Ensemble approach assisted grade capacitance prediction of biomass-derived electrode materials: New insights and implications for high performance supercapacitors

Biomass derived carbon precursors have emerged as the promising candidates for electrode materials in supercapacitors. Beyond structural diversity, biomass-based materials offer various advantages of sustainability, biodegradability, heteroatom abundance, hierarchical structure along with eco friendliness. Activated carbon electrode synthesis and operational parameters play significant role in affecting the electrochemical performance of biomass-based supercapacitors. In the current research, grade prediction of specific capacitance for biomass derived activated carbon (BDAC) supercapacitor was performed using ten ensemble approaches. Proposed models M2, M9 and M10 showed highest kappa values of 0.996, 0.977 and 0.981 respectively and lowest RMSE values of 0.179, 0.212 and 0.201 respectively by selecting 14 top rank features on the basis of chemical activation, electrode preparation procedures, structural parameters and electrode operational parameters. Further, sensitivity and specificity parameters were evaluated to provide effectiveness in predicting the actual capacitance values. Ensemble approach facilitated to improve the overall prediction accuracy by capturing a more explicit understanding of the considered dataset. Principal Component Analysis and Attribute polarization analysis showed prominent effect of activation ratio, conductive material ratio and the gas adsorption parameters (V 0.1 -V 0.9 ) on biomass-based supercapacitors. This multi-data approach supported in attaining cognizance of biomass derived materials contributing to electrode fabrication for achieving higher capacitance. ➢ 10 ensemble machine learning approach and 14 principal variables specifically: chemical activation, principal structural features, electrode preparation and operational parameters provided better accuracy. ➢ Proposed models M2 (RF+AB), M9 (RF+Bagging) and M10 (RF+CVR) predicted capacitance accurately shown by highest kappa values of 0.996, 0.977 and 0.981 respectively and lowest RMSE values of 0.179, 0.212 and 0.201 respectively. ➢ Impact of synthesizing and modifying parameters on performance of biomass-based supercapacitors was carried out ➢ Grade prediction was performed by classifying the extracted 400 specific capacitance values into four grades. ➢ Attribute prioritization analysis showed prominent effect of activation ratio, conductive material ratio and the gas adsorption parameters (V 0.1 -V 0.9 ) on biomass-based supercapacitors.