ORIGINAL RESEARCH article
Front. Earth Sci.
Sec. Geohazards and Georisks
This article is part of the Research TopicMonitoring, Early Warning and Mitigation of Natural and Engineered Slopes – Volume VView all 10 articles
The Evaluation of Landslide Comprehensive Susceptibility Based on Stacking Ensemble Learning Fusion Model and SBAS-InSAR: a case study in Lexi highway
Provisionally accepted
- 1Chengdu University of Technology, Chengdu, China
- 2Sichuan Lexi Expressway Co., Ltd., Chengdu, 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
Frequent landslides along the Lexi highway have significantly hindered the construction and operation of engineering projects and regional development. To clarify the distribution patterns and regional risks of landslides, this paper first constructed an ensemble learning fusion model combining Random Forest (RF) and Extreme Gradient Boosting (XGBoost) using a Stacking algorithm to evaluate landslide susceptibility on the Lexi highway. Next, SBAS-InSAR method was used to analyze long-term data from Sentinel-1A's ascending and descending orbits, enabling the determination of surface deformation rates in the study area. Finally, a comprehensive susceptibility evaluation matrix was utilized, combining susceptibility results with regional surface deformation rates to generate a landslide comprehensive susceptibility map. The specific research conclusions are as follows: Landslide sites are densely distributed along the Lexi highway, with an areal density of 15 landslides per 100 km² and a linear density of 0.89 landslides per kilometer; The influence of distance to the fault zones, human activity intensity and rainfall on the distribution of landslides along the Lexi highway is the most significant, with the importance indexes of 0.27、0.24、0.21, respectively; Compared to other models, the Stacking ensemble learning fusion model shows superior predictive performance and generalization ability, achieving an AUC of 0.977 in evaluating landslide susceptibility along the Lexi highway; The landslide comprehensive susceptibility map effectively identifies regions with significant deformation, reducing very low and low susceptibility zones while increasing very high susceptibility zones by about 1.1%; This improvement enhances landslide susceptibility accuracy and reduces false alarms in areas with intensive engineering and high deformation rates.
Keywords: Lexi highway1, SBAS-InSAR2, ensemble learning3, landslide4, susceptibility5
Received: 29 Jul 2025; Accepted: 12 Nov 2025.
Copyright: © 2025 Li, Li, Lan, Ren, Wen and Cai. 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: Tianbin Li, ltb@cdut.edu.cn
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.