Molecular Dynamics with Neural-Network Potentials

TL;DR

This paper explores how machine learning can enhance molecular dynamics simulations by reducing computational costs and increasing accuracy, through active learning, modeling molecular properties, and aiding chemical system understanding.

Contribution

It introduces practical methods for active learning, demonstrates machine learning models for molecular dipole moments, and discusses broader applications in chemical system analysis.

Findings

Active learning improves reference data selection.

ML models accurately predict molecular dipole moments.

ML aids in understanding complex chemical systems.

Abstract

Molecular dynamics simulations are an important tool for describing the evolution of a chemical system with time. However, these simulations are inherently held back either by the prohibitive cost of accurate electronic structure theory computations or the limited accuracy of classical empirical force fields. Machine learning techniques can help to overcome these limitations by providing access to potential energies, forces and other molecular properties modeled directly after an electronic structure reference at only a fraction of the original computational cost. The present text discusses several practical aspects of conducting machine learning driven molecular dynamics simulations. First, we study the efficient selection of reference data points on the basis of an active learning inspired adaptive sampling scheme. This is followed by the analysis of a machine-learning based model for simulating molecular dipole moments in the framework of predicting infrared spectra via molecular dynamics simulations. Finally, we show that machine learning models can offer valuable aid in understanding chemical systems beyond a simple prediction of quantities.