PhD Project in Mathematical Image Analysis for Sustainable Materials

The Department of Computer Science invites applicants for a PhD fellowship in Mathematical Image Analysis for Sustainable Materials to be part of the Novo Nordisk Foundation–funded project RAPTOR, a collaboration between Lund University (LU), the University of Copenhagen (UCPH), and the Technical University of Denmark (DTU). RAPTOR aims to develop a next-generation foundation model for 3D volumetric data, enabling robust classification, segmentation, and quantitative characterisation of multiscale structures across imaging modalities, synchrotron imaging, including X-ray microtomography, electron microscopy, and medical imaging. The foundation model is already under development, trained on large and diverse datasets, and will be further refined and applied to key challenges in materials and biomedical sciences. The central research question for this position is how learned visual representations can be combined with mathematically grounded structural descriptors to support quantitative characterisation of complex materials. Start date is expected to be December 1, 2026, or as soon as possible thereafter. The project This position focuses on sustainable materials, including fibre-based materials, porous systems, and metals, where structural organisation across scales determines key material properties. The project is carried out in close collaboration with domain experts in LU who formulate scientific questions related to how production conditions and usage influence material performance. The project does not focus on developing new foundation-model architectures, but on understanding, evaluating, and exploiting learned representations for scientific image analysis. The developed methods will be used to investigate how manufacturing and usage affect material structure and performance. At the University of Copenhagen, the project contributes to RAPTOR through benchmarking, modelling, and analysis. In this context, the successful candidate will develop methods for quantitative structural characterisation of complex materials, with an emphasis on approaches that do not rely exclusively on segmentation. In particular, the work will explore structure-aware representations such as orientation fields and tensor-based descriptors, enabling robust analysis of heterogeneous and fibrous materials, and in close collaboration with the domain experts, the work will focus on identifying what matters from the analysis to inform the domain experts about the material and how the next exeriment should be formed. The candidate will take part in the development and applications of methods to evaluate how RAPTOR representations perform on relevant analysis tasks, using well-defined benchmarks and comparisons to established approaches. Further, the candidate will take part in the development of concise, interpretable models that relate material structure to key properties, with a focus on robust and practical descriptors. The project will deliver validated analysis methods, benchmark tasks, and structural descriptors, developed in close collaboration with materials scientists and tested on real-world data. Who are we looking for? We are looking for candidates within the field(s) of Computer Science, Mathematics, Physics, Engineering etc. Applicants should have solid mathematical maturity and an interest in developing, analysing, and evaluating quantitative methods for image-based characterisation of complex structures. Experience with machine learning, image analysis, scientific computing, or data science is advantageous, but the project focuses on understanding, benchmarking, and developing methodology around visual representations rather than on large-scale deep-learning model development. Our group and research- and what do we offer? The project is supervised by Jon Sporring (UCPH), Anders Bjorholm Dahl (DTU), Stephen Hall (LU), and Martin Bech (LU), combining expertise in mathematical image analysis, computer vision, quantitative imaging, X-ray imaging, and materials science. The student will have opportunities to collaborate with researchers at UCPH, DTU, LU, and international imaging infrastructures, and to contribute to open-source research software and datasets. The candidate will join the IMAGE section at the University of Copenhagen, an active research group working on image analysis, computer vision, geometry, computational modelling, and AI. The section is closely connected to QIM, Danish BioImaging, Euro-BioImaging, the Human Organ Atlas, and the Pioneer Centre for AI, providing access to leading imaging infrastructures, large-scale datasets, and broad interdisciplinary collaborations. IMAGE offers a friendly, collaborative, and informal research environment with close interaction between faculty, postdoctoral researchers, and PhD students. We value curiosity, mathematical depth, openness, and teamwork, and provide a supportive setting for developing independent research careers. Principal supervisor is Professor, Jon Sporring, Department of Computer Science, sporring@di.ku.dk, +45 2425 2334 The PhD programme Depending of your level of education, you can undertake the PhD programme as either: Option A: A three-year full-time study within the framework of the regular PhD programme (5+3 scheme), if you already have an education equivalent to a relevant Danish master’s degree. Option B: An up to five-year full-time study programme within the framework of the integrated MSc and PhD programme (the 3+5 scheme), if you do not have an education equivalent to a relevant Danish master´s degree – but you have an education equivalent to a Danish bachelors’ degree. ****************************************************************************** Option A: Getting into a position on the regular PhD programme Qualifications needed for the regular programme To be eligible for the regular PhD programme, you must have completed a degree programme, equivalent to a Danish master’s degree (180 ECTS/3 FTE BSc + 120 ECTS/2 FTE MSc) related to the subject area of the project, e.g. [relevant educations]. For information of eligibility of completed programs, see General assessments for specific countries and Assessment database. Terms of employment in the regular programme Employment as PhD fellow is full time and for maximum 3 years. Employment is conditional upon your successful enrolment as a PhD student at the PhD School at the Science, University of Copenhagen. This requires submission and acceptance of an application for the specific project formulated by the applicant. The position is covered by the Memorandum on Job Structure for Academic Staff. Salary, pension and other conditions of employment are set in accordance with the Agreement between the Ministry of Taxation and AC (Danish Confederation of Professional Associations) or other relevant organisation. Currently, the monthly salary starts at 31,800 DKK/approx. 4,200 EUR (August 2026-level). Depending on qualifications, a supplement may be negotiated. The employer will pay an additional 18,07 % to your pension fund. Foreign and Danish applicants may be eligible for tax reductions, if they hold a PhD degree and have not lived in Denmark the last 10 years. Option B: Getting into a position on the integrated MSc and PhD programme Qualifications needed for the integrated MSc and PhD programme If you do not have an education equivalent to a relevant Danish master´s degree, you might be qualified for the integrated MSc and PhD programme, if you have an education equivalent to a relevant Danish bachelor´s degree. Here you can find out, if that is relevant for you: General assessments for specific countries and Assessment database. Terms of the integrated programme To be eligible for the integrated scholarship, you are (or are eligible to be) enrolled at one of the faculty’s master programs in Computer Science. Students on the integrated programme will enroll as PhD students simultaneously with completing their enrollment in this