Data-driven and physics-informed Bayesian learning of spatiotemporally varying consolidation settlement from sparse site investigation and settlement monitoring data

Tian, Hao; Wang, Yu

doi:10.1016/j.compgeo.2023.105328

Cited by 18 publications

(5 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data-driven and nonparametric methods, such as BCS [9], can be employed to interpret sparse CPT data (e.g., cone penetration resistance qc and sleeve friction fs) to generate N probable cross sections [13]. CPT-based correlations can also be adopted to relate CPT data (e.g., qc and fs) to different soil properties (e.g., compression index) required for geotechnical analysis empirically [10]. Thus, using the BCS and existing CPT-based correlations, N probable geological cross-sections (including soil properties) were obtained for geotechnical analysis [11].…”

Section: Dictionary Construction Using Fem Results Of Multiple Consol...mentioning

confidence: 99%

“…CPT-based correlations can also be adopted to relate CPT data (e.g., qc and fs) to different soil properties (e.g., compression index) required for geotechnical analysis empirically [10]. Thus, using the BCS and existing CPT-based correlations, N probable geological cross-sections (including soil properties) were obtained for geotechnical analysis [11]. Subsequently, an FEM was developed for each given geological cross section, as illustrated in figure 2(c).…”

Section: Dictionary Construction Using Fem Results Of Multiple Consol...mentioning

confidence: 99%

“…In this study, B 4D is constructed using multiple sets of geotechnical analysis outputs of different types, obtained using probable numerical models (e.g., FEM; see figure 2(c)). FEM models are developed from probable geological cross-sections automatically obtained based on sparse site investigation data and data-driven methods, such as Bayesian compressive sampling (BCS) [9,10]. In addition, multi-source monitoring data (e.g., figure 1(a)) are employed to identify non-trivial atoms and estimate the sparse weights, ω, in equation ( 1) [11].…”

Section: Multi-source Sparse Dictionary Learningmentioning

confidence: 99%

“…FEM models are developed from probable geological cross-sections automatically obtained based on sparse site investigation data and data-driven methods, such as Bayesian compressive sampling (BCS) [9,10]. In addition, multi-source monitoring data (e.g., figure 1(a)) are employed to identify non-trivial atoms and estimate the sparse weights, ω, in equation ( 1) [11]. An illustration of the proposed MS-SDL approach is provided below.…”

Section: Multi-source Sparse Dictionary Learningmentioning

confidence: 99%

See 3 more Smart Citations

Physics-informed machine learning of multi-source monitoring data sparsely measured within a 2D vertical cross-section

Tian,

Wang

2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Conventional machine learning (ML) methods suffer from several limitations, e.g., overreliance on large training datasets and poor performance in extrapolating beyond observations. Geotechnical monitoring data at specific sites are multi-sourced (e.g., settlement and horizontal displacement data). Moreover, each source of monitoring data may vary temporally and be sparsely measured, e.g., within a two-dimensional (2D) geological cross-section. Thus, effectively learning multi-source and limited monitoring data is difficult using existing ML methods. To address this challenge, this study proposes a physics-informed ML method combining geotechnical numerical models (e.g., the finite element model (FEM)) with sparse dictionary learning (SDL) methods. It uses a range of probable numerical model results corresponding to multiple, temporally varying responses in a 2D spatial range to construct a “dictionary” in SDL and employs multi-source and limited monitoring data to identify a few “atoms” from the constructed dictionary to improve model predictions. An engineering project for embankment construction is used to illustrate the proposed approach. Our results indicate that the proposed approach effectively integrates FEM results with multi-source and sparsely measured monitoring data and improves the predictions of multiple spatio-temporally varying geotechnical responses significantly, particularly those at subsequent time steps and unmonitored spatial locations within a 2D vertical cross-section.

show abstract

Section: Dictionary Construction Using Fem Results Of Multiple Consol...mentioning

confidence: 99%

Section: Dictionary Construction Using Fem Results Of Multiple Consol...mentioning

confidence: 99%

Section: Multi-source Sparse Dictionary Learningmentioning

confidence: 99%

Section: Multi-source Sparse Dictionary Learningmentioning

confidence: 99%

See 2 more Smart Citations

Physics-informed machine learning of multi-source monitoring data sparsely measured within a 2D vertical cross-section

Tian,

Wang

2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Nowadays, Bayesian methods have been widely applied in geotechnical engineering, such as the characterization of model uncertainties [7][8][9][10], updating of geotechnical parameters [1,11], and seismic liquefaction assessment and monitoring of liquefaction-induced settlement [12,13]. Bayesian compressive sensing/sampling (BCS) is an application of Bayesian methods in compressive sensing or sampling (CS) for efficient reconstruction of signals or images at low sampling rates [14].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Fusion Sampling Strategy Combining Geotechnical and Geophysical Data for Evaluating Two-Dimensional Soil Liquefaction Potential and Reconsolidation Settlement

et al. 2023

View full text Add to dashboard Cite

In engineering practice, properly characterizing the spatial distribution of soil liquefaction potential and induced surface settlement is essential for seismic hazard assessment and mitigation. However, geotechnical site investigations (e.g., cone penetration test (CPT)) usually provide limited and sparse data with high accuracy. Geophysical surveys provide abundant two-dimensional (2D) data, yet their accuracy is lower than that of geotechnical investigations. Moreover, correlating geotechnical and geophysical data can effectively reduce site investigation costs. This study proposes a data-driven adaptive fusion sampling strategy that automatically develops an assessment model of the spatial distribution of soil liquefaction potential from spatially sparse geotechnical data, performs monitoring of liquefaction-induced settlement, and integrates spatiotemporally unconstrained geophysical data to update the model systematically and quantitatively. The proposed strategy is illustrated using real data, and the results indicate that the proposed strategy overcomes the difficulty of generating high-resolution spatial distributions of liquefaction potential from sparse geotechnical data, enables more accurate judgment of settlement variations in local areas, and is an effective tool for site liquefaction hazard analysis.

show abstract

Autonomous steering control for tunnel boring machines

Zheng,

Luo,

Tan

et al. 2024

Automation in Construction

View full text Add to dashboard Cite

Data-driven and physics-informed Bayesian learning of spatiotemporally varying consolidation settlement from sparse site investigation and settlement monitoring data

Cited by 18 publications

References 63 publications

Physics-informed machine learning of multi-source monitoring data sparsely measured within a 2D vertical cross-section

Physics-informed machine learning of multi-source monitoring data sparsely measured within a 2D vertical cross-section

Adaptive Fusion Sampling Strategy Combining Geotechnical and Geophysical Data for Evaluating Two-Dimensional Soil Liquefaction Potential and Reconsolidation Settlement

Autonomous steering control for tunnel boring machines

Contact Info

Product

Resources

About