Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity Levels
Plants respond to biotic and abiotic pressures by changing their biophysical and biochemical aspects, such as reducing their biomass and developing chlorosis, which can be readily identified using remote-sensing techniques applied to the VIS/NIR/SWIR spectrum range. In the current scenario of agricu...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | AgriEngineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-7402/6/1/20 |
| _version_ | 1797242421597175808 |
|---|---|
| author | José Donizete de Queiroz Otone Gustavo de Faria Theodoro Dthenifer Cordeiro Santana Larissa Pereira Ribeiro Teodoro Job Teixeira de Oliveira Izabela Cristina de Oliveira Carlos Antonio da Silva Junior Paulo Eduardo Teodoro Fabio Henrique Rojo Baio |
| author_facet | José Donizete de Queiroz Otone Gustavo de Faria Theodoro Dthenifer Cordeiro Santana Larissa Pereira Ribeiro Teodoro Job Teixeira de Oliveira Izabela Cristina de Oliveira Carlos Antonio da Silva Junior Paulo Eduardo Teodoro Fabio Henrique Rojo Baio |
| author_sort | José Donizete de Queiroz Otone |
| collection | DOAJ |
| description | Plants respond to biotic and abiotic pressures by changing their biophysical and biochemical aspects, such as reducing their biomass and developing chlorosis, which can be readily identified using remote-sensing techniques applied to the VIS/NIR/SWIR spectrum range. In the current scenario of agriculture, production efficiency is fundamental for farmers, but diseases such as target spot continue to harm soybean yield. Remote sensing, especially hyperspectral sensing, can detect these diseases, but has disadvantages such as cost and complexity, thus favoring the use of UAVs in these activities, as they are more economical. The objectives of this study were: (i) to identify the most appropriate input variable (bands, vegetation indices and all reflectance ranges) for the metrics assessed in machine learning models; (ii) to verify whether there is a statistical difference in the response of NDVI (normalized difference vegetation index), grain weight and yield when subjected to different levels of severity; and (iii) to identify whether there is a relationship between the spectral bands and vegetation indices with the levels of target spot severity, grain weight and yield. The field experiment was carried out in the 2022/23 crop season and involved different fungicide treatments to obtain different levels of disease severity. A spectroradiometer and UAV (unmanned aerial vehicle) imagery were used to collect spectral data from the leaves. Data were subjected to machine learning analysis using different algorithms. LR (logistic regression) and SVM (support vector machine) algorithms performed better in classifying target spot severity levels when spectral data were used. Multivariate canonical analysis showed that healthy leaves stood out at specific wavelengths, while diseased leaves showed different spectral patterns. Disease detection using hyperspectral sensors enabled detailed information acquisition. Our findings reveal that remote sensing, especially using hyperspectral sensors and machine learning techniques, can be effective in the early detection and monitoring of target spot in the soybean crop, enabling fast decision-making for the control and prevention of yield losses. |
| first_indexed | 2024-04-24T18:38:57Z |
| format | Article |
| id | doaj.art-8f2cb2f1324e4a848d75f7bba06e94fc |
| institution | Directory Open Access Journal |
| issn | 2624-7402 |
| language | English |
| last_indexed | 2024-04-24T18:38:57Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AgriEngineering |
| spelling | doaj.art-8f2cb2f1324e4a848d75f7bba06e94fc2024-03-27T13:16:18ZengMDPI AGAgriEngineering2624-74022024-02-016133034310.3390/agriengineering6010020Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity LevelsJosé Donizete de Queiroz Otone0Gustavo de Faria Theodoro1Dthenifer Cordeiro Santana2Larissa Pereira Ribeiro Teodoro3Job Teixeira de Oliveira4Izabela Cristina de Oliveira5Carlos Antonio da Silva Junior6Paulo Eduardo Teodoro7Fabio Henrique Rojo Baio8Departament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilDepartament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilDepartament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilDepartament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilDepartament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilDepartament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilDepartment of Geography, State University of Mato Grosso (UNEMAT), Sinop 78550-000, MT, BrazilDepartament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilDepartament of Agronomy, Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul 79560-000, MS, BrazilPlants respond to biotic and abiotic pressures by changing their biophysical and biochemical aspects, such as reducing their biomass and developing chlorosis, which can be readily identified using remote-sensing techniques applied to the VIS/NIR/SWIR spectrum range. In the current scenario of agriculture, production efficiency is fundamental for farmers, but diseases such as target spot continue to harm soybean yield. Remote sensing, especially hyperspectral sensing, can detect these diseases, but has disadvantages such as cost and complexity, thus favoring the use of UAVs in these activities, as they are more economical. The objectives of this study were: (i) to identify the most appropriate input variable (bands, vegetation indices and all reflectance ranges) for the metrics assessed in machine learning models; (ii) to verify whether there is a statistical difference in the response of NDVI (normalized difference vegetation index), grain weight and yield when subjected to different levels of severity; and (iii) to identify whether there is a relationship between the spectral bands and vegetation indices with the levels of target spot severity, grain weight and yield. The field experiment was carried out in the 2022/23 crop season and involved different fungicide treatments to obtain different levels of disease severity. A spectroradiometer and UAV (unmanned aerial vehicle) imagery were used to collect spectral data from the leaves. Data were subjected to machine learning analysis using different algorithms. LR (logistic regression) and SVM (support vector machine) algorithms performed better in classifying target spot severity levels when spectral data were used. Multivariate canonical analysis showed that healthy leaves stood out at specific wavelengths, while diseased leaves showed different spectral patterns. Disease detection using hyperspectral sensors enabled detailed information acquisition. Our findings reveal that remote sensing, especially using hyperspectral sensors and machine learning techniques, can be effective in the early detection and monitoring of target spot in the soybean crop, enabling fast decision-making for the control and prevention of yield losses.https://www.mdpi.com/2624-7402/6/1/20disease monitoringclassification analysismachine learningprecision agricultureremote sensing |
| spellingShingle | José Donizete de Queiroz Otone Gustavo de Faria Theodoro Dthenifer Cordeiro Santana Larissa Pereira Ribeiro Teodoro Job Teixeira de Oliveira Izabela Cristina de Oliveira Carlos Antonio da Silva Junior Paulo Eduardo Teodoro Fabio Henrique Rojo Baio Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity Levels AgriEngineering disease monitoring classification analysis machine learning precision agriculture remote sensing |
| title | Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity Levels |
| title_full | Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity Levels |
| title_fullStr | Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity Levels |
| title_full_unstemmed | Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity Levels |
| title_short | Hyperspectral Response of the Soybean Crop as a Function of Target Spot (<i>Corynespora cassiicola</i>) Using Machine Learning to Classify Severity Levels |
| title_sort | hyperspectral response of the soybean crop as a function of target spot i corynespora cassiicola i using machine learning to classify severity levels |
| topic | disease monitoring classification analysis machine learning precision agriculture remote sensing |
| url | https://www.mdpi.com/2624-7402/6/1/20 |
| work_keys_str_mv | AT josedonizetedequeirozotone hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT gustavodefariatheodoro hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT dthenifercordeirosantana hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT larissapereiraribeiroteodoro hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT jobteixeiradeoliveira hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT izabelacristinadeoliveira hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT carlosantoniodasilvajunior hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT pauloeduardoteodoro hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels AT fabiohenriquerojobaio hyperspectralresponseofthesoybeancropasafunctionoftargetspoticorynesporacassiicolaiusingmachinelearningtoclassifyseveritylevels |