Interpretable Machine Learning Analysis of Design Factors in Hydrogel Supercapacitors

Area of Science:

• Materials Science
• Electrochemistry
• Machine Learning

Background:

• Hydrogel supercapacitors are promising energy storage devices.
• Optimizing their performance requires understanding complex design factor relationships.
• Current knowledge lacks clarity on the relative importance and interdependencies of these factors.

Purpose of the Study:

• To employ interpretable machine learning for analyzing design factors influencing hydrogel supercapacitor performance.
• To quantify parameter importance and reveal feature interactions among key design parameters.
• To provide evidence-based guidelines for rational material selection in hydrogel supercapacitor development.

Main Methods:

• Utilized interpretable machine learning, specifically SHAP analysis.
• Analyzed 232 experimental samples from 41 recent studies.
• Investigated 16 key design parameters, including polymer types, electrolyte formulations, and operating conditions.

Main Results:

• Synthetic vinyl polymers significantly impact specific capacitance.
• Conductive polymers predominantly influence cycle stability.
• Ionic conductivity is the most impactful parameter, exhibiting complex nonlinear relationships with performance.
• Interdependencies exist between polymer concentration and electrolyte formulation.

Conclusions:

• Optimal hydrogel supercapacitor design necessitates coordinated parameter selection.
• Interpretable machine learning provides quantitative insights into design factor hierarchies and interdependencies.
• This framework supports evidence-based guidelines for material selection and device optimization.