Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network

TL;DR

This paper introduces a neural network-based method to predict charge densities in ionic systems, enabling highly accurate energy calculations that account for charge transfer and ionization, surpassing traditional approaches.

Contribution

The authors propose predicting charge densities instead of total energies using neural networks, improving accuracy and transferability for ionic systems including ionized states.

Findings

Achieved chemical accuracy (<1 mHartree per atom) for NaCl clusters.

Successfully modeled charge redistribution in neutral and ionized systems.

Enhanced stability and transferability of the machine learning potential.

Abstract

Based on an analysis of the short range chemical environment of each atom in a system, standard machine learning based approaches to the construction of interatomic potentials aim at determining directly the central quantity which is the total energy. This prevents for instance an accurate description of the energetics of systems where long range charge transfer is important as well as of ionized systems. We propose therefore not to target directly with machine learning methods the total energy but an intermediate physical quantity namely the charge density, which then in turn allows to determine the total energy. By allowing the electronic charge to distribute itself in an optimal way over the system, we can describe not only neutral but also ionized systems with unprecedented accuracy. We demonstrate the power of our approach for both neutral and ionized NaCl clusters where charge redistribution plays a decisive role for the energetics. We are able to obtain chemical accuracy, i.e. errors of less than a milli Hartree per atom compared to the reference density functional results. The introduction of physically motivated quantities which are determined by the short range atomic environment via a neural network leads also to an increased stability of the machine learning process and transferability of the potential.