Density-based long-range electrostatic descriptors for machine learning force fields

Author(s)
Carolin Faller, Merzuk Kaltak, Georg Kresse
Abstract

This study presents a long-range descriptor for machine learning force fields that maintains translational and rotational symmetry, similar to short-range descriptors while being able to incorporate long-range electrostatic interactions. The proposed descriptor is based on an atomic density representation and is structurally similar to classical short-range atom-centered descriptors, making it straightforward to integrate into machine learning schemes. The effectiveness of our model is demonstrated through comparative analysis with the long-distance equivariant (LODE) [Grisafi and Ceriotti, J. Chem. Phys. 151, 204105 (2019)] descriptor. In a toy model with purely electrostatic interactions, our model achieves errors below 0.1%, worse than LODE but still very good. For real materials, we perform tests for liquid NaCl, rock salt NaCl, and solid zirconia. For NaCl, the present descriptors improve on short-range density descriptors, reducing errors by a factor of two to three and coming close to message-passing networks. However, for solid zirconia, no improvements are observed with the present approach, while message-passing networks reduce the error by almost a factor of two to three. Possible shortcomings of the present model are briefly discussed.

Organisation(s)
Computational Materials Physics
External organisation(s)
VASP Software GmbH
Journal
Journal of Chemical Physics
Volume
161
No. of pages
11
ISSN
0021-9606
DOI
https://doi.org/10.48550/arXiv.2406.17595
Publication date
12-2024
Peer reviewed
Yes
Austrian Fields of Science 2012
103018 Materials physics, 102019 Machine learning
Keywords
Portal url
https://ucrisportal.univie.ac.at/en/publications/bdee2509-0b5d-45a9-aed4-d1c276ea7cdf