Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an Example
Accurately extracting impervious surfaces (IS) and continuously monitoring their dynamics are crucial practices for promoting sustainable development in regional ecological environments and resources. In this context, we conducted experiments to extract IS of the Dianchi Lake Basin by utilizing vari...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/12/6/1210 |
| _version_ | 1797593876550123520 |
|---|---|
| author | Yimin Li Xue Yang Bowen Wu Juanzhen Zhao Xuanlun Deng |
| author_facet | Yimin Li Xue Yang Bowen Wu Juanzhen Zhao Xuanlun Deng |
| author_sort | Yimin Li |
| collection | DOAJ |
| description | Accurately extracting impervious surfaces (IS) and continuously monitoring their dynamics are crucial practices for promoting sustainable development in regional ecological environments and resources. In this context, we conducted experiments to extract IS of the Dianchi Lake Basin by utilizing various features extracted from remote sensing images and applying three different machine learning algorithms. Through this process, we obtained the optimal combination of features and a machine learning algorithm. Utilizing this model, our objective is to map the evolution of IS in the Dianchi Lake Basin, from 2000 to 2022, and analyze its dynamic changes. Our results showed the following: (1) The optimal model for IS extraction in the Dianchi Lake Basin was IMG-SPESVM based on the support vector machine, remote sensing images, and spectral features. (2) From 2000 to 2022, the spatial distribution and shape of the IS in the Dianchi Lake Basin changed significantly, but they all developed in the area around Dianchi Lake. (3) From 2000 to 2015, the rate of expansion of IS gradually accelerated, while from 2015 to 2022, it contracted. (4) From 2000 to 2022, the center of mass of IS moved to the northeast, and the standard deviation ellipse shifted greatly in the south–north direction. (5) Natural factors negatively affected the expansion of IS, while social factors positively affected the distribution of the IS. |
| first_indexed | 2024-03-11T02:15:39Z |
| format | Article |
| id | doaj.art-b233a5f2a81e4c88aa67f48841d32b38 |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-11T02:15:39Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-b233a5f2a81e4c88aa67f48841d32b382023-11-18T11:14:21ZengMDPI AGLand2073-445X2023-06-01126121010.3390/land12061210Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an ExampleYimin Li0Xue Yang1Bowen Wu2Juanzhen Zhao3Xuanlun Deng4School of Earth Sciences, Yunnan University, Kunming 650091, ChinaSchool of Earth Sciences, Yunnan University, Kunming 650091, ChinaSchool of Earth Sciences, Yunnan University, Kunming 650091, ChinaInstitute of International Rivers and Ecological Security, Yunnan University, Kunming 650091, ChinaSchool of Earth Sciences, Yunnan University, Kunming 650091, ChinaAccurately extracting impervious surfaces (IS) and continuously monitoring their dynamics are crucial practices for promoting sustainable development in regional ecological environments and resources. In this context, we conducted experiments to extract IS of the Dianchi Lake Basin by utilizing various features extracted from remote sensing images and applying three different machine learning algorithms. Through this process, we obtained the optimal combination of features and a machine learning algorithm. Utilizing this model, our objective is to map the evolution of IS in the Dianchi Lake Basin, from 2000 to 2022, and analyze its dynamic changes. Our results showed the following: (1) The optimal model for IS extraction in the Dianchi Lake Basin was IMG-SPESVM based on the support vector machine, remote sensing images, and spectral features. (2) From 2000 to 2022, the spatial distribution and shape of the IS in the Dianchi Lake Basin changed significantly, but they all developed in the area around Dianchi Lake. (3) From 2000 to 2015, the rate of expansion of IS gradually accelerated, while from 2015 to 2022, it contracted. (4) From 2000 to 2022, the center of mass of IS moved to the northeast, and the standard deviation ellipse shifted greatly in the south–north direction. (5) Natural factors negatively affected the expansion of IS, while social factors positively affected the distribution of the IS.https://www.mdpi.com/2073-445X/12/6/1210impervious surfaceDianchi Basinmachine learning algorithmmodel optimization |
| spellingShingle | Yimin Li Xue Yang Bowen Wu Juanzhen Zhao Xuanlun Deng Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an Example Land impervious surface Dianchi Basin machine learning algorithm model optimization |
| title | Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an Example |
| title_full | Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an Example |
| title_fullStr | Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an Example |
| title_full_unstemmed | Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an Example |
| title_short | Impervious Surface Mapping Based on Remote Sensing and an Optimized Coupled Model: The Dianchi Basin as an Example |
| title_sort | impervious surface mapping based on remote sensing and an optimized coupled model the dianchi basin as an example |
| topic | impervious surface Dianchi Basin machine learning algorithm model optimization |
| url | https://www.mdpi.com/2073-445X/12/6/1210 |
| work_keys_str_mv | AT yiminli impervioussurfacemappingbasedonremotesensingandanoptimizedcoupledmodelthedianchibasinasanexample AT xueyang impervioussurfacemappingbasedonremotesensingandanoptimizedcoupledmodelthedianchibasinasanexample AT bowenwu impervioussurfacemappingbasedonremotesensingandanoptimizedcoupledmodelthedianchibasinasanexample AT juanzhenzhao impervioussurfacemappingbasedonremotesensingandanoptimizedcoupledmodelthedianchibasinasanexample AT xuanlundeng impervioussurfacemappingbasedonremotesensingandanoptimizedcoupledmodelthedianchibasinasanexample |