Identifying Nematode Damage on Soybean through Remote Sensing and Machine Learning Techniques

被引:12
作者
Santos, Leticia Bernabe [1 ,2 ]
Bastos, Leonardo Mendes [2 ,3 ]
de Oliveira, Mailson Freire [1 ,4 ]
Martins Soares, Pedro Luiz [5 ]
Ciampitti, Ignacio Antonio [2 ]
da Silva, Rouverson Pereira [1 ]
机构
[1] Sao Paulo State Univ Julio de Mesquita Filho, UNESP, Sch Agr & Veterinarian Sci, Dept Engn & Math Sci, Via Acesso Prof Paulo Donato Castellane, BR-14884900 Jaboticabal, SP, Brazil
[2] Kansas State Univ, Dept Agron, 1712 Claflin Rd, Manhattan, KS 66506 USA
[3] Univ Georgia, Dept Crop & Soil Sci, Miller Plant Sci, Athens, GA 30602 USA
[4] Auburn Univ, Dept Crop Soil & Environm Sci, 350 S Coll St, Auburn, AL 36830 USA
[5] Sao Paulo State Univ Julio de Mesquita Filho, Sch Agr & Veterinarian Sci, UNESP, Dept Agr Prod Sci, Via Acesso Prof Paulo Donato Castellane, BR-14884900 Jaboticabal, SP, Brazil
来源
AGRONOMY-BASEL | 2022年 / 12卷 / 10期
关键词
digital agriculture; disease detection; machine learning; multispectral mapping; nematodes; remote sensing; CYST-NEMATODE; RED-EDGE; VEGETATION; STRESS; REFLECTANCE; INDEX; SOIL;
D O I
10.3390/agronomy12102404
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
Identifying nematode damage in large soybean areas is not always achievable in a practical way. Multispectral reflectance sensors have not been thoroughly evaluated to detect nematode damage in soybeans (Glycine max L.). The main research aims of this study were to: (i) determine the bivariate relationship between individual spectral bands and vegetation indices (VIs) relative to soybean conditions (symptomatic versus asymptomatic), and (ii) to select the best model for identifying plant conditions using three algorithms (logistic regression-LR, random forest-RF, conditional inference tree-CIT) and three options for data input using bands, vegetation indices (VIs), and bands plus VIs. The trial was conducted in Brazil on three on-farm soybean fields presenting different species of nematode infestation. Multispectral imagery was obtained using a drone-mounted MicaSense RedEdge (R) sensor. At each sampling, georeferenced point nematode infestation and spectral measurements of soybean plants were retrieved for the classification of symptomatic and asymptomatic areas, according to the threshold level adopted. Bivariate analysis of variance (ANOVA), LR, RF, and CIT were used to select the multispectral bands/VIs that discriminated among symptomatic and asymptomatic plants, assessing the best model via their respective parameters for accuracy, sensitivity, and specificity. The greatest classification accuracy (>0.70) was achieved when using the CIT algorithm with the spectral bands only, with green (560 +/- 20 nm) and near-infrared (840 +/- 40 nm) included as the main spectral input variables in the model. These results demonstrate the potential of combining remotely sensed data and machine learning to distinguish nematode-symptomatic and asymptomatic soybean plants.
引用
收藏
页数:14
相关论文
共 46 条
[1]   Evaluating the impact of red-edge band from Rapideye image for classifying insect defoliation levels [J].
Adelabu, Samuel ;
Mutanga, Onisimo ;
Adam, Elhadi .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 95 :34-41
[2]  
Allen TW, 2017, PLANT HLTH PROG, V18, P19, DOI 10.1094/PHP-RS-16-0066
[3]  
Askary TH, 2014, BIOCONTROL AGENTS OF PHYTONEMATODES, P1
[4]   Soybean Disease Monitoring with Leaf Reflectance [J].
Bajwa, Sreekala G. ;
Rupe, John C. ;
Mason, Johnny .
REMOTE SENSING, 2017, 9 (02)
[5]   POTENTIALS AND LIMITS OF VEGETATION INDEXES FOR LAI AND APAR ASSESSMENT [J].
BARET, F ;
GUYOT, G .
REMOTE SENSING OF ENVIRONMENT, 1991, 35 (2-3) :161-173
[6]  
Barnes E. M., 2000, Proceedings of the 5th International Conference on Precision Agriculture, Bloomington, Minnesota, USA, 16-19 July, 2000, P1
[7]   Detection of early plant stress responses in hyperspectral images [J].
Behmann, Jan ;
Steinruecken, Joerg ;
Pluemer, Lutz .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 93 :98-111
[8]   MACRONUTRIENT UPTAKE, TRANSLOCATION, AND TISSUE CONCENTRATION OF SOYBEANS INFESTED WITH THE SOYBEAN CYST-NEMATODE AND ELEMENTAL COMPOSITION OF CYSTS ISOLATED FROM ROOTS [J].
BLEVINS, DG ;
DROPKIN, VH ;
LUEDDERS, VD .
JOURNAL OF PLANT NUTRITION, 1995, 18 (03) :579-591
[9]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[10]  
Carneiro Rui G., 2002, Fitopatologia Brasileira, V27, P141, DOI 10.1590/S0100-41582002000200004