Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches
Research on the forest structure classification is essential, as it plays an important role in assessing the vitality and diversity of vegetation. However, classifying forest structure involves in situ surveying, which requires considerable time and money, and cannot be conducted directly in some in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/21/4282 |
| _version_ | 1797511878528729088 |
|---|---|
| author | Jin-Woo Yu Young-Woong Yoon Won-Kyung Baek Hyung-Sup Jung |
| author_facet | Jin-Woo Yu Young-Woong Yoon Won-Kyung Baek Hyung-Sup Jung |
| author_sort | Jin-Woo Yu |
| collection | DOAJ |
| description | Research on the forest structure classification is essential, as it plays an important role in assessing the vitality and diversity of vegetation. However, classifying forest structure involves in situ surveying, which requires considerable time and money, and cannot be conducted directly in some instances; also, the update cycle of the classification data is very late. To overcome these drawbacks, feasibility studies on mapping the forest vertical structure from aerial images using machine learning techniques were conducted. In this study, we investigated (1) the performance improvement of the forest structure classification, using a high-resolution LiDAR-derived digital surface model (DSM) acquired from an unmanned aerial vehicle (UAV) platform and (2) the performance comparison of results obtained from the single-seasonal and two-seasonal data, using random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM). For the performance comparison, the UAV optic and LiDAR data were divided into three cases: (1) only used autumn data, (2) only used winter data, and (3) used both autumn and winter data. From the results, the best model was XGBoost, and the F1 scores achieved using this method were approximately 0.92 in the autumn and winter cases. A remarkable improvement was achieved when both two-seasonal images were used. The F1 score improved by 35.3% from 0.68 to 0.92. This implies that (1) the seasonal variation in the forest vertical structure can be more important than the spatial resolution, and (2) the classification performance achieved from the two-seasonal UAV optic images and LiDAR-derived DSMs can reach 0.9 with the application of an optimal machine learning approach. |
| first_indexed | 2024-03-10T05:54:10Z |
| format | Article |
| id | doaj.art-b91cb541b46c42dc90934cb0731d52c1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T05:54:10Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b91cb541b46c42dc90934cb0731d52c12023-11-22T21:31:09ZengMDPI AGRemote Sensing2072-42922021-10-011321428210.3390/rs13214282Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine ApproachesJin-Woo Yu0Young-Woong Yoon1Won-Kyung Baek2Hyung-Sup Jung3Department of Geoinformatics, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaResearch on the forest structure classification is essential, as it plays an important role in assessing the vitality and diversity of vegetation. However, classifying forest structure involves in situ surveying, which requires considerable time and money, and cannot be conducted directly in some instances; also, the update cycle of the classification data is very late. To overcome these drawbacks, feasibility studies on mapping the forest vertical structure from aerial images using machine learning techniques were conducted. In this study, we investigated (1) the performance improvement of the forest structure classification, using a high-resolution LiDAR-derived digital surface model (DSM) acquired from an unmanned aerial vehicle (UAV) platform and (2) the performance comparison of results obtained from the single-seasonal and two-seasonal data, using random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM). For the performance comparison, the UAV optic and LiDAR data were divided into three cases: (1) only used autumn data, (2) only used winter data, and (3) used both autumn and winter data. From the results, the best model was XGBoost, and the F1 scores achieved using this method were approximately 0.92 in the autumn and winter cases. A remarkable improvement was achieved when both two-seasonal images were used. The F1 score improved by 35.3% from 0.68 to 0.92. This implies that (1) the seasonal variation in the forest vertical structure can be more important than the spatial resolution, and (2) the classification performance achieved from the two-seasonal UAV optic images and LiDAR-derived DSMs can reach 0.9 with the application of an optimal machine learning approach.https://www.mdpi.com/2072-4292/13/21/4282forest vertical structuremultiseasonmachine learningclassification |
| spellingShingle | Jin-Woo Yu Young-Woong Yoon Won-Kyung Baek Hyung-Sup Jung Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches Remote Sensing forest vertical structure multiseason machine learning classification |
| title | Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches |
| title_full | Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches |
| title_fullStr | Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches |
| title_full_unstemmed | Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches |
| title_short | Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches |
| title_sort | forest vertical structure mapping using two seasonal optic images and lidar dsm acquired from uav platform through random forest xgboost and support vector machine approaches |
| topic | forest vertical structure multiseason machine learning classification |
| url | https://www.mdpi.com/2072-4292/13/21/4282 |
| work_keys_str_mv | AT jinwooyu forestverticalstructuremappingusingtwoseasonalopticimagesandlidardsmacquiredfromuavplatformthroughrandomforestxgboostandsupportvectormachineapproaches AT youngwoongyoon forestverticalstructuremappingusingtwoseasonalopticimagesandlidardsmacquiredfromuavplatformthroughrandomforestxgboostandsupportvectormachineapproaches AT wonkyungbaek forestverticalstructuremappingusingtwoseasonalopticimagesandlidardsmacquiredfromuavplatformthroughrandomforestxgboostandsupportvectormachineapproaches AT hyungsupjung forestverticalstructuremappingusingtwoseasonalopticimagesandlidardsmacquiredfromuavplatformthroughrandomforestxgboostandsupportvectormachineapproaches |