ORIGINAL RESEARCH article
Front. Earth Sci.
Sec. Earth and Planetary Materials
Volume 13 - 2025 | doi: 10.3389/feart.2025.1604724
This article is part of the Research TopicAdvances in Structure, Characterization, and Failure Mechanisms of Geomaterials: Theoretical, Experimental, and Numerical ApproachesView all 9 articles
Research on Landslide Displacement Prediction in Reservoir Area Based on Deep Learning Combination Prediction Model
Provisionally accepted
- China Construction Eighth Bureau Engineering Research Institute, China Construction Eighth Engineering Division (China), pudong, Shanghai, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The prediction of landslide displacement in the Three Gorges Reservoir area is critically important for effective landslide monitoring and early warning; therefore, establishing a stable and reliable landslide displacement prediction model is essential. This study introduces a landslide displacement prediction method that integrates convolutional neural networks (CNN) with attention mechanisms. This model is validated through a case study of the Liujiabao landslide in the Three Gorges Reservoir area. A comprehensively analysis of 7-year monitoring data-including rainfall, reservoir water level, and surface displacement of the landslide-is conducted. This analysis facilitates the development of a CNN-GRU-Attention deep learning combination prediction model that combines CNN, gated recurrent unit (GRU) network, and attention mechanism. The model is trained using an adaptive learning rate to enhance its generalization capabilities while mitigating the risk of overfitting. Moreover, it is compared to traditional GRU models to assess its performance. The results show that this model significantly outperforms traditional machine learning and neural network methods in terms of landslide displacement prediction accuracy. Consequently, it offers valuable insights and guidance for landslide displacement prediction in the Three Gorges Reservoir area.
Keywords: Three Gorges Reservoir Area, Landslide displacement, GRU, attention mechanism, Prediction model
Received: 02 Apr 2025; Accepted: 19 May 2025.
Copyright: © 2025 Qi, Zhang, Ma, Sun, Wu and Dou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Yonggang Zhang, China Construction Eighth Bureau Engineering Research Institute, China Construction Eighth Engineering Division (China), pudong, Shanghai, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.