Powdery mildew is a disease that threatens wheat production and causes severe economic losses world-wide.Its timely diagnosis is imperative for preventing and controlling its spread.In this study,the multi-angle canopy spectra and disease severity of wheat were investigated at several developmental stages and degrees of disease severity.Four wavelength variable-selected algorithms:successive projection(SPA),competitive adaptive reweighted sampling(CARS),feature selection learning(Relief-F),and genetic algorithm(GA),were used to identify bands sensitive to powdery mildew.The wavelength vari-ables selected were used as input variables for partial least squares(PLS),extreme learning machine(ELM),random forest(RF),and support vector machine(SVM)algorithms,to construct a suitable predic-tion model for powdery mildew.Spectral reflectance and conventional vegetation indices(VIs)displayed angle effects under several disease severity indices(DIs).The CARS method selected relatively few wave-length variables and showed a relatively homogeneous distribution across the 13 viewing zenith angles.Overall accuracies of the four modeling algorithms were ranked as follows:ELM(0.70-0.82)＞PLS(0.63-0.79)＞SVM(0.49-0.69)＞RF(0.43-0.69).Combinations of features and algorithms generated varied accuracies,with coefficients of determination(R2)single-peaked at different observation angles.The con-structed CARS-ELM model extracted a predictable bivariate relationship between the multi-angle canopy spectrum and disease severity,yielding an R2＞0.8 at each measured angle.Especially for larger angles,monitoring accuracies were increased relative to the optimal VI model(40％at-60°,33％at+60°),indi-cating that the CARS-ELM model is suitable for extreme angles of-60° and+60°.The results are proposed to provide a technical basis for rapid and large-scale monitoring of wheat powdery mildew.

Li Song;Luyuan Wang;Zheqing Yang;Li He;Ziheng Feng;Jianzhao Duan;Wei Feng;Tiancai Guo

State Key Laboratory of Wheat and Maize Crop Science,Agronomy College,Henan Agriculture University,Zhengzhou 450046,Henan,China;CIMMYT-China Wheat and Maize Joint Research Center,State Key Laboratory of Wheat and Maize Crop Science,Henan Agricultural University,Zhengzhou 450046,Henan,China;Information and Management Science College,Henan Agricultural University,Zhengzhou 450046,Henan,China

作物学报（英文版）

[1]Li Song;Luyuan Wang;Zheqing Yang;Li He;Ziheng Feng;Jianzhao Duan;Wei Feng;Tiancai Guo-.Comparison of algorithms for monitoring wheat powdery mildew using multi-angular remote sensing data)[J].作物学报（英文版）,2022(05):1312-1322

DIs,at+60,and+60

Comparison,algorithms,monitoring,wheat,powdery,mildew,using,multi,angular,remote,sensing,data,Powdery,disease,that,threatens,production,causes,severe,economic,losses,world,wide,Its,timely,diagnosis,imperative,preventing,controlling,its,spread,In,this,study,canopy,spectra,severity,were,investigated,several,developmental,stages,degrees,Four,wavelength,selected,successive,projection,SPA,competitive,adaptive,reweighted,sampling,CARS,selection,learning,Relief,genetic,GA,used,identify,bands,sensitive,input,variables,partial,least,squares,PLS,extreme,machine,ELM,random,forest,RF,support,vector,construct,suitable,Spectral,reflectance,conventional,vegetation,indices,VIs,displayed,effects,under,method,relatively,few,showed,homogeneous,distribution,across,viewing,zenith,angles,Overall,accuracies,four,modeling,ranked,follows,Combinations,features,generated,varied,coefficients,determination,single,peaked,different,observation,structed,extracted,predictable,bivariate,relationship,between,spectrum,yielding,each,measured,Especially,larger,increased,optimal,cating,results,proposed,provide,technical,basis,rapid,scale

0.550485