PNNL

Abstract

Organic redox flow batteries (ORFB) are recognized as an innovative technology for the large-scale storage of renewable energy. The redox potential of organic redox-active molecules plays a vital role in their performance. Advanced screening techniques like high-throughput experiment and machine learning (ML) have significantly enhanced organic material performance and transformed the field of ORFB. However, the scarcity of experimental data poses a considerable challenge for ML model development in this domain. In our study, we developed lightweight Gaussian Process Regression (GPR) models to predict the redox potentials of organic redox-active molecules for ORFBs, specifically focusing on small datasets. To evaluate model accuracy, we assembled computational and experimental datasets for various organic redox-active molecules. We also considered some key parameters, such as pH conditions and solvent type, to assess their impact on redox potential prediction. Our GPR model, employing the marginalized graph kernel, predicted redox potentials with high accuracy across all datasets using minimal training data. The study delivers valuable guidance on designing training datasets for costly experiments and illustrates the possibility of creating accurate ML models for redox potential prediction using small datasets.