Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest
The monitoring of forest resources is crucial for their sustainable management, and tree species identification is one of the fundamental tasks in this process. Unmanned aerial vehicles (UAVs) and miniaturized lightweight sensors can rapidly provide accurate monitoring information. The objective of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/2/244 |
| _version_ | 1819280346520223744 |
|---|---|
| author | Gabriela Takahashi Miyoshi Nilton Nobuhiro Imai Antonio Maria Garcia Tommaselli Marcus Vinícius Antunes de Moraes Eija Honkavaara |
| author_facet | Gabriela Takahashi Miyoshi Nilton Nobuhiro Imai Antonio Maria Garcia Tommaselli Marcus Vinícius Antunes de Moraes Eija Honkavaara |
| author_sort | Gabriela Takahashi Miyoshi |
| collection | DOAJ |
| description | The monitoring of forest resources is crucial for their sustainable management, and tree species identification is one of the fundamental tasks in this process. Unmanned aerial vehicles (UAVs) and miniaturized lightweight sensors can rapidly provide accurate monitoring information. The objective of this study was to investigate the use of multitemporal, UAV-based hyperspectral imagery for tree species identification in the highly diverse Brazilian Atlantic forest. Datasets were captured over three years to identify eight different tree species. The study area comprised initial to medium successional stages of the Brazilian Atlantic forest. Images were acquired with a spatial resolution of 10 cm, and radiometric adjustment processing was performed to reduce the variations caused by different factors, such as the geometry of acquisition. The random forest classification method was applied in a region-based classification approach with leave-one-out cross-validation, followed by computing the area under the receiver operating characteristic (AUCROC) curve. When using each dataset alone, the influence of different weather behaviors on tree species identification was evident. When combining all datasets and minimizing illumination differences over each tree crown, the identification of three tree species was improved. These results show that UAV-based, hyperspectral, multitemporal remote sensing imagery is a promising tool for tree species identification in tropical forests. |
| first_indexed | 2024-12-24T00:42:20Z |
| format | Article |
| id | doaj.art-3a49712b54974ac08ac54ea84f117616 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-24T00:42:20Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3a49712b54974ac08ac54ea84f1176162022-12-21T17:23:54ZengMDPI AGRemote Sensing2072-42922020-01-0112224410.3390/rs12020244rs12020244Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic ForestGabriela Takahashi Miyoshi0Nilton Nobuhiro Imai1Antonio Maria Garcia Tommaselli2Marcus Vinícius Antunes de Moraes3Eija Honkavaara4Graduate Program in Cartographic Sciences, São Paulo State University (UNESP), Roberto Simonsen 305, Presidente Prudente SP 19060-900, BrazilGraduate Program in Cartographic Sciences, São Paulo State University (UNESP), Roberto Simonsen 305, Presidente Prudente SP 19060-900, BrazilGraduate Program in Cartographic Sciences, São Paulo State University (UNESP), Roberto Simonsen 305, Presidente Prudente SP 19060-900, BrazilGraduate Program in Cartographic Sciences, São Paulo State University (UNESP), Roberto Simonsen 305, Presidente Prudente SP 19060-900, BrazilFinnish Geospatial Research Institute, National Land Survey of Finland, Geodeetinrinne 2, 02430 Masala, FinlandThe monitoring of forest resources is crucial for their sustainable management, and tree species identification is one of the fundamental tasks in this process. Unmanned aerial vehicles (UAVs) and miniaturized lightweight sensors can rapidly provide accurate monitoring information. The objective of this study was to investigate the use of multitemporal, UAV-based hyperspectral imagery for tree species identification in the highly diverse Brazilian Atlantic forest. Datasets were captured over three years to identify eight different tree species. The study area comprised initial to medium successional stages of the Brazilian Atlantic forest. Images were acquired with a spatial resolution of 10 cm, and radiometric adjustment processing was performed to reduce the variations caused by different factors, such as the geometry of acquisition. The random forest classification method was applied in a region-based classification approach with leave-one-out cross-validation, followed by computing the area under the receiver operating characteristic (AUCROC) curve. When using each dataset alone, the influence of different weather behaviors on tree species identification was evident. When combining all datasets and minimizing illumination differences over each tree crown, the identification of three tree species was improved. These results show that UAV-based, hyperspectral, multitemporal remote sensing imagery is a promising tool for tree species identification in tropical forests.https://www.mdpi.com/2072-4292/12/2/244tree species classificationsemideciduous foresthyperspectral multitemporal informationuav |
| spellingShingle | Gabriela Takahashi Miyoshi Nilton Nobuhiro Imai Antonio Maria Garcia Tommaselli Marcus Vinícius Antunes de Moraes Eija Honkavaara Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest Remote Sensing tree species classification semideciduous forest hyperspectral multitemporal information uav |
| title | Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest |
| title_full | Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest |
| title_fullStr | Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest |
| title_full_unstemmed | Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest |
| title_short | Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest |
| title_sort | evaluation of hyperspectral multitemporal information to improve tree species identification in the highly diverse atlantic forest |
| topic | tree species classification semideciduous forest hyperspectral multitemporal information uav |
| url | https://www.mdpi.com/2072-4292/12/2/244 |
| work_keys_str_mv | AT gabrielatakahashimiyoshi evaluationofhyperspectralmultitemporalinformationtoimprovetreespeciesidentificationinthehighlydiverseatlanticforest AT niltonnobuhiroimai evaluationofhyperspectralmultitemporalinformationtoimprovetreespeciesidentificationinthehighlydiverseatlanticforest AT antoniomariagarciatommaselli evaluationofhyperspectralmultitemporalinformationtoimprovetreespeciesidentificationinthehighlydiverseatlanticforest AT marcusviniciusantunesdemoraes evaluationofhyperspectralmultitemporalinformationtoimprovetreespeciesidentificationinthehighlydiverseatlanticforest AT eijahonkavaara evaluationofhyperspectralmultitemporalinformationtoimprovetreespeciesidentificationinthehighlydiverseatlanticforest |