报告题目：Machine learning of soil stratigraphy and property variability for geotechnical analysis and design
报告人：Prof. WANG Yu City University of Hong Kong
报告时间：2022年6月30日 下午15:00-17:00
报告地点：线上腾讯会议ID：470-903-250
主办单位：轨道交通学院
Abstract:
Geotechnical analysis and design are greatly affected by spatial distribution of subsurface zones with different soil types (i.e., stratigraphic heterogeneities and uncertainty) and spatial variability of soil properties. In current practice, geotechnical analysis and design often use simplified stratigraphic boundaries (e.g., connecting the same stratigraphic boundaries between adjacent boreholes or CPTs by straight lines) without considering stratigraphic uncertainty or soil property spatial variability. This practice might encounter difficulty for complicated subsurface stratigraphic profiles (e.g., interbedded alluvial sand/clay layers or lens often found for reclamations in Hong Kong), particularly when the site-specific measurements are sparse. In this presentation, a data-driven framework is proposed for geotechnical analysis and design with explicit modeling of stratigraphic uncertainty and spatial variability of soil properties by machine learning of limited site investigation data (e.g., CPT data). Performance of the proposed framework is demonstrated using an illustrative example, which is modified from a real reclamation project in Hong Kong. Machine learning offers an effective, automatic, and fast way of developing soil stratigraphic and geotechnical analysis models from limited site investigation data for geotechnical design.
About the speaker:
Dr. Yu Wang is a professor of geotechnical engineering at City University of Hong Kong and an elected Fellow of American Society of Civil Engineers (ASCE). His recent research efforts have focused on digital twin of subsurface geo-structures, machine learning in geotechnical engineering, analytics and simulation of geo-data, geotechnical uncertainty, reliability and risk, soil-structure interaction, and seismic risk assessment of critical civil infrastructure systems. His research has earned a number of international/national recognitions, including the 2020 Best Paper Award by the ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, the 2020 Higher Education Outstanding Scientific Research Output Awards (the First-class Natural Science Award) by the Ministry of Education, China, the Highly Cited Research Award by the international journal of Engineering Geology in 2017, the GEOSNet Young Researcher Award by the Geotechnical Safety Network (GEOSNet) in 2015 in the Netherlands, and the Wilson Tang Best Paper Award in 2012 in Singapore. Dr Wang has authored/co-authored over 130 SCI-listed journal papers and two books. He served as president of ASCE Hong Kong Section in 2012-2013 and currently serves in editorial boards of several top journals in geotechnical engineering or risk and uncertainty analysis.