Machine learning electronic structure and atomistic properties from the external potential

TL;DR

This paper introduces an operator-centered machine learning framework that uses the external potential as input to predict molecular properties and electronic structure, leveraging hierarchical representations and equivariant neural networks.

Contribution

It proposes a novel approach based on the external potential, inspired by the Hohenberg-Kohn theorem, enabling scalable, long-range, and operator-to-operator mappings in electronic structure modeling.

Findings

Successfully models energies and dipole moments from the external potential

Learns effective operator-to-operator maps like Fock and density matrices

Provides a scalable, long-range description of molecular properties

Abstract

Electronic structure calculations remain a major bottleneck in atomistic simulations and, not surprisingly, have attracted significant attention in machine learning (ML). Most existing approaches learn a direct map from molecular geometries, typically represented as graphs or encoded local environments, to molecular properties or use ML as a surrogate for electronic structure theory by targeting quantities such as Fock or density matrices expressed in an atomic orbital (AO) basis. Inspired by the Hohenberg-Kohn theorem, in this work, we propose an operator-centered framework in which the external (nuclear) potential, expressed in an AO basis, serves as the model input. From this operator, we construct hierarchical, body-ordered representations of atomic configurations that closely mirror the principles underlying several popular atom-centered descriptors. At the same time, the matrix-valued nature of the external potential provides a natural connection to equivariant message-passing neural networks. In particular, we show that successive products of the external potential provide a scalable route to equivariant message passing and enable an efficient description of long-range effects. We demonstrate that this approach can be used to model molecular properties, such as energies and dipole moments, from the external potential, or learn effective operator-to-operator maps, including mappings to the Fock matrix and the reduced density matrix from which multiple molecular observables can be simultaneously derived.