Abstract
Pseudocapacitors outperform lithium-ion batteries in terms of charging rate and power density. However, their electrode manufacturing procedures are prolonged and environmentally unfriendly, posing a research challenge. To address this issue, the one-step synthesis approach of ultra-short laser pulses for in situ nanostructure generation (ULPING) has been proposed. The generated nanostructures on the substrate through ULPING depend on the laser parameters, which leaves room for improvement in this field. The present study aims to build a theoretical bridge between the laser parameters used in the fabrication of pseudocapacitors and their electrochemical performance through machine learning approaches. Gaussian process regression (GPR), random forest (RF), and artificial neural network (ANN) have been employed to mimic the electrochemical behavior of pseudocapacitors, demonstrating the potential of ULPING in generating nanostructures on transition metals that can serve as pseudocapacitor electrodes. This research presents a promising method for producing binder-free and carbon-free pseudocapacitor electrodes efficiently and sustainably.