// PhD Researcher · Monash University
Mohammad
Matin Rouhani
Mechanized Excavation · Geotechnical Engineering · Applied AI
Monash University, Melbourne, Australia
// PhD Researcher · Monash University
Mechanized Excavation · Geotechnical Engineering · Applied AI
01 — About
I am a PhD candidate at Monash University, working at the intersection of underground infrastructure inspection and deep learning. My research centres on automated structural assessment and prediction of segmental metro tunnels.
Before joining Monash, I completed my MSc with a full-mark GPA in Mining Engineering (Tunnel & Underground Spaces) at Amirkabir University of Technology (Tehran Polytechnic). There I developed expertise in TBM performance prediction, cutter wear modelling, and cutting tool design — combining numerical methods with modern machine learning.
My work bridges the gap between traditional geotechnical engineering and data-driven AI, enabling smarter, safer, and more efficient underground construction.
02 — Research
Applying advanced tabular machine learning (TabM, SAINT, TabNet, KAN) and metaheuristic optimisation to predict TBM penetration rate, disc cutter forces, and screw conveyor performance in real geological conditions.
Developing surrogate models (DeepONet, TabPFN, TabICL, GINN) that approximate complex geotechnical behaviour — enabling fast, differentiable, and physics-consistent predictions for tunnel settlement and seepage.
Investigating disc cutter and drag bit performance through numerical modelling and CSM-based force prediction, coupled with rock property characterisation and cutterhead layout optimisation.
03 — Publications
Predicting disc cutter forces for hard rock TBM cutterhead modeling: a comparative analysis of modified CSM semi-theoretical model and hybrid deep learning approach
Screw Conveyor Speed Prediction for EPB-TBM Excavations Using Hybrid Deep Learning Models
TBM performance prediction based on XGBoost models: a case study of the Ghomrud water conveyance tunnel (Lots 3 and 4)
04 — Contact
I welcome scholarly collaboration — whether in joint research, dataset development, or co-authorship on tunnelling, geomechanics, or AI-driven infrastructure inspection. Feel free to reach out.
Any scholarly cooperation is welcome. If you have ideas or shared interests in mechanized excavation or AI-driven inspection, let's talk.
✉ Start a Conversation