Kernel charge equilibration: efficient and accurate prediction of molecular dipole moments with a machine-learning enhanced electron density model

Staacke, Carsten G and Wengert, Simon and Kunkel, Christian and Csányi, Gábor and Reuter, Karsten and Margraf, Johannes T (2022) Kernel charge equilibration: efficient and accurate prediction of molecular dipole moments with a machine-learning enhanced electron density model. Machine Learning: Science and Technology, 3 (1). 015032. ISSN 2632-2153

[thumbnail of Staacke_2022_Mach._Learn.__Sci._Technol._3_015032.pdf] Text
Staacke_2022_Mach._Learn.__Sci._Technol._3_015032.pdf - Published Version

Download (1MB)

Abstract

State-of-the-art machine learning (ML) interatomic potentials use local representations of atomic environments to ensure linear scaling and size-extensivity. This implies a neglect of long-range interactions, most prominently related to electrostatics. To overcome this limitation, we herein present a ML framework for predicting charge distributions and their interactions termed kernel charge equilibration (kQEq). This model is based on classical charge equilibration (QEq) models expanded with an environment-dependent electronegativity. In contrast to previously reported neural network models with a similar concept, kQEq takes advantage of the linearity of both QEq and Kernel Ridge Regression to obtain a closed-form linear algebra expression for training the models. Furthermore, we avoid the ambiguity of charge partitioning schemes by using dipole moments as reference data. As a first application, we show that kQEq can be used to generate accurate and highly data-efficient models for molecular dipole moments.

Item Type: Article
Subjects: STM Open Press > Multidisciplinary
Depositing User: Unnamed user with email support@stmopenpress.com
Date Deposited: 17 Jul 2023 05:33
Last Modified: 14 Sep 2024 04:00
URI: http://journal.submissionpages.com/id/eprint/1737

Actions (login required)

View Item
View Item