A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing Imagery
Coastal wetland monitoring is essential for protecting marine and terrestrial ecosystems. However, the complex spatial, temporal, and spectral characteristics of these wetlands pose significant challenges for accurate mapping. Coastal wetlands exhibit high spatial heterogeneity due to varied landfor...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11077365/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850034409957228544 |
|---|---|
| author | Xiang Li Shenfu Zhang Qiang Liu Liang Chen Gang Yang Rui Zhao Weiwei Sun Feng Shao Xiangchao Meng |
| author_facet | Xiang Li Shenfu Zhang Qiang Liu Liang Chen Gang Yang Rui Zhao Weiwei Sun Feng Shao Xiangchao Meng |
| author_sort | Xiang Li |
| collection | DOAJ |
| description | Coastal wetland monitoring is essential for protecting marine and terrestrial ecosystems. However, the complex spatial, temporal, and spectral characteristics of these wetlands pose significant challenges for accurate mapping. Coastal wetlands exhibit high spatial heterogeneity due to varied landforms and fluctuating hydrological conditions. Temporal dynamics driven by seasonal cycles and tidal effects, along with spectral similarities across categories and variability within categories, further complicate accurate classification. Existing mapping methods struggle to integrate spatiotemporal and spectral information from time-series data, limiting their ability to model complex boundaries and dynamic changes. To address these challenges, we propose a deep temporal–spatial–spectral interaction learning framework for coastal wetland mapping using time-series remote sensing imagery. The model incorporates a multiscale, multidimensional convolutional module to extract and interact spatial, temporal, and spectral features. A hybrid transformer-convolution module enhances fine-grained feature extraction. While a temporal index extraction module and dual-focus attention module provide prior information, improve the accuracy of challenging wetland category identification. The feature fusion and adaptive classification module, dynamically assigning weights based on the importance of temporal, spatial, and spectral features for optimal information aggregation boosting classification performance. We validated the model using Sentinel-2 time-series multispectral datasets from the Yellow River Estuary, Yancheng coastal wetlands, and Hangzhou Bay. Experimental results demonstrate competitive performance: the overall accuracy reaches 98.07% for Yellow River Estuary, 91.55% for Yancheng, and 97.82% for Hangzhou Bay. |
| format | Article |
| id | doaj-art-57a5de210520473dbfc08ca198b2cfd6 |
| institution | DOAJ |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-57a5de210520473dbfc08ca198b2cfd62025-08-20T02:57:51ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118189411896110.1109/JSTARS.2025.358779811077365A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing ImageryXiang Li0Shenfu Zhang1Qiang Liu2https://orcid.org/0000-0002-9966-7803Liang Chen3https://orcid.org/0000-0002-2974-8616Gang Yang4https://orcid.org/0000-0002-7001-2037Rui Zhao5https://orcid.org/0000-0002-9577-7714Weiwei Sun6https://orcid.org/0000-0003-3399-7858Feng Shao7https://orcid.org/0000-0002-2495-9924Xiangchao Meng8https://orcid.org/0000-0002-7405-3143Faculty of Information Science and Engineering, Ningbo University, Ningbo, ChinaFaculty of Information Science and Engineering, Ningbo University, Ningbo, ChinaCollege of Computer and Artificial Intelligence, Huanghuai University, Zhumadian, ChinaFaculty of Information Science and Engineering, Ningbo University, Ningbo, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaFaculty of Information Science and Engineering, Ningbo University, Ningbo, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaFaculty of Information Science and Engineering, Ningbo University, Ningbo, ChinaFaculty of Information Science and Engineering, Ningbo University, Ningbo, ChinaCoastal wetland monitoring is essential for protecting marine and terrestrial ecosystems. However, the complex spatial, temporal, and spectral characteristics of these wetlands pose significant challenges for accurate mapping. Coastal wetlands exhibit high spatial heterogeneity due to varied landforms and fluctuating hydrological conditions. Temporal dynamics driven by seasonal cycles and tidal effects, along with spectral similarities across categories and variability within categories, further complicate accurate classification. Existing mapping methods struggle to integrate spatiotemporal and spectral information from time-series data, limiting their ability to model complex boundaries and dynamic changes. To address these challenges, we propose a deep temporal–spatial–spectral interaction learning framework for coastal wetland mapping using time-series remote sensing imagery. The model incorporates a multiscale, multidimensional convolutional module to extract and interact spatial, temporal, and spectral features. A hybrid transformer-convolution module enhances fine-grained feature extraction. While a temporal index extraction module and dual-focus attention module provide prior information, improve the accuracy of challenging wetland category identification. The feature fusion and adaptive classification module, dynamically assigning weights based on the importance of temporal, spatial, and spectral features for optimal information aggregation boosting classification performance. We validated the model using Sentinel-2 time-series multispectral datasets from the Yellow River Estuary, Yancheng coastal wetlands, and Hangzhou Bay. Experimental results demonstrate competitive performance: the overall accuracy reaches 98.07% for Yellow River Estuary, 91.55% for Yancheng, and 97.82% for Hangzhou Bay.https://ieeexplore.ieee.org/document/11077365/Classificationcoastal wetlandsdata fusiontemporal–spatial–spectral interactiontime-series data |
| spellingShingle | Xiang Li Shenfu Zhang Qiang Liu Liang Chen Gang Yang Rui Zhao Weiwei Sun Feng Shao Xiangchao Meng A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing Imagery IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Classification coastal wetlands data fusion temporal–spatial–spectral interaction time-series data |
| title | A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing Imagery |
| title_full | A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing Imagery |
| title_fullStr | A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing Imagery |
| title_full_unstemmed | A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing Imagery |
| title_short | A Temporal–Spatial–Spectral Fusion Framework for Coastal Wetland Mapping on Time-Series Remote Sensing Imagery |
| title_sort | temporal x2013 spatial x2013 spectral fusion framework for coastal wetland mapping on time series remote sensing imagery |
| topic | Classification coastal wetlands data fusion temporal–spatial–spectral interaction time-series data |
| url | https://ieeexplore.ieee.org/document/11077365/ |
| work_keys_str_mv | AT xiangli atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT shenfuzhang atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT qiangliu atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT liangchen atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT gangyang atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT ruizhao atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT weiweisun atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT fengshao atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT xiangchaomeng atemporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT xiangli temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT shenfuzhang temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT qiangliu temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT liangchen temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT gangyang temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT ruizhao temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT weiweisun temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT fengshao temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery AT xiangchaomeng temporalx2013spatialx2013spectralfusionframeworkforcoastalwetlandmappingontimeseriesremotesensingimagery |