ORIGINAL RESEARCH article
Front. Earth Sci.
Sec. Geohazards and Georisks
Mechanism Guided Forecasting Model for Landslide Displacement Prediction: Case Study For Baishuihe Landslide
Provisionally accepted
- 1Jiangsu Province Engineering Investigation and Research Institute Co., Ltd, yangzhou, China
- 2Yangzhou Polytechnic College, Yangzhou, 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 deformation process of landslides is characterized by step-like, abrupt increases and large displacement magnitudes, making precise early warning extremely challenging. To enhance prediction accuracy, this study develops a forecasting model. Grounded in a deep understanding of landslide evolution mechanisms, the model first utilizes Variational Mode Decomposition (VMD) to analyze the dynamic response relationship between displacement and influencing factors such as rainfall and reservoir water levels. Subsequently, the Double Exponential Smoothing (DES) method is applied to decompose cumulative displacement into trend and periodic components, thereby identifying effective external input features for the Informer machine learning model. The model further integrates a multi-head attention mechanism and pooling layers to accurately capture key periodic information within the time-series data. Using the Baishuihe Landslide in the Three Gorges Reservoir Area as a case study and validating the model with six consecutive years of monitoring data, the results demonstrate that the proposed model achieves high overall prediction accuracy, significantly outperforming mainstream models and achieving superior error control.
Keywords: deformation, displacement, Influencing factors, landslide, prediction
Received: 09 Jan 2026; Accepted: 03 Feb 2026.
Copyright: © 2026 Nianhong, wang and zhang. 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: Wang Nianhong
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.