About the Project A fully funded PhD opportunity to participate in the world-leading research undertaken by the EPSRC Doctoral Landscape
Award at the University of Sheffield. Supervised by Prof Paul Richmond and Edwin Brown . The University of Sheffield is one of the leading Russell Group universities in the UK. We carry out cutting-edge research with strong links to industry. When you enrol to do a PhD with us, you will be working with world-leading academics and have access to top of the range facilities. As a PhD student you will have the opportunity to gain skills not only to conduct research, but also to take your career to the next level, whether you want to stay in academia, go into industry or the public sector, or set up your own company. You will have access to a range of training and support services to help you excel in your studies and beyond. Project Description Digital twins are computer-based representations of real-world systems. They can be used to explore how complex systems behave, test ideas, and understand what might happen under different conditions. However, building and using these simulations can require specialist programming and significant expertise. This project will investigate how recent advances in artificial intelligence can make digital twins easier to create, explore and improve, while also enabling new approaches to scientific discovery. The project will use FLAME GPU, a high-performance simulation framework designed to model large numbers of interacting entities, such as people, animals, vehicles or other components of complex systems. The research will extend this framework with artificial intelligence systems that can understand and respond to natural language. This could allow a researcher to describe a system or experiment in ordinary language and have an intelligent system create an initial simulation, run it, examine the results and suggest improvements. The research will investigate intelligent software agents that can work with simulations as active research tools rather than simply answering questions about them. For example, an agent could be asked to model the spread of a behaviour through a population. It could construct a model, run experiments, compare the results with observations from the real world, identify where the model does not agree with those observations, and then propose and test changes to improve it. This creates the possibility of a more iterative and interactive approach to developing computer models. A key part of the research will be understanding how artificial intelligence systems can be reliably connected to simulations and scientific knowledge. Potential research areas include methods for allowing agents to retrieve and use relevant information from existing models, documentation and experimental data; natural-language methods for controlling simulation parameters and experiments; automated approaches for designing experiments and exploring possible model configurations; and techniques for validating and calibrating simulations against real-world observations. The project will also investigate how simulation results can be represented so that researchers can ask meaningful questions about them using natural language. More broadly, the project will explore how intelligent agents can reason about models, use computational tools, assess uncertainty, challenge their own assumptions and work collaboratively to investigate complex systems. This could lead to new frameworks for interactive and agent-driven digital twins, where researchers can move naturally between describing a problem, creating a model, running experiments, examining evidence and refining their understanding. It offers opportunities to develop both fundamental new methods and practical software that could change how complex computational models are created and used across areas such as engineering, environmental science, transport, biology and social systems. The project will work closely with the Research Software Engineering Team at the University of Sheffield, providing opportunities to explore both the research and industrial applications of agent-driven digital twins. The student may have opportunities to undertake secondments with the RSE team, contribute to industrially funded research projects, and gain experience in developing robust, research-grade software for real-world applications. This combination of doctoral research, professional software engineering practice and industrial engagement will provide strong preparation for careers in research software engineering, scientific computing and industrial research and development, with potential pathways into RSE roles within academia, industry or research organisations. How to apply Interested candidates are strongly encouraged to contact the project supervisors to discuss your interest in and suitability for the project prior to submitting your application. Please refer to the EPSRC DLA webpage for detailed information about the EPSRC DLA and how to apply. Applicants must ensure that they use the correct application form linked to the EPSRC DLA webpage and must submit an application for October 2027 entry. The form is unique to the EPSRC DLA. It contains the list of advertised projects from which to select, and three questions specific to the DLA. The application deadline is 17:00 GMT 13 January 2027. The majority of our DLA studentships will be allocated to candidates who qualify for Home fee status, in accordance with EPSRC funding regulations which place strict limits on international recruitment. Funding Notes The award will fund the full tuition fee and a maintenance stipend at the UKRI rate (currently £21,805 per annum) for 3.5 years, as well as a research grant to support costs associated with the project.


