Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, China
Developing an effective vegetation classification method for mountain–plain transition zones is critical for understanding ecological patterns, evaluating ecosystem services, and guiding conservation efforts. Existing methods perform well in mountainous and plain areas but lack verification in mount...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/14/1/184 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588130706784256 |
|---|---|
| author | Wenqian Bai Zhengwei He Yan Tan Guy M. Robinson Tingyu Zhang Xueman Wang Li He Linlong Li Shuang Wu |
| author_facet | Wenqian Bai Zhengwei He Yan Tan Guy M. Robinson Tingyu Zhang Xueman Wang Li He Linlong Li Shuang Wu |
| author_sort | Wenqian Bai |
| collection | DOAJ |
| description | Developing an effective vegetation classification method for mountain–plain transition zones is critical for understanding ecological patterns, evaluating ecosystem services, and guiding conservation efforts. Existing methods perform well in mountainous and plain areas but lack verification in mountain–plain transition zones. This study utilized terrain data and Sentinel-1 and Sentinel-2 imagery to extract topographic, spectral, texture, and SAR features as well as the vegetation index. By combining feature sets and applying feature elimination algorithms, the classification performance of one-dimensional convolutional neural networks (1D-CNNs), Random Forest (RF), and Multilayer Perceptron (MLP) was evaluated to determine the optimal feature combinations and methods. The results show the following: (1) multi-feature combinations, especially spectral and topographic features, significantly improved classification accuracy; (2) Recursive Feature Elimination based on Random Forest (RF-RFE) outperformed ReliefF in feature selection, identifying more representative features; (3) all three algorithms performed well, with consistent spatial results. The MLP algorithm achieved the best overall accuracy (OA: 81.65%, Kappa: 77.75%), demonstrating robustness and lower dependence on feature quantity. This study presents an efficient and robust vegetation classification workflow, verifies its applicability in mountain–plain transition zones, and provides valuable insights for small-region vegetation classification under similar topographic conditions globally. |
| format | Article |
| id | doaj-art-5ac7d9e46ee2485aaf54d818ac3353f3 |
| institution | Kabale University |
| issn | 2073-445X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj-art-5ac7d9e46ee2485aaf54d818ac3353f32025-01-24T13:38:14ZengMDPI AGLand2073-445X2025-01-0114118410.3390/land14010184Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, ChinaWenqian Bai0Zhengwei He1Yan Tan2Guy M. Robinson3Tingyu Zhang4Xueman Wang5Li He6Linlong Li7Shuang Wu8State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaDepartment of Geography, Environment and Population, The University of Adelaide, Adelaide 5000, AustraliaDepartment of Geography, Environment and Population, The University of Adelaide, Adelaide 5000, AustraliaSchool of Statistics, Dongbei University of Finance and Economics, Dalian 116025, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaSchool of Land Resources and Surveying and Mapping Engineering, Shandong Agricultural and Engineering University, Jinan 250100, ChinaDeveloping an effective vegetation classification method for mountain–plain transition zones is critical for understanding ecological patterns, evaluating ecosystem services, and guiding conservation efforts. Existing methods perform well in mountainous and plain areas but lack verification in mountain–plain transition zones. This study utilized terrain data and Sentinel-1 and Sentinel-2 imagery to extract topographic, spectral, texture, and SAR features as well as the vegetation index. By combining feature sets and applying feature elimination algorithms, the classification performance of one-dimensional convolutional neural networks (1D-CNNs), Random Forest (RF), and Multilayer Perceptron (MLP) was evaluated to determine the optimal feature combinations and methods. The results show the following: (1) multi-feature combinations, especially spectral and topographic features, significantly improved classification accuracy; (2) Recursive Feature Elimination based on Random Forest (RF-RFE) outperformed ReliefF in feature selection, identifying more representative features; (3) all three algorithms performed well, with consistent spatial results. The MLP algorithm achieved the best overall accuracy (OA: 81.65%, Kappa: 77.75%), demonstrating robustness and lower dependence on feature quantity. This study presents an efficient and robust vegetation classification workflow, verifies its applicability in mountain–plain transition zones, and provides valuable insights for small-region vegetation classification under similar topographic conditions globally.https://www.mdpi.com/2073-445X/14/1/184mountain–plain vegetation classificationmachine learningfeature optimizationSentinel-1Sentinel-2 |
| spellingShingle | Wenqian Bai Zhengwei He Yan Tan Guy M. Robinson Tingyu Zhang Xueman Wang Li He Linlong Li Shuang Wu Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, China Land mountain–plain vegetation classification machine learning feature optimization Sentinel-1 Sentinel-2 |
| title | Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, China |
| title_full | Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, China |
| title_fullStr | Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, China |
| title_full_unstemmed | Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, China |
| title_short | Vegetation Classification in a Mountain–Plain Transition Zone in the Sichuan Basin, China |
| title_sort | vegetation classification in a mountain plain transition zone in the sichuan basin china |
| topic | mountain–plain vegetation classification machine learning feature optimization Sentinel-1 Sentinel-2 |
| url | https://www.mdpi.com/2073-445X/14/1/184 |
| work_keys_str_mv | AT wenqianbai vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT zhengweihe vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT yantan vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT guymrobinson vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT tingyuzhang vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT xuemanwang vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT lihe vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT linlongli vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina AT shuangwu vegetationclassificationinamountainplaintransitionzoneinthesichuanbasinchina |