AI-driven geomechanics and TBM intelligence
Data-driven lithology classification, cutter wear prediction, and autonomous tunnelling workflows for safer and faster underground excavation.
This site is designed as a premium publication portfolio with a cinematic tunnel control-room aesthetic. It keeps the academic content readable while giving the first impression of advanced engineering and applied AI.
The narrative connects TBM operational data, geotechnical interpretation, machine learning, and field-ready decision support.
All files are static. Upload them to the repository root and enable GitHub Pages from the main branch.
Research system
Each block below can become a publication cluster, thesis chapter, or industry collaboration pitch.
Selected publications
Searchable cards with DOI links, research tags, and quick citation copying.
Code and prototypes
A curated GitHub-facing layer for TBM analytics, tunnelling AI, and engineering calculators.
Visual method
The design uses an engineering dashboard metaphor: sensor traces feed models, models produce lithology and wear insight, and the output supports more reliable TBM operation.
Trajectory
A concise story for reviewers, collaborators, and research visitors.
Collaboration
Academic and industry collaborations on AI-enabled TBM performance, cutter wear, lithology identification, and autonomous underground construction.
Use these links to keep the portfolio aligned with the public research footprint.