Research

There are two main strategies to derive and deduce models — either using theory-based first principles or data-driven approaches. My overall research aim is to create new tools for using these two modeling strategies in conjunction. Most of the tracks below is financially supported by the Swedish Research Council (VR) via the project Physics-informed machine learning (registration number: 2021-04321)

Constrained Gaussian processes

How can prior physical knowledge be incorporated into data-driven Gaussian process models?

Physics-informed neural networks for dynamical systems

How can physics-informed neural networks be used in a probabilistic setting? The project has a special focus on dynamical systems.

Physics-informed generative models

We are developing physics-informed generative models tailored for scientific applications.

Vision-based AI for exploration of new solar cell materials

In this project, we aim to realize an autonomous laboratory capable of exploring and optimizing new solar cell materials using a high-resolution camera.

Magnetic localization

Localization of magnetic objects using a sensor network of magnetometers.