Illuminating Photodynamics with Machine Learning Techniques

Illuminating Photodynamics with Machine Learning Techniques

Author(s): Carolin Müller

Publication: Bunsen-Magazin 2023, 6, 191-193

Publisher: Deutsche Bunsen-Gesellschaft für physikalische Chemie e.V., Frankfurt

Language: English

DOI: 10.26125/0ehr-vk47

Abstract: When molecules absorb light, they enter non-equilibrium states, triggering a cascade of nonadiabatic processes. Theoretical modeling of such photoinduced dynamics is pivotal for advancing research and innovation. Nevertheless, these simulations are constrained due to the resource-intensive aspects of quantum chemical methods. Machine learning (ML) offers a solution to this challenge. This article outlines how ML can accelerate and facilitate excited-state simulations.

Cite this:  C. Müller, Bunsen-Magazin 2023, 6, 191-193, DOI: 10.26125/0ehr-vk47

Get the full article​​​​​​​ (pdf)