Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation

TL;DR

This paper introduces the embedded atom neural network (EANN), a physically inspired machine learning model that efficiently and accurately predicts potential energy surfaces, outperforming traditional models in speed and parameter efficiency.

Contribution

The paper presents the EANN model, which replaces scalar embedded atom densities with Gaussian orbital-based vectors and uses neural networks to capture complex relationships, reducing parameters and computational cost.

Findings

EANN achieves accuracy comparable to established ML models.

EANN requires fewer parameters and configurations.

EANN implicitly includes three-body interactions efficiently.

Abstract

We propose a simple, but efficient and accurate machine learning (ML) model for developing high-dimensional potential energy surface. This so-called embedded atom neural network (EANN) approach is inspired by the well-known empirical embedded atom method (EAM) model used in condensed phase. It simply replaces the scalar embedded atom density in EAM with a Gaussian-type orbital based density vector, and represents the complex relationship between the embedded density vector and atomic energy by neural networks. We demonstrate that the EANN approach is equally accurate as several established ML models in representing both big molecular and extended periodic systems, yet with much fewer parameters and configurations. It is highly efficient as it implicitly contains the three-body information without an explicit sum of the conventional costly angular descriptors. With high accuracy and efficiency, EANN potentials can vastly accelerate molecular dynamics and spectroscopic simulations in complex systems at ab initio level.