🎓 Discover PhD and Master's programmes at leading universities worldwide — Sign up free to save searches and get email alerts
UOG

The Self-Driving Microscope: Predicting Stochastic Failure in Solid-State Batteries using Physics-Informed AI (Ref: M34Impact-MSE2)

University of Greenwich London, United Kingdom Faculty of Engineering and Science
✓ Funded (Competition) ⏰ Closing Soon 🎓 Computational Mathematics 🎓 Computational Physics 🎓 Energy Technologies 🎓 Materials Science 🎓 Mathematical Modelling 🎓 Solid State Physics battery failure beamlines generative ai graph neural networks materials modelling physics informed ai solid state batteries x-ray tomography

Funded PhD at the University of Greenwich developing physics-informed AI to predict failure in solid-state batteries using X-ray imaging, simulations, and generative models.

Project Description

This PhD project focuses on predicting stochastic failure in solid-state batteries using physics-informed AI. It forms part of a major research initiative aimed at developing a self-driving microscope capable of identifying hidden failure mechanisms in real time. The research integrates AI, physics-based simulation, and materials science to detect microscopic flaws such as dendrite formation, cracking, and short-circuiting in battery materials. Key components include: Building multi-scale datasets from 3D X-ray tomography of battery cells Developing AI models (e.g., Graph Neural Networks) to identify failure precursors Integrating physics-based simulations to derive features such as tortuosity and ionic flux Using generative AI (diffusion models/GANs) to augment datasets Working with experimental data from national facilities such as Diamond Light Source The project is part of the M34Impact programme and contributes to the development of autonomous scientific instruments. The student will be embedded in the BASE Laboratory with links to Rutherford Appleton Laboratory.

Entry Requirements

Not explicitly specified

How to Apply

Apply via University of Greenwich PhD application process
Include required academic documents

Eligibility

UK/Home
EU
International

Supervisor Profile

DJ
Dr James Le Houx, Dr Andrew Kao, Dr Mikhail Poluektov
University of Greenwich, Faculty of Engineering and Science

Related Opportunities

Constrained Bismuth–Metal-Free Scaffolds for Ammonia Activation
Maynooth University Dr Daniela Bezuidenhout 🎓 Chemistry 🎓 Materials Science Deadline: 30 Apr 2026

Explore developing precious metal-free bismuth-based scaffolds for catalyzing ammonia activation under Dr Daniela Bezuidenhout's supervision at Maynooth University. Synthesize and characterize novel compounds to advance…

This research targets sustainable catalytic activation of ammonia, a key molecule in green energy and chemical industry. By designing preci…

1080+ citations · h20
Bismuth Scaffolds Ammonia Activation Organic Ligands Catalyst Development
Manufacture of sustainable electrocatalysts for CO2 conversion by dealloying
CNRS and Imperial College London 🎓 Chemistry 🎓 Materials Science Deadline: 01 May 2026

Explore atomic-scale processes in brass dealloying to produce nanoporous copper for CO2 electrocatalysis. Use advanced microscopy to understand how alloy composition affects catalytic activity and contribute to sustaina…

This research aims to develop efficient, sustainable electrocatalysts for CO2 conversion, providing pathways to reduce greenhouse gases and…

Dealloying Electrocatalysis Nanostructured Materials Transmission Electron Microscopy
Surface Engineering of Inorganic Nanoparticles
University of Technology Sydney Prof Jiajia Zhou 🎓 Biotechnology 🎓 Materials Science Deadline: 31 Jan 2026

Explore surface engineering of inorganic nanoparticles to improve cellular targeting and imaging within quantum biotechnology. Develop new nanoparticle designs to bypass cellular barriers and enhance single-cell sensing…

This research advances quantum biotechnology by developing nanoparticles capable of precise cellular targeting and imaging, which can revol…

10760+ citations · h49
Upconversion Nanothemometry Single nanoparticle spectroscopy Point-of-care testing
: Spatial Artificial Intelligence for Hyperspectral Image Analysis
University of Bath Prof Matthew Nunes, Dr Matthias Ehrhardt 🎓 Computational Mathematics 🎓 Computer Vision Deadline: 30 Apr 2026

Funded PhD at the University of Bath developing spatially-aware AI and machine learning methods for hyperspectral image analysis across scientific and industrial applications.