Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qian, Chen, Vitartas, Valdas, Kermode, James, Maurer, Reinhard J.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917376459538432
author Qian, Chen
Vitartas, Valdas
Kermode, James
Maurer, Reinhard J.
author_facet Qian, Chen
Vitartas, Valdas
Kermode, James
Maurer, Reinhard J.
contents Machine learning surrogate models of Kohn-Sham Density Functional Theory Hamiltonians provide a powerful tool for accelerating the prediction of electronic properties of materials, such as electronic band structures and density of states. For large-scale applications, an ideal model would exhibit high generalization ability and computational efficiency. Here, we introduce the MACE-H graph neural network, which combines high body-order message passing with a node-order expansion to efficiently obtain all relevant $O(3)$ irreducible representations. The model achieves high accuracy and computational efficiency and captures the full local chemical environment features of, currently, up to $f$ orbital matrix interaction blocks. We demonstrate the model's accuracy and transferability on several open materials benchmark datasets of two-dimensional materials and a new dataset for bulk gold, achieving sub-meV prediction errors on matrix elements and high accuracy on eigenvalues across all systems. We further analyze the interplay of high-body-order message passing and locality that makes this model a good candidate for high-throughput material screening.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing
Qian, Chen
Vitartas, Valdas
Kermode, James
Maurer, Reinhard J.
Materials Science
Machine learning surrogate models of Kohn-Sham Density Functional Theory Hamiltonians provide a powerful tool for accelerating the prediction of electronic properties of materials, such as electronic band structures and density of states. For large-scale applications, an ideal model would exhibit high generalization ability and computational efficiency. Here, we introduce the MACE-H graph neural network, which combines high body-order message passing with a node-order expansion to efficiently obtain all relevant $O(3)$ irreducible representations. The model achieves high accuracy and computational efficiency and captures the full local chemical environment features of, currently, up to $f$ orbital matrix interaction blocks. We demonstrate the model's accuracy and transferability on several open materials benchmark datasets of two-dimensional materials and a new dataset for bulk gold, achieving sub-meV prediction errors on matrix elements and high accuracy on eigenvalues across all systems. We further analyze the interplay of high-body-order message passing and locality that makes this model a good candidate for high-throughput material screening.
title Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing
topic Materials Science
url https://arxiv.org/abs/2508.15108