Design and fabrication of machine learning optimized Ni and Co-doped CuO nanocomposite as promising material for supercapacitor application

Transition metal (TM) doped transition metal oxides (TMOs) have emerged as promising materials for supercapacitor application due to their redox activity, large surface area, and high specific capacitance. However, optimizing their electrochemical properties remains challenging. In this work, we have synthesized Ni- and Co-doped CuO nanocomposites via a straightforward hydrothermal approach to examine the effects of doping on their nanostructure, crystallinity, and redox properties. Additionally, machine learning (ML) was employed to optimize fabricated material composition to enhance the electrochemical efficacy of the designed materials. Results demonstrate that ML-optimized Ni-doped CuO has shown a high specific capacitance of 496 Fg −1 at a current density of 1.5 Ag −1 as compared to Co-doped CuO (245 Fg −1 ). Ni-doped CuO achieved a high-power density of 12,469 Wkg −1 and energy density of 111 Whkg −1 , demonstrating enhanced electrochemical performance. The improved properties of Ni-doped CuO are attributed to enhance synergistic effect between Ni-doped CuO, which facilitates faster electron transfer and enhances the material's stability and achieved capacitance retention of 95.1 %. This study presents an economical and effective method for optimizing TM-doped CuO nanocomposites. Ni-doping exhibits excellent performance, which offers significant potential for next-generation energy storage devices.