Skip to main content Skip to navigation

Wojciech Stark

Postdoctoral Research Fellow

About my research:

I work on machine learning models for gas-surface dynamics, which include developing active learning workflows with direct validation on dynamical observables, utilising uncertainty quantification. I also develop machine learning models that allow studying the impact of nonadiabatic effects on the dynamics (density and electronic friction tensor models), specifically for state-to-state scattering dynamics.

Selected publications:

  • M. Sachs, W. G. Stark, R. J. Maurer, and C. Ortner, Equivariant representation of configuration-dependent friction tensors in Langevin heatbaths, arXiv:2407.13935 (2024) [arXiv]Link opens in a new window

  • W. G. Stark, C. van der Oord, I. Batatia, Y. Zhang, B. Jiang, G. Csányi, and R. J. Maurer, Benchmarking of machine learning interatomic potentials for reactive hydrogen dynamics at metal surfaces, Mach. Learn.: Sci. Technol., 5, 3, 030501 (2024) [arXiv]Link opens in a new window [journal]Link opens in a new window

  • W. G. Stark, J. Westermayr, O. A. Douglas-Gallardo, J. Gardner, S. Habershon, R. J. Maurer, Machine learning interatomic potentials for reactive hydrogen dynamics at metal surfaces based on iterative refinement of reaction probabilities, J. Phys. Chem. C, 127, 50, 24168–24182 (2023) [arXiv]Link opens in a new window [journal]Link opens in a new window

Previous education:

BSc, MSc in Chemical Technology and Catalysis (Warsaw University of Technology)