A Machine Learning Model for the Chemistry of a Solvated Electron

TL;DR

This paper introduces an electron-aware machine learning force field that models an excess electron quantum mechanically within molecular simulations, accurately capturing reactions like proton transfer in solvated water.

Contribution

The work develops a novel machine learning force field explicitly incorporating quantum electron modeling, enabling accurate simulation of solvated electrons and related reactions.

Findings

Accurately predicts reaction rates with Arrhenius activation energy of 3.2 kcal/mol.

Reproduces experimental reaction free energies and equilibrium constants.

Demonstrates effective modeling of electron-driven processes in aqueous environments.

Abstract

In molecular simulations, machine-learning force fields can achieve ab initio accuracy at a lower cost but remain limited in the explicit modeling of electrons. In this work, we develop an electron-aware machine-learning force field, in which an excess electron of interest is modeled quantum mechanically, while the remaining short-range interactions and long-range Coulombic forces are machine-learned to reproduce a density functional theory calculation. We demonstrate the method on the solvated electron in bulk water and its reaction with a hydronium ion. We identify a proton transfer mechanism by which the excess proton recombines with the electron. We determine the forward reaction rates between 350 K and 450 K from first-passage survival functions, which yield an Arrhenius relationship with an activation energy of 3.2 kcal$\cdot$mol$^{-1}$, in good agreement with experiment. From an enhanced sampling simulation, we determine the equilibrium constant, and thus the reaction free energy, which is also consistent with experimental measurements.