PhD Studentship: Machine Learning Driven Corrosion Modelling in Bio Feedback Refining

Faculty of Engineering and Physical Sciences EPSRC Project Proposals 2026/27 (jobs.ac.uk) 

Project Link via the 'Apply' button above

Project Title: Machine Learning Driven Corrosion Modelling in Bio Feedback Refining 

School/Faculty: Mechanical Engineering 

Closing Date: 26 June 2026 

Eligibility: UK Only 

Funding: School of Mechanical Engineering Scholarship, in support of the IMPACT-Bio Research Grant, providing full academic fees, together with a tax-free maintenance grant at the standard UKRI rate of £21,805 per year for 3.5 years. 

Lead Supervisor’s full name & email address 

Professor Richard Barker: r.j.barker@leeds.ac.uk  

Co-supervisor’s full name & email address 

Professor Harvey Thompson: h.m.thompson@leeds.ac.uk

Dr Joshua Owen: j.j.owen@leeds.ac.uk  

Project summary 

The global shift toward renewable bio based fuels is creating exciting new scientific and engineering challenges. Compared with traditional crude oil, bio feedstocks behave very differently during processing, sometimes causing much faster corrosion of refinery equipment. Understanding these behaviours is essential if society is to move confidently toward low carbon fuels. This PhD studentship offers the opportunity to contribute directly to this challenge by developing modern data driven tools that help predict and manage corrosion in next generation bio refineries. 

The project brings together leading researchers from University of Leeds, Imperial College London, University College London, and the University of Illinois at Urbana–Champaign, supported by industrial scientists at bp. Regular engagement with bp and the experimental team in Illinois will provide unique insight into industrial corrosion challenges and support the development of adaptive, data driven sampling strategies to accelerate experimental progress. This environment will provide you with a unique perspective on how data, modelling, experiments, and industrial needs come together in an emerging area of sustainable technology. The research will also contribute to the creation of high throughput approaches for assessing the corrosivity of bio refinery environments. 

Please state your entry requirements plus any necessary or desired background 

A first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. 

Subject Area 

Mechanical Engineering, Computer Science & IT, Data Analytics 

Keywords

Optimisation, adaptive sampling, corrosion, corrosion sampling, data analysis, machine learning