PhD student in computerized image processing and physics-informed machine learning for green hydrogen production Full-time

PhD Student In Computerized Image Processing And Physics-Informed Machine Learning For Green Hydrogen Production

Are you interested in accelerating Sweden's transition to green hydrogen by combining 3D image processing and physics-informed machine learning? Would you like to work together with competent and friendly colleagues in an international environment? Are you seeking an employer that offers safe and favorable working conditions? We welcome you to apply for a PhD position at the Department of Information Technology, Uppsala University.

The Department of Information Technology holds a leading position in both research and education at all levels. We are Uppsala University's third largest department, with 350 employees, including 120 teachers and 120 PhD students. Approximately 5,000 undergraduate students take one or more courses at the department each year.

Project description: Proton exchange membrane water electrolyzers (PEMWE) are a cornerstone technology for green hydrogen production, but their widespread adoption is held back by cost and durability constraints. A novel strategy for addressing these constraints is the use of thermally sprayed titanium layers for corrosion protection, an approach that enables more cost-effective materials while preserving performance. The challenge is that these layers have a complex, three-dimensional microstructure, and understanding how that microstructure influences electrochemical performance requires methods that can bridge the scales from 3D imaging to functional prediction to process optimization.

The focus of this PhD project is to develop and apply machine learning methods across three interconnected tasks:

1. 3D microstructure characterisation. The student will develop automated pipelines for segmenting and analysing X-ray computed tomography (XCT) images of titanium layers. This includes deep learning-based image analysis and the extraction of quantitative microstructural descriptors that are physically meaningful and predictive.
2. Probabilistic surrogate modelling and digital twin construction. The extracted microstructural descriptors will be used to learn a probabilistic forward model (a digital twin) that maps microstructure to electrochemical performance. This involves simulation-based inference and physics-informed machine learning techniques that can quantify and propagate uncertainty from image features to predicted PEMWE behavior.
3. Bayesian experimental design and process optimization. The digital twin will form the basis for Bayesian optimization of manufacturing process parameters. Rather than running expensive physical experiments at random, the goal is to design experiment sequences that maximally reduce uncertainty about which process conditions lead to optimal performance

The PhD student will be supervised by Ida-Maria Sintorn, Professor in digital image processing, and Jens Sjölund, Assistant Professor in AI at the Department of Information Technology, and conducted in close collaboration with Alleima and Sandvik.

Duties: The doctoral student will primarily devote their time to graduate education. Other departmental duties of at most 20%, including teaching and administration, may also be included in the employment.

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

• hold a Master's (second-cycle) degree in engineering physics, electrical engineering, image processing, computer vision, AI, machine learning, data science, computer science, applied mathematics, or in a similar field, 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 University may permit an exemption from the general entry requirements for an individual applicant, if there are special grounds (Chapter 7, § 39 of the Higher Education Ordinance). For special entry requirements, please see the subject's general study plan.

We are looking for candidates with:

• a strong interest in developing new methods for image processing, computational mathematics and machine learning,
• excellent study results,
• high proficiency in programming (preferably in Python),
• good communication skills with sufficient proficiency in oral and written English,
• personal characteristics such as a high level of creativity, thoroughness, and/or a structured approach to problem-solving.

Additional qualifications: Coursework or other experiences in image analysis and machine learning are valued, for example within linear algebra, calculus, numerical linear algebra, optimization, statistical machine learning, computer vision, 3D image processing, visualization, material science, deep learning, and software engineering.

Application: The application should contain:

• A cover letter (max 2 pages) in English, briefly describing your motivation for applying for this position and the earliest possible employment date. The cover letter should include the heading “Suitability for this position”, containing a self-assessment on why you would be the right candidate for this position.
• A curriculum vitae (CV).
• Degree diploma and transcript of records with grades (translated into English or Swedish).
• The Master's thesis (or a draft thereof, and/or some other self-produced technical or scientific text), publications, and other relevant documents.
• Contact information for two references (names, emails and telephone number) and up to two letters of recommendation.

About the employment: The employment is a temporary position according to the Higher Education Ordinance chapter 5 § 7. Scope of employment 100 %. Starting date 1 September 2026 or as agreed. Placement: Uppsala.

For further information about the position, please contact: Ida-Maria Sintorn (ida.sintorn@it.uu.se) or Jens Sjölund (jens.sjolund@it.uu.se).

Please submit your application by 7 May 2026, UFV-PA 2026/1161.