Machine Learning Prediction of the Redox Activity of Quinones

Abstract

The redox properties of quinones underlie their unique characteristics as organic battery components that outperform the conventional inorganic ones. Furthermore, these redox properties could be precisely tuned by using different substituent groups. Machine learning and statistics, on the other hand, have proven to be very powerful approaches for the efficient in silico design of novel materials. Herein, we demonstrated the machine learning approach for the prediction of the redox activity of quinones that potentially can serve as organic battery components. For the needs of the present study, a database of small quinone-derived molecules was created. A large number of quantum chemical and chemometric descriptors were generated for each molecule and, subsequently, different statistical approaches were applied to select the descriptors that most prominently characterized the relationship between the structure and the redox potential. Various machine learning methods for the screening of prospective organic battery electrode materials were deployed to select the most trustworthy strategy for the machine learning-aided design of organic redox materials. It was found that Ridge regression models perform better than Regression decision trees and Decision tree-based ensemble algorithms.

Carbonyl Chemistry for Advanced Electrochemical Energy Storage Systems

“…Kichev et al have employed the ML approach to predict the redox activity of quinones in organic battery components, in which the 100 quinone derivatives extracted from the Pub-Chem database have been constructed as a data set. 318 Importantly, it was found that the ridge regression is an excellent method for the screening of databases, and the model performance is increased in the following order: regression decision tree < random forest regression < extra trees regression, gradient boosting regression < ridge regression. Moreover, the descriptors (LUMO and Estate) related to the electronic structure have a large significance of electrode potential.…”

“…Particularly, the redox property can be regulated by introducing different substituent groups in the organic skeleton. Kichev et al have employed the ML approach to predict the redox activity of quinones in organic battery components, in which the 100 quinone derivatives extracted from the Pub-Chem database have been constructed as a data set . Importantly, it was found that the ridge regression is an excellent method for the screening of databases, and the model performance is increased in the following order: regression decision tree < random forest regression < extra trees regression, gradient boosting regression < ridge regression.…”