I am a Doctoral Researcher at the University of Edinburgh developing the statistical foundational framework for advanced Bayesian graphical modelling aimed at real-time uncertainty quantification and evidence fusion in complex-contested-multi-domain environments. The work builds on Bayesian network methodologies for combining heterogeneous information and deploys machine learning based emulators within dynamic-data-driven systems. The research is funded by the Ministry of Defence (MoD) and the motivation is around the applications of modular digital twin architectures for autonomous systems (spanning aerial, underwater, and ground-based robotics) operating in defence and security contexts, where interpretable and high-fidelity predictive analysis is critical.
I have previously conducted research in explainable AI at the Zuse Institute Berlin and studied Engineering (bachelor's and master's) at the University of Cambridge, specialising in Transformational Machine Learning. I maintain an ongoing collaborative research with the Faculty of Divinity at Cambridge.
I also serve, in a limited part-time capacity, as a Senior Modelling Engineer at Network Rail, where I co-lead R&D initiatives integrating machine learning and advanced analytics for infrastructure fault prediction. In this capacity, I have engaged with experts from leading firms including Deloitte, Cognizant, Capgemini, Faculty AI and Arthur D. Little.