Theoretical and Computational Chemistry

Using Machine Learning to Greatly Accelerate Path Integral Ab Initio Molecular Dynamics

Authors

Abstract

Ab initio molecular dynamics (AIMD) has become one of the most popular and robust approaches for modeling complicated chemical, liquid, and material systems. However, the formidable computational cost often limits its widespread application in simulations of the largest scale systems. The situation becomes even more severe in cases where the hydrogen nuclei may be better described as quantized particles using a path integral representation. Here, we present a computational approach that combines machine learning with recent advances in path integral contraction schemes, and we achieve a two-orders-of-magnitude acceleration over direct path integral AIMD simulation while at the same time maintaining its accuracy.

Version notes

Added more clarity to several points.

Content

Thumbnail image of ML-PIMD-Rev.pdf

Supplementary material

Thumbnail image of ML-PIMD-SI.pdf
Using Machine Learning to Greatly Accelerate Path Integral Ab Initio Molecular Dynamics
Simulation Details