Machine learning potentials for redox chemistry in solution

TL;DR

This paper introduces advanced machine learning potentials capable of accurately modeling redox reactions in solution, including electron transfer processes, by incorporating global system information into the potentials.

Contribution

The authors develop fourth-generation machine learning potentials that can correctly describe oxidation states and electron transfer in redox chemistry, overcoming previous limitations.

Findings

Correct oxidation states are obtained matching chloride counter ions.

The method accurately describes electron transfer between Fe$^{2+}$ and Fe$^{3+}$.

Enables simulations of redox reactions in solution.

Abstract

Machine learning potentials (MLPs) represent atomic interactions with quantum mechanical accuracy offering an efficient tool for atomistic simulations in many fields of science. However, most MLPs rely on local atomic energies without information about the global composition of the system. To date, this has prevented the application of MLPs to redox reactions in solution, which involve chemical species in different oxidation states and electron transfer between them. Here, we show that fourth-generation MLPs overcome this limitation and can provide a physically correct description of redox chemical reactions. For the example of ferrous (Fe$^{2+}$) and ferric (Fe$^{3+}$) ions in water we show that the correct oxidation states are obtained matching the number of chloride counter ions irrespective of their positions in the system. Moreover, we demonstrate that our method can describe electron-transfer processes between ferrous and ferric ions, paving the way to simulations of general redox chemistry in solution.