021 period，and prediction accuracies of 98.06 % and 95.49% for 2022 and 2O23.Based on these results，BP neural network model 1 was identifiedastheoptialpredictionmodel.Usingthismodel，thepredictedincidenceareaoficeblastinXinyangCityfor24was 26 500 hectares（ hm2 ）

KeyWords：riceblast；incidencearea；allsubsetregresion；BPneuralnetworkalgorithm；predictionmodel；construction；Xinyang City

水稻作为全球重要的粮食作物，其高产和稳产直接关系国民经济的稳定和发展。（剩余8703字）