Remote sensing monitoring of wheat leaf rust based on <scp>UAV</scp> multispectral imagery and the <scp>BPNN</scp> method

Wheat (Triticum aestivum L.) leaf rust is the most common and widely distributed wheat disease. Non-destructive real-time methods for monitoring can help prevent control plant diseases in agricultural production. In this study, we obtained multispectral imagery of canopy acquired by an unmanned aerial vehicle, selected vegetation index using K-means algorithm (KA) genetic (GA), established a model based on backpropagation neural network (BPNN) method. The results showed that R2 RMSE KA-BPNN were 0.902% 5.45% modeling set, respectively, 0.784% 4.76% validation respectively; GA-BPNN was 0.922% 4.88% 0.780% 4.28% respectively. prediction after optimizing variables KA GA had higher accuracy than BPNN model, implying variable dimensionality reduction complex machine learning algorithms to construct estimation models improve significantly. These accurately monitored winter wheat, providing theoretical basis technical support assessing screening disease-resistant varieties.