Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral features
Landslides frequently cause serious property damage and casualties. Therefore, it is crucial to have rapid and accurate landslide mapping (LM) to support post-earthquake landslide damage assessment and emergency rescue efforts. Many studies have been conducted in recent years on the application of a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223004363 |
| _version_ | 1797357798582910976 |
|---|---|
| author | Lei Wu Rui Liu Nengpan Ju Ao Zhang Jingsong Gou Guolei He Yuzhu Lei |
| author_facet | Lei Wu Rui Liu Nengpan Ju Ao Zhang Jingsong Gou Guolei He Yuzhu Lei |
| author_sort | Lei Wu |
| collection | DOAJ |
| description | Landslides frequently cause serious property damage and casualties. Therefore, it is crucial to have rapid and accurate landslide mapping (LM) to support post-earthquake landslide damage assessment and emergency rescue efforts. Many studies have been conducted in recent years on the application of automatic LM methods using remote sensing images (RSIs). However, existing methods face challenges in accurately distinguishing landslides due to the problems of large differences in features and scales among landslides, as well as similarities among different ground objects in optical RSIs. Here, we propose a semantic segmentation model called SCDUNet++, which combines the advantages of convolutional neural network (CNN) and transformer to enhance the discrimination and extraction of landslide features. Then, we constructed a multi-channel landslide dataset in the Luding and Jiuzhaigou earthquake areas using Sentinel-2 and NASADEM data. We evaluated the performance of SCDUNet++ on this dataset. The results showed that SCDUNet++ can extract and fuse spectral and topographic information more effectively. Compared with other state-of-the-art models, SCDUNet++ achieved the highest IoU and F1 score in all four test areas. In addition, the models achieved significant improvements in mapping the landslides of the Jiuzhaigou area after knowledge transfer and fine-tuning. Compared with direct prediction, eight models, namely DeepLabv3+, Segformer, TransUNet, SwinUNet, STUNet, UNet, UNet++, and SCDUNet++, demonstrated improvements in IoU ranging from 8.33% to 27.5% and F1 from 6.58% to 23.67% after implementing deep transfer learning (DTL). This finding highlights the significant practicality of using DTL for cross-domain LM in data-poor areas. |
| first_indexed | 2024-03-08T14:50:25Z |
| format | Article |
| id | doaj.art-badcdd2fdee44207a1944a584ecac584 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-08T14:50:25Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-badcdd2fdee44207a1944a584ecac5842024-01-11T04:30:27ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-02-01126103612Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral featuresLei Wu0Rui Liu1Nengpan Ju2Ao Zhang3Jingsong Gou4Guolei He5Yuzhu Lei6State Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology), Chengdu 610059, China; College of Geophysics, Chengdu University of Technology, Chengdu 610059, China; Key Lab of Earth Exploration and Information Technique of Ministry Education, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology), Chengdu 610059, China; College of Geophysics, Chengdu University of Technology, Chengdu 610059, China; Key Lab of Earth Exploration and Information Technique of Ministry Education, Chengdu University of Technology, Chengdu 610059, China; Corresponding author at: Chengdu University of Technology, Chengdu 610059, China.State Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology), Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology), Chengdu 610059, China; College of Geophysics, Chengdu University of Technology, Chengdu 610059, China; Key Lab of Earth Exploration and Information Technique of Ministry Education, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology), Chengdu 610059, China; College of Geophysics, Chengdu University of Technology, Chengdu 610059, China; Key Lab of Earth Exploration and Information Technique of Ministry Education, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology), Chengdu 610059, China; College of Geophysics, Chengdu University of Technology, Chengdu 610059, China; Key Lab of Earth Exploration and Information Technique of Ministry Education, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology), Chengdu 610059, China; College of Geophysics, Chengdu University of Technology, Chengdu 610059, China; Key Lab of Earth Exploration and Information Technique of Ministry Education, Chengdu University of Technology, Chengdu 610059, ChinaLandslides frequently cause serious property damage and casualties. Therefore, it is crucial to have rapid and accurate landslide mapping (LM) to support post-earthquake landslide damage assessment and emergency rescue efforts. Many studies have been conducted in recent years on the application of automatic LM methods using remote sensing images (RSIs). However, existing methods face challenges in accurately distinguishing landslides due to the problems of large differences in features and scales among landslides, as well as similarities among different ground objects in optical RSIs. Here, we propose a semantic segmentation model called SCDUNet++, which combines the advantages of convolutional neural network (CNN) and transformer to enhance the discrimination and extraction of landslide features. Then, we constructed a multi-channel landslide dataset in the Luding and Jiuzhaigou earthquake areas using Sentinel-2 and NASADEM data. We evaluated the performance of SCDUNet++ on this dataset. The results showed that SCDUNet++ can extract and fuse spectral and topographic information more effectively. Compared with other state-of-the-art models, SCDUNet++ achieved the highest IoU and F1 score in all four test areas. In addition, the models achieved significant improvements in mapping the landslides of the Jiuzhaigou area after knowledge transfer and fine-tuning. Compared with direct prediction, eight models, namely DeepLabv3+, Segformer, TransUNet, SwinUNet, STUNet, UNet, UNet++, and SCDUNet++, demonstrated improvements in IoU ranging from 8.33% to 27.5% and F1 from 6.58% to 23.67% after implementing deep transfer learning (DTL). This finding highlights the significant practicality of using DTL for cross-domain LM in data-poor areas.http://www.sciencedirect.com/science/article/pii/S1569843223004363Convolutional neural networkDeep transfer learningLandslide mappingRemote sensing dataTransformer |
| spellingShingle | Lei Wu Rui Liu Nengpan Ju Ao Zhang Jingsong Gou Guolei He Yuzhu Lei Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral features International Journal of Applied Earth Observations and Geoinformation Convolutional neural network Deep transfer learning Landslide mapping Remote sensing data Transformer |
| title | Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral features |
| title_full | Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral features |
| title_fullStr | Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral features |
| title_full_unstemmed | Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral features |
| title_short | Landslide mapping based on a hybrid CNN-transformer network and deep transfer learning using remote sensing images with topographic and spectral features |
| title_sort | landslide mapping based on a hybrid cnn transformer network and deep transfer learning using remote sensing images with topographic and spectral features |
| topic | Convolutional neural network Deep transfer learning Landslide mapping Remote sensing data Transformer |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223004363 |
| work_keys_str_mv | AT leiwu landslidemappingbasedonahybridcnntransformernetworkanddeeptransferlearningusingremotesensingimageswithtopographicandspectralfeatures AT ruiliu landslidemappingbasedonahybridcnntransformernetworkanddeeptransferlearningusingremotesensingimageswithtopographicandspectralfeatures AT nengpanju landslidemappingbasedonahybridcnntransformernetworkanddeeptransferlearningusingremotesensingimageswithtopographicandspectralfeatures AT aozhang landslidemappingbasedonahybridcnntransformernetworkanddeeptransferlearningusingremotesensingimageswithtopographicandspectralfeatures AT jingsonggou landslidemappingbasedonahybridcnntransformernetworkanddeeptransferlearningusingremotesensingimageswithtopographicandspectralfeatures AT guoleihe landslidemappingbasedonahybridcnntransformernetworkanddeeptransferlearningusingremotesensingimageswithtopographicandspectralfeatures AT yuzhulei landslidemappingbasedonahybridcnntransformernetworkanddeeptransferlearningusingremotesensingimageswithtopographicandspectralfeatures |