Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network
The role of forests is increasing because of rapid land use changes worldwide that have implications on ecosystems and the carbon cycle. Therefore, it is necessary to obtain accurate information about forests and build forest inventories. However, it is difficult to assess the internal structure of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/18/3736 |
| _version_ | 1797517335169335296 |
|---|---|
| author | Sung-Hwan Park Hyung-Sup Jung Sunmin Lee Eun-Sook Kim |
| author_facet | Sung-Hwan Park Hyung-Sup Jung Sunmin Lee Eun-Sook Kim |
| author_sort | Sung-Hwan Park |
| collection | DOAJ |
| description | The role of forests is increasing because of rapid land use changes worldwide that have implications on ecosystems and the carbon cycle. Therefore, it is necessary to obtain accurate information about forests and build forest inventories. However, it is difficult to assess the internal structure of the forest through 2D remote sensing techniques and fieldwork. In this aspect, we proposed a method for estimating the vertical structure of forests based on full-waveform light detection and ranging (FW LiDAR) data in this study. Voxel-based tree point density maps were generated by estimating the number of canopy height points in each voxel grid from the raster digital terrain model (DTM) and canopy height points after pre-processing the LiDAR point clouds. We applied an unsupervised classification algorithm to the voxel-based tree point density maps and identified seven classes by profile pattern analysis for the forest vertical types. The classification accuracy was found to be 72.73% from the validation from 11 field investigation sites, which was additionally confirmed through comparative analysis with aerial images. Based on this pre-classification reference map, which is assumed to be ground truths, the deep neural network (DNN) model was finally applied to perform the final classification. As a result of accuracy assessment, it showed accuracy of 92.72% with a good performance. These results demonstrate the potential of vertical structure estimation for extensive forests using FW LiDAR data and that the distinction between one-storied and two-storied forests can be clearly represented. This technique is expected to contribute to efficient and effective management of forests based on accurate information derived from the proposed method. |
| first_indexed | 2024-03-10T07:14:13Z |
| format | Article |
| id | doaj.art-37a6a17fa8ad465aab74d5b306ed1ee3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T07:14:13Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-37a6a17fa8ad465aab74d5b306ed1ee32023-11-22T15:07:33ZengMDPI AGRemote Sensing2072-42922021-09-011318373610.3390/rs13183736Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural NetworkSung-Hwan Park0Hyung-Sup Jung1Sunmin Lee2Eun-Sook Kim3Marine Disaster Research Center, Korea Institute of Ocean Science & Technology, Busan 49111, KoreaDepartment of Geoinformatics, University of Seoul, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, Seoul 02504, KoreaDivision of Forest Ecology, National Institute of Forest Science, Seoul 02455, KoreaThe role of forests is increasing because of rapid land use changes worldwide that have implications on ecosystems and the carbon cycle. Therefore, it is necessary to obtain accurate information about forests and build forest inventories. However, it is difficult to assess the internal structure of the forest through 2D remote sensing techniques and fieldwork. In this aspect, we proposed a method for estimating the vertical structure of forests based on full-waveform light detection and ranging (FW LiDAR) data in this study. Voxel-based tree point density maps were generated by estimating the number of canopy height points in each voxel grid from the raster digital terrain model (DTM) and canopy height points after pre-processing the LiDAR point clouds. We applied an unsupervised classification algorithm to the voxel-based tree point density maps and identified seven classes by profile pattern analysis for the forest vertical types. The classification accuracy was found to be 72.73% from the validation from 11 field investigation sites, which was additionally confirmed through comparative analysis with aerial images. Based on this pre-classification reference map, which is assumed to be ground truths, the deep neural network (DNN) model was finally applied to perform the final classification. As a result of accuracy assessment, it showed accuracy of 92.72% with a good performance. These results demonstrate the potential of vertical structure estimation for extensive forests using FW LiDAR data and that the distinction between one-storied and two-storied forests can be clearly represented. This technique is expected to contribute to efficient and effective management of forests based on accurate information derived from the proposed method.https://www.mdpi.com/2072-4292/13/18/3736forest vertical structurefull-waveform LiDARdeep neural networkdeep learningforest genetic resource reserve |
| spellingShingle | Sung-Hwan Park Hyung-Sup Jung Sunmin Lee Eun-Sook Kim Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network Remote Sensing forest vertical structure full-waveform LiDAR deep neural network deep learning forest genetic resource reserve |
| title | Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network |
| title_full | Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network |
| title_fullStr | Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network |
| title_full_unstemmed | Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network |
| title_short | Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network |
| title_sort | mapping forest vertical structure in sogwang ri forest from full waveform lidar point clouds using deep neural network |
| topic | forest vertical structure full-waveform LiDAR deep neural network deep learning forest genetic resource reserve |
| url | https://www.mdpi.com/2072-4292/13/18/3736 |
| work_keys_str_mv | AT sunghwanpark mappingforestverticalstructureinsogwangriforestfromfullwaveformlidarpointcloudsusingdeepneuralnetwork AT hyungsupjung mappingforestverticalstructureinsogwangriforestfromfullwaveformlidarpointcloudsusingdeepneuralnetwork AT sunminlee mappingforestverticalstructureinsogwangriforestfromfullwaveformlidarpointcloudsusingdeepneuralnetwork AT eunsookkim mappingforestverticalstructureinsogwangriforestfromfullwaveformlidarpointcloudsusingdeepneuralnetwork |