PhD student in core optimisation using machine learning Full-time

PhD Student In Core Optimisation Using Machine Learning

Are you interested in working with machine learning, optimisation and reactor physics, with the support of competent and friendly colleagues in an international environment? Would you like to contribute to the development of advanced computational methods for the nuclear energy systems of the future? Are you looking for an employer that invests in sustainable employeeship and offers secure, favourable working conditions? We welcome you to apply for a PhD student position at Uppsala University.

The Department of Physics and Astronomy, Division of Applied Nuclear Physics at Uppsala University conducts research and education in nuclear engineering. The research includes modelling, simulation and optimisation of nuclear reactors, with particular focus on methods that can contribute to safe, efficient and competitive nuclear energy systems.

As a PhD student, you will be part of a research group working with reactor physics, fuel cycle analysis and computational methods for core and fuel optimisation. The group combines physics-based computational models with modern optimisation and data analysis methods. The working environment is international and interdisciplinary, with a close connection between fundamental method development and technically relevant applications.

The project is a continuation of an ongoing PhD project on core and fuel optimisation for small modular reactors, SMRs, within the competence centre ANItA (Academic-industrial Nuclear technology Initiative to Achieve a sustainable energy future). The competence centre brings together academia and industry to strengthen Swedish nuclear engineering expertise and contribute to a sustainable energy transition. The previous PhD project has developed methods for equilibrium-cycle optimisation, where the aim is to identify recurring fuel management strategies that provide good fuel economy while satisfying reactor-physics safety margins. Particular focus has been placed on combining advanced optimisation algorithms with machine-learning-based surrogate models, including graph-based representations of core loading patterns.

You will further develop this research direction. The project may, for example, include cycle-to-cycle optimisation, development of new machine learning models, improved optimisation strategies, uncertainty quantification, more efficient handling of physical constraints, and extended analysis of fuel design, loading patterns and safety-related quantities. The aim is to develop methods that enable faster and more reliable exploration of large design spaces in core and fuel optimisation.

The duties mainly consist of doctoral studies, where you will conduct research within the project and take courses within the doctoral education programme. The work includes development, implementation and evaluation of computational methods for core and fuel optimisation using machine learning and optimisation algorithms.

The duties include:

• developing and applying machine-learning-based surrogate models for reactor-physics calculations,
• developing and evaluating optimisation methods for fuel loading patterns and fuel composition,
• analysing safety-related parameters such as reactivity, power distributions, fuel utilisation and margins to technical limits,
• working with large datasets from reactor-physics simulations,
• implementing and documenting computational tools, for example in Python,
• compiling and publishing research results in scientific articles,
• presenting results at national and international conferences,
• participating in the research group's seminars, project meetings and other scientific activities.

Teaching and other departmental duties may be included, up to a maximum of 20 percent of full-time employment.

To meet the entry requirements for doctoral studies, you must:

• hold a Master's degree in engineering physics, nuclear engineering, energy engineering, machine learning, computer science, applied mathematics or another area relevant to the project, or
• have completed at least 240 credits in higher education, with at least 60 credits at Master's level, including an independent project worth at least 15 credits, or
• have acquired substantially equivalent knowledge in some other way.

The position also requires:

• good knowledge of physics, numerical methods and/or machine learning,
• good programming skills, for example in Python, Julia, C++ or equivalent,
• good ability to work independently and in a structured manner,
• good collaboration skills,
• good ability to express yourself in spoken and written English.

Great emphasis will be placed on personal qualities such as analytical ability, initiative, accuracy and motivation to pursue doctoral studies in an interdisciplinary field.

Experience in one or more of the following areas is considered a merit:

• reactor physics, nuclear engineering or neutron transport,
• core optimisation, fuel cycle analysis or fuel management,
• machine learning, particularly neural networks, graph neural networks or surrogate modelling,
• optimisation algorithms, for example evolutionary algorithms, stochastic optimisation or multi-objective optimisation,
• uncertainty quantification or statistical modelling,
• work with scientific computing software and high-performance computing,
• experience of version control and reproducible computational workflows.