Machine learning and excited-state molecular dynamics

TL;DR

This paper reviews recent machine learning methods applied to excited-state molecular dynamics, discussing successes, challenges, and future directions in modeling light-induced quantum chemical processes.

Contribution

It provides a comprehensive survey of recent advances in machine learning for excited-state dynamics, highlighting key successes and identifying current challenges and future research avenues.

Findings

Machine learning has been successfully applied to excited-state molecular dynamics.

Challenges include accurately modeling nonadiabatic processes and large systems.

Future research should focus on overcoming current limitations and expanding applications.

Abstract

Machine learning is employed at an increasing rate in the research field of quantum chemistry. While the majority of approaches target the investigation of chemical systems in their electronic ground state, the inclusion of light into the processes leads to electronically excited states and gives rise to several new challenges. Here, we survey recent advances for excited-state dynamics based on machine learning. In doing so, we highlight successes, pitfalls, challenges and future avenues for machine learning approaches for light-induced molecular processes.