Research Themes

Deep learning, neural networks, and advanced AI methods applied to geotechnical prediction, classification, and decision-making. Covers supervised and unsupervised learning, reinforcement learning, and hybrid AI approaches for soil and rock characterisation.

Applying LLMs and foundation models to geotechnical knowledge extraction and engineering design. Includes natural language processing for geotechnical reports, automated code compliance checking, and AI-assisted design workflows.

Integrating physical laws and domain knowledge into ML architectures for reliable geotechnical predictions. Combines constitutive modelling with data-driven approaches to ensure physically consistent outputs.

Real-time digital replicas of tunnels, mines, and underground infrastructure for monitoring and management. Integrates sensor data, numerical models, and AI to enable predictive maintenance and operational optimisation.

Interpretable and transparent AI models for geotechnical risk assessment and engineering decision support. Addresses the black-box problem in ML through SHAP, LIME, and attention-based interpretability methods.

ML-driven advances in rock mass characterisation, tunnel design, and underground excavation engineering. Covers automated rock classification, TBM performance prediction, and AI-assisted tunnel face mapping.

Probabilistic and AI-based frameworks for quantifying and managing geotechnical hazards and uncertainties. Includes slope stability analysis, liquefaction assessment, and failure probability estimation using ML.

IoT, sensors, and AI for intelligent monitoring and adaptive management of geotechnical infrastructure. Covers smart foundations, retaining structures, and real-time construction monitoring systems.

Advanced data processing, statistical learning, and interactive visualization for geotechnical datasets. Includes geospatial data analytics, 3D subsurface modelling, and interactive dashboards for engineering data.

High-performance numerical methods, FEM/DEM, and ML-accelerated simulation for geomechanical problems. Covers surrogate modelling, reduced-order models, and AI-enhanced finite element analysis.

Satellite imagery, LiDAR, and drone-based data combined with ML for large-scale geotechnical mapping and hazard assessment. Includes InSAR ground deformation monitoring and automated feature extraction.

AI-enhanced laboratory testing, automated triaxial and CPT interpretation, and ML-driven field investigation planning. Covers intelligent testing protocols and data quality assurance for geotechnical experiments.

Machine learning applications for climate-resilient geotechnical design, including rainfall-induced landslide prediction, permafrost degradation modelling, and sea-level rise impact assessment.

AI-assisted analysis of micro-CT imaging, particle-scale simulations, and nano-scale soil behaviour. Covers machine learning for grain morphology analysis and pore-scale flow modelling.

Autonomous drilling, robotic site investigation, and AI-controlled ground improvement systems. Covers unmanned ground vehicles for geotechnical surveys and automated grouting control.

Machine learning and AI techniques applied to automate and accelerate numerical modelling workflows in geotechnical engineering. Covers surrogate models, automated mesh generation, and AI-driven parameter calibration for FEM and DEM simulations.

Intelligent systems for collecting, storing, processing, and interpreting large geotechnical datasets. Includes automated data pipelines, anomaly detection, and AI-assisted interpretation of borehole logs, CPT data, and monitoring records.

Application of AI and machine learning to improve the efficiency and accuracy of ground investigation programs and subsurface characterisation. Covers intelligent planning of site investigations, automated logging, and spatial interpolation of geotechnical properties.

AI-powered frameworks for geotechnical risk quantification, hazard identification, and engineering decision support. Includes probabilistic risk models, Bayesian networks, and AI-assisted design optimisation under uncertainty.

Real-time AI-driven monitoring of construction activities and geotechnical structures using digital twin technology. Covers sensor integration, anomaly detection during construction, and predictive analytics for infrastructure performance.

Leveraging large language models and AI tools to automate the creation, retrieval, and management of geotechnical engineering documentation. Includes AI-assisted report writing, standards compliance checking, and knowledge graph construction.

Addressing the ethical, reliability, and governance challenges of deploying AI in geotechnical and civil engineering practice. Covers model transparency, bias mitigation, regulatory frameworks, and professional responsibility in AI-assisted engineering.

Innovative use of AI and machine learning tools in geotechnical engineering education, training, and professional development. Covers AI-powered learning platforms, simulation-based training, and intelligent tutoring systems for geotechnical practice.