Atomistic Simulations for Reactions and Spectroscopy in the Era of Machine Learning -- Quo Vadis?
This is an incremental perspective on integrating machine learning into atomistic simulations for researchers in computational chemistry and materials science.
The paper reviews the current state of atomistic simulations that combine accurate energy functions with machine learning to improve molecular dynamics, aiming to make such simulations more realistic, but does not report specific results or numbers.
Atomistic simulations using accurate energy functions can provide molecular-level insight into functional motions of molecules in the gas- and in the condensed phase. Together with recently developed and currently pursued efforts in integrating and combining this with machine learning techniques provides a unique opportunity to bring such dynamics simulations closer to reality. This perspective delineates the present status of the field from efforts of others in the field and some of your own work and discusses open questions and future prospects.