Land subsidence prediction model based on its influencing factors and machine learning methods

Abstract

Land subsidence has caused huge economic losses in the Beijing plains (BP) since 1980s. Building land subsidence prediction models that can predict the development of land subsidence is of great signi cance for improving the safety of cities and reducing economic losses in Eastern Beijing plains.The pattern of evolution of land subsidence is affected by many factors including groundwater level in different aquifers, thicknesses of compressible layers, and static and dynamic loads caused by urban construction. First, we used the small baseline subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology on 47 ENVISAT ASAR images and 48 RADARSAT-2 images and used Persistent Scatterers Interferometric Aperture Radar (PS-InSAR) technology on 27 Sentinel-1 images to obtain the land subsidence monitoring results from June 2003 to September 2018. Second, the accuracy of the InSAR monitoring results were validated by using leveling benchmark land subsidence monitoring results.Finally, we built land subsidence rate prediction models and land subsidence gradient prediction models by combining land subsidence in uencing factors and four machine learning methods including support vector machine (SVM), Gradient Boosting Decision Tree (GBDT), Random forest (RF) and Extremely Randomized Trees (ERT). The ndings show: (1) The InSAR monitoring results revealed that the maximum land subsidence rate reached − 110.7 mm/year, -144.4 mm/year and − 136.8 mm/year during the 2003-2010, 2011-2015 and 2016-2018 periods, respectively. (2): The InSAR monitoring results agreed well with the leveling benchmark monitoring results with the Pearson correlation coe cients of two monitoring results were 0.97, 0.96 and 0.95 during the 2003-2010, 2011-2015 and 2016-2018 periods, respectively. (3): We found that the land subsidence prediction based on ERT method is the optimal model among four land subsidence prediction models and that the prediction performance of land subsidence prediction model based on ERT method will be greatly improved when apply this prediction model in sub study areas where the land subsidence mechanism is similar owning to the similar hydrogeological parameters.

Enhancement of land subsidence prediction capabilities using machine learning and SHAP value analysis with Sentinel-1 InSAR Data

“…The majority of contemporary land subsidence prediction fields employ tree models. For example, Li et al (2023) used four machine learning approaches using support vector machine (SVM), gradient boosted decision tree (GBDT), random forest (RF), and extreme random tree (ERT) to create surface subsidence rate prediction model and surface subsidence gradient prediction model. Ebrahimy et al (2020) employed augmented regression tree (BRT), Random Forest (RF), and Classification and Regression Tree (CART) techniques to generate and compare Land Surface Sedimentation Sensitivity Maps (LSSM).…”

Optimization of land subsidence prediction features based on machine learning and SHAP value with Sentinel-1 InSAR Data

“…Most of the current fields of land subsidence prediction use tree models. For example, Li et al [14] used four machine learning methods using support vector machine (SVM), gradient boosted decision tree (GBDT), random forest (RF), and extreme random tree (ERT) to construct surface subsidence rate prediction model and surface subsidence gradient prediction model. Ebrahimy et al [15] used augmented regression tree ( BRT), Random Forest (RF), and Classification and Regression Tree (CART) methods to produce and compare Land Surface Sedimentation Sensitivity Maps (LSSM) and verified that the prediction accuracy of BRT model (AUROC=0.819) was higher than RF model (AUROC=0.798) and CART model (AUROC=0.764).…”

Urban Ground Subsidence Monitoring and Prediction Using Time-Series InSAR and Machine Learning Approaches: A Case Study of Tianjin, China

“…While InSAR techniques can accurately detect historical and current ground deformation, predicting future land subsidence remains a challenge. In recent years, machine learning and deep learning methods have emerged as promising approaches to overcome the limitations of traditional prediction methods, exhibiting vast potential in ground deformation forecasting (Li et al 2023; Wang et al 2023a; Xu et al 2023). Conventional machine learning techniques, such as Support Vector Machines (SVMs), Gradient Boosting Decision Trees (GBDTs), Random Forests (RFs), and Extremely Randomized Trees (ERTs), have demonstrated their effectiveness in ground deformation prediction (Dagès et Ma et al 2023).…”