Logo image
Data-driven geotechnical site recognition using machine learning and sparse representation
Journal article   Peer reviewed

Data-driven geotechnical site recognition using machine learning and sparse representation

Zheng Guan, Yu Wang and Kok-Kwang Phoon
Engineering geology, Vol.346, p.107893
21/02/2025

Abstract

Geotechnical site characterization Proper orthogonal decomposition Site recognition Sparse representation Spatial variability
To harness available generic geotechnical databases (i.e., the so-called big indirect data) as a supplement to sparse site-specific geotechnical data from a given site, it is crucial to first address the “site recognition challenge” (i.e., identification of sites similar to a target site from the generic database). Existing methods often quantify site similarity based solely on the multivariate distribution (or cross-correlations) of geotechnical properties, without accounting for similarity in spatial variation of geotechnical properties among different sites, potentially resulting in incomplete identification outcomes. To overcome this limitation, this study proposes a novel site recognition method for automatically identifying sites similar to a target site from a generic geotechnical database, based on similarity in spatial variation of geotechnical properties among different sites in a data-driven manner. In the proposed method, spatial variation basis modes of geotechnical properties for different sites are first extracted from existing geotechnical databases using machine learning methods. Then, geotechnical data from the target site is used to identify the site with similar spatial variation patterns from the databases using sparse representation and sparsity-promotion techniques. The effectiveness of the proposed method is demonstrated using a real geotechnical database (i.e., the ISSMGE TC304 database). •A novel site recognition method is proposed for identifying similar sites.•Spatial variation similarities across different sites are considered.•Machine learning methods are used to extract important spatial variation patterns.•The method is illustrated using real-world database.

Metrics

1 Record Views

Details

Logo image