Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain Forest
Effective forest management necessitates spatially explicit information about tree species composition. This information supports the safeguarding of native species, sustainable timber harvesting practices, precise mapping of wildlife habitats, and identification of invasive species. Tree species id...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/21/4060 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850193452072960000 |
|---|---|
| author | Ram Avtar Xinyu Chen Jinjin Fu Saleh Alsulamy Hitesh Supe Yunus Ali Pulpadan Albertus Stephanus Louw Nakaji Tatsuro |
| author_facet | Ram Avtar Xinyu Chen Jinjin Fu Saleh Alsulamy Hitesh Supe Yunus Ali Pulpadan Albertus Stephanus Louw Nakaji Tatsuro |
| author_sort | Ram Avtar |
| collection | DOAJ |
| description | Effective forest management necessitates spatially explicit information about tree species composition. This information supports the safeguarding of native species, sustainable timber harvesting practices, precise mapping of wildlife habitats, and identification of invasive species. Tree species identification and geo-location by machine learning classification of UAV aerial imagery offer an alternative to tedious ground surveys. However, the timing (season) of the aerial surveys, input variables considered for classification, and the model type affect the classification accuracy. This work evaluates how the seasons and input variables considered in the species classification model affect the accuracy of species classification in a temperate broadleaf and mixed forest. Among the considered models, a Random Forest (RF) classifier demonstrated the highest performance, attaining an overall accuracy of 83.98% and a kappa coefficient of 0.80. Simultaneously using input data from summer, winter, autumn, and spring seasons improved tree species classification accuracy by 14–18% from classifications made using only single-season input data. Models that included vegetation indices, image texture, and elevation data obtained the highest accuracy. These results strengthen the case for using multi-seasonal data for species classification in temperate broadleaf and mixed forests since seasonal differences in the characteristics of species (e.g., leaf color, canopy structure) improve the ability to discern species. |
| format | Article |
| id | doaj-art-63a185627ccc4aff949b1a7ff2e2b763 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-63a185627ccc4aff949b1a7ff2e2b7632025-08-20T02:14:16ZengMDPI AGRemote Sensing2072-42922024-10-011621406010.3390/rs16214060Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain ForestRam Avtar0Xinyu Chen1Jinjin Fu2Saleh Alsulamy3Hitesh Supe4Yunus Ali Pulpadan5Albertus Stephanus Louw6Nakaji Tatsuro7Graduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, JapanGraduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, JapanGraduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, JapanDepartment of Architecture, College of Architecture & Planning, King Khalid University, Abha 61421, Saudi ArabiaGraduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, JapanDepartment of Earth and Environmental Sciences, Indian Institute of Science Education and Research Mohali, Punjab 140-306, IndiaGraduate School of Environmental Science, Hokkaido University, Sapporo 060-0810, JapanField Science Center for Northern Biosphere, Hokkaido University, Sapporo 060-0809, JapanEffective forest management necessitates spatially explicit information about tree species composition. This information supports the safeguarding of native species, sustainable timber harvesting practices, precise mapping of wildlife habitats, and identification of invasive species. Tree species identification and geo-location by machine learning classification of UAV aerial imagery offer an alternative to tedious ground surveys. However, the timing (season) of the aerial surveys, input variables considered for classification, and the model type affect the classification accuracy. This work evaluates how the seasons and input variables considered in the species classification model affect the accuracy of species classification in a temperate broadleaf and mixed forest. Among the considered models, a Random Forest (RF) classifier demonstrated the highest performance, attaining an overall accuracy of 83.98% and a kappa coefficient of 0.80. Simultaneously using input data from summer, winter, autumn, and spring seasons improved tree species classification accuracy by 14–18% from classifications made using only single-season input data. Models that included vegetation indices, image texture, and elevation data obtained the highest accuracy. These results strengthen the case for using multi-seasonal data for species classification in temperate broadleaf and mixed forests since seasonal differences in the characteristics of species (e.g., leaf color, canopy structure) improve the ability to discern species.https://www.mdpi.com/2072-4292/16/21/4060tree speciesforest managementLiDARunmanned aerial vehiclemachine learning |
| spellingShingle | Ram Avtar Xinyu Chen Jinjin Fu Saleh Alsulamy Hitesh Supe Yunus Ali Pulpadan Albertus Stephanus Louw Nakaji Tatsuro Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain Forest Remote Sensing tree species forest management LiDAR unmanned aerial vehicle machine learning |
| title | Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain Forest |
| title_full | Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain Forest |
| title_fullStr | Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain Forest |
| title_full_unstemmed | Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain Forest |
| title_short | Tree Species Classification by Multi-Season Collected UAV Imagery in a Mixed Cool-Temperate Mountain Forest |
| title_sort | tree species classification by multi season collected uav imagery in a mixed cool temperate mountain forest |
| topic | tree species forest management LiDAR unmanned aerial vehicle machine learning |
| url | https://www.mdpi.com/2072-4292/16/21/4060 |
| work_keys_str_mv | AT ramavtar treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest AT xinyuchen treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest AT jinjinfu treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest AT salehalsulamy treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest AT hiteshsupe treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest AT yunusalipulpadan treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest AT albertusstephanuslouw treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest AT nakajitatsuro treespeciesclassificationbymultiseasoncollecteduavimageryinamixedcooltemperatemountainforest |