Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVM
In order to address the challenge of early detection of cotton verticillium wilt disease, naturally infected cotton plants in the field, which were divided into five categories based on the degree of disease severity, have been investigated in this study. Canopies of infected cotton plants were anal...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/13/3373 |
| _version_ | 1827734538506207232 |
|---|---|
| author | Nannan Zhang Xiao Zhang Peng Shang Rui Ma Xintao Yuan Li Li Tiecheng Bai |
| author_facet | Nannan Zhang Xiao Zhang Peng Shang Rui Ma Xintao Yuan Li Li Tiecheng Bai |
| author_sort | Nannan Zhang |
| collection | DOAJ |
| description | In order to address the challenge of early detection of cotton verticillium wilt disease, naturally infected cotton plants in the field, which were divided into five categories based on the degree of disease severity, have been investigated in this study. Canopies of infected cotton plants were analyzed with spectral data measured, and various preprocessing techniques, including multiplicative scatter correction (MSC) and MSC-continuous wavelet analysis algorithms, were used to predict the disease severity. With a combination of support vector machine (SVM) models with such optimization algorithms as genetic algorithm (GA), grid search (GS), particle swarm optimization (PSO), and grey wolf optimizer (GWO), a grading model of cotton verticillium wilt disease was established in this study. The study results show that the MSC-PSO-SVM model outperforms the other three models in terms of classification accuracy, and the accuracy, macro precision, macro recall, and macro F1-score of this model are 80%, 81.26%, 80%, and 79.57%, respectively. Among those eight models constructed on the basis of continuous wavelet analyses using mexh and db3, the MSC-db3(2<sup>3</sup>)-PSO-SVM and MSC-db3(2<sup>3</sup>)-GWO-SVM models perform best, with the latter having a shorter running time. An overall evaluation shows that the MSC-db3(2<sup>3</sup>)-GWO-SVM model is an optimal model, with values of its accuracy, macro precision, macro recall, and macro F1-score indicators being 91.2%, 92.02%, 91.2%, and 91.16%, respectively. Moreover, under this model, the prediction accuracy on disease levels 1 and 5 has achieved the highest rate of 100%, with a prediction accuracy rate of 88% on disease level 2 and the lowest prediction accuracy rate of 84% on both disease levels 3 and 4. These results demonstrate that it is effective to use spectral technology in classifying the cotton verticillium wilt disease and satisfying the needs of field detection and grading. This study provides a new approach for the detection and grading of cotton verticillium wilt disease and offered a theoretical basis for early prevention, precise drug application, and instrument development for the disease. |
| first_indexed | 2024-03-11T01:30:01Z |
| format | Article |
| id | doaj.art-15aa8f7f0a22449fa4f2e6289e883518 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T01:30:01Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-15aa8f7f0a22449fa4f2e6289e8835182023-11-18T17:25:19ZengMDPI AGRemote Sensing2072-42922023-07-011513337310.3390/rs15133373Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVMNannan Zhang0Xiao Zhang1Peng Shang2Rui Ma3Xintao Yuan4Li Li5Tiecheng Bai6Key Laboratory of Smart Agriculture System Integration, Ministry of Education, China Agricultural University, Beijing 100083, ChinaKey Laboratory of Tarim Oasis Agriculture (Tarim University), Ministry of Education, Alar 843300, ChinaKey Laboratory of Tarim Oasis Agriculture (Tarim University), Ministry of Education, Alar 843300, ChinaKey Laboratory of Tarim Oasis Agriculture (Tarim University), Ministry of Education, Alar 843300, ChinaKey Laboratory of Tarim Oasis Agriculture (Tarim University), Ministry of Education, Alar 843300, ChinaKey Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs, China Agricultural University, Beijing 100083, ChinaKey Laboratory of Tarim Oasis Agriculture (Tarim University), Ministry of Education, Alar 843300, ChinaIn order to address the challenge of early detection of cotton verticillium wilt disease, naturally infected cotton plants in the field, which were divided into five categories based on the degree of disease severity, have been investigated in this study. Canopies of infected cotton plants were analyzed with spectral data measured, and various preprocessing techniques, including multiplicative scatter correction (MSC) and MSC-continuous wavelet analysis algorithms, were used to predict the disease severity. With a combination of support vector machine (SVM) models with such optimization algorithms as genetic algorithm (GA), grid search (GS), particle swarm optimization (PSO), and grey wolf optimizer (GWO), a grading model of cotton verticillium wilt disease was established in this study. The study results show that the MSC-PSO-SVM model outperforms the other three models in terms of classification accuracy, and the accuracy, macro precision, macro recall, and macro F1-score of this model are 80%, 81.26%, 80%, and 79.57%, respectively. Among those eight models constructed on the basis of continuous wavelet analyses using mexh and db3, the MSC-db3(2<sup>3</sup>)-PSO-SVM and MSC-db3(2<sup>3</sup>)-GWO-SVM models perform best, with the latter having a shorter running time. An overall evaluation shows that the MSC-db3(2<sup>3</sup>)-GWO-SVM model is an optimal model, with values of its accuracy, macro precision, macro recall, and macro F1-score indicators being 91.2%, 92.02%, 91.2%, and 91.16%, respectively. Moreover, under this model, the prediction accuracy on disease levels 1 and 5 has achieved the highest rate of 100%, with a prediction accuracy rate of 88% on disease level 2 and the lowest prediction accuracy rate of 84% on both disease levels 3 and 4. These results demonstrate that it is effective to use spectral technology in classifying the cotton verticillium wilt disease and satisfying the needs of field detection and grading. This study provides a new approach for the detection and grading of cotton verticillium wilt disease and offered a theoretical basis for early prevention, precise drug application, and instrument development for the disease.https://www.mdpi.com/2072-4292/15/13/3373cotton verticillium wiltcanopy spectrumSVMcontinuous wavelet transformdisease severity |
| spellingShingle | Nannan Zhang Xiao Zhang Peng Shang Rui Ma Xintao Yuan Li Li Tiecheng Bai Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVM Remote Sensing cotton verticillium wilt canopy spectrum SVM continuous wavelet transform disease severity |
| title | Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVM |
| title_full | Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVM |
| title_fullStr | Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVM |
| title_full_unstemmed | Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVM |
| title_short | Detection of Cotton Verticillium Wilt Disease Severity Based on Hyperspectrum and GWO-SVM |
| title_sort | detection of cotton verticillium wilt disease severity based on hyperspectrum and gwo svm |
| topic | cotton verticillium wilt canopy spectrum SVM continuous wavelet transform disease severity |
| url | https://www.mdpi.com/2072-4292/15/13/3373 |
| work_keys_str_mv | AT nannanzhang detectionofcottonverticilliumwiltdiseaseseveritybasedonhyperspectrumandgwosvm AT xiaozhang detectionofcottonverticilliumwiltdiseaseseveritybasedonhyperspectrumandgwosvm AT pengshang detectionofcottonverticilliumwiltdiseaseseveritybasedonhyperspectrumandgwosvm AT ruima detectionofcottonverticilliumwiltdiseaseseveritybasedonhyperspectrumandgwosvm AT xintaoyuan detectionofcottonverticilliumwiltdiseaseseveritybasedonhyperspectrumandgwosvm AT lili detectionofcottonverticilliumwiltdiseaseseveritybasedonhyperspectrumandgwosvm AT tiechengbai detectionofcottonverticilliumwiltdiseaseseveritybasedonhyperspectrumandgwosvm |