TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA
For studies of urban development, it is an important method for obtaining the distribution of impervious surface (IS) areas and their dynamic change from remote sensing data. The dilemma of the same spectrum for different features and different spectrums for the same features, posed by the complexit...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-05-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2022/85/2022/isprs-archives-XLIII-B3-2022-85-2022.pdf |
| _version_ | 1818213571135275008 |
|---|---|
| author | J. Gao Y. Chen Y. Guo S. Yang |
| author_facet | J. Gao Y. Chen Y. Guo S. Yang |
| author_sort | J. Gao |
| collection | DOAJ |
| description | For studies of urban development, it is an important method for obtaining the distribution of impervious surface (IS) areas and their dynamic change from remote sensing data. The dilemma of the same spectrum for different features and different spectrums for the same features, posed by the complexity of the IS objects, is the fundamental obstacle encountered in the extraction of urban IS areas. In this study, an automatic extraction method for urban IS areas is proposed and analyzed, based on classification and regression tree (CART) and ensemble learning strategies. The Sentinel-2 MSI data of 30 cities in China from 2018 to 2020 were selected for IS extraction experiments. We perform temporal and spatial modeling of the splitting threshold offset in the classification model to explore the effect of time and space on IS extraction. The obtained offset models show that the temporal variation is not significant, while the spatial offsets have more obvious linear relationships. |
| first_indexed | 2024-12-12T06:06:24Z |
| format | Article |
| id | doaj.art-00924a5f53984bd5846afc517777a522 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-12T06:06:24Z |
| publishDate | 2022-05-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-00924a5f53984bd5846afc517777a5222022-12-22T00:35:16ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342022-05-01XLIII-B3-2022859110.5194/isprs-archives-XLIII-B3-2022-85-2022TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATAJ. Gao0Y. Chen1Y. Guo2S. Yang3School of Geographic and Biologic Information Nanjing University of Posts and Telecommunications, Nanjing, ChinaSchool of Geographic and Biologic Information Nanjing University of Posts and Telecommunications, Nanjing, ChinaSchool of Geographic and Biologic Information Nanjing University of Posts and Telecommunications, Nanjing, ChinaSchool of Geographic and Biologic Information Nanjing University of Posts and Telecommunications, Nanjing, ChinaFor studies of urban development, it is an important method for obtaining the distribution of impervious surface (IS) areas and their dynamic change from remote sensing data. The dilemma of the same spectrum for different features and different spectrums for the same features, posed by the complexity of the IS objects, is the fundamental obstacle encountered in the extraction of urban IS areas. In this study, an automatic extraction method for urban IS areas is proposed and analyzed, based on classification and regression tree (CART) and ensemble learning strategies. The Sentinel-2 MSI data of 30 cities in China from 2018 to 2020 were selected for IS extraction experiments. We perform temporal and spatial modeling of the splitting threshold offset in the classification model to explore the effect of time and space on IS extraction. The obtained offset models show that the temporal variation is not significant, while the spatial offsets have more obvious linear relationships.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2022/85/2022/isprs-archives-XLIII-B3-2022-85-2022.pdf |
| spellingShingle | J. Gao Y. Chen Y. Guo S. Yang TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA |
| title_full | TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA |
| title_fullStr | TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA |
| title_full_unstemmed | TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA |
| title_short | TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA |
| title_sort | temporal and spatial analysis of classification tree for impervious surface mapping from sentinel 2 msi data |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2022/85/2022/isprs-archives-XLIII-B3-2022-85-2022.pdf |
| work_keys_str_mv | AT jgao temporalandspatialanalysisofclassificationtreeforimpervioussurfacemappingfromsentinel2msidata AT ychen temporalandspatialanalysisofclassificationtreeforimpervioussurfacemappingfromsentinel2msidata AT yguo temporalandspatialanalysisofclassificationtreeforimpervioussurfacemappingfromsentinel2msidata AT syang temporalandspatialanalysisofclassificationtreeforimpervioussurfacemappingfromsentinel2msidata |