Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks

TL;DR

This paper introduces an equivariant graph neural network that predicts atomic multipoles up to quadrupoles, enabling accurate electrostatic potential modeling without expensive quantum calculations, improving long- and short-range electrostatics treatment.

Contribution

The novel equivariant GNN predicts atomic multipoles efficiently, capturing electrostatic interactions accurately without quantum computations, addressing limitations of previous ML potentials.

Findings

High fidelity reproduction of electrostatic potentials across systems

Effective prediction of atomic multipoles up to quadrupoles

Enforces correct symmetry through equivariant architecture

Abstract

The accurate description of electrostatic interactions remains a challenging problem for fitted potential-energy functions. The commonly used fixed partial-charge approximation fails to reproduce the electrostatic potential at short range due to its insensitivity to conformational changes and anisotropic effects. At the same time, possibly more accurate machine-learned (ML) potentials struggle with the long-range behaviour due to their inherent locality ansatz. Employing a multipole expansion offers in principle an exact treatment of the electrostatic potential such that the long-range and short-range electrostatic interaction can be treated simultaneously with high accuracy. However, such an expansion requires the calculation of the electron density using computationally expensive quantum-mechanical (QM) methods. Here, we introduce an equivariant graph neural network (GNN) to address this issue. The proposed model predicts atomic multipoles up to the quadrupole, circumventing the need of expensive QM computations. By using an equivariant architecture, the model enforces the correct symmetry by design without relying on local reference frames. The GNN reproduces the electrostatic potential of various systems with high fidelity. Possible use cases for such an approach include the separate treatment of long-range interactions in ML potentials, the analysis of electrostatic potential surfaces, and for the static multipoles in polarizable force fields.