Intelligent Materials Health Monitoring: Utilising Machine Learning to Ensure the Long-term Stability of Perovskite Solar Cells

Solar energy is a cornerstone of Net-Zero. Metal halide perovskites (MHPs) are promising candidates for next-generation solar panels. However, their long-term stability is low and poorly understood, complicating their commercialisation. This project will develop an open-source AI system to assess the ‘health’ of MHPs across device-relevant areas, accessed through luminescence imaging. This will enable the community to predict, visualise, understand and overcome degradation.

Project Description:

Solar cells are a cornerstone of the pursuit of sustainable energy towards a Net-Zero future. To make solar power more efficient and affordable, we need new materials and innovative device designs. Metal halide perovskite (MHP) photovoltaics are a cutting-edge technology that has simple low-temperature (~100 ℃) fabrication routes. The efficiency of MHP photovoltaics has increased dramatically, from ~10% to 26.1% over the past decade, comparable with the best silicon cells in the world (27.1%). Despite this unprecedented rise in their efficiency, the longterm stability of MHPs is poor, which currently complicates their commercialisation. The root causes of this instability remain elusive, especially in full device configurations.

This project seeks to build an advanced artificial intelligence (AI) tool to overcome this critical bottleneck in the development of MHPs. Working with a multidisciplinary team, the student will combine predictive machine learning techniques and high-throughput photoluminescence mapping techniques measured in these materials over the course of a range of accelerated ageing conditions. Photoluminescence data directly correlates with device performance, providing an excellent evaluation metric for machine learning techniques.

The overarching goal of this project is to develop an open-source AI software tool to assess the ‘health’ of MHPs across a large, device-relevant area. To achieve this, we will create an openaccess dataset from the literature and our in-house data. We will employ the recent largelanguage models (LLMs) for mining the literature and other advanced data science tools for curating the mined data and our in-house data to build a standardised dataset. Secondly, we will take a multimodal AI approach to develop machine-learning models that can leverage imaging data, metadata, and domain knowledge to power photoluminescence map analysis during the ageing process. Next, we will build on these analyses to develop advanced tools for identifying regions at risk of degradation before the ageing process has started. Finally, working with experimental colleagues in the groups of Dr Oliver and Dr Ramadan, these regions will be investigated by the unique Near-Field Optical Spectroscopy Centre within the University of Sheffield. This will be able to determine, with extremely high spatial resolution, the chemical properties of the regions responsible for the poor stability, which will, in turn, inform device optimisation to ensure the long-term stability of these materials. The student would be supervised by a multidisciplinary team: Dr Robert Oliver (School of Chemical, Materials and Biological Engineering), Dr Alex Ramadan (School of Mathematical and Physical Science) and Professor Haiping Lu (School of Computer Science), as well as from industry Dr David Bushnell (Oxford Photovoltaics).

The student will benefit from a well-balanced and dynamic supervisory team, as well as the expertise, lab space, computational facilities and technical support across three schools and two faculties. You will meet with the supervisors regularly (weekly with your main supervisor and monthly with those supporting) to discuss the project and your progress to ensure the objectives remain achievable. You will interact closely with the AI Research Engineering team of the Centre for Machine Intelligence at the University of Sheffield. Your career development will be tailored to your goals and will be supported throughout. The skills gained over the course of your PhD will make you a highly attractive candidate for industry positions or your next steps in academia. Additionally, you will have the opportunity to present at conferences both nationally and internationally.

Supervisors:

1. Robert Oliver ([email protected])
2. Alex Ramadan ([email protected])
3. Haiping Lu ([email protected])

If you are interested in this PhD, we encourage you to contact the project supervisor(s) directly.

Application Deadline:

Applications open until successful candidate is recruited (no later than Summer 2025)

Funding Notes:

This is a fully funded project, part of cohort 2 of the EPSRC CDT in Materials 4.0. CDT. The studentship covers fees (home & international), a tax-free stipend of at least £19,237 plus London allowance if applicable, and a research training support grant.

Candidates of all nationalities are welcome to apply; up to 30% of studentships across the CDT can be awarded to outstanding international applicants. Early applications from interested overseas candidates are encouraged.

The Materials 4.0 CDT is committed to Equality, Diversity and Inclusion. Five countries are represented in cohort 1. We would like to see a more gender-balanced cohort 2, so we strongly encourage applications from female candidates.

Enquiries:

For application-related queries, please contact Sharon Brown ([email protected]). Please note that each partner of the CDT in Materials 4.0 will have its own application process

Application Webpage:

https://www.sheffield.ac.uk/postgradapplication/login.do

After the personal details, you need to ‘add research course’, and select ‘Doctoral Training Course’, and then ‘Developing National Capability for Materials 4.0’.