Scientific machine learning
Physics-informed learning, operator learning, DeepONets, differentiable physics and PDE surrogate modelling.
RESEARCH
Learning from physics.
Reasoning with uncertainty.
My research sits at the intersection of computational engineering and artificial intelligence, with an emphasis on architectures that exploit physical structure.
Dynamical systems
Neural ODEs, controlled dynamics, latent-state modelling, stiff and long-horizon systems, and sensor-informed state estimation.
Computational engineering
Finite element methods, stochastic mechanics, uncertainty quantification, Bayesian inference and surrogate modelling.
Engineering applications
Energy infrastructure, structural integrity, fatigue and fracture, thermal-fluid systems and advanced manufacturing.
PUBLICATIONS
A foundation in computational mechanics.
My doctoral research developed stochastic numerical methods and uncertainty-aware models, alongside international collaborations in Luxembourg, Australia, and Chile.
View publication recordTALKS & PRESENTATIONS
Sharing research with the engineering community.
2024
NVIDIA GTC
Scientific machine learning and accelerated engineering simulation for industrial applications.
NVIDIA author page ↗2026
ASME Turbo Expo
Physics-guided AI and probabilistic crack-growth modelling.
PATENT APPLICATIONS
Research translated into invention.
2025
AutoCast Pouring Calculator
Quality castings through consistent metal pours. Patent application filed.
2026
Fast Probabilistic Crack Growth Prediction for Turbomachinery via Physics-Guided Neural ODEs
Patent application filed.
THE NEXT CONVERSATION