TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations

TL;DR

TeaNet is a novel graph neural network architecture that models electronic relaxation processes to create a universal interatomic potential capable of accurately predicting energies across diverse chemical systems involving elements H to Ar.

Contribution

The paper introduces TeaNet, a deep residual GCN that incorporates Euclidean tensors to represent electronic relaxation, enabling a universal potential for multiple elements and complex structures.

Findings

Achieves 19 meV/atom mean absolute error in energy predictions.

Successfully models diverse structures including molecules, metals, and amorphous materials.

Demonstrates robustness across a wide range of chemistries involving elements H to Ar.

Abstract

A universal interatomic potential for an arbitrary set of chemical elements is urgently needed in computational materials science. Graph convolution neural network (GCN) has rich expressive power, but previously was mainly employed to transport scalars and vectors, not rank $\ge 2$ tensors. As classic interatomic potentials were inspired by tight-binding electronic relaxation framework, we want to represent this iterative propagation of rank $\ge 2$ tensor information by GCN. Here we propose an architecture called the tensor embedded atom network (TeaNet) where angular interaction is translated into graph convolution through the incorporation of Euclidean tensors, vectors and scalars. By applying the residual network (ResNet) architecture and training with recurrent GCN weights initialization, a much deeper (16 layers) GCN was constructed, whose flow is similar to an iterative electronic relaxation. Our traning dataset is generated by density functional theory calculation of mostly chemically and structurally randomized configurations. We demonstrate that arbitrary structures and reactions involving the first 18 elements on the periodic table (H to Ar) can be realized satisfactorily by TeaNet, including C-H molecular structures, metals, amorphous SiO${}_2$, and water, showing surprisingly good performance (energy mean absolute error 19 meV/atom) and robustness for arbitrary chemistries involving elements from H to Ar.