Machine Learning for Organic Materials: From Molecules to Mobility
This is a fully-funded 4-year PhD position based in the HetSys Centre for Doctoral Training at the University of Warwick.
Project outline
Accurately predicting how gases move through organic materials such as polymers underpins major challenges - from reducing hydrogen crossover in fuel cells to controlling gas transport that drives battery degradation.
The key challenge is to build models that capture gas/polymer interactions and ageing with quantum-level accuracy at the larger scales of real materials.
This project will train machine-learning models on high-quality quantum data, use them for molecular simulations, and connect the results to continuum models via reproducible multiscale approaches. The focus will be on gas/polymer systems relevant to AWE-NST, a UK stakeholder promoting fundamental science with practical impact.
Please note that due to the nature of AWE-NST's work, nationality restrictions apply to applications for this project
Supervisors
Primary: Prof. Gabriele Sosso (Chemistry)
Dr Lukasz Figiel (WMG)
Prof. James Kermode (Engineering)
Project Partner: AWE-NST
- Build, train and validate tailored machine-learning force fields for gas-polymer systems of interest to AWE-NST.
- Curate high-quality QM/MM datasets for training and benchmark against classical force fields and DFT.
- Predict mass transport properties (e.g. diffusivities, solubilities) and their evolution with material aging; compare to experiment and continuum models.
- Gain fundamental understanding of microscopic transport properties in disordered media.
- Quantify model uncertainty and establish robust, reproducible software workflows aligned with HetSys training priorities.
- Explore coarse-graining/enhanced sampling to access longer time- and length-scales where needed.
- A robust, transferable machine learning potential for selected polymer/gas pairs and an end-to-end workflow that AWE-NST can reuse/extend.
- Validated predictions (diffusion, sorption/solubility, aging trends) with documented uncertainty.
- Open, well-documented code and curated training/test datasets; reproducible pipelines.
- Publications and conference presentations in computational materials/ML for molecules; opportunities for joint AWE-NST/Warwick outputs.
- Guidance for integrating molecular insights into continuum/engineering models used by AWE-NST.
- Data science, Python/C++ programming, statistical analysis, and problem-solving in complex systems. These skills position you for careers in AI research, computational materials science, national laboratories (e.g. AWE-NST), tech industry or academic research.
- Machine-learning interatomic potentials (graph neural networks, data curation, active learning) and uncertainty quantification.
- Electronic-structure (DFT/QM) for dataset generation; molecular dynamics (atomistic and, where appropriate, coarse-grained).
- Molecular dynamics simulations, including enhanced sampling techniques with emphasis on applications on glasses.
- Robust software engineering: version control, testing, automation, reproducibility, documentation.
- Multiscale modelling and comparison with experimental/continuum descriptions; statistical analysis of transport properties.
- HPC workflows and collaboration/communication skills through close work with an industrial partner (AWE-NST).
These skills position you for careers in AI research, computational materials science, national laboratories, tech industry or academic research. The HetSys training provides a foundation for these skills through dedicated courses and cohort activities.
We require at least a II(i) honours degree at BSc or an integrated masters degree (e.g. MPhys, MChem, MSci, MEng etc.) in a physical sciences, mathematics or engineering discipline. We do not accept applications from existing PhD holders.
If you are an overseas candidate please check here that you hold the equivalent grades before applying.
For postgraduate study in HetSys, the term “overseas” or “international” student refers to anyone who does not qualify for UK home fee status. This includes applicants from the European Union (EU), European Economic Area (EEA), and Switzerland, unless they hold settled or pre-settled status under the UK’s EU Settlement Scheme.
If you are a European applicant without UK residency or immigration status that qualifies you for home fees, you will be classified as an overseas student.