defence for underlying structural materials, yet coating design still relies heavily on iterative, trial-and-error experimental campaigns that cannot keep pace with the accelerating timelines of fusion demonstrator programmes.
This project proposes a paradigm shift from empirical to AI-guided coating design: building a generative, physics-informed machine learning framework that learns process–structure–property relationships across existing coating datasets and then proposes, screens, and ranks novel coating architectures and manufacturing parameter sets before any physical trial is needed. This is a desk-based, fully data-driven PhD project, where all work is carried out through data curation, physics-based simulation, and machine learning model development, making it well suited to self-funded or part-time study.
Prerequisite: The applicant must have adequate AI/ML skills.
How to Apply
Interested applicants should check Heriot-Watt University admission requirements at https://www.hw.ac.uk/about/our-schools/engineering-and-physical-sciences/research/postgraduate-research/how-to-apply. If you meet the admission and self-funding requirements, send the following documents to a.zia@hw.ac.uk
- A CV
- A short (1-page) statement of research interest
- Academic transcripts
Funding Notes
This is a self-funded project. Applicants should have, or be in the process of securing, funding to cover tuition fees and living costs (e.g. personal funding, external scholarship, or sponsorship).
References
IMPEE/AWZ
