Artificial intelligence for geotechnical engineering

Summary

Geotechnical engineering involves the study and use of earth materials such as soil. Soil is characterised by its complex physical, mechanical, and chemical behaviours, which are often non-linear. Further, it is typically anisotropic, non-heterogeneous and its properties vary significantly over short distances.

These characteristics result in traditional geotechnical analysis suffering from high complexity and significant uncertainty. However, recent developments in artificial intelligence are improving the reliability, accuracy and speed of geotechnical analysis. Thus, this project provides the opportunity to develop and apply new artificial intelligence technologies in the field of geotechnics.

Example applications of AI in geotechnical engineering include:

• Subgrade soil and pavements: AI assessment of resilient modulus, deformation, dynamic modulus, and susceptibility to cracking.
• Geotechnical practise/standards: Large language models (e.g. ChatGPT plugins) to assimilate international geotechnical knowledge.
• Space technology: Using computer vision of satellite and UAV/drone imagery to monitor geotechnical assets. For example, the factor of safety and deformation of earthwork slopes
• Dams: Deep learning to analyse seepage flow, leakage and deformation.
• Geotechnical site investigation: AI interpolation of sparsely-populated site investigation data.
• Geotechnical site safety: Computer vision to detect unsafe behaviour and on-site risks.
• Foundations: Machine learning to detect settlement and study bearing capacity.
• Unsaturated soils: Neural networks to determine volumetric water content, soil matric head hydraulic conductivity, effective stresses and soil water retention curves.
• Rock mechanics: AI assessment of rock fragmentation and unconfined compressive strength.
• Tunnelling: Analysis of tunnel boring machine penetration rate, tunnel and surface settlement.
• Landslide and soil liquefaction: Determination of landslide susceptibility, landslide displacement and liquefaction triggers
• Frozen soils and soils thermal properties: Machine learning for thermal conductivity, water temperature and frost groundwater level.

Please identify your preferred area of geotechnical AI study and contact me to discuss a potential project outline.

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.0 overall with at least 5.5 in each component (reading, writing, listening and speaking) or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.