Hybrid ML-Physics Optimisation Framework for Pharmaceutical Reactors

About the Project

Chemical flow reactors, especially crystallisation reactors, play a vital role in pharmaceutical manufacturing. Reactor geometry has a major influence on solute-solvent mixing, which directly affects product consistency, and ultimately drug quality. Yet high-performing reactor designs remain largely undiscovered as high-fidelity models for so called ‘many-query’ problems are expensive for large-scale design space exploration.

https://nausheen13.github.io/nausheen-webpage/phd-opportunity.pdf

This PhD project will develop a new multi-fidelity Bayesian optimisation framework for reactor design, enabling efficient exploration of complex design spaces while reducing computational cost. The key challenge is that Computational fluid dynamics models have an unusually rich fidelity structure. Fidelity can vary continuously through mesh refinement, but also discretely through the choice of physical model, from simpler species transport descriptions to more advanced multiphase formulations. Existing optimisation approaches are not designed to handle both of these together.

The project will address this gap by creating a computational framework that can learn across these mixed fidelity levels and use them to accelerate reactor design. The methodology will be developed and validated on crystallisation reactors, with broader relevance to advanced flow systems in pharmaceutical manufacturing.

Research objectives and methodology

This project builds on successful prior work in machine learning-assisted optimisation of flow reactors (Savage, Basha et al., Nature Chemical Engineering, 2024) and extends it to far more complex fidelity settings. The student will develop Gaussian process surrogate models that can capture relationships across mixed discrete-continuous fidelity spaces. In practice, this means learning how inexpensive low-fidelity simulations, such as species transport models, can be used to improve predictions for expensive high-fidelity multiphase simulations.

The student will work at the interface of machine learning, computational fluid dynamics, and process engineering, developing both fundamental methods and design tools. The project combines methodological innovation with real engineering impact, offering the opportunity to contribute to next-generation computational design strategies for pharmaceutical manufacturing.

The PhD will be supervised by Dr Nausheen Basha, an expert in this area, together with Dr Claudio P Fonte. The student will benefit from a highly collaborative research environment spanning the Multiscale Modelling Group at the University of Manchester, as well as Multiphase modelling and ML for Chemical Engineering Groups at Imperial College London. By the end of this PhD, student would have developed a rare combination of skills: Bayesian machine learning, CFD simulations, and demonstrated ability to apply both to real world engineering design problems, a profile that is highly sought after in both industry and academia.

What we can offer:

• Dynamic and growing Computational Design Intelligence group where fluid dynamics, engineering design, and AI converge to accelerate next-generational chemical technologies
• Highly collaborative research environment spanning Chemical Engineering and Computing departments at Imperial College London
• Dedicated mentorship as well as the freedom to explore your own ideas
• By the end of this PhD, you will have developed a rare combination of skills: Bayesian machine learning and physics-based models, a profile that is highly sought after in both industry (pharma and lucrative tech sector) and academia.

Check out the group and collaborators: https://nausheen13.github.io/nausheen-webpage/#/people

Eligibility

Applicants should hold (or be about to obtain) a First or Upper Second class (2:1) UK honours degree (or international equivalent) in a relevant subject such as in a relevant discipline such as Chemical Engineering, Mechanical Engineering, Aerospace Engineering, Physics, Mathematics, Computing, Data Science or a closely related subject.

Applications are invited for a fully funded 3.5-year studentship covering stipend and fees. The PhD is expected to start in September 2026. Applications will be considered until the position is filled, and early application is encouraged as the advert will be withdrawn once the post has been filled.

This studentship is available to Home students only.

Before you apply

We strongly recommend that you contact the lead supervisor for this project, Dr Nausheen Basha (nausheen.basha@manchester.ac.uk), before you apply. Please include details of your current level of study, academic background, and any relevant experience (including your Github page, if any), together with a cover letter explaining your motivation to undertake this PhD project. It is essential that you also include a copy of your CV and transcripts. Please include the project title and your name in the subject line of your email.

How to apply

Apply online through our website: https://uom.link/pgr-apply-2425

When applying, you’ll need to specify the full name of this project, the name of your supervisor, if you already having funding or if you wish to be considered for available funding through the university, details of your previous study, and names and contact details of two referees.

Your application will not be processed without all of the required documents submitted at the time of application, and we cannot accept responsibility for late or missed deadlines. Incomplete applications will not be considered.

After you have applied you will be asked to upload the following supporting documents:

• Final Transcript and certificates of all awarded university level qualifications
• Interim Transcript of any university level qualifications in progress
• CV
• Supporting statement: A one or two page statement outlining your motivation to pursue postgraduate research and why you want to undertake postgraduate research at Manchester, any relevant research or work experience, the key findings of your previous research experience, and techniques and skills you’ve developed. (This is mandatory for all applicants and the application will be put on hold without it).
• Contact details for two referees (please make sure that the contact email you provide is an official university/work email address as we may need to verify the reference)
• English Language certificate (if applicable)

If you have any questions about making an application, please contact our admissions team at FSE.doctoralacademy.admissions@manchester.ac.uk.

Funding Notes

This 3.5-year PhD project is fully funded and home students are eligible to apply (we also welcome students from the Republic of Ireland and EU students with settled status). The successful candidate will receive an annual tax-free stipend set at the UKRI rate (£21,805 for 2026/27) and tuition fees will be paid. We expect the stipend to increase each year. The start date is October 2026.

We recommend that you apply early as the advert may be removed before the deadline.