Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization
Urban land use/land cover (LULC) classification has long been a hotspot for remote sensing applications. With high spatio-temporal resolution and multispectral, the recently launched GF-6 satellite provides ideal open imagery for LULC mapping. In this study, we utilized multitemporal GF-6 images to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/10106049.2023.2236579 |
| _version_ | 1797681585120608256 |
|---|---|
| author | Xiaobing Wei Wen Zhang Zhen Zhang Haosheng Huang Lingkui Meng |
| author_facet | Xiaobing Wei Wen Zhang Zhen Zhang Haosheng Huang Lingkui Meng |
| author_sort | Xiaobing Wei |
| collection | DOAJ |
| description | Urban land use/land cover (LULC) classification has long been a hotspot for remote sensing applications. With high spatio-temporal resolution and multispectral, the recently launched GF-6 satellite provides ideal open imagery for LULC mapping. In this study, we utilized multitemporal GF-6 images to generate six types of land features, including spectral bands, texture features, built-up, waterbody, vegetation, and red-edge indices. The minimum Redundancy Maximum Relevance (mRMR) algorithm was employed to optimize feature selection. Subsequently, Random Forest (RF) and Extreme Gradient Boosting (XGBT) were assessed using different feature selections. Besides, various feature configurations were designed for LULC classification and comparison. The results indicate that the mRMR-based RF method achieved the highest overall accuracy of 91.37%. The temporal red-edge indices were important features for urban LULC classification and contributed mainly to grassland and cropland. These results supplement existing classification methods and assist in improving LULC mapping in urban areas with complex landscapes. |
| first_indexed | 2024-03-11T23:47:03Z |
| format | Article |
| id | doaj.art-65e4f20089cd4b358636d9d0fd779c1f |
| institution | Directory Open Access Journal |
| issn | 1010-6049 1752-0762 |
| language | English |
| last_indexed | 2024-03-11T23:47:03Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj.art-65e4f20089cd4b358636d9d0fd779c1f2023-09-19T09:13:18ZengTaylor & Francis GroupGeocarto International1010-60491752-07622023-12-0138110.1080/10106049.2023.22365792236579Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimizationXiaobing Wei0Wen Zhang1Zhen Zhang2Haosheng Huang3Lingkui Meng4School of Remote Sensing and Information Engineering, Wuhan UniversitySchool of Remote Sensing and Information Engineering, Wuhan UniversitySchool of Remote Sensing and Information Engineering, Wuhan UniversityDepartment of Geography, Ghent UniversitySchool of Remote Sensing and Information Engineering, Wuhan UniversityUrban land use/land cover (LULC) classification has long been a hotspot for remote sensing applications. With high spatio-temporal resolution and multispectral, the recently launched GF-6 satellite provides ideal open imagery for LULC mapping. In this study, we utilized multitemporal GF-6 images to generate six types of land features, including spectral bands, texture features, built-up, waterbody, vegetation, and red-edge indices. The minimum Redundancy Maximum Relevance (mRMR) algorithm was employed to optimize feature selection. Subsequently, Random Forest (RF) and Extreme Gradient Boosting (XGBT) were assessed using different feature selections. Besides, various feature configurations were designed for LULC classification and comparison. The results indicate that the mRMR-based RF method achieved the highest overall accuracy of 91.37%. The temporal red-edge indices were important features for urban LULC classification and contributed mainly to grassland and cropland. These results supplement existing classification methods and assist in improving LULC mapping in urban areas with complex landscapes.http://dx.doi.org/10.1080/10106049.2023.2236579gf-6 imageryurban land use/land covermrmrrandom forestextreme gradient boosting |
| spellingShingle | Xiaobing Wei Wen Zhang Zhen Zhang Haosheng Huang Lingkui Meng Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization Geocarto International gf-6 imagery urban land use/land cover mrmr random forest extreme gradient boosting |
| title | Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization |
| title_full | Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization |
| title_fullStr | Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization |
| title_full_unstemmed | Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization |
| title_short | Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization |
| title_sort | urban land use land cover classification based on gf 6 satellite imagery and multi feature optimization |
| topic | gf-6 imagery urban land use/land cover mrmr random forest extreme gradient boosting |
| url | http://dx.doi.org/10.1080/10106049.2023.2236579 |
| work_keys_str_mv | AT xiaobingwei urbanlanduselandcoverclassificationbasedongf6satelliteimageryandmultifeatureoptimization AT wenzhang urbanlanduselandcoverclassificationbasedongf6satelliteimageryandmultifeatureoptimization AT zhenzhang urbanlanduselandcoverclassificationbasedongf6satelliteimageryandmultifeatureoptimization AT haoshenghuang urbanlanduselandcoverclassificationbasedongf6satelliteimageryandmultifeatureoptimization AT lingkuimeng urbanlanduselandcoverclassificationbasedongf6satelliteimageryandmultifeatureoptimization |