Prediction of biosorption of total chromium by Bacillus sp. using artificial neural network

An artificial neural network (ANN) model was developed to predict the biosorption efficiency of Bacillus sp. for the removal of total chromium from aqueous solution based on 360 data sets obtained in a laboratory batch study. Experimental parameters affecting the biosorption process such as pH, contact time and initial concentration of chromium were studied. A contact time of 2 h was generally sufficient to achieve equilibrium. At optimal conditions, metal ion uptake increased with increasing initial metal ion concentration. The Freundlich model was applied to describe the biosorption isotherm. Chromium biosorption was most significantly influenced by pH, followed by the initial metal concentration of the solution. The findings indicated that the ANN model provided reasonable predictive performance (R(2) = 0.971) of chromium biosorption.