Long-range electrostatics in atomistic machine learning: a physical perspective

TL;DR

This paper discusses how to incorporate long-range electrostatic effects into atomistic machine learning models, emphasizing physical principles and different modeling paradigms to improve accuracy in molecular and material property predictions.

Contribution

It provides a physical perspective on modeling long-range electrostatics, distinguishing between local charge models and nonlocal approaches, and discusses implications for electrochemical and ionic transport simulations.

Findings

Different modeling paradigms capture electrostatics effectively.

Nonlocal models improve accuracy for electrochemical interfaces.

Long-range effects are less critical for ionic transport phenomena.

Abstract

The inclusion of long-range electrostatics in atomistic machine learning (ML) is receiving increasing attention for achieving quantum-mechanical accuracy in predicting a wide range of molecular and material properties. However, there is still no general prescription on how long-range physical effects should be incorporated into the model while preserving well-established locality principles underlying most transferable ML representations. Here, we provide a physical perspective on the problem, by discussing how distinct contributions to the system's electrostatics can be captured through the adoption of different learning paradigms. Specifically, we discern between local charge models, which rely either on explicit charge-density decompositions or implicit auxiliary variables, and models where a notion of nonlocality is deliberately introduced, either via self-consistent procedures or by using nonlocal descriptors and learning architectures. We further address the related aspect of incorporating finite-field effects through the coupling with the system's polarization, relevant for the application of an external electric bias. We conclude by discussing the implications for the simulation of electrochemical interfaces, where long-range electrostatics are essential to capture the interplay between charge redistribution, interfacial dynamics, and ionic screening, and for ionic transport phenomena, which, although less explored, appear far less sensitive to their inclusion.