Applications are invited for a fully funded 4-year PhD project within the Mathematics and Data in Scientific and Industrial Modelling (MADSIM) Centre (https://www.madsim.manchester.ac.uk/). This is a collaborative project between the departments of Mathematics and Chemistry, with advisory involvement of an industry partner.
The aim of this project is to develop new machine learning and AI approaches to learn parameters of chemical reactions from simulated and measured data. The outcome of this work has potential for high impact in the optimization of industrial chemical processes, the design of new synthetic tools and new improved catalysts, and for the understanding of biochemical systems.
Experimentally, for a given chemical reaction the concentration of reagents and products can be measured over time from different initial concentrations. Mathematically, the mechanisms of catalytic chemical reactions are governed by ordinary differential equations (ODEs). Inferring the mechanism’s defining ODEs, and then the mechanism from the ODEs, from the measured concentrations using currently available approaches is a nontrivial task, generally requiring numerous simplifications and assumptions, and leading to imperfect models.
This project will develop new mathematical methods that can recover the mechanism of catalytic chemical reactions from simulated and measured data, incorporating important constraints which are naturally satisfied by chemical reaction equations (such as conservation of matter). As a starting point, the project will build on recent progress in the sparse recovery of nonlinear dynamical systems and will significantly develop them further. For some background reading on related work, see: Nature 2023, https://www.nature.com/articles/s41586-022-05639-4
We are looking for an enthusiastic and motivated graduate with the following:
* Obtained or working towards a 1st class degree in Mathematics, or a closely related discipline with strong mathematical component such as Chemistry, Physics, or Engineering (Master’s level or equivalent)
* deep knowledge and understanding of concepts from optimization and numerical analysis, including sparse regression and ordinary differential equations
* Very good communication skills (orally and written)
* Good programming skills in a language such as MATLAB or Python
* Openness to working across disciplines
* ideally (but not essential), some experience with deep learning models for time series data
Before you apply
Interested candidates should email Prof. Stefan Güttel [[Email Address Removed]] in the first instance with a CV, cover letter, transcripts and contact details for two referees.
How to apply
To be considered for this project you’ll need to complete a formal application through our online application portal.
When applying, you’ll need to specify the full name of this project, the name of your supervisor, 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.
If you have any questions about making an application, please contact our admissions team by emailing [Email Address Removed].
Equality, diversity and inclusion
Equality, diversity and inclusion is fundamental to the success of The University of Manchester and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact.
We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.
We also support applications from those returning from a career break or other roles. We consider offering flexible study arrangements (including part-time: 50%, 60% or 80%, depending on the project/funder).
Continue with Facebook
