Details
| Original language | English |
|---|---|
| Pages (from-to) | 3625-3639 |
| Number of pages | 15 |
| Journal | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Volume | 18 |
| Publication status | Published - 26 Dec 2024 |
Abstract
Land subsidence is a widespread geo-hazard, and it can be effectively monitored with the Interferometric Synthetic Aperture Radar (InSAR) technique. Assessing land subsidence plays a significant role in ensuring safety and enhancing disaster prevention. It requires not only focusing on the extent or rate of deformation but also evaluating the susceptibility and risk of subsidence. In this article, we propose a new comprehensive subsidence susceptibility and risk assessment strategy by integrating InSAR observation and hybrid machine learning models, which is first and successfully employed over Xi'an area. In this study, four machine learning models are compared to determine the optimal model, and found that the Random Forest (RF) performs the best in predicting InSAR-derived spatial deformation (Root Mean Square Error = 3.53 mm) and susceptibility (Area Under the Curve = 0.97). Also, the authenticity and reliability of the susceptibility results from RF model are improved by further Isotonic regression calibration processes. Then, subsidence risk map is obtained from the hazard and vulnerability assessment using the Analytic Hierarchy Process by combining multiple conditional factors. Remarkably, the results revealed that regions with the very high and high risk level of subsidence are 12.33 km2 and correspond to 1.34% of the total. It further found that the groundwater level and its changes are the domain factors in Xi'an from machine learning method. This work provides an integrated assessment approach for subsidence from a new perspective, and the findings can serve as theoretical support for early warning and disaster prevention.
Keywords
- Interferometric Synthetic Aperture Radar (InSAR), land subsidence, machine learning, susceptibility and risk mapping
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
- Earth and Planetary Sciences(all)
- Atmospheric Science
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 18, 26.12.2024, p. 3625-3639.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Mapping Susceptibility and Risk of Land Subsidence by Integrating InSAR and Hybrid Machine Learning Models
T2 - A Case Study in Xi'an, China
AU - Chen, Chen
AU - Peng, Mimi
AU - Motagh, Mahdi
AU - Guo, Xinxin
AU - Xing, Mengdao
AU - Quan, Yinghui
N1 - Publisher Copyright: © 2008-2012 IEEE.
PY - 2024/12/26
Y1 - 2024/12/26
N2 - Land subsidence is a widespread geo-hazard, and it can be effectively monitored with the Interferometric Synthetic Aperture Radar (InSAR) technique. Assessing land subsidence plays a significant role in ensuring safety and enhancing disaster prevention. It requires not only focusing on the extent or rate of deformation but also evaluating the susceptibility and risk of subsidence. In this article, we propose a new comprehensive subsidence susceptibility and risk assessment strategy by integrating InSAR observation and hybrid machine learning models, which is first and successfully employed over Xi'an area. In this study, four machine learning models are compared to determine the optimal model, and found that the Random Forest (RF) performs the best in predicting InSAR-derived spatial deformation (Root Mean Square Error = 3.53 mm) and susceptibility (Area Under the Curve = 0.97). Also, the authenticity and reliability of the susceptibility results from RF model are improved by further Isotonic regression calibration processes. Then, subsidence risk map is obtained from the hazard and vulnerability assessment using the Analytic Hierarchy Process by combining multiple conditional factors. Remarkably, the results revealed that regions with the very high and high risk level of subsidence are 12.33 km2 and correspond to 1.34% of the total. It further found that the groundwater level and its changes are the domain factors in Xi'an from machine learning method. This work provides an integrated assessment approach for subsidence from a new perspective, and the findings can serve as theoretical support for early warning and disaster prevention.
AB - Land subsidence is a widespread geo-hazard, and it can be effectively monitored with the Interferometric Synthetic Aperture Radar (InSAR) technique. Assessing land subsidence plays a significant role in ensuring safety and enhancing disaster prevention. It requires not only focusing on the extent or rate of deformation but also evaluating the susceptibility and risk of subsidence. In this article, we propose a new comprehensive subsidence susceptibility and risk assessment strategy by integrating InSAR observation and hybrid machine learning models, which is first and successfully employed over Xi'an area. In this study, four machine learning models are compared to determine the optimal model, and found that the Random Forest (RF) performs the best in predicting InSAR-derived spatial deformation (Root Mean Square Error = 3.53 mm) and susceptibility (Area Under the Curve = 0.97). Also, the authenticity and reliability of the susceptibility results from RF model are improved by further Isotonic regression calibration processes. Then, subsidence risk map is obtained from the hazard and vulnerability assessment using the Analytic Hierarchy Process by combining multiple conditional factors. Remarkably, the results revealed that regions with the very high and high risk level of subsidence are 12.33 km2 and correspond to 1.34% of the total. It further found that the groundwater level and its changes are the domain factors in Xi'an from machine learning method. This work provides an integrated assessment approach for subsidence from a new perspective, and the findings can serve as theoretical support for early warning and disaster prevention.
KW - Interferometric Synthetic Aperture Radar (InSAR)
KW - land subsidence
KW - machine learning
KW - susceptibility and risk mapping
UR - http://www.scopus.com/inward/record.url?scp=85213419273&partnerID=8YFLogxK
U2 - 10.1109/JSTARS.2024.3522995
DO - 10.1109/JSTARS.2024.3522995
M3 - Article
AN - SCOPUS:85213419273
VL - 18
SP - 3625
EP - 3639
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
SN - 1939-1404
ER -