Advancing Cobalt-Based Supercapacitor Electrodes via Machine Learning: A Review of Predictive and Optimization Strategies
Abstract
Cobalt & cobalt based hybrid nanostructured materials have attracted interest of researcher and scientist for supercapacitor applications. They have hierarchical architecture and high pseudocapacitive performance resulted in better store energy than a regular capacitor as well as charge/discharge much faster than a battery. However, the nonlinear correlation between specific capacitance and synthesis conditions, structural morphology and electrochemical parameters relying on conventional experimental approach insufficient for material design. Thereby necessitating data-driven and machine learningassisted strategies are preferred. This review examines the application of machine learning as a systematic framework for characterizing of materials, predicting and optimizing the electrochemical performance of cobalt based supercapacitor system. Herein, ML model selection on charge storage mechanisms, material classifications and relevant synthesis and characterization techniques are discussed.