Repository logo
 

Atomic permutationally invariant polynomials for fitting molecular force fields

Published version
Peer-reviewed

Change log

Abstract

Abstract: We introduce and explore an approach for constructing force fields for small molecules, which combines intuitive low body order empirical force field terms with the concepts of data driven statistical fits of recent machine learned potentials. We bring these two key ideas together to bridge the gap between established empirical force fields that have a high degree of transferability on the one hand, and the machine learned potentials that are systematically improvable and can converge to very high accuracy, on the other. Our framework extends the atomic permutationally invariant polynomials (aPIP) developed for elemental materials in (2019 Mach. Learn.: Sci. Technol. 1 015004) to molecular systems. The body order decomposition allows us to keep the dimensionality of each term low, while the use of an iterative fitting scheme as well as regularisation procedures improve the extrapolation outside the training set. We investigate aPIP force fields with up to generalised 4-body terms, and examine the performance on a set of small organic molecules. We achieve a high level of accuracy when fitting individual molecules, comparable to those of the many-body machine learned force fields. Fitted to a combined training set of short linear alkanes, the accuracy of the aPIP force field still significantly exceeds what can be expected from classical empirical force fields, while retaining reasonable transferability to both configurations far from the training set and to new molecules.

Description

Keywords

Paper, molecular mechanics, molecular potentials, force field parametrization, small molecules

Journal Title

Machine Learning: Science and Technology

Conference Name

Journal ISSN

2632-2153

Volume Title

2

Publisher

IOP Publishing
Sponsorship
Leverhulme Trust (RPG-2017-191)
Investissements d’Avenir (ANR-15-IDEX-0003)