Wil Ward is a Research Associate in the Resources, Infrastructure Systems and Built Environments (RISE) group in the Department of Civil and Structural Engineering at the University of Sheffield. He is working on developing machine learning workflows for the efficient retrofit of residential buildings to increase energy efficiency. Previously, he worked in Physics, Statistics and Computer Science departments, researching physically-informed probabilistic machine learning techniques, in particular Gaussian processes, for solutions to non-linear dynamical problems. He studied his undergraduate degree to Masters level in Mathematics and Computer Science at the University of Nottingham. He went on to study a PhD in Computer Science in a collaborative project with the British Geological Survey, funded by the BGS-University Funding Initiative.
He is also the founder and former network coordinator of the Sheffield Machine Learning Research Network, involved in promoting community for researchers using machine learning in the University of Sheffield. The role involved organising events, tutorials and promoting machine learning in the university.
PhD Computer Science, 2018
University of Nottingham
MSci Mathematics and Computer Science, 2013
University of Nottingham
The Active Building Centre Research Programme is researching and developing innovative tools and technologies that will ensure buildings of all scales contribute to a reduction in carbon emissions and a more sustainable built environment.
This project was an EPSRC feasibility study, looking at applying probabilistic machine learning approaches to non-linear partial differential equations, particularly the Cahn-Hilliard model for polymer demixing.
In this project, we developed scalable approaches for applying Gaussian process regression to multi-output signals with non-linear dependencies. This included using physics-based techniques, including series representation and ordinary differential equation solvers, combined with machine learning techniques such as GPs and autoregressive flows, to infer latent variables and forces.
This project was part of a collaborative effort and joint supervision with British Geological Survey addressing the need for automatic feature detection and interpretation 3D time-lapse images of subsurface geology obtained through electrical resistivity tomography.
I have been involved with the organisation of the Gaussian Process Summer School as School Coordinator since 2018, as well as developing and leading demonstration labs.