Integrated data mining for prediction of specific capacitance of porous carbon materials for flexible energy storage devices

Porous carbon materials have gained wide attention owing to their remarkable electrical conductivity and large surface area. Predicting the specific capacitance based on these materials is a crucial step towards designing and manufacturing flexible energy storage devices. To achieve this objective, we employed integrated data mining to construct a database comprising 18 input variables (such as precursor material, activation type, reference electrode, electrolyte, annealing temperature, annealing time, activation temperature, ramp rate of activation temperature, activation time, specific surface area of the pore, total volume of the pore, mesoporous volume, micropore volume, current density, activator material ratio, mass fraction, average pore size, nitrogen content) and one output variable (specific capacitance). We selected characteristic variables to build a porous carbon electrode material database and imported it into a layer fusion model and single-model such as XGBoost, LightGBM, and linear regression to calculate the influence ranking of characteristic variables. The layer fusion model was compared with the single-model by importing a blind dataset into the training, and the prediction correlation coefficient R-2 of the layer fusion model was found to be 0.981, indicating superior performance compared to the single-model. This layer fusion model enables simulation predictions for the selection and preparation of porous carbon electrode materials, guides experimental design, optimizes experimental schemes, and targets experimental parameters by referencing the influence of characteristic variables to obtain optimal experimental results.