Bayesian Back Analysis of Spatial Variability with Machine Learning Surrogates

作     者：Chen, Xiaoying Wang, Shen Yang, Hao-Qing Zhang, Lulu Tang, Chao-Sheng 

作者机构：Nanjing Univ Sch Earth Sci & Engn 163 Xianlin Ave Nanjing 210023 Peoples R China Southwest Jiaotong Univ SWJTU Leeds Joint Sch 999 Xian Rd Chengdu 611756 Peoples R China Univ Leeds Sch Civil Engn Woodhouse Ln Leeds LS2 9JT England Nanyang Technol Univ Sch Civil & Environm Engn 50 Nanyang Ave Singapore 639798 Singapore Shanghai Jiao Tong Univ Dept Civil Engn State Key Lab Ocean Engn Shanghai 200240 Peoples R China 

出 版 物：《ASCE-ASME JOURNAL OF RISK AND UNCERTAINTY IN ENGINEERING SYSTEMS PART A-CIVIL ENGINEERING》 (ASCE-ASME J. Risk Uncertain. Eng. Syst. Part A. Civ. Eng.)

年 卷 期：2025年第11卷第2期

核心收录：

基　　金：Natural Science Foundation of China [52025094, 51979158] Shanghai Municipal Education Commission [2021-01-07-00-02-E00089] Key Projects for Intergovernmental Cooperation in International Science, Technology, and Innovation [2018YFE0125100] 

主　　题：Back analysis Spatial variability Machine learning Surrogate model Bayesian inference 

摘      要：Geotechnical sensors provide the advantage of directly monitoring model responses that accurately reflect field conditions. Within these field monitoring data lies the latent potential to glean insights into soil parameters. Beyond relying solely on site-investigation data, the incorporation of field monitoring data serves as a valuable complementary strategy. It aids in evaluating soil spatial variability and addressing uncertainties related to field responses. In this study, a surrogate-based Bayesian back-analysis method is proposed to assess the spatial variability in ground profiles and the uncertainty of field responses. The surrogate models are constructed using machine learning algorithms. To validate the effectiveness of the proposed approach and select the optimal machine learning surrogates, a hypothetical example involving an unsaturated soil slope subjected to rainfall infiltration is first employed. The proposed method is further applied to a hydraulic monitoring project in Hong Kong. The results demonstrate the promising potential of Gaussian process regression with the Matern 5/2 kernel based on 100 training samples for training surrogate models. The saturated hydraulic conductivity obtained from the maximum a posterior (MAP) and borehole logs exhibit similarity, and the MAP estimate accurately captures the observed spatial variation in the dynamic probe test. The proposed method can effectively estimate the soil spatial variability and provides reasonable uncertainty predictions of pore pressure head.