Â鶹ÊÓƵ

Since September 2023, I have been taught in the School of Computing and Mathematical Sciences. I joined Leicester from the University of Sheffield, where I was a research associate in data driven methods for retrofit and energy efficiency; and physically-inspired machine learning using Gaussian processes.

I received my PhD, titled "Development of machine learning techniques for characterising changes in time-lapse resistivity monitoring", in 2018 from the University of Nottingham, in conjunction with the British Geological Survey.

My research interests lie in inference and decision making in systems where there is limited quantity or quality of data, particularly in environmental and sustainability research. 

Past research projects have included:

• Utilising Bayesian state space modelling to infer below-ground environmental systems using indirect measurements with electrical resistivity tomography
• Combining deep learning with statistical and physical constraints to infer systems with partially known dynamics and indirect observations
• Large scale capture and modelling of the built environment to characterise residential building stock at a large scale, to create digital shadows for energy analysis
• Mixed methods approach to characterising barriers and enablers of data usage in decision making in the domestic retrofit sector

I am particularly interested in multi-modal approaches to inferring environmental systems, including the built environment, with defined uncertainty.

At the Â鶹ÊÓƵ, I have been involved in teaching the following modules:

From 2018 to 2021, I acted as school coordinator of the annual , held in Sheffield.