Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote Sensing
The unique characteristics of desert vegetation, such as different leaf morphology, discrete canopy structures, sparse and uneven distribution, etc., pose significant challenges for remote sensing-based estimation of fractional vegetation cover (FVC). The Unmanned Aerial Vehicle (UAV) system can acc...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/15/2665 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849765972263567360 |
|---|---|
| author | Jie Han Jinlei Zhu Xiaoming Cao Lei Xi Zhao Qi Yongxin Li Xingyu Wang Jiaxiu Zou |
| author_facet | Jie Han Jinlei Zhu Xiaoming Cao Lei Xi Zhao Qi Yongxin Li Xingyu Wang Jiaxiu Zou |
| author_sort | Jie Han |
| collection | DOAJ |
| description | The unique characteristics of desert vegetation, such as different leaf morphology, discrete canopy structures, sparse and uneven distribution, etc., pose significant challenges for remote sensing-based estimation of fractional vegetation cover (FVC). The Unmanned Aerial Vehicle (UAV) system can accurately distinguish vegetation patches, extract weak vegetation signals, and navigate through complex terrain, making it suitable for applications in small-scale FVC extraction. In this study, we selected the floodplain fan with <i>Caragana korshinskii Kom</i> as the constructive species in Hatengtaohai National Nature Reserve, Bayannur, Inner Mongolia, China, as our study area. We investigated the remote sensing extraction method of desert sparse vegetation cover by placing samples across three gradients: the top, middle, and edge of the fan. We then acquired UAV multispectral images; evaluated the applicability of various vegetation indices (VIs) using methods such as supervised classification, linear regression models, and machine learning; and explored the feasibility and stability of multiple machine learning models in this region. Our results indicate the following: (1) We discovered that the multispectral vegetation index is superior to the visible vegetation index and more suitable for FVC extraction in vegetation-sparse desert regions. (2) By comparing five machine learning regression models, it was found that the XGBoost and KNN models exhibited relatively lower estimation performance in the study area. The spatial distribution of plots appeared to influence the stability of the SVM model when estimating fractional vegetation cover (FVC). In contrast, the RF and LASSO models demonstrated robust stability across both training and testing datasets. Notably, the RF model achieved the best inversion performance (R<sup>2</sup> = 0.876, RMSE = 0.020, MAE = 0.016), indicating that RF is one of the most suitable models for retrieving FVC in naturally sparse desert vegetation. This study provides a valuable contribution to the limited existing research on remote sensing-based estimation of FVC and characterization of spatial heterogeneity in small-scale desert sparse vegetation ecosystems dominated by a single species. |
| format | Article |
| id | doaj-art-b34f5c8d95d247979c9fafa12cd45481 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-b34f5c8d95d247979c9fafa12cd454812025-08-20T03:04:43ZengMDPI AGRemote Sensing2072-42922025-08-011715266510.3390/rs17152665Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote SensingJie Han0Jinlei Zhu1Xiaoming Cao2Lei Xi3Zhao Qi4Yongxin Li5Xingyu Wang6Jiaxiu Zou7Institute of Ecological Conservation and Restoration, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Ecological Conservation and Restoration, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Ecological Conservation and Restoration, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Ecological Conservation and Restoration, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Ecological Conservation and Restoration, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Ecological Conservation and Restoration, Chinese Academy of Forestry, Beijing 100091, ChinaSchool of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, ChinaInstitute of Ecological Conservation and Restoration, Chinese Academy of Forestry, Beijing 100091, ChinaThe unique characteristics of desert vegetation, such as different leaf morphology, discrete canopy structures, sparse and uneven distribution, etc., pose significant challenges for remote sensing-based estimation of fractional vegetation cover (FVC). The Unmanned Aerial Vehicle (UAV) system can accurately distinguish vegetation patches, extract weak vegetation signals, and navigate through complex terrain, making it suitable for applications in small-scale FVC extraction. In this study, we selected the floodplain fan with <i>Caragana korshinskii Kom</i> as the constructive species in Hatengtaohai National Nature Reserve, Bayannur, Inner Mongolia, China, as our study area. We investigated the remote sensing extraction method of desert sparse vegetation cover by placing samples across three gradients: the top, middle, and edge of the fan. We then acquired UAV multispectral images; evaluated the applicability of various vegetation indices (VIs) using methods such as supervised classification, linear regression models, and machine learning; and explored the feasibility and stability of multiple machine learning models in this region. Our results indicate the following: (1) We discovered that the multispectral vegetation index is superior to the visible vegetation index and more suitable for FVC extraction in vegetation-sparse desert regions. (2) By comparing five machine learning regression models, it was found that the XGBoost and KNN models exhibited relatively lower estimation performance in the study area. The spatial distribution of plots appeared to influence the stability of the SVM model when estimating fractional vegetation cover (FVC). In contrast, the RF and LASSO models demonstrated robust stability across both training and testing datasets. Notably, the RF model achieved the best inversion performance (R<sup>2</sup> = 0.876, RMSE = 0.020, MAE = 0.016), indicating that RF is one of the most suitable models for retrieving FVC in naturally sparse desert vegetation. This study provides a valuable contribution to the limited existing research on remote sensing-based estimation of FVC and characterization of spatial heterogeneity in small-scale desert sparse vegetation ecosystems dominated by a single species.https://www.mdpi.com/2072-4292/17/15/2665Unmanned Aerial Vehicle (UAV)sparse vegetationvegetation indexFractional Vegetation Cover (FVC)Machine Learning (ML) |
| spellingShingle | Jie Han Jinlei Zhu Xiaoming Cao Lei Xi Zhao Qi Yongxin Li Xingyu Wang Jiaxiu Zou Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote Sensing Remote Sensing Unmanned Aerial Vehicle (UAV) sparse vegetation vegetation index Fractional Vegetation Cover (FVC) Machine Learning (ML) |
| title | Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote Sensing |
| title_full | Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote Sensing |
| title_fullStr | Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote Sensing |
| title_full_unstemmed | Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote Sensing |
| title_short | Extraction of Sparse Vegetation Cover in Deserts Based on UAV Remote Sensing |
| title_sort | extraction of sparse vegetation cover in deserts based on uav remote sensing |
| topic | Unmanned Aerial Vehicle (UAV) sparse vegetation vegetation index Fractional Vegetation Cover (FVC) Machine Learning (ML) |
| url | https://www.mdpi.com/2072-4292/17/15/2665 |
| work_keys_str_mv | AT jiehan extractionofsparsevegetationcoverindesertsbasedonuavremotesensing AT jinleizhu extractionofsparsevegetationcoverindesertsbasedonuavremotesensing AT xiaomingcao extractionofsparsevegetationcoverindesertsbasedonuavremotesensing AT leixi extractionofsparsevegetationcoverindesertsbasedonuavremotesensing AT zhaoqi extractionofsparsevegetationcoverindesertsbasedonuavremotesensing AT yongxinli extractionofsparsevegetationcoverindesertsbasedonuavremotesensing AT xingyuwang extractionofsparsevegetationcoverindesertsbasedonuavremotesensing AT jiaxiuzou extractionofsparsevegetationcoverindesertsbasedonuavremotesensing |