An essential task in many geotechnical projects is delineation of subsurface soil stratigraphy from scatter measurements. Geotechnical engineers often use their knowledge on local geology and interpret soil strata boundaries by linear interpolation of measured data. This usual practice may encounter difficulties when interpreting complex deposits, particularly when measurements are limited. In this study, a novel nonparametric, data-driven method based on multiple point statistics (MPS) is proposed to interpolate subsurface soil stratigraphy from sparse measurements. MPS may be formulated as Bayesian supervised machine learning, which adaptively learns high-order spatial information (e.g., curvilinear features of soil layers) using sparse measurements obtained in a specific site and training image that reflects pre-existing engineering knowledge on similar geological settings. The proposed method is the first ever purely data-driven method (i.e., without using any pre-specified parametric functions) for geotechnical site characterization. The proposed method is illustrated by a simulated example and real data from a reclamation site in Hong Kong. The proposed method not only accurately interpolates the subsurface soil stratigraphy from sparse measurements, but also quantifies uncertainty associated with the interpolation. Effects of governing parameters in the proposed method are explicitly investigated, and parameters appropriate for subsurface soil stratigraphy are identified.

The subsurface geological cross-section is indispensable before design and construction of a geotechnical structure can commence. The development of geological cross-sections often requires significant manual efforts for simplification of stratigraphic boundaries. For example, straight lines are commonly used to connect stratum boundaries at adjacent boreholes, and soil layers with small thicknesses are often ignored. Such a simplification heavily relies on practitioners’ experience and may induce great uncertainties in the developed geological cross-sections and subsequent geotechnical analysis and design (e.g. slope stability analysis). In this study, a Bayesian supervised machine learning method, multiple-point statistics, is adopted to automatically generate high-resolution subsurface geological cross-section with proper incorporation of prior geological knowledge and all details observed from limited borehole logs. Locations and number of boreholes are automatically determined with due consideration of slope failure mechanism. The proposed method is demonstrated using an illustrative example. It is shown that the proposed method successfully captures geological details and local stratigraphic variations within a slope and quantifies the associated interpretation uncertainties. The geological details and local stratigraphic variations have great effects on the slope failure mechanism. There is a risk of overestimating overall slope stability if an over-simplified geological model is adopted for slope design.