EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images

Juan Li, Jin Zhang, Yongyong Fu

Sensors · 06.01.2025 · 25 (1) · 273

DOI: 10.3390/s25010273 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.01.2025. Verfasst von Juan Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, China. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Central Government Guides Local Science and Technology Development Special Fund Projects, Central Government Guides Local Science and Technology Development Special Fund Projects of Shanxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

CNNdeep learningdisaster extractionlandslide detectionremote sensing

Autor:innen und Institutionen

  • College of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, China.
  • Shanxi Institute of Surveying, Mapping and Geo-Information, Taiyuan 030001, China.
  • College of Resources and Environment, Shanxi University of Finance and Economics, Taiyuan 030006, China.

Förderung

  • National Natural Science Foundation of China
  • Central Government Guides Local Science and Technology Development Special Fund Projects
  • Central Government Guides Local Science and Technology Development Special Fund Projects of Shanxi Province

Zitieren

APA

Li, J., Zhang, J., & Fu, Y. (2025). CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images. Sensors, 25(1), 273. https://doi.org/10.3390/s25010273

Vancouver

Li J, Zhang J, Fu Y. CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images. Sensors. 2025;25(1):273. doi:10.3390/s25010273

BibTeX
@article{Li2025,
  author = {Li, Juan and Zhang, Jin and Fu, Yongyong},
  title = {CTHNet: A CNN–Transformer Hybrid Network for Landslide Identification in Loess Plateau Regions Using High-Resolution Remote Sensing Images},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {1},
  pages = {273},
  doi = {10.3390/s25010273}
}
Kostenlos starten →