Research
Computational mechanics | Bayesian machine learning | Sustainable materials
Machine learning for trustworthy material modelling, design, and optimisation.
I am a postdoctoral research assistant in the Department of Engineering Science at the University of Oxford. My research develops Bayesian machine learning, uncertainty quantification, and multi-fidelity modelling methods for data-driven mechanics and sustainable material design.
Research Focus
Uncertainty-aware learning
Bayesian neural networks and variance estimation methods that separate epistemic uncertainty from aleatoric uncertainty in engineering data.
Multi-fidelity modelling
Learning strategies that fuse scarce high-fidelity simulations or experiments with cheaper low-fidelity data for reliable prediction and design.
Data-driven mechanics
Machine learning constitutive models and design workflows for materials under variability, limited data, and history-dependent behaviour.
Current Appointments
- 2026-nowPostdoctoral Research Assistant, Department of Engineering Science, University of Oxford. Research on AI-informed material processing and testing, recycled polymer design, and uncertainty quantification.
- 2026Postdoctoral Research Scholar, School of Engineering, Brown University. Research on scalable Bayesian optimization, uncertainty quantification, and recycled polymer design.
Research Vision
My long-term goal is to develop trustworthy and interpretable machine learning models with principled uncertainty quantification, enabling reliable AI-assisted discovery and design of sustainable materials and engineering systems.