Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imagery
Wetlands provide vital ecological services for both humans and environment, necessitating continuous, refined and up-to-date mapping of wetlands for conservation and management. In this study, we developed an automated and refined wetland mapping framework integrating training sample migration metho...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2023.2241428 |
| _version_ | 1797678442186014720 |
|---|---|
| author | Yawen Deng Weiguo Jiang Ziyan Ling Xiaoya Wang Kaifeng Peng Zhuo Li |
| author_facet | Yawen Deng Weiguo Jiang Ziyan Ling Xiaoya Wang Kaifeng Peng Zhuo Li |
| author_sort | Yawen Deng |
| collection | DOAJ |
| description | Wetlands provide vital ecological services for both humans and environment, necessitating continuous, refined and up-to-date mapping of wetlands for conservation and management. In this study, we developed an automated and refined wetland mapping framework integrating training sample migration method, supervised machine learning and knowledge-driven rules using Google Earth Engine (GEE) platform and open-source geospatial tools. We applied the framework to temporally dense Sentinel-1/2 imagery to produce annual refined wetland maps of the Dongting Lake Wetland (DLW) during 2015–2021. First, the continuous change detection (CCD) algorithm was utilized to migrate stable training samples. Then, annual 10 m preliminary land cover maps with 9 classes were produced using random forest algorithm and migrated samples. Ultimately, annual 10 m refined wetland maps were generated based on preliminary land cover maps via knowledge-driven rules from geometric features and available water-related inventories, with Overall Accuracy (OA) ranging from 81.82% (2015) to 93.84% (2020) and Kappa Coefficient (KC) between 0.73 (2015) and 0.91 (2020), demonstrating satisfactory performance and substantial potential for accurate, timely and type-refined wetland mapping. Our methodological framework allows rapid and accurate monitoring of wetland dynamics and could provide valuable information and methodological support for monitoring, conservation and sustainable development of wetland ecosystem. |
| first_indexed | 2024-03-11T22:59:51Z |
| format | Article |
| id | doaj.art-b4834edfbed64e84a11a5dfbdd3f0eaa |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T22:59:51Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-b4834edfbed64e84a11a5dfbdd3f0eaa2023-09-21T15:09:03ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552023-12-011613199322110.1080/17538947.2023.22414282241428Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imageryYawen Deng0Weiguo Jiang1Ziyan Ling2Xiaoya Wang3Kaifeng Peng4Zhuo Li5Beijing Normal UniversityBeijing Normal UniversityBeijing Normal UniversityBeijing Normal UniversityNanjing University of Information Science and TechnologyBeijing Normal UniversityWetlands provide vital ecological services for both humans and environment, necessitating continuous, refined and up-to-date mapping of wetlands for conservation and management. In this study, we developed an automated and refined wetland mapping framework integrating training sample migration method, supervised machine learning and knowledge-driven rules using Google Earth Engine (GEE) platform and open-source geospatial tools. We applied the framework to temporally dense Sentinel-1/2 imagery to produce annual refined wetland maps of the Dongting Lake Wetland (DLW) during 2015–2021. First, the continuous change detection (CCD) algorithm was utilized to migrate stable training samples. Then, annual 10 m preliminary land cover maps with 9 classes were produced using random forest algorithm and migrated samples. Ultimately, annual 10 m refined wetland maps were generated based on preliminary land cover maps via knowledge-driven rules from geometric features and available water-related inventories, with Overall Accuracy (OA) ranging from 81.82% (2015) to 93.84% (2020) and Kappa Coefficient (KC) between 0.73 (2015) and 0.91 (2020), demonstrating satisfactory performance and substantial potential for accurate, timely and type-refined wetland mapping. Our methodological framework allows rapid and accurate monitoring of wetland dynamics and could provide valuable information and methodological support for monitoring, conservation and sustainable development of wetland ecosystem.http://dx.doi.org/10.1080/17538947.2023.2241428wetland classification; continuous change detection algorithm; sample migrationtime seriesdongting lake wetlandgoogle earth engine |
| spellingShingle | Yawen Deng Weiguo Jiang Ziyan Ling Xiaoya Wang Kaifeng Peng Zhuo Li Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imagery International Journal of Digital Earth wetland classification; continuous change detection algorithm; sample migration time series dongting lake wetland google earth engine |
| title | Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imagery |
| title_full | Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imagery |
| title_fullStr | Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imagery |
| title_full_unstemmed | Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imagery |
| title_short | Automated and refined wetland mapping of Dongting Lake using migrated training samples based on temporally dense Sentinel 1/2 imagery |
| title_sort | automated and refined wetland mapping of dongting lake using migrated training samples based on temporally dense sentinel 1 2 imagery |
| topic | wetland classification; continuous change detection algorithm; sample migration time series dongting lake wetland google earth engine |
| url | http://dx.doi.org/10.1080/17538947.2023.2241428 |
| work_keys_str_mv | AT yawendeng automatedandrefinedwetlandmappingofdongtinglakeusingmigratedtrainingsamplesbasedontemporallydensesentinel12imagery AT weiguojiang automatedandrefinedwetlandmappingofdongtinglakeusingmigratedtrainingsamplesbasedontemporallydensesentinel12imagery AT ziyanling automatedandrefinedwetlandmappingofdongtinglakeusingmigratedtrainingsamplesbasedontemporallydensesentinel12imagery AT xiaoyawang automatedandrefinedwetlandmappingofdongtinglakeusingmigratedtrainingsamplesbasedontemporallydensesentinel12imagery AT kaifengpeng automatedandrefinedwetlandmappingofdongtinglakeusingmigratedtrainingsamplesbasedontemporallydensesentinel12imagery AT zhuoli automatedandrefinedwetlandmappingofdongtinglakeusingmigratedtrainingsamplesbasedontemporallydensesentinel12imagery |