Accurate Fourth-Generation Machine Learning Potentials by Electrostatic Embedding

TL;DR

This paper introduces an advanced machine learning potential that incorporates electrostatic embedding, significantly improving accuracy and transferability in atomistic simulations, especially for ionic systems like NaCl.

Contribution

The work presents a novel electrostatically embedded fourth-generation neural network potential that enhances descriptor information with electrostatic potential, overcoming previous limitations.

Findings

Improved accuracy in energy predictions for NaCl clusters.

Enhanced transferability to charged and molten states.

Effective resolution of small energy differences between geometries.

Abstract

In recent years, significant progress has been made in the development of machine learning potentials (MLPs) for atomistic simulations with applications in many fields from chemistry to materials science. While most current MLPs are based on environment-dependent atomic energies, the limitations of this locality approximation can be overcome, e.g., in fourth-generation MLPs, which incorporate long-range electrostatic interactions based on an equilibrated global charge distribution. Apart from the considered interactions, the quality of MLPs crucially depends on the information available about the system, i.e., the descriptors. In this work we show that including -- in addition to structural information -- the electrostatic potential arising from the charge distribution in the atomic environments significantly improves the quality and transferability of the potentials. Moreover, the extended descriptor allows to overcome current limitations of two- and three-body based feature vectors regarding artificially degenerate atomic environments. The capabilities of such an electrostatically embedded fourth-generation high-dimensional neural network potential (ee4G-HDNNP), which is further augmented by pairwise interactions, are demonstrated for NaCl as a benchmark system. Employing a data set containing only neutral and negatively charged NaCl clusters, even small energy differences between different cluster geometries can be resolved, and the potential shows an impressive transferability to positively charged clusters as well as the melt.