Artificial neural network (ANN) approach for modeling Zn(II) adsorption in batch process

Abstract

Artificial neural networks (ANN) were applied to predict adsorption efficiency of peanut shells for the removal of Zn(II) ions from aqueous solutions. Effects of initial pH, Zn(II) concentrations, temperature, contact duration and adsorbent dosage were determined in batch experiments. The sorption capacities of the sorbents were predicted with the aid of equilibrium and kinetic models. The Zn(II) ions adsorption onto peanut shell was better defined by the pseudo-second-order kinetic model, for both initial pH, and temperature. The highest R2 value in isotherm studies was obtained from Freundlich isotherm for the inlet concentration and from Temkin isotherm for the sorbent amount. The high R2 values prove that modeling the adsorption process with ANN is a satisfactory approach. The experimental results and the predicted results by the model with the ANN were found to be highly compatible with each other.