NTU-CEE Distinguished Seminar Series: Professor Wang Yu

06 Aug 2024 02.00 PM - 03.00 PM CEE Seminar Room A (N1, B1b-06) Current Students, Prospective Students, Public

Organized By

CEE Seminar Committee

Host By

Assistant Professor Shi Chao

Topic

Generative AI for 3D Subsurface Geological Modeming from Sparse Site Investigation Data

 

About the Seminar

With the launch of ChatGPT by OpenAI in 2022, generative artificial intelligence (AI) has attracted significant attention in various disciplines, which involves creation of digital content by mimicking different types of data (e.g., text, image, and video). It has also been applied to smart city development recently, such as digitalization of aboveground and underground infrastructures. In geo-engineering practice, due to the time, budget, technical, or access constraints, geotechnical site investigation data from a specific site are often sparse and limited, although some prior geological knowledge of the site might be available.

It is particularly challenging to integrate sparse site-specific measurements with prior geological knowledge to develop 3D subsurface ground models with a high spatial resolution. To tackle this challenge, a generative machine learning method called multi-scale generative adversarial networks (MS-GAN) is proposed for developing 3D subsurface geological models from limited boreholes and a 3D training image representing prior geological knowledge. The proposed method automatically learns multi-scale 3D stratigraphic patterns extracted from the 3D training image and generates 3D geological models conditioned on limited borehole data in an iterative manner. The proposed method is illustrated using both numerical and real data examples.

Both accuracy and associated uncertainty of 3D models are quantified.

About the Speaker

Dr. Wang Yu 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, and seismic risk assessment of critical civil infrastructure systems. His research has earned several prestigious international/national awards, including the 2023 Thomas A. Middlebrooks Award from ASCE, the 2022 R.M. Quigley Award (Honourable Mention) from Canadian Geotechnical Society, the 2020 Best Paper Award from 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) from the Ministry of Education, China, the First-class Natural Science Award from the Hubei Provincial Government in 2017, the Highly Cited Research Award from the international journal of Engineering Geology in 2017, and the GEOSNet Young Researcher Award from the Geotechnical Safety Network (GEOSNet) in 2015.

Dr Wang has authored/co-authored over 180 journal papers and two books in English. 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 (e.g., Associate Editor for the ASCE Journal of Geotechnical and Geoenvironmental Engineering).

Registration

Click here for registration (Closes on 6 August 2024, 01:50 pm)