Interpretable Machine Learning Analysis of Design Factors in Hydrogel Supercapacitors.

Abstract

Understanding the relationships between design factors is crucial for the development of hydrogel supercapacitors, yet the relative importance and interdependencies of material properties and operating conditions remain unclear. This study employs interpretable machine learning to analyze the design factors that affect hydrogel supercapacitor performance, using 232 experimental samples from 41 recent studies. SHAP analysis was implemented to quantify parameter importance and reveal feature interactions among 16 key design parameters, including polymer types, electrolyte formulations, and operating conditions. Results show that synthetic vinyl polymers most strongly influence specific capacitance, while conductive polymers predominantly affect cycle stability. Ionic conductivity emerged as the most impactful parameter despite moderate feature importance, indicating complex nonlinear relationships. Critical interdependencies between polymer concentration and electrolyte formulation suggest that optimal design requires coordinated parameter selection rather than independent optimization. This interpretable framework provides quantitative insights into design factor hierarchies and parameter interdependencies, offering evidence-based guidelines for rational material selection in hydrogel supercapacitor development.