Artificial neural network (ANN) approach for modeling Zn(II) adsorption from leachate using a new biosorbent

In this study, an artificial neural network (ANN) based classification technique is applied for the prediction of percentage adsorption efficiency for the removal of Zn(II) ions from leachate by hazelnut shell. The effect of operational parameters—such as initial pH, adsorbent dosage, contact time, and temperature—are studied to optimize the conditions for maximum removal of Zn(II) ions. The model was first developed using a three-layer feed forward back propagation network with 4, 8 and 4 neurons in the first, second, and third layers, respectively. A comparison between the model results and experimental data gave a high correlation coefficient (Raverage_ANN2=0.99) and showed that the model is able to predict the removal of Zn(II) from leachate. In order to evaluate the results obtained by ANN, full factor experimental design was applied to the batch experiments. As a result, Zn(II) concentration was reduced to 321.41 ± 12.24 mg L−1 from the initial concentration of 367.25 ± 23.43 mg L−1 by using hazelnut shell.

► The removal of Zn(II) ions from leachate by hazelnut shell is proposed.
► The ANN model is developed using a three layer feed forward back propagation network.
► To evaluate the results, an experimental design is applied to the batch experiments.
► According to optimization process, optimal removal capacity is found as 81.68%.