The use of artificial neural networks (ANN) for modeling of adsorption of Cu(II) from industrial leachate by pumice

In this present work, artificial neural networks (ANN) are applied for the prediction of percentage adsorption efficiency for the removal of Cu(II) ions from industrial leachate by pumice. The effect of operational parameters such as initial pH, adsorbent dosage, temperature, and contact time is studied to optimize the conditions for maximum removal of Cu(II) ions. The model is first developed using a three layer feed forward backpropagation network with 4, 8 and 4 neurons in first, second and third layers, respectively. Furthermore, radial basis function (RBF) network is also proposed and its performance is compared to traditional network type. A comparison between the ANN models presents high correlation coefficient (R2 = 0.999) and shows that the RBF network model is able to predict the removal of Cu(II) from industrial leachate more accurately.

► Artificial neural networks are applied for prediction of removal efficiency by pumice.
► Pumice is a cheap, readily available and effective adsorbent material.
► Initial pH, adsorbent dosage, temperature, contact time are studied for optimization.
► RBF network is able to predict the removal of Cu(II) more accurately.