Density Functional Theory and Machine Learning for Electrochemical Square-Scheme Prediction: An Application to Quinone-type Molecules Relevant to Redox Flow Batteries

Proton-electron transfer (PET) reactions are rather common in chemistry and crucial in energy storage applications. How electrons and protons are involved or which mechanism dominates is strongly molecule and pH dependent. It is the nature of the participants in the reaction that dictates how electrons and protons are involved and which mechanism dominates. Quantum chemical methods can be used to assess redox potential and acidity constant values but the computations are rather time consuming. In this work, supervised machine learning (ML) models are used to predict PET reactions and analyze molecular space. The data for ML have been created by density functional theory (DFT) calculations. Random Forest Regression models are trained and tested on a dataset that we created. The dataset contains more than 8200 organic molecules that each underwent a two-proton two-electron transfer process. Both structural and chemical descriptors are used. The HOMO of the reactant and LUMO of the product participating in the oxidation reaction appeared to be inversely associated with \oxE. Trained models using a SMILES-based descriptor can efficiently predict the pKa and redox potential with a mean absolute error of less than 1 and 66 mV, respectively. High prediction accuracy of $R^2 > 0.76$ and $> 0.90$ was also obtained on the external test set for redox potential and pKa, respectively. This hybrid DFT-ML study can be applied to speed up the screening of quinone-type molecules for energy storage and other applications.