sGDML: Constructing accurate and data efficient molecular force fields using machine learning

doi:10.1016/j.cpc.2019.02.007

Return

sGDML: Constructing accurate and data efficient molecular force fields using machine learning

2019-07-01

173

Stefan Chmiela

Huziel E. Sauceda

Igor Poltavsky

Klaus-Robert Müller *

Alexandre Tkatchenko *

DOI：10.1016/j.cpc.2019.02.007

Original

Save

View PDF

Abstract

En 中文

We present an optimized implementation of the recently proposed symmetric gradient domain machine learning (sGDML) model. The sGDML model is able to faithfully reproduce global potential energy surfaces (PES) for molecules with a few dozen atoms from a limited number of user-provided reference molecular conformations and the associated atomic forces. Here, we introduce a Python software package to reconstruct and evaluate custom sGDML force fields (FFs), without requiring in-depth knowledge about the details of the model. A user-friendly command-line interface offers assistance through the complete process of model creation, in an effort to make this novel machine learning approach accessible to broad practitioners. Our paper serves as a documentation, but also includes a practical application example of how to reconstruct and use a PBEO+MBD FF for paracetamol. Finally, we show how to interface 5GDML with the FF simulation engines ASE (Larsen et al., 2017) and i-PI (Kapil et al., 2019) to run numerical experiments, including structure optimization, classical and path integral molecular dynamics and nudged elastic band calculations. (C) 2019 The Author(s). Published by Elsevier B.V.

Keywords:

Machine learning potential

Machine learning force field

Ab initio molecular dynamics

Path integral molecular dynamics

Coupled cluster calculations

Molecular property prediction

Quantum chemistry

Gradient domain machine learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.