PhD Student in Multimodal Machine Learning for Energy Storage Materials
Description:
Department of Chemistry - Ångström conducts research and education in chemistry. The department has 270 employees and generates annual revenue of 300 million kronor. The department's six programs conduct highly successful research of international caliber. We have a large number of externally funded research projects, often with international collaboration, and we see continued strong growth within our field. The department provides education within engineering and civil engineering programs as well as master's programs. Project Description The development of tomorrow's energy storage materials relies on a fundamental understanding of how their chemical composition and structure change during operation in applications. No single method can capture the complete picture. Instead, researchers must rely on multiple complementary techniques, each providing an incomplete and indirect view of the same underlying process and which are traditionally interpreted manually and separately. Multimodal machine learning offers a principled alternative: integrating heterogeneous data streams from both experiments and simulations into a unified, physically grounded model. The project focuses on developing such a framework and applying it specifically to electrode/electrolyte interfaces in batteries, where surface-sensitive X-ray scattering techniques (X-ray reflectometry, GISAXS, and GIWAXS) and electrochemical quartz crystal microbalance with dissipation monitoring (EQCM-D) are combined in operando experiments. The core of the methodology is data assimilation, where the interface's underlying properties (mass, volume, density, porosity, and morphology) are treated as a latent state evolving in time, with each measurement technique contributing a noisy and incomplete observation through its own forward model. The work encompasses sequential Bayesian inference, deep state-space models, and uncertainty-aware representations trained on both experimental data and simulations, such as phase-field simulations of metal nucleation and growth coupled to lattice-Boltzmann modeling of the quartz crystal's acoustic response. Machine learning-accelerated surrogate models make these simulations sufficiently fast to function as transition and observation operators in the inference engine. Finally, the learned latent space is analyzed to extract physical meaning, and the models' generative capability is leveraged to translate data between techniques. The goal is an interpretable and uncertainty-quantified model of how interfaces form and grow, deepening understanding of metal deposition and surface passivation in Li-, Zn-, and Cu-based systems, and transferable to other materials and analytical techniques. The PhD student's task is to develop and implement this framework in close collaboration between chemistry and computer science at Uppsala University and together with our German partners. This involves building and validating inference and simulation pipelines, actively participating in planning and conducting operando experiments – including measurement campaigns at the synchrotron facility PETRA III (DESY, Hamburg) – and developing deep expertise in probabilistic machine learning, data assimilation, scientific computing, and analysis of electrochemical interfaces. The PhD student's focus is research. Some teaching responsibility may be assigned but will not exceed 20% of total working time. The PhD student will also take graduate courses closely connected to the project's research themes. We are looking for a highly motivated person who will contribute to high-quality scientific work in a multidisciplinary research environment, aiming to publish results in leading scientific journals and present them at both national and international conferences. Qualifications Required Applicants must have: - completed a degree at an advanced level, or - completed course requirements of at least 240 credits, of which at least 60 credits at advanced level (of which 15 credits constitute independent work), with content relevant to doctoral studies, or - in some other way, within or outside the country, acquired substantially equivalent knowledge - very good knowledge of English, both spoken and written - a degree at an advanced level or equivalent as described above in chemistry, materials science, computer science, applied mathematics, engineering physics, or a related field - the ability to express yourself clearly, document your work, and contribute to the community in a research environment Great weight will also be placed on personal qualities such as good collaboration skills, drive, and independence, as well as how the applicant, through their experience and competence, is assessed to have the ability to manage doctoral studies. Desirable/Meriting Additional Qualifications Practical experience with probabilistic machine learning, Bayesian inference, generative models, data assimilation, or scientific computing is meriting, as are strong programming skills (e.g., Python, PyTorch, or JAX). Experience with electrochemistry, battery research, X-ray scattering techniques, or analysis of experimental time series data is also advantageous. About the Position The employment is temporary according to the Higher Education Ordinance (HF) 5 chapter § 7. Full-time position. Start date October 1, 2026, or by agreement. Work location: Chemistry-Ångström Regulations for PhD students are found in the Higher Education Ordinance 5 chapter §§ 1-7 and in the university's rules and guidelines. Information about the position is provided by: Prof. Erik Berg ([email protected]) Welcome to submit your application by September 11, 2026, UFV-PA 2026/2414. Uppsala University is a broad research university with a strong international position. The ultimate goal is to conduct education and research of the highest quality and relevance to make a difference in society. The employment may be subject to security clearance. For security clearance, it is a prerequisite for employment that the applicant is approved. We decline offers of recruitment and advertising assistance. Applications are received through Uppsala University's recruitment system. Union representatives: Saco-S - [email protected], Seko - [email protected], ST (OFR/S) - [email protected]
Ask AI
Common questions about this listing — opens your AI with a ready-made prompt including the listing link.
- Is the salary in this job offer competitive for the role and location?
- What questions should I ask at the interview for this position?
- Which skills should I highlight in my application for this job?
Overview
- Type
- job
- Status
- active
- Visibility
- public
- City
- Uppsala
- Address
- box 256
- GPS
- 59.8710738, 17.5946002
- Phone
- Published
- 11. 8. 2026
- Edited
- 15. 8. 2026