Predicting the Redox Potentials of Phenazine Derivatives using DFT Assisted Machine Learning

Here, four machine-learning models were employed to predict the redox potentials of phenazine derivatives in DME using DFT. A small dataset of 189 phenazine derivatives having only one type of functional group per molecule (20 unique groups) was used for the training. Models were validated on the external test-set containing new functional groups and diverse molecular structures and achieved reasonable accuracies (R2 > 0.57). Despite being trained on the molecules with a single type of functional group, models were able to predict the redox potentials of derivatives containing multiple and different types of functional groups with reasonable accuracy (R2 > 0.6). This type of performance for predicting redox potential from such a small and simple dataset of phenazine derivatives has never been reported before. Redox Flow Batteries (RFBs) are emerging as promising candidates for energy storage systems. However, new green and efficient materials are required for their widespread usage. We believe that the hybrid DFT-ML approach demonstrated in this report would help in accelerating the virtual screening of phenazine derivatives saving computational and experimental resources. This approach could potentially identify novel molecules for green energy storage systems such as RBF.