CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images
The Loess Plateau in northwest China features fragmented terrain and is prone to landslides. However, the complex environment of the Loess Plateau, combined with the inherent limitations of convolutional neural networks (CNNs), often results in false positives and missed detection for deep learning...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/273 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548926867472384 |
|---|---|
| author | Juan Li Jin Zhang Yongyong Fu |
| author_facet | Juan Li Jin Zhang Yongyong Fu |
| author_sort | Juan Li |
| collection | DOAJ |
| description | The Loess Plateau in northwest China features fragmented terrain and is prone to landslides. However, the complex environment of the Loess Plateau, combined with the inherent limitations of convolutional neural networks (CNNs), often results in false positives and missed detection for deep learning models based on CNNs when identifying landslides from high-resolution remote sensing images. To deal with this challenge, our research introduced a CNN–transformer hybrid network. Specifically, we first constructed a database consisting of 1500 loess landslides and non-landslide samples. Subsequently, we proposed a neural network architecture that employs a CNN–transformer hybrid as an encoder, with the ability to extract high-dimensional, local-scale features using CNNs and global-scale features using a multi-scale lightweight transformer module, thereby enabling the automatic identification of landslides. The results demonstrate that this model can effectively detect loess landslides in such complex environments. Compared to approaches based on CNNs or transformers, such as U-Net, HCNet and TransUNet, our proposed model achieved greater accuracy, with an improvement of at least 3.81% in the F1-score. This study contributes to the automatic and intelligent identification of landslide locations and ranges on the Loess Plateau, which has significant practicality in terms of landslide investigation, risk assessment, disaster management, and related fields. |
| format | Article |
| id | doaj-art-75c6d9d80a9143af824aa009d3e91791 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-75c6d9d80a9143af824aa009d3e917912025-01-10T13:21:26ZengMDPI AGSensors1424-82202025-01-0125127310.3390/s25010273CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing ImagesJuan Li0Jin Zhang1Yongyong Fu2College of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Resources and Environment, Shanxi University of Finance and Economics, Taiyuan 030006, ChinaThe Loess Plateau in northwest China features fragmented terrain and is prone to landslides. However, the complex environment of the Loess Plateau, combined with the inherent limitations of convolutional neural networks (CNNs), often results in false positives and missed detection for deep learning models based on CNNs when identifying landslides from high-resolution remote sensing images. To deal with this challenge, our research introduced a CNN–transformer hybrid network. Specifically, we first constructed a database consisting of 1500 loess landslides and non-landslide samples. Subsequently, we proposed a neural network architecture that employs a CNN–transformer hybrid as an encoder, with the ability to extract high-dimensional, local-scale features using CNNs and global-scale features using a multi-scale lightweight transformer module, thereby enabling the automatic identification of landslides. The results demonstrate that this model can effectively detect loess landslides in such complex environments. Compared to approaches based on CNNs or transformers, such as U-Net, HCNet and TransUNet, our proposed model achieved greater accuracy, with an improvement of at least 3.81% in the F1-score. This study contributes to the automatic and intelligent identification of landslide locations and ranges on the Loess Plateau, which has significant practicality in terms of landslide investigation, risk assessment, disaster management, and related fields.https://www.mdpi.com/1424-8220/25/1/273landslide detectiondisaster extractiondeep learningCNNremote sensing |
| spellingShingle | Juan Li Jin Zhang Yongyong Fu CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images Sensors landslide detection disaster extraction deep learning CNN remote sensing |
| title | CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images |
| title_full | CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images |
| title_fullStr | CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images |
| title_full_unstemmed | CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images |
| title_short | CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images |
| title_sort | cthnet a cnn transformer hybrid network for landslide identification in loess plateau regions using high resolution remote sensing images |
| topic | landslide detection disaster extraction deep learning CNN remote sensing |
| url | https://www.mdpi.com/1424-8220/25/1/273 |
| work_keys_str_mv | AT juanli cthnetacnntransformerhybridnetworkforlandslideidentificationinloessplateauregionsusinghighresolutionremotesensingimages AT jinzhang cthnetacnntransformerhybridnetworkforlandslideidentificationinloessplateauregionsusinghighresolutionremotesensingimages AT yongyongfu cthnetacnntransformerhybridnetworkforlandslideidentificationinloessplateauregionsusinghighresolutionremotesensingimages |