Learning charges and long-range interactions from energies and forces

TL;DR

This paper introduces an extension of the Latent Ewald Summation (LES) method that learns physical partial charges and long-range electrostatics in atomistic simulations, improving accuracy and interpretability.

Contribution

The paper presents an extended LES framework capable of learning physical charges, encoding charge states, and enforcing charge neutrality, enhancing modeling of long-range interactions.

Findings

LES effectively infers physical partial charges and multipole moments.

LES outperforms methods that explicitly learn charges in accuracy.

The approach is applicable to diverse complex systems.

Abstract

Accurate modeling of long-range forces is critical in atomistic simulations, as they play a central role in determining the properties of materials and chemical systems. However, standard machine learning interatomic potentials (MLIPs) often rely on short-range approximations, limiting their applicability to systems with significant electrostatics and dispersion forces. We recently introduced the Latent Ewald Summation (LES) method, which captures long-range electrostatics without explicitly learning atomic charges or charge equilibration. Extending LES, we incorporate the ability to learn physical partial charges, encode charge states, and the option to impose charge neutrality constraints. We benchmark LES on diverse and challenging systems, including charged molecules, ionic liquid, electrolyte solution, polar dipeptides, surface adsorption, electrolyte/solid interfaces, and solid-solid interfaces. Our results show that LES can effectively infer physical partial charges, dipole and quadrupole moments, as well as achieve better accuracy compared to methods that explicitly learn charges. LES thus provides an efficient, interpretable, and generalizable MLIP framework for simulating complex systems with intricate charge transfer and long-range