Predictive Model Based on K-Nearest Neighbor Coupled with the Gray Wolf Optimizer Algorithm (KNN_GWO) for Estimating the Amount of Phenol Adsorption on Powdered Activated Carbon

In this work, the adsorption mechanism of phenol on activated carbon from aqueous solutions was investigated. Batch experiments were performed as a function adsorbent rate, solution temperature, initial concentration, stirring speed, and pH. The optimal operating condition were: mass/volume ratio 0.6 g.L?1, temperature 20 °C speed 300 rpm. equilibrium data for analyzed by Langmuir, Freundlich, Temkin isotherm models. It found that Freundlich models fitted well process is favorable. Langmuir provides maximum 156.26 mg.g?1 at °C. pseudo-first-order, pseudo-second-order, intraparticle diffusion, Boyd used to fit kinetic data. kinetics described pseudo-second-order model. controlled external diffusion macropore mesopore, micropore diffusion. thermodynamic study revealed exothermic spontaneous nature with increased randomness solid-solution interface. On other hand, very large model based optimization parameters using k-nearest neighbor coupled gray wolf optimizer algorithm launched predict amount adsorption. KNN_GWO showed an advantage in giving more precise values related high statistical coefficients (R = 0.9999, R2 0.9998 R2adj 0.9998) low errors (RMSE 0, 0070, MSE 0.2347 MAE 0.2763). These advantages show efficiency performance used.