Kok Kwang Phoon, Singapore University of Technology and Design, kkphoon@sutd.edu.sg
Takayuki Shuku, Okayama University, shuku@cc.okayama-u.ac.jp

Data-centric geotechnics is an emerging field that advocates a “digital first” agenda. One aspect of this agenda is to develop methods that can make sense of actual data. The end goal for any analysis is to improve decision making in geotechnical engineering, which is always related to a project carried out at a specific site. A site-specific knowledge of the ground conditions is thus necessary. It is natural for data-driven site characterization (DDSC) to attract the most attention in data-centric geotechnics. The purpose of DDSC is to produce a 3D stratigraphic map of the subsurface volume below a full-scale project site and to estimate relevant engineering properties at each spatial point based on site investigation data at the target site and relevant Big Indirect Data (BID) from other sites. This will fill an existing gap in Building Information Modeling (BIM) where a digital model for the subsurface is largely missing. There is an exciting prospect to implement risk and reliability-informed design at the systems level using BIM as a platform. Benchmark testing or benchmarking is used in machine learning (ML) to support unbiased and competitive evaluation of emerging ML methods. Recently, the theme of benchmarking has been discussed in geotechnical engineering to accelerate the progress of DDSC. DDSC has received increasing attention and a number of DDSC methods have been proposed in the literature. This session strives to highlight recent advances in DDSC methods and their practical application. This session also discusses how to evaluate the performance of different DDSC methods in a balanced and unbiased ways.