Efficient determination of the Hamiltonian and electronic properties using graph neural network with complete local coordinates

TL;DR

This paper introduces a graph neural network model that accurately predicts the Hamiltonian and electronic properties of large-scale materials using only local atomic structures, achieving ab initio accuracy efficiently.

Contribution

The authors develop an extendable, rotationally equivariant neural network that uses complete local coordinates to predict Hamiltonians from small systems for large-scale applications.

Findings

Predicts Hamiltonians for large systems within ab initio accuracy

Achieves rapid computation, e.g., seconds for 1728-atom systems

Demonstrates applicability to graphene and SiGe alloys

Abstract

Despite the successes of machine learning methods in physical sciences, prediction of the Hamiltonian, and thus electronic properties, is still unsatisfactory. Here, based on graph neural network architecture, we present an extendable neural network model to determine the Hamiltonian from ab initio data, with only local atomic structures as inputs. Rotational equivariance of the Hamiltonian is achieved by our complete local coordinates. The local coordinates information, encoded using the convolutional neural network and designed to preserve Hermitian symmetry, is used to map hopping parameters onto local structures. We demonstrate the performance of our model using graphene and SiGe random alloys as examples. We show that our neural network model, although trained using small-size systems, can predict the Hamiltonian, as well as electronic properties such as band structures and densities of states (DOS) for large-size systems within the ab initio accuracy, justifying its extensibility. In combination with the high efficiency of our model, which takes only seconds to get the Hamiltonian of a 1728-atom system, present work provides a general framework to predict electronic properties efficiently and accurately, which provides new insights into computational physics and will accelerate the research for large-scale materials.