PhD Studentship – Machine Learning Driven Corrosion Modelling in Bio‐Feedstock Refining

RFCSR; Leeds; On-site; GBP 19,000 - 25,000; Full time

Job summary

The University of Leeds – School of Mechanical Engineering in Leeds, UK, invites applications for a fully funded PhD studentship on Machine Learning Driven Corrosion Modelling in Bio‑Feedstock Refining. The project investigates how bio feedstocks affect refinery corrosion and develops data‑driven tools to predict and mitigate it, combining ML with physical chemistry.

You will collaborate with Imperial College London, UCL, UIUC, and BP, progress from statistics to hybrid and physics‑informed

Qualifications

• Strong analytical skills and data analysis experience.
• Interest in machine learning and data‑driven modelling.
• Ability to work collaboratively within international research teams and with industry partners.

Responsibilities

• Develop data‑driven models to predict corrosion in bio‑refinery environments.
• Progress from statistical methods to hybrid/physics‑informed models; engage in adaptive experimental strategies.

Skills

Data analysis

Machine learning

Python

MATLAB

Interdisciplinary collaboration

Education

Bachelor's degree or MSc

Tools

Python

MATLAB

Job description

University of Leeds – School of Mechanical Engineering

Leeds, United Kingdom

General Description – include all relevant details from the source

This fully funded PhD studentship at the University of Leeds offers a research opportunity focused on Machine Learning Driven Corrosion Modelling in Bio‑Feedstock Refining. The project addresses the emerging engineering challenge posed by corrosion in next‑generation bio‑based fuel processing. Bio feedstocks often exhibit behaviours distinct from traditional crude oil, which can accelerate corrosion in refinery environments. Bio feedstocks often exhibit behaviours distinct from traditional crude oil, which can accelerate corrosion in refinery environments. This studentship enables the successful candidate to develop advanced data‑driven tools that predict and manage corrosion in these complex systems, integrating modern machine learning techniques with physical and chemical understanding. Regular collaboration with researchers from Imperial College London, University College London, and the University of Illinois at Urbana‑Champaign, alongside industrial scientists at BP, will support a multidisciplinary research context. The work will involve progressing from initial statistical and machine learning methods to hybrid and physics‑informed models, contributing to adaptive experimental strategies and high‑throughput assessment approaches relevant to sustainable bio‑refineries. The role includes opportunities to present findings, publish research, and engage with industrial challenges in sustainable technology and corrosion management.

Eligibility Criteria

Applicants should hold a first‑class or upper second‑class honours bachelor’s degree (or equivalent), or a relevant master’s degree, in disciplines such as engineering, materials science, chemistry, physics, computer science, applied mathematics, or related fields. Candidates must be eligible to pay tuition fees at the UK fee rate; the studentship is open only to UK applicants at the UK fee status. Applicants who have previously been awarded a PhD or are currently registered for a PhD are not eligible.

Required expertise/skills

• Strong analytical skills and a foundational understanding of data analysis and modelling.
• Experience or familiarity with programming languages such as Python or MATLAB is advantageous.
• Interest in machine learning, data‑driven modelling, corrosion science, and interdisciplinary research.
• Ability to work collaboratively within international research teams and engage with industrial partners.

Salary details

The studentship includes full academic fees coverage and a tax‑free maintenance grant at the standard UKRI rate of £21,805 per year for 3.5 years.

Application Deadline

Applications must be submitted by Friday 26 June 2026.