Early detection of pine wilt disease tree candidates using time-series of spectral signatures
Pine wilt disease (PWD), caused by pine wood nematode (PWN), poses a tremendous threat to global pine forests because it can result in rapid and widespread infestations within months, leading to large-scale tree mortality. Therefore, the implementation of preventive measures relies on early detectio...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.1000093/full |
| _version_ | 1828324611725459456 |
|---|---|
| author | Run Yu Langning Huo Huaguo Huang Yuan Yuan Bingtao Gao Yujie Liu Linfeng Yu Haonan Li Liyuan Yang Lili Ren Lili Ren Youqing Luo Youqing Luo |
| author_facet | Run Yu Langning Huo Huaguo Huang Yuan Yuan Bingtao Gao Yujie Liu Linfeng Yu Haonan Li Liyuan Yang Lili Ren Lili Ren Youqing Luo Youqing Luo |
| author_sort | Run Yu |
| collection | DOAJ |
| description | Pine wilt disease (PWD), caused by pine wood nematode (PWN), poses a tremendous threat to global pine forests because it can result in rapid and widespread infestations within months, leading to large-scale tree mortality. Therefore, the implementation of preventive measures relies on early detection of PWD. Unmanned aerial vehicle (UAV)-based hyperspectral images (HSI) can detect tree-level changes and are thus an effective tool for forest change detection. However, previous studies mainly used single-date UAV-based HSI data, which could not monitor the temporal changes of disease distribution and determine the optimal detection period. To achieve these purposes, multi-temporal data is required. In this study, Pinus koraiensis stands were surveyed in the field from May to October during an outbreak of PWD. Concurrently, multi-temporal UAV-based red, green, and blue bands (RGB) and HSI data were also obtained. During the survey, 59 trees were confirmed to be infested with PWD, and 59 non-infested trees were used as control. Spectral features of each tree crown, such as spectral reflectance, first and second-order spectral derivatives, and vegetation indices (VIs), were analyzed to identify those useful for early monitoring of PWD. The Random Forest (RF) classification algorithm was used to examine the separability between the two groups of trees (control and infested trees). The results showed that: (1) the responses of the tree crown spectral features to PWD infestation could be detected before symptoms were noticeable in RGB data and field surveys; (2) the spectral derivatives were the most discriminable variables, followed by spectral reflectance and VIs; (3) based on the HSI data from July to October, the two groups of trees were successfully separated using the RF classifier, with an overall classification accuracy of 0.75–0.95. Our results illustrate the potential of UAV-based HSI for PWD early monitoring. |
| first_indexed | 2024-04-13T19:08:08Z |
| format | Article |
| id | doaj.art-7f65b492e9264d9aa3aca43b8ece9595 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-13T19:08:08Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-7f65b492e9264d9aa3aca43b8ece95952022-12-22T02:33:55ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-10-011310.3389/fpls.2022.10000931000093Early detection of pine wilt disease tree candidates using time-series of spectral signaturesRun Yu0Langning Huo1Huaguo Huang2Yuan Yuan3Bingtao Gao4Yujie Liu5Linfeng Yu6Haonan Li7Liyuan Yang8Lili Ren9Lili Ren10Youqing Luo11Youqing Luo12Beijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaDepartment of Forest Resource Management, Swedish University of Agriculture Sciences, Umeå, SwedenResearch Center of Forest Management Engineering of State Forestry and Grassland Administration, Beijing Forestry University, Beijing, ChinaFrench National Research Institute for Agriculture, Food and Environment (INRAE)—Zoologie Forestiere Centre de recherche d’Orléans, Orléans, FranceBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaSino-French Joint Laboratory for Invasive Forest Pests in Eurasia, Beijing Forestry University—French National Research Institute for Agriculture, Food and Environment (INRAE), Beijing, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing, ChinaSino-French Joint Laboratory for Invasive Forest Pests in Eurasia, Beijing Forestry University—French National Research Institute for Agriculture, Food and Environment (INRAE), Beijing, ChinaPine wilt disease (PWD), caused by pine wood nematode (PWN), poses a tremendous threat to global pine forests because it can result in rapid and widespread infestations within months, leading to large-scale tree mortality. Therefore, the implementation of preventive measures relies on early detection of PWD. Unmanned aerial vehicle (UAV)-based hyperspectral images (HSI) can detect tree-level changes and are thus an effective tool for forest change detection. However, previous studies mainly used single-date UAV-based HSI data, which could not monitor the temporal changes of disease distribution and determine the optimal detection period. To achieve these purposes, multi-temporal data is required. In this study, Pinus koraiensis stands were surveyed in the field from May to October during an outbreak of PWD. Concurrently, multi-temporal UAV-based red, green, and blue bands (RGB) and HSI data were also obtained. During the survey, 59 trees were confirmed to be infested with PWD, and 59 non-infested trees were used as control. Spectral features of each tree crown, such as spectral reflectance, first and second-order spectral derivatives, and vegetation indices (VIs), were analyzed to identify those useful for early monitoring of PWD. The Random Forest (RF) classification algorithm was used to examine the separability between the two groups of trees (control and infested trees). The results showed that: (1) the responses of the tree crown spectral features to PWD infestation could be detected before symptoms were noticeable in RGB data and field surveys; (2) the spectral derivatives were the most discriminable variables, followed by spectral reflectance and VIs; (3) based on the HSI data from July to October, the two groups of trees were successfully separated using the RF classifier, with an overall classification accuracy of 0.75–0.95. Our results illustrate the potential of UAV-based HSI for PWD early monitoring.https://www.frontiersin.org/articles/10.3389/fpls.2022.1000093/fullpine wilt diseaseunmanned aerial vehiclehyperspectral imagesmulti-temporal dataremote sensingearly detection |
| spellingShingle | Run Yu Langning Huo Huaguo Huang Yuan Yuan Bingtao Gao Yujie Liu Linfeng Yu Haonan Li Liyuan Yang Lili Ren Lili Ren Youqing Luo Youqing Luo Early detection of pine wilt disease tree candidates using time-series of spectral signatures Frontiers in Plant Science pine wilt disease unmanned aerial vehicle hyperspectral images multi-temporal data remote sensing early detection |
| title | Early detection of pine wilt disease tree candidates using time-series of spectral signatures |
| title_full | Early detection of pine wilt disease tree candidates using time-series of spectral signatures |
| title_fullStr | Early detection of pine wilt disease tree candidates using time-series of spectral signatures |
| title_full_unstemmed | Early detection of pine wilt disease tree candidates using time-series of spectral signatures |
| title_short | Early detection of pine wilt disease tree candidates using time-series of spectral signatures |
| title_sort | early detection of pine wilt disease tree candidates using time series of spectral signatures |
| topic | pine wilt disease unmanned aerial vehicle hyperspectral images multi-temporal data remote sensing early detection |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.1000093/full |
| work_keys_str_mv | AT runyu earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT langninghuo earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT huaguohuang earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT yuanyuan earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT bingtaogao earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT yujieliu earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT linfengyu earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT haonanli earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT liyuanyang earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT liliren earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT liliren earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT youqingluo earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures AT youqingluo earlydetectionofpinewiltdiseasetreecandidatesusingtimeseriesofspectralsignatures |