Lecture overview:
The interactions between soil, water, chemicals, and bacteria pose significant challenges to the development of foundational theories, which are crucial for accurate physics-based modelling. These challenges have constrained innovation in modern geotechnical engineering. In this presentation, we will introduce the concept of Mixture-Coupling theory as an alternative framework firmly rooted in non-equilibrium thermodynamics, complement to existing foundational theories in Geotechnical Engineering.
Furthermore, in line with the advancements in physical theory, we have directed our focus towards machine learning to bridge the gap between physics and deep learning. This talk will also highlight our recent developments in physics-informed machine learning techniques, which aim to combine the power of physics-based understanding with the data-driven capabilities of machine learning algorithms.
Biography:
Prof. Dr. Chen is an Associate Professor in Geotechnical Engineering at the University of Leeds. As the founder and director of the Geomodelling and AI Group at Leeds, Professor Chen leads a team comprising four postdoctoral researchers, twelve PhD students, and nine MSc/MEng students. He is also a member of the Technical Committee TC309 (Machine Learning) and TC215 (Environmental Geotechnics) of ISSMGE and heads the sub-committee on Physics-Informed Machine Learning (PIML). Professor Chen is a Fellow of the Institution of Environmental Sciences (UK) and serves as an Associate Editor for the International Journals of Environmental Geotechnics (ICE) and Geomechanics and Geoengineering (Taylor & Francis).