Can AI learn to obey physics?
I am a Research Scientist at the UK Atomic Energy Authority (UKAEA), where I lead a team developing “actionable” surrogate models for exascale simulations and data-driven models for the Fusion industry. My research focusses on enhancing machine learning models’ performance, robustness and interpretability through physics-based approaches.
I am also a visiting researcher with the SciML group at STFC’s Rutherford Appleton Laboratory.
Concurrently, I’m pursuing a PhD in Machine Learning under Marc Deisenroth at University College London.
Current Research:
- Physics-Informed Machine Learning
- Continuous Dynamics Modelling
- Uncertainty Quantification
- Design of Experiments
Building simvue.io : AI-driven, open-source simulation management and tracking dashboard for streamlining engineering workflows. Developed with public funding from the UK Government. Currently in private \(\beta\).
“If there is a God, it must be a differential equation” - Bertrand Russell