Physics-Guided Continual Learning for Predicting Emerging Aqueous Organic Redox Flow Battery Material Performance

TL;DR

This paper introduces a physics-guided continual learning method for predicting the performance of emerging aqueous organic redox flow battery materials, improving efficiency and robustness over traditional models.

Contribution

The study presents a novel physics-guided continual learning approach that effectively predicts battery material performance while mitigating catastrophic forgetting.

Findings

PGCL outperforms non-physics-guided models in efficiency and robustness.

The method successfully assesses new ASO materials within the established parameter space.

Demonstrated capability on dihydroxyphenazine isomers.

Abstract

Aqueous organic redox flow batteries (AORFBs) have gained popularity in renewable energy storage due to their low cost, environmental friendliness and scalability. The rapid discovery of aqueous soluble organic (ASO) redox-active materials necessitates efficient machine learning surrogates for predicting battery performance. The physics-guided continual learning (PGCL) method proposed in this study can incrementally learn data from new ASO electrolytes while addressing catastrophic forgetting issues in conventional machine learning. Using a ASO anolyte database with a thousand potential materials generated by a 780 $\text{cm}^2$ interdigitated cell model, PGCL incorporates AORFB physics to optimize the continual learning task formation and training process. This achieves higher efficiency and robustness compared to the non-physics-guided continual learning while retaining previously learned battery material knowledge. The trained PGCL demonstrates its capability in assessing emerging ASO materials within the established parameter space when evaluated with the dihydroxyphenazine isomers.