Analysis of Ground Subsidence Evolution Characteristics and Attribution Along the Beijing–Xiong’an Intercity Railway with Time-Series InSAR and Explainable Machine-Learning Technique

Xin Liu, Huili Gong, Chaofan Zhou, Beibei Chen, Yanmin Su, Jiajun Zhu () and Wei Lu
Additional contact information
Xin Liu: Heilongjiang Institute of Ecological Geological Survey, 904 Building, 2299 Zhongyuan Avenue, Songbei District, Harbin 150028, China
Huili Gong: Key Laboratory of the Ministry of Education Land Subsidence Mechanism and Prevention, Capital Normal University, Beijing 100048, China
Chaofan Zhou: Key Laboratory of the Ministry of Education Land Subsidence Mechanism and Prevention, Capital Normal University, Beijing 100048, China
Beibei Chen: Key Laboratory of the Ministry of Education Land Subsidence Mechanism and Prevention, Capital Normal University, Beijing 100048, China
Yanmin Su: Heilongjiang Institute of Ecological Geological Survey, 904 Building, 2299 Zhongyuan Avenue, Songbei District, Harbin 150028, China
Jiajun Zhu: College of Resources Environment and Tourism, Capital Normal University, Beijing 100048, China
Wei Lu: Key Laboratory of the Ministry of Education Land Subsidence Mechanism and Prevention, Capital Normal University, Beijing 100048, China

Land, 2025, vol. 14, issue 2, 1-22

Abstract: The long-term overextraction of groundwater in the Beijing–Tianjin–Hebei region has led to the formation of the world’s largest groundwater depression cone and the most extensive land subsidence zone, posing a potential threat to the operational safety of high-speed railways in the region. As a critical transportation hub connecting Beijing and the Xiong’an New Area, the Beijing–Xiong’an Intercity Railway traverses geologically complex areas with significant ground subsidence issues. Monitoring and analyzing the causes of land subsidence along the railway are essential for ensuring its safe operation. Using Sentinel-1A radar imagery, this study applies PS-InSAR technology to extract the spatiotemporal evolution characteristics of ground subsidence along the railway from 2016 to 2022. By employing a buffer zone analysis and profile analysis, the subsidence patterns at different stages (pre-construction, construction, and operation) are revealed, identifying the major subsidence cones along the Yongding River, Yongqing, Daying, and Shengfang regions, and their impacts on the railway. Furthermore, the XGBoost model and SHAP method are used to quantify the primary influencing factors of land subsidence. The results show that changes in confined water levels are the most significant factor, contributing 34.5%, with strong interactions observed between the compressible layer thickness and confined water levels. The subsidence gradient analysis indicates that the overall subsidence gradient along the Beijing–Xiong’an Intercity Railway currently meets safety standards. This study provides scientific evidence for risk prevention and the control of land subsidence along the railway and holds significant implications for ensuring the safety of high-speed rail operations.

Keywords: PS-InSAR; explainable machine learning; land subsidence; evolution characteristics; attribution analysis (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/14/2/364/pdf (application/pdf)
https://www.mdpi.com/2073-445X/14/2/364/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:14:y:2025:i:2:p:364-:d:1587695

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().