The development of high-performance composite supercapacitors remains challenging because the specific capacitance of composite electrodes is jointly governed by electronic percolation, ion accessibility, and interfacial contact, all of which are strongly affected by the balance among active materials, conductive agents, and binders. Traditional equivalent circuit modeling and empirical trial-and-error methods are often inadequate for describing these non-linear relationships and optimizing electrode design. To address this limitation, we establish a physics-guided and interpretable machine learning (ML) framework for predicting the specific capacitance of composite electrodes. Unlike traditional methods that rely on macroscopic mass fractions, our approach constructs a feature space comprising ten descriptors, including two newly introduced binder-related proxy descriptors—Binder-to-Conductive Ratio (BCR) and Specific Binder Loading (SBL)—to better represent the influence of binder content. By systematically evaluating 17 machine learning algorithms on a high-fidelity dataset, we identify the XGBoost model, optimized via Bayesian optimization, as the best predictor, achieving a coefficient of determination (R2) of 0.981 and a low mean absolute percentage error (MAPE) of 14.49%. Importantly, interpretability analysis using Shapley Additive Explanations (SHAP) provides physically interpretable statistical insights, revealing that high BCR suppresses specific capacitance through an insulating barrier effect, whereas lattice distortion in the filler material promotes ion transport. This study offers a robust, data-driven framework for optimizing composite electrode performance, demonstrating the potential of interpretable ML models for the rational design of advanced energy-storage materials.
Gong et al. (Fri,) studied this question.