Jujube stones based highly efficient activated carbon for methylene blue adsorption: Kinetics and isotherms modeling, thermodynamics and mechanism study, optimization via response surface methodology and machine learning approaches

Water contaminated by methylene blue (MB) dye was treated with activated carbon based on locally collected jujube stones. This characterized physico-chemical methods after preparation and chemical activation. Response surface methodology (RSM) used to maximize the MB uptake a dependent variable in Box-Behnken Design (BBD) initial concentration of (400–700 mg/L), adsorbent dosage (0.6–1.6 g/L), contact time (30–540 min), pH (7−11) temperature (20–50 °C) as independent variables. Then, database created BBD further modeled using Gaussian Process Regression coupled Bagging (Bootstrap Aggregation_Bag) Dragonfly optimization algorithm (GPR_DA_Bootstrap). The results analysis GPR_DA_Bootstrap model are shown be superior those model. experimental validation optimal conditions (X1 = 700 mg/L, X2 0.6 g/L, X3 540 min, X4 11, X5 =50 led an (501.01 mg/g) significantly higher than that (456.00 g/g). In addition, very low error between predicted values given (8.64 compared (22.19 mg/g), should highlighted. clearly shows efficiency performance one hand; well effectiveness prepared from stones (PJAC) low-cost other hand.