Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning
Coseismic landslides often cause significant property damage and loss of life, necessitating timely and accurate detection for emergency response and hazard mitigation. Optical remote sensing imagery plays a critical role in landslide identification; however, sufficient high-resolution images might...
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/11002703/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849683921799741440 |
|---|---|
| author | Tianhe Ren Wenping Gong Jun Chen Liang Gao Jiahao Wu Xuyang Xiang |
| author_facet | Tianhe Ren Wenping Gong Jun Chen Liang Gao Jiahao Wu Xuyang Xiang |
| author_sort | Tianhe Ren |
| collection | DOAJ |
| description | Coseismic landslides often cause significant property damage and loss of life, necessitating timely and accurate detection for emergency response and hazard mitigation. Optical remote sensing imagery plays a critical role in landslide identification; however, sufficient high-resolution images might not be accessible after an earthquake. Traditional detection methods struggle with the coarse spatial details of low-resolution images, limiting their reliability in such scenarios. This study introduces a novel landslide mapping method leveraging the Trans-UNet model and a transfer learning strategy to overcome these challenges. The Trans-UNet model integrates a UNet-like encoder–decoder structure with a Transformer module to enhance global context extraction, a U-shaped full-scale feature extraction module to preserve multiscale spatial details, and a convolutional decoder for effective feature fusion and resolution restoration. During model training, a transfer learning strategy is employed to enhance the performance of the model on low-resolution images by utilizing rich feature information obtained from high-resolution images. In addition, this study constructs an open dataset of coseismic landslides triggered by the 2022 <italic>M<sub>S</sub></italic> 6.8 Luding earthquake, using the Gaofen-2 images with a 1-m resolution and the Sentinel-2 images with a 10-m resolution. The effectiveness and superiority of the proposed method are validated through its application to the Luding Landslide Dataset and comparisons with other state-of-the-art models. This method provides a reliable solution for rapid post-earthquake assessment in resource-constrained environments. |
| format | Article |
| id | doaj-art-1c0e28a290b14ca4bb2593df09019bde |
| 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-1c0e28a290b14ca4bb2593df09019bde2025-08-20T03:23:38ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118130741308610.1109/JSTARS.2025.356974311002703Coseismic Landslide Mapping Based on Trans-UNet and Transfer LearningTianhe Ren0https://orcid.org/0000-0003-3121-4020Wenping Gong1https://orcid.org/0000-0003-3062-313XJun Chen2https://orcid.org/0000-0001-9005-6849Liang Gao3https://orcid.org/0000-0002-1180-4384Jiahao Wu4Xuyang Xiang5https://orcid.org/0000-0002-0898-9568Faculty of Engineering, China University of Geosciences, Wuhan, ChinaFaculty of Engineering, China University of Geosciences, Wuhan, ChinaSchool of Automation, China University of Geosciences, Wuhan, ChinaState Key Laboratory of Internet of Things for Smart City and the Department of Ocean Science and Technology, University of Macau, Macao, ChinaState Key Laboratory of Internet of Things for Smart City and the Department of Ocean Science and Technology, University of Macau, Macao, ChinaChangjiang Institute of Survey Technical Research, Ministry of Water Resources, Wuhan, ChinaCoseismic landslides often cause significant property damage and loss of life, necessitating timely and accurate detection for emergency response and hazard mitigation. Optical remote sensing imagery plays a critical role in landslide identification; however, sufficient high-resolution images might not be accessible after an earthquake. Traditional detection methods struggle with the coarse spatial details of low-resolution images, limiting their reliability in such scenarios. This study introduces a novel landslide mapping method leveraging the Trans-UNet model and a transfer learning strategy to overcome these challenges. The Trans-UNet model integrates a UNet-like encoder–decoder structure with a Transformer module to enhance global context extraction, a U-shaped full-scale feature extraction module to preserve multiscale spatial details, and a convolutional decoder for effective feature fusion and resolution restoration. During model training, a transfer learning strategy is employed to enhance the performance of the model on low-resolution images by utilizing rich feature information obtained from high-resolution images. In addition, this study constructs an open dataset of coseismic landslides triggered by the 2022 <italic>M<sub>S</sub></italic> 6.8 Luding earthquake, using the Gaofen-2 images with a 1-m resolution and the Sentinel-2 images with a 10-m resolution. The effectiveness and superiority of the proposed method are validated through its application to the Luding Landslide Dataset and comparisons with other state-of-the-art models. This method provides a reliable solution for rapid post-earthquake assessment in resource-constrained environments.https://ieeexplore.ieee.org/document/11002703/Convolutional neural network (CNN)coseismic landslidelandslide mappingtransfer learningtransformer |
| spellingShingle | Tianhe Ren Wenping Gong Jun Chen Liang Gao Jiahao Wu Xuyang Xiang Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Convolutional neural network (CNN) coseismic landslide landslide mapping transfer learning transformer |
| title | Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning |
| title_full | Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning |
| title_fullStr | Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning |
| title_full_unstemmed | Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning |
| title_short | Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning |
| title_sort | coseismic landslide mapping based on trans unet and transfer learning |
| topic | Convolutional neural network (CNN) coseismic landslide landslide mapping transfer learning transformer |
| url | https://ieeexplore.ieee.org/document/11002703/ |
| work_keys_str_mv | AT tianheren coseismiclandslidemappingbasedontransunetandtransferlearning AT wenpinggong coseismiclandslidemappingbasedontransunetandtransferlearning AT junchen coseismiclandslidemappingbasedontransunetandtransferlearning AT lianggao coseismiclandslidemappingbasedontransunetandtransferlearning AT jiahaowu coseismiclandslidemappingbasedontransunetandtransferlearning AT xuyangxiang coseismiclandslidemappingbasedontransunetandtransferlearning |