Special Collection on Benchmarking Data-Driven Site Characterization

Guest Editors:
Kok-Kwang Phoon, Professor, Singapore University of Technology and Design
Takayuki Shuku, Doctor, Okayama University
Jianye Ching, Professor, National Taiwan University
Ikumasa Yoshida, Professor, Tokyo City University

Data-driven site characterization (DDSC) is attracting attention given its exciting potential to realize an almost “real” subsurface digital model for Building Information Modeling (BIM) and digital twins. To promote the development of DDSC methods that are applicable to routine projects in a more purposeful way, one important step is to create reference geotechnical datasets and standard performance metrics to train and measure different DDSC methods on a uniform basis. This benchmark testing or benchmarking is widely used in machine learning (ML) to support unbiased and competitive evaluation of emerging ML methods. The papers published in this special collection constitute the first application of DDSC benchmarking using four types of virtual ground and two CPT layouts as training datasets.