PhD Studentship: The Self-Driving Microscope – Predicting Stochastic Failure in Solid-State Batteries using Physics-Informed AI University of Greenwich in United Kingdom

[Fully funded studentship with annual stipend of £22,780 to £24,780, supported by the University's £9M Research England-funded M 3 4Impact expansion programme.]

The University of Greenwich invites applications for a fully funded PhD studentship as part of the pioneering 'Self-Driving Microscope' project, aimed at predicting stochastic failure in solid-state batteries using physics-informed AI. This project addresses a critical challenge in battery technology: the unpredictable microscopic flaws that lead to catastrophic failure, such as dendrite penetration and structural cracking, which are often hidden from standard diagnostic tests. As the first PhD student and a founding member of the new BASE (Beamlines for Autonomous Science and Engineering) Laboratory, you will play a central role in designing and building the core predictive engine for an autonomous, AI-piloted X-ray imaging platform. This platform will intelligently hunt for hidden failure points in real-time, advancing the next generation of beamlines and battery diagnostics.

The research is at the intersection of AI, physics-based simulation, and materials science. Key objectives include building a multi-scale training dataset using 3D X-ray tomograms of next-generation solid-state cells (such as Li-metal/Li₆PS₅Cl) acquired at the I13-2 beamline (Diamond Light Source). The dataset will capture cells at various stages: pristine, aged, and post-failure. You will develop advanced AI models, including Graph Neural Networks (GNNs), to distinguish benign aging from true failure precursors, retrospectively confirmed as the origin of cracks. The project goes beyond image recognition by integrating physics-based signatures using high-performance computing solvers (like OpenImpala) to transform static 3D porosity maps into dynamic maps of local tortuosity and ionic flux, providing physically-grounded features for AI learning. Additionally, you will augment experimental data with generative AI models (Diffusion models/GANs) to create a diverse library of synthetic microstructures, enhancing model generalisation against noisy, live data.

This studentship is fully funded, offering an annual stipend of £22,780 to £24,780, and is supported by the University's £9M Research England-funded M 3 4Impact expansion programme. The project is a cornerstone of the Computational Science and Engineering Group’s (CSEG) goals and will serve as a foundational project for the new BASE Laboratory. You will be embedded within the M 3 4Impact doctoral cohort and co-supervised by Prof. Andrew Kao, whose group provides validated simulation models, and Dr. Mikhail Poluektov. Dr. James Le Houx, Faraday Institution Emerging Leader Fellow at Rutherford Appleton Laboratory (RAL) and co-leader of the UK's Battery Imaging BAG at Diamond Light Source, will also supervise. The BASE Laboratory is structured with a computational core at the University of Greenwich and an experimental hub at RAL, offering direct links to national facilities and a dynamic, collaborative research environment.

Applicants should hold a first-class or upper second-class undergraduate degree in a relevant field such as materials science, physics, computer science, or chemistry. Experience with computational modelling, machine learning, or AI is highly desirable. Strong analytical skills and familiarity with scientific programming are preferred. English language proficiency is required; specific test requirements are not mentioned. The application deadline is 17 April 2026. To apply, submit your application via the University of Greenwich portal, including your CV, academic transcripts, and a cover letter outlining your suitability for the project. For further information, contact the supervisors listed in the project description.