Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learning
The learning-based integration of optical and synthetic aperture radar (SAR) satellite imagery is known to be effective in promoting the accuracy of wetland land-cover classification. However, the distribution of wetland categories is characterized as spatially heterogeneous and highly dynamic. It r...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843225000421 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087701489188864 |
|---|---|
| author | Linwei Yue Meiyue Wang Chengpeng Huang Qing Cheng Qiangqiang Yuan Huanfeng Shen |
| author_facet | Linwei Yue Meiyue Wang Chengpeng Huang Qing Cheng Qiangqiang Yuan Huanfeng Shen |
| author_sort | Linwei Yue |
| collection | DOAJ |
| description | The learning-based integration of optical and synthetic aperture radar (SAR) satellite imagery is known to be effective in promoting the accuracy of wetland land-cover classification. However, the distribution of wetland categories is characterized as spatially heterogeneous and highly dynamic. It remains a challenge to fuse the inherent characteristics of optical and SAR data by exploiting their discriminative feature representations for delineating wetland landscapes. To fully integrate the complementary information among optical and SAR data, a dual-branch deep network is proposed for mapping hierarchical wetland characteristics, which is referred to as HiWet-DBNet. Within the network, two parallel branches are designed to collaboratively learn the spatial, spectral or polarized, and temporal dependencies in the optical image and SAR image time series, respectively. Inspired by the relationships of deep and shallow features, the intra-layer features are fused across the branches to generate the multi-level wetland mapping results (i.e., general wetland land cover, and wetland vegetation types). The proposed method was tested on the Poyang Lake wetland in China using Sentinel-1 and Sentinel-2 imagery. The evaluation results show that the overall accuracy of HiWet-DBNet reaches 88.51% and 88.61% in the dry and wet seasons, which is superior to the other solutions with only a single data source or insufficient fusion of multi-modal features. For the challenging task of submerged vegetation detection, the producer’s accuracy of HiWet-DBNet is improved by 1.70% to 16.59% compared with the VBI algorithm and state-of-art deep learning-based wetland classification methods. |
| format | Article |
| id | doaj-art-3b84416982c549a0a04f6d54f8eb2a82 |
| institution | Kabale University |
| issn | 1569-8432 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-3b84416982c549a0a04f6d54f8eb2a822025-02-06T05:11:17ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-02-01136104395Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learningLinwei Yue0Meiyue Wang1Chengpeng Huang2Qing Cheng3Qiangqiang Yuan4Huanfeng Shen5School of Geography and Information Engineering, China University of Geosciences, Wuhan, PR China; Key Laboratory of Urban and Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen, PR China; Corresponding author.School of Geography and Information Engineering, China University of Geosciences, Wuhan, PR ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan, PR ChinaSchool of Computer Science, China University of Geosciences, Wuhan, PR China; Corresponding author.School of Geodesy and Geomatics, Wuhan University, Wuhan, PR ChinaSchool of Resources and Environmental Science, Wuhan University, Wuhan, PR ChinaThe learning-based integration of optical and synthetic aperture radar (SAR) satellite imagery is known to be effective in promoting the accuracy of wetland land-cover classification. However, the distribution of wetland categories is characterized as spatially heterogeneous and highly dynamic. It remains a challenge to fuse the inherent characteristics of optical and SAR data by exploiting their discriminative feature representations for delineating wetland landscapes. To fully integrate the complementary information among optical and SAR data, a dual-branch deep network is proposed for mapping hierarchical wetland characteristics, which is referred to as HiWet-DBNet. Within the network, two parallel branches are designed to collaboratively learn the spatial, spectral or polarized, and temporal dependencies in the optical image and SAR image time series, respectively. Inspired by the relationships of deep and shallow features, the intra-layer features are fused across the branches to generate the multi-level wetland mapping results (i.e., general wetland land cover, and wetland vegetation types). The proposed method was tested on the Poyang Lake wetland in China using Sentinel-1 and Sentinel-2 imagery. The evaluation results show that the overall accuracy of HiWet-DBNet reaches 88.51% and 88.61% in the dry and wet seasons, which is superior to the other solutions with only a single data source or insufficient fusion of multi-modal features. For the challenging task of submerged vegetation detection, the producer’s accuracy of HiWet-DBNet is improved by 1.70% to 16.59% compared with the VBI algorithm and state-of-art deep learning-based wetland classification methods.http://www.sciencedirect.com/science/article/pii/S1569843225000421Wetland mappingoptical and SARMulti-level classificationDeep learning |
| spellingShingle | Linwei Yue Meiyue Wang Chengpeng Huang Qing Cheng Qiangqiang Yuan Huanfeng Shen Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learning International Journal of Applied Earth Observations and Geoinformation Wetland mapping optical and SAR Multi-level classification Deep learning |
| title | Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learning |
| title_full | Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learning |
| title_fullStr | Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learning |
| title_full_unstemmed | Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learning |
| title_short | Mapping hierarchical wetland characteristics by optical-SAR integration with collaborative spatial-spectral-temporal learning |
| title_sort | mapping hierarchical wetland characteristics by optical sar integration with collaborative spatial spectral temporal learning |
| topic | Wetland mapping optical and SAR Multi-level classification Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S1569843225000421 |
| work_keys_str_mv | AT linweiyue mappinghierarchicalwetlandcharacteristicsbyopticalsarintegrationwithcollaborativespatialspectraltemporallearning AT meiyuewang mappinghierarchicalwetlandcharacteristicsbyopticalsarintegrationwithcollaborativespatialspectraltemporallearning AT chengpenghuang mappinghierarchicalwetlandcharacteristicsbyopticalsarintegrationwithcollaborativespatialspectraltemporallearning AT qingcheng mappinghierarchicalwetlandcharacteristicsbyopticalsarintegrationwithcollaborativespatialspectraltemporallearning AT qiangqiangyuan mappinghierarchicalwetlandcharacteristicsbyopticalsarintegrationwithcollaborativespatialspectraltemporallearning AT huanfengshen mappinghierarchicalwetlandcharacteristicsbyopticalsarintegrationwithcollaborativespatialspectraltemporallearning |