I joined Strathclyde in 2020 as a Chancellor's Fellow (Lecturer) and my research is focused on leveraging cutting-edge probabilistic machine learning techniques to develop intelligent modelling tools to automate and improve the decision-making process involved in geotechnical foundation design (especially for offshore renewable structures such as offshore wind turbines). 

The overall aim is to develop an 'autonomous digital assistant' that helps geotechnical engineers work smarter and faster (especially for large-scale projects such as offshore wind farms), thereby improving engineering productivity, design reliability and reproducibility. 

For more details (including past publications), please visit my lab website at http://www.autogeolab.com

Research Opportunities

I am currently accepting undergraduate/Masters final year project students and PhD applicants who are interested in working in the areas of Bayesian machine learning in geotechnical engineering, offshore soil-structure interaction and automated ground modelling, amongst others (see list of research interests below). If you are interested in doing research with me, please contact me by email with your background and an outline of your proposed research topic.

Probabilistic machine learning:

• Gaussian Process
• Bayesian Changepoint detection
• Markov chain Monte Carlo (MCMC)
• Uncertainty Quantification

Offshore soil-structure interaction:

• Development of simplified design methods for foundations
• High-fidelity numerical modelling of soil-structure interaction
• Thermodynamically-consistent soil constitutive modelling
• Surrogate/Reduced-order modelling