Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning Algorithms
Pine wilt disease (PWD) has caused huge economic and environmental losses since it invaded China. Although early monitoring is an effective way to control this hazard, the monitoring window for the early stage is hard to identify, and varies in different hosts and environments. We used UAV-based mul...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/2/444 |
| _version_ | 1797437460136853504 |
|---|---|
| author | Dewei Wu Linfeng Yu Run Yu Quan Zhou Jiaxing Li Xudong Zhang Lili Ren Youqing Luo |
| author_facet | Dewei Wu Linfeng Yu Run Yu Quan Zhou Jiaxing Li Xudong Zhang Lili Ren Youqing Luo |
| author_sort | Dewei Wu |
| collection | DOAJ |
| description | Pine wilt disease (PWD) has caused huge economic and environmental losses since it invaded China. Although early monitoring is an effective way to control this hazard, the monitoring window for the early stage is hard to identify, and varies in different hosts and environments. We used UAV-based multispectral images of <i>Pinus thunbergii</i> forest in East China to identify the change in the number of infected trees in each month of the growing season. We built classification models to detect different PWD infection stages by testing three machine learning algorithms—random forest, support vector machine, and linear discriminant analysis—and identified the best monitoring period for each infection stage (namely, green attack, early, middle, and late). From the obtained results, the early monitoring window period was determined to be in late July, whereas the monitoring window for middle and late PWD stages ranged from mid-August to early September. We also identified four important vegetation indices to monitor each infection stage. In conclusion, this study demonstrated the effectiveness of using machine learning algorithms to analyze multitemporal multispectral data to establish a window for early monitoring of pine wilt disease infestation. The results could provide a reference for future research and guidance for the control of pine wilt disease. |
| first_indexed | 2024-03-09T11:20:38Z |
| format | Article |
| id | doaj.art-d2e04e124f414898a2c20a13a67ad577 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:20:38Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d2e04e124f414898a2c20a13a67ad5772023-12-01T00:20:55ZengMDPI AGRemote Sensing2072-42922023-01-0115244410.3390/rs15020444Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning AlgorithmsDewei Wu0Linfeng Yu1Run Yu2Quan Zhou3Jiaxing Li4Xudong Zhang5Lili Ren6Youqing Luo7Beijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaPine wilt disease (PWD) has caused huge economic and environmental losses since it invaded China. Although early monitoring is an effective way to control this hazard, the monitoring window for the early stage is hard to identify, and varies in different hosts and environments. We used UAV-based multispectral images of <i>Pinus thunbergii</i> forest in East China to identify the change in the number of infected trees in each month of the growing season. We built classification models to detect different PWD infection stages by testing three machine learning algorithms—random forest, support vector machine, and linear discriminant analysis—and identified the best monitoring period for each infection stage (namely, green attack, early, middle, and late). From the obtained results, the early monitoring window period was determined to be in late July, whereas the monitoring window for middle and late PWD stages ranged from mid-August to early September. We also identified four important vegetation indices to monitor each infection stage. In conclusion, this study demonstrated the effectiveness of using machine learning algorithms to analyze multitemporal multispectral data to establish a window for early monitoring of pine wilt disease infestation. The results could provide a reference for future research and guidance for the control of pine wilt disease.https://www.mdpi.com/2072-4292/15/2/444<i>Pinus thunbergia</i><i>Bursaphelenchus xylophilus</i>green attackrandom forest |
| spellingShingle | Dewei Wu Linfeng Yu Run Yu Quan Zhou Jiaxing Li Xudong Zhang Lili Ren Youqing Luo Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning Algorithms Remote Sensing <i>Pinus thunbergia</i> <i>Bursaphelenchus xylophilus</i> green attack random forest |
| title | Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning Algorithms |
| title_full | Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning Algorithms |
| title_fullStr | Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning Algorithms |
| title_full_unstemmed | Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning Algorithms |
| title_short | Detection of the Monitoring Window for Pine Wilt Disease Using Multi-Temporal UAV-Based Multispectral Imagery and Machine Learning Algorithms |
| title_sort | detection of the monitoring window for pine wilt disease using multi temporal uav based multispectral imagery and machine learning algorithms |
| topic | <i>Pinus thunbergia</i> <i>Bursaphelenchus xylophilus</i> green attack random forest |
| url | https://www.mdpi.com/2072-4292/15/2/444 |
| work_keys_str_mv | AT deweiwu detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms AT linfengyu detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms AT runyu detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms AT quanzhou detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms AT jiaxingli detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms AT xudongzhang detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms AT liliren detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms AT youqingluo detectionofthemonitoringwindowforpinewiltdiseaseusingmultitemporaluavbasedmultispectralimageryandmachinelearningalgorithms |