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 profile of geotechnical properties is often needed for geotechnical design and analysis. However, site-specific data might be characterized as MUSIC-X (i.e., Multivariate, Uncertain and Unique, Sparse, Incomplete, and potentially Corrupted with “X” denoting the spatial/temporal variability), posing a significant challenge in accurately interpreting geotechnical property profiles. Different sources, or types, of data are commonly available from a specific site investigation program, and they are usually cross-correlated, and thus can provide complementary information. This leads to an important question in geotechnical site investigation: how to integrate multiple sources of sparse data for enhancing the profiling of different geotechnical properties. To address this issue, this study proposes a novel method, called fusion Bayesian compressive sampling (Fusion-BCS), for integrating sparse and non-co-located geotechnical data. In the proposed method, the auto- and cross-correlation structures of different sources of data are exploited in a data-driven manner through a joint sparse representation. Then, profiles of different geotechnical properties are jointly reconstructed from all measurements under a framework of compressive sampling/sensing. The proposed method is illustrated using simulated and real geotechnical data. The results indicate that the accuracy of the interpreted geotechnical property profiles may be significantly improved by integrating multiple sources of site investigation data.

Due to time, budget, and/or technical constraints, geotechnical site investigation data from a specific site are often limited and sparse, leading to a long-lasting challenge in characterization of spatially varying geotechnical properties. During preliminary stages of site characterization, geotechnical data from neighboring sites or sites with similar geological conditions are often collected and used as valuable prior knowledge in geotechnical engineering practice. Nevertheless, existing methods for spatial variability characterization often rely solely on site-specific data and cannot effectively incorporate prior knowledge or existing databases. To address this issue, this study proposes a novel machine learning method that systematically combines sparsely measured data at a specific site with existing data from neighboring sites or sites with similar geological settings for characterization of property spatial variability in a data-driven manner. The proposed method starts with the construction of a dictionary that draws the dominant spatially varying patterns from a property measured at sites with similar geology under a dictionary learning framework. Leveraging the developed dictionary, the spatial variability of a property is interpreted from sparse site-specific measurements using Bayesian learning. The effectiveness of the proposed method is demonstrated using real data, and improved performance over existing methods is observed.