Fragment-Constrained Charge Equilibration for Charge-Aware Machine Learning Potentials at Electrochemical Interfaces

TL;DR

This paper introduces Soft-FQEq, a differentiable fragment-constrained charge equilibration method for reactive machine learning potentials at electrochemical interfaces, capturing interfacial charge gradients.

Contribution

It develops a novel, differentiable, fragment-aware charge equilibration layer that enhances charge distribution modeling in reactive MLIPs for electrochemical systems.

Findings

Soft-FQEq recovers electrode-electrolyte charge gradients.

Replacing Soft-FQEq with global QEq removes the charge gradient.

Model trained on DFT data accurately predicts charge distributions.

Abstract

Predictive simulation of electrochemical interfaces requires atomistic models that capture reactive bond rearrangements, long-range electrostatics, and charge distributions reflecting the electronic distinctness of electrode and electrolyte. Existing charge-aware machine-learned interatomic potentials (MLIPs) built on global charge equilibration (QEq) settle electrode and electrolyte at a common electrochemical potential, leaving no room for the interfacial gradient that the double layer requires and admitting spurious charge transfer between electronically disconnected regions. Per-fragment charge equilibration is the established remedy in classical molecular dynamics, but reliance on predefined molecular topology has confined it to non-reactive systems. We lift this restriction by making fragment identification itself a differentiable function of atomic geometry, yielding soft fragment-constrained charge equilibration (Soft-FQEq) -- a solver layer that restores fragment-resolved charge conservation in reactive MLIPs. The layer consumes four scalar MLP readouts from a shared atomic-feature network -- per-atom electronegativity, source charge, short-range energy, and a soft bond connectivity -- and returns equilibrated charges together with per-fragment chemical potentials. We implement Soft-FQEq as an extension of the hippynn framework on a HIP-NN feature network and train it on DFT energies, forces, and DDEC6 charges for IrO2/H2O/Na+/ClO4- interfaces. The trained model recovers a clear electrode-to-electrolyte gradient in the per-atom electrochemical potential. With the same trained weights but the fragment-constrained solver replaced by global QEq at inference, this gradient collapses to an essentially uniform profile, directly showing that the gradient cannot be sustained within global QEq while the fragment formulation recovers it.