Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing
Abstract Large‐scale dieback of ash trees (Fraxinus spp.) caused by the fungus Hymenoscyphus fraxineus is posing an immense threat to forest health in Europe, requiring effective monitoring at large scales. In this study, a pipeline was created to find ash trees and classify dieback severity using h...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-06-01
|
| Series: | Remote Sensing in Ecology and Conservation |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/rse2.190 |
| _version_ | 1818436614718750720 |
|---|---|
| author | Aland H. Y. Chan Chloe Barnes Tom Swinfield David A. Coomes |
| author_facet | Aland H. Y. Chan Chloe Barnes Tom Swinfield David A. Coomes |
| author_sort | Aland H. Y. Chan |
| collection | DOAJ |
| description | Abstract Large‐scale dieback of ash trees (Fraxinus spp.) caused by the fungus Hymenoscyphus fraxineus is posing an immense threat to forest health in Europe, requiring effective monitoring at large scales. In this study, a pipeline was created to find ash trees and classify dieback severity using high‐resolution hyperspectral imagery of individual tree crowns (ITCs). Hyperspectral data were collected in four forest sites near Cambridge, UK, where 422 ITCs were manually delineated and labelled using field‐measurements of species and dieback severity (for ash trees). Four algorithms, namely linear discriminant analysis (LDA), principal components analysis coupled with LDA (PCA‐LDA), partial least squares discriminant analysis (PLS‐DA) and random forest (RF), were used to build classification models for species and dieback severity classification. The effect of dark‐pixel filtering on classification accuracy was evaluated. The best performing models were then coupled with automatic ITC segmentation to map species and ash dieback distribution over 16.8 hectares of woodland. We calculated and partitioned the coefficient of variation (CV) of the reflected ash spectra to find variable wavebands associated with dieback. PLS‐DA and LDA were most accurate for classifying ITC species identifies (overall accuracy >90%), whereas RF was most accurate for classifying ash dieback severity (overall accuracy 77%). Dark pixel filtering further increased the accuracy of species classification (+6%), but not disease classification. The reflectances of narrow blue (415 nm), red‐edge (680 nm) and NIR (760 nm) bands had high CV across disease classes and should be included if multispectral imagery were to be used to monitor ash dieback. The study demonstrates the possibility of using remote sensing to forward epidemiological research by monitoring forest pathogens in landscape scales, which would allow temperate forest managers to control pathogen outbreaks, assess associated impacts and restore affected forests much more effectively. |
| first_indexed | 2024-12-14T17:11:35Z |
| format | Article |
| id | doaj.art-1d1dd7fb3b66427aba16b37a7451947c |
| institution | Directory Open Access Journal |
| issn | 2056-3485 |
| language | English |
| last_indexed | 2024-12-14T17:11:35Z |
| publishDate | 2021-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Remote Sensing in Ecology and Conservation |
| spelling | doaj.art-1d1dd7fb3b66427aba16b37a7451947c2022-12-21T22:53:34ZengWileyRemote Sensing in Ecology and Conservation2056-34852021-06-017230632010.1002/rse2.190Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensingAland H. Y. Chan0Chloe Barnes1Tom Swinfield2David A. Coomes3Forest Ecology and Conservation Group Department of Plant Sciences University of Cambridge Downing Street CambridgeCB2 3EAUK2Excel geoHall Farm 2Sywell Aerodrome SywellNN6 0BNUKForest Ecology and Conservation Group Department of Plant Sciences University of Cambridge Downing Street CambridgeCB2 3EAUKForest Ecology and Conservation Group Department of Plant Sciences University of Cambridge Downing Street CambridgeCB2 3EAUKAbstract Large‐scale dieback of ash trees (Fraxinus spp.) caused by the fungus Hymenoscyphus fraxineus is posing an immense threat to forest health in Europe, requiring effective monitoring at large scales. In this study, a pipeline was created to find ash trees and classify dieback severity using high‐resolution hyperspectral imagery of individual tree crowns (ITCs). Hyperspectral data were collected in four forest sites near Cambridge, UK, where 422 ITCs were manually delineated and labelled using field‐measurements of species and dieback severity (for ash trees). Four algorithms, namely linear discriminant analysis (LDA), principal components analysis coupled with LDA (PCA‐LDA), partial least squares discriminant analysis (PLS‐DA) and random forest (RF), were used to build classification models for species and dieback severity classification. The effect of dark‐pixel filtering on classification accuracy was evaluated. The best performing models were then coupled with automatic ITC segmentation to map species and ash dieback distribution over 16.8 hectares of woodland. We calculated and partitioned the coefficient of variation (CV) of the reflected ash spectra to find variable wavebands associated with dieback. PLS‐DA and LDA were most accurate for classifying ITC species identifies (overall accuracy >90%), whereas RF was most accurate for classifying ash dieback severity (overall accuracy 77%). Dark pixel filtering further increased the accuracy of species classification (+6%), but not disease classification. The reflectances of narrow blue (415 nm), red‐edge (680 nm) and NIR (760 nm) bands had high CV across disease classes and should be included if multispectral imagery were to be used to monitor ash dieback. The study demonstrates the possibility of using remote sensing to forward epidemiological research by monitoring forest pathogens in landscape scales, which would allow temperate forest managers to control pathogen outbreaks, assess associated impacts and restore affected forests much more effectively.https://doi.org/10.1002/rse2.190hyperspectral remote sensingash diebackHymenoscyphus fraxineustemperate forestsdark pixel filteringspecies classification |
| spellingShingle | Aland H. Y. Chan Chloe Barnes Tom Swinfield David A. Coomes Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing Remote Sensing in Ecology and Conservation hyperspectral remote sensing ash dieback Hymenoscyphus fraxineus temperate forests dark pixel filtering species classification |
| title | Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing |
| title_full | Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing |
| title_fullStr | Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing |
| title_full_unstemmed | Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing |
| title_short | Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing |
| title_sort | monitoring ash dieback hymenoscyphus fraxineus in british forests using hyperspectral remote sensing |
| topic | hyperspectral remote sensing ash dieback Hymenoscyphus fraxineus temperate forests dark pixel filtering species classification |
| url | https://doi.org/10.1002/rse2.190 |
| work_keys_str_mv | AT alandhychan monitoringashdiebackhymenoscyphusfraxineusinbritishforestsusinghyperspectralremotesensing AT chloebarnes monitoringashdiebackhymenoscyphusfraxineusinbritishforestsusinghyperspectralremotesensing AT tomswinfield monitoringashdiebackhymenoscyphusfraxineusinbritishforestsusinghyperspectralremotesensing AT davidacoomes monitoringashdiebackhymenoscyphusfraxineusinbritishforestsusinghyperspectralremotesensing |