Lund university is currently offering a position as Doctoral student in Numerical Analysis. The main duties of doctoral students are to devote themselves to their research studies, which includes participating in research projects and third cycle courses. The work duties may also include teaching and other departmental duties (no more than 20%). The research will focus on Numerical Analysis for Physics-Aware Deep Kernel Learning.
Project description
This doctoral project lies at the intersection of numerical analysis and scientific machine learning, focusing on the development of reliable, physics-aware AI frameworks. The aim is to build a mathematically grounded approach for approximating partial differential equations (PDEs) using deep kernel learning, which integrates deep neural networks into Gaussian processes constrained by PDEs. Drawing on tools from numerical analysis and reproducing kernel Hilbert space theory, the project seeks to rigorously embed physical laws into deep learning while enabling uncertainty quantification and error estimation. This research offers an opportunity to contribute to foundational advances in physics-informed machine learning. The project is supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP), and the successful candidate will join the WASP graduate school.
Workplace description
Lund University was founded in 1666 and is repeatedly ranked among the world’s top universities. The University has around 47 000 students and more than 8 800 staff based in Lund, Helsingborg and Malmö. We are united in our efforts to understand, explain and improve our world and the human condition.
Within the Faculty of Science research and education is conducted within Biology, Astronomy, Physics, Geosciences, Chemistry, Mathematics and Environmental Sciences. The Faculty of Science is organized into eight departments, gathered in the northern campus area in Lund. The Faculty of Science has approximately 1500 students, 360 PhD students and 700 employees.