Skip to Content

Research area(s)

Scientific Machine Learning and Physical AI, Digital Twins, Multiphysics Simulation, Reduced-Order and Surrogate Modelling, Inverse Problems and Bayesian Optimisation, Signal Processing and Sensor Fusion, Uncertainty Quantification, Computational Materials Science, Intelligent Manufacturing and Industrial Automation.

Research Interests

My research focuses on bridging fundamental scientific understanding with artificial intelligence to develop predictive, interpretable, and computationally efficient solutions for complex engineering challenges.

I am particularly interested in combining mathematical models with experimental observations to uncover hidden physical behaviour, improve predictive accuracy, and accelerate computationally demanding analyses. This includes exploring hybrid approaches that leverage both established scientific principles and patterns learned from data.

My current work investigates the digitalisation of advanced manufacturing processes, particularly high-shear aluminium melt conditioning, through integrated sensing, real-time process monitoring, and intelligent decision support. I am interested in translating these technologies into scalable industrial solutions that improve product quality, operational efficiency, and sustainability.

More broadly, I am motivated by the potential of AI to transform how physical systems are understood, simulated, monitored, and optimised, with applications extending across advanced materials, fluid dynamics, electronics systems and emerging industrial technologies.

Research grants and projects

Project details

Project title: Digital High-Shear Melt Conditioning for Resource-Efficient Aluminium Processing (DIGI-HSMC)

Funding: Innovate UK

Research partners: Brunel University London (BCAST), Zyomax Ltd, Aeromet International Ltd, and International Syalons Ltd.

Project description:

DIGI-HSMC is a collaborative industrial research project focused on transforming conventional aluminium melt processing through digital twin technology, computational fluid dynamics (CFD), and intelligent sensing.

My research contributes to the development of a computational framework integrating experimental measurements, multiphysics modelling, and decision support algorithms. The work includes developing reduced-order models, integrating industrial sensor data, and enabling near-real-time assessment of complex fluid dynamics and manufacturing conditions.

The project aims to improve process visibility, melt quality, energy efficiency, and operational decision-making, supporting the transition towards smarter, more sustainable metal manufacturing.