Physics-inspired Equivariant Descriptors of Non-bonded Interactions

TL;DR

This paper introduces an extension to the LODE framework that effectively models long-range non-bonded interactions in atomistic systems, integrating physical principles with machine learning for improved accuracy and efficiency.

Contribution

It generalizes the LODE framework to handle diverse long-range interactions using multipole expansion, enabling consistent and physically interpretable modeling of non-bonded forces.

Findings

Successfully applied to toy systems demonstrating proof of concept.

Extended to molecular dimers to test limits and versatility.

Provides a unified, physically interpretable approach for non-bonded interactions.

Abstract

One essential ingredient in many machine learning (ML) based methods for atomistic modeling of materials and molecules is the use of locality. While allowing better system-size scaling, this systematically neglects long-range (LR) effects, such as electrostatics or dispersion interaction. We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way, and seamlessly integrates with preexisting methods by building new sets of atom centered features. We provide a direct physical interpretation of these using the multipole expansion, which allows for simpler and more efficient implementations. The framework is applied to simple toy systems as proof of concept, and a heterogeneous set of molecular dimers to push the method to its limits. By generalizing LODE to arbitrary asymptotic behaviors, we provide a coherent approach to treat arbitrary two- and many-body non-bonded interactions in the data-driven modeling of matter.