Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 images
Wetlands have suffered from considerable degradation due to anthropogenic and natural disturbances in recent decades. Although some advancements have been made, effective methods that can produce large-scale wetland maps with detailed categories are still lacking due to the diversity and complexity...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X23002558 |
| _version_ | 1827985704551972864 |
|---|---|
| author | Kaifeng Peng Weiguo Jiang Peng Hou Zhifeng Wu Ziyan Ling Xiaoya Wang Zhenguo Niu Dehua Mao |
| author_facet | Kaifeng Peng Weiguo Jiang Peng Hou Zhifeng Wu Ziyan Ling Xiaoya Wang Zhenguo Niu Dehua Mao |
| author_sort | Kaifeng Peng |
| collection | DOAJ |
| description | Wetlands have suffered from considerable degradation due to anthropogenic and natural disturbances in recent decades. Although some advancements have been made, effective methods that can produce large-scale wetland maps with detailed categories are still lacking due to the diversity and complexity of wetland ecosystems. To address this issue, we developed a novel algorithm for detailed wetland types classification integrating k-fold random forest and hierarchical decision tree, and so named two-step classification algorithm. Firstly, the phenology-based features were composited based on time series Sentinel-1/2 images, and the k-fold random forest was used to extract five rough wetland types in Google Earth Engine platform. Secondly, the hierarchical decision tree designed based on geometric features was used to separate the rough wetland types into fourteen detailed types. Application of the two-step classification method in Northern, Central and Southern Asia (NCSA) resulted in a continental-scale wetland map with an overall accuracy of 90.0 ± 0.5%. Wetland types, including inland marsh, lake, river, coastal swamp, estuarine water, lagoon, shallow marine water, reservoir, canal/channel and agricultural pond, had good accuracy with both UA and PA over 77%. The remaining wetland types had moderate accuracy, with both UA and PA over 58%. As we calculated, total wetland areas of NCSA were 1,375,489.27 km2. Among the fourteen wetland categories, the inland marsh had the largest area (544,584.38 km2) and was primarily distributed in subarctic and humid continental climates, while the canal/channel had the smallest area (1,651.57 km2) and was primarily scattered in desert, semiarid and humid subtropical climates. The lake and floodplain shared generally large areas with value of 392,413.55 km2 and 173,255.71 km2 respectively, which were typically distributed across desert and semiarid climates. This study successfully mapped continental-scale wetlands with detailed categories at a 10-m spatial resolution, which can provide valuable information for the management of wetland ecosystems and facilitate the implementation of wetland-related sustainable development goals. |
| first_indexed | 2024-04-09T23:19:48Z |
| format | Article |
| id | doaj.art-89ae98b9242f43fb8d150bce89e3be13 |
| institution | Directory Open Access Journal |
| issn | 1470-160X |
| language | English |
| last_indexed | 2024-04-09T23:19:48Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj.art-89ae98b9242f43fb8d150bce89e3be132023-03-22T04:36:20ZengElsevierEcological Indicators1470-160X2023-04-01148110113Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 imagesKaifeng Peng0Weiguo Jiang1Peng Hou2Zhifeng Wu3Ziyan Ling4Xiaoya Wang5Zhenguo Niu6Dehua Mao7State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China; Beijing Key Laboratory for Remote Sensing of Environment and Digital Cities, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China; Corresponding authors at: State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China.Satellite Environment Centre, Ministry of Ecology and Environment, Beijing 100094, China; Corresponding authors at: State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China.School of Geography and Remote Sensing, Guangzhou University, Guangzhou 510006, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China; School of Geography and Planning, Nanning Normal University, Nanning 530001, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Wetland Ecology and Environment, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, ChinaWetlands have suffered from considerable degradation due to anthropogenic and natural disturbances in recent decades. Although some advancements have been made, effective methods that can produce large-scale wetland maps with detailed categories are still lacking due to the diversity and complexity of wetland ecosystems. To address this issue, we developed a novel algorithm for detailed wetland types classification integrating k-fold random forest and hierarchical decision tree, and so named two-step classification algorithm. Firstly, the phenology-based features were composited based on time series Sentinel-1/2 images, and the k-fold random forest was used to extract five rough wetland types in Google Earth Engine platform. Secondly, the hierarchical decision tree designed based on geometric features was used to separate the rough wetland types into fourteen detailed types. Application of the two-step classification method in Northern, Central and Southern Asia (NCSA) resulted in a continental-scale wetland map with an overall accuracy of 90.0 ± 0.5%. Wetland types, including inland marsh, lake, river, coastal swamp, estuarine water, lagoon, shallow marine water, reservoir, canal/channel and agricultural pond, had good accuracy with both UA and PA over 77%. The remaining wetland types had moderate accuracy, with both UA and PA over 58%. As we calculated, total wetland areas of NCSA were 1,375,489.27 km2. Among the fourteen wetland categories, the inland marsh had the largest area (544,584.38 km2) and was primarily distributed in subarctic and humid continental climates, while the canal/channel had the smallest area (1,651.57 km2) and was primarily scattered in desert, semiarid and humid subtropical climates. The lake and floodplain shared generally large areas with value of 392,413.55 km2 and 173,255.71 km2 respectively, which were typically distributed across desert and semiarid climates. This study successfully mapped continental-scale wetlands with detailed categories at a 10-m spatial resolution, which can provide valuable information for the management of wetland ecosystems and facilitate the implementation of wetland-related sustainable development goals.http://www.sciencedirect.com/science/article/pii/S1470160X23002558Wetland mappingTwo-step classificationK-fold random forestPhenology-based featuresHierarchical decision treeGoogle Earth Engine |
| spellingShingle | Kaifeng Peng Weiguo Jiang Peng Hou Zhifeng Wu Ziyan Ling Xiaoya Wang Zhenguo Niu Dehua Mao Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 images Ecological Indicators Wetland mapping Two-step classification K-fold random forest Phenology-based features Hierarchical decision tree Google Earth Engine |
| title | Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 images |
| title_full | Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 images |
| title_fullStr | Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 images |
| title_full_unstemmed | Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 images |
| title_short | Continental-scale wetland mapping: A novel algorithm for detailed wetland types classification based on time series Sentinel-1/2 images |
| title_sort | continental scale wetland mapping a novel algorithm for detailed wetland types classification based on time series sentinel 1 2 images |
| topic | Wetland mapping Two-step classification K-fold random forest Phenology-based features Hierarchical decision tree Google Earth Engine |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X23002558 |
| work_keys_str_mv | AT kaifengpeng continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images AT weiguojiang continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images AT penghou continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images AT zhifengwu continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images AT ziyanling continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images AT xiaoyawang continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images AT zhenguoniu continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images AT dehuamao continentalscalewetlandmappinganovelalgorithmfordetailedwetlandtypesclassificationbasedontimeseriessentinel12images |