Machine learning of geological details from borehole logs for development of high-resolution subsurface geological cross-section and geotechnical analysis

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

1 Scopus Citations
View graph of relations



Original languageEnglish
Number of pages19
Journal / PublicationGeorisk
Online published30 Sep 2021
Publication statusOnline published - 30 Sep 2021


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.

Research Area(s)

  • Multiple-point statistics, machine learning, sparse measurements, slope stability