Dr Xiaohui Chen

Dr Xiaohui Chen


I am an Associate Professor in Geotechnical Engineering at the University of Leeds with extensive cross-disciplinary research experience in geomechanics and geochemistry. My research focuses on Coupled Multiphysics Modelling and Physics-Informed Machine Intelligence, with broad industrial applications including geotechnical engineering, water research, subsurface disposal and energy, sustainable agriculture, and environmental engineering. I am also a Fellow of the Institution of Environmental Sciences and a Chartered Environmentalist (UK).

Geomodelling and Artificial Intelligence Group: I am the founder and director of the Geomodelling and AI Group, which comprises four postdoctoral researchers, 12 PhD students, and nine MSc/MEng students. The group has secured over £2.7 million in funding from research councils (including NERC, EPSRC, Horizon EU, and CSC) and industry partners. Our research focuses on cutting-edge theoretical, numerical, mathematical, and AI modelling in Geoengineering, with a proven impact in various industries such as petroleum, nuclear waste, carbon capture and storage, landfill, tunnelling, water, and agriculture. The group collaborates with world-renowned academics and institutions to achieve low-carbon, long-life geo-infrastructure, circular economy, and environmental protection, which mitigates the impact of climate change on human civilisation.

Group members (updated on 7 May 2023): 
Research Fellow/PDRAs: Dr Shashank Bettadapura Subramanyam (Marie Curie Fellow), Dr Yue Ma (with University of Minnesota, US), Dr Liyang Xu (with Zhejiang University), Dr Cailin Wang (with China University of Petroleum-Qingdao) 
PhD students: Mr Jiangwei Zhang, Mr Sulaiman Abdullah, Mr Yunsheng Tian, Mr Yuan Biao, Mr Yejie Song, Mr Lei Chen, Mr George Appiah-Kubi, Mr He Yang, Mr Paul R Howlett, Miss Maria Luisa Taccari, Mr Kai Wang, Mr Jianting Feng (as Secondary Supervisor). 
MSc/MEng students: School of Civil Engineering: Chenxi Li, Davood Goodarzi, Ning Fang, Xiang Li, Chenchen Feng, Wenqing Yuan; EPSRC-funded MSc team projects: Jake Cray, Matthew Oram, Andrea Sendula
International Standing:

  • UK representative on the International Society of Soil Mechanics and Geotechnical Engineering (ISSMGE) Technical Committee (TC309) Machine Learning and Taskforce Leader on Physics-Informed Machine Learning (PIML)
  • UK representative on the International Society of Soil Mechanics and Geotechnical Engineering (ISSMGE) Technical Committee (TC215) Environmental Geotechnics
  • Champion of a Themed Issue for ICE International Journal Environmental Geotechnics:“ Physical-Chemical Coupling in Environmental Geotechnics"
  • Associate Editor of the Journal: Geomechanics and Geoengineering
  • Editor Board: Environmental Geotechnics   

Awards and Distinctions:

  • Winner of Faculty (EPS) Partnership Awards 2022 for Academic Personal Tutor/Supervisor Award.   
  • "Top 5 Highly Downloaded Articles in 2013" from International Journal of Engineering Science (IF:9.052).
  • Champion the themed issue of Environmental Geotechnics (2020-2021): “Physical-Chemical Coupling in Environmental Geotechnics”.
  • First author of an article (2018) from International Journal of Numerical and Analytical Methods in Geomechanics (IF:2.481), which fundamentally extended Darcy's Law, Fick's Law, Fourier's law. Reviewers’ comments on this paper: “The manuscript is a welcome complement to the existing literature on frictional forces in membranes.”
  • Co-author of the "front cover" article from Environmental Science & Technology (IF:7.149).
  • Solo author of an article from International Journal of Solids and Structures (IF:2.787).
  • One of the founders of Tay-Gene Geotechnical Centre (2014-2015), Dundee.
  • Fellow of Higher Education Academy, was nominated for a university teaching award of “most inspiration moments”, and contributed to increasing the satisfaction rate of students in Civil Engineering at UoA from 65% to 97% (NSS) (2015).
  • ORS Award (2007-2010), and NERC PDRA within £3m BIGRAD consortium (2010-2014).

Publications Summary: >50 international journal articles, including:

  • Highly Cross-disciplinary Engineering: International Journal of Engineering Science (3, IF=9.219), Journal of Hazardous Materials (2, IF=9.038), Chemical Engineering Journal (1, IF= 13.273). 
  • Geotechnical and Geoenvironmental Engineering: Water Research (1, IF=13.4), Environmental Science and Technology (1, IF=7.864, Front Cover), International Journal for Numerical and Analytical Methods in Geomechanics (4, IF=4.621), Advances in Water Resources (1, IF=4.5), Journal of Hydrology (1, IF=4.5), Science of The Total Environment (1, IF=6.551), Journal of Geotechnical and Geoenvironmental Engineering (1, IF= 4.012), Computers and Geotechnics (4, IF= 4.956), International Journal of Solids and Structures (2, IF=3.9), Applied Thermal Engineering (1, IF=6.46), Journal of Geotechnical and Geoenvironmental Engineering (1, IF= 4.012), Journal of the Mechanics and Physics of Solids (1, IF=5.582).  


  • Deputy Director of Research and Innovation

Research interests

Key Research Directions

  • Mixture Coupling Theory aims to develop a unified theory for multiphase flow transport in deformable porous media, with applications in various disciplines such as Geotechnics (e.g., nuclear waste disposal, CCS, borehole instability, etc.), Biogeotechnics (e.g. agricultural soils),  Medical and Bio Tissue Engineering (e.g., cancer research and tumour growth), and Chemical Engineering (e.g. steel erosion), among others. 
  • Coupled Multiphysics Modelling in Geotechnics and Environmental Engineering (Thermo-Hydro-Mechanical-Chemical-Bio) research focuses on filling the gap between subsurface geochemistry/geomicrobiology/hydrogeology/mineralogy and their effects on chemical transport. This research will lead to a deeper understanding of the influence of geochemical reactions and micro-organism activity on the transport of groundwater/heat/gas/air/radionuclide and the subsequent alteration of stress/strain underground. 
  • Physics-Informed Machine Learning (PIML) are a recent development in the field of machine learning. They combine the power of neural networks with the underlying physical laws governing a system. By incorporating physical laws as constraints during the training process, PIML can learn from limited and noisy data and predict the behavior of complex physical systems with high accuracy. This approach has shown great promise in various applications, including fluid dynamics, geomechanics, and materials science, among others. PIML represent a promising avenue for bridging the gap between data-driven machine learning and physics-based modelling, offering a more accurate and efficient means of modelling complex systems in the real world.
<h4>Research projects</h4> <p>Any research projects I'm currently working on will be listed below. Our list of all <a href="https://eps.leeds.ac.uk/dir/research-projects">research projects</a> allows you to view and search the full list of projects in the faculty.</p>


  • PhD The University of Manchester, 2010
  • MSc Dalian University of Technology, 2007
  • BEng Dalian University of Technology, 2003

Professional memberships

  • Fellow of The Institution of Environmental Science
  • Chartered Environmentalist
  • Fellow of Higher Education Academy

Student education

I presently teach:

  • CIVE5162 (MSc Geotechnical Engineering) Constitutive Model and Numerical Analysis (Module Leader)
  • CIVE5574/5575 (MSc EEPM and Geotechnical Engineering) Groundwater Pollution and Contaminated Land (Module Leader)
  • CIVE3750 Individual Research Project
  • CIVE5755 Individual Research Project

Research groups and institutes

  • Water, Public Health and Environmental Engineering

Current postgraduate researchers

<h4>Postgraduate research opportunities</h4> <p>We welcome enquiries from motivated and qualified applicants from all around the world who are interested in PhD study. Our <a href="https://phd.leeds.ac.uk">research opportunities</a> allow you to search for projects and scholarships.</p>
    <li><a href="//phd.leeds.ac.uk/project/906-coupled-thermo-hydro-mechanical-chemical-modelling">Coupled Thermo-Hydro-Mechanical-Chemical Modelling</a></li> <li><a href="//phd.leeds.ac.uk/project/1133-physics-informed-deep-learning">Physics informed deep learning</a></li> <li><a href="//phd.leeds.ac.uk/project/907-temperature-water-plant-soil-coupled-modelling-for-biogeotechnics">Temperature-water-plant-soil coupled modelling for biogeotechnics</a></li>