USE OF RESPONSE SURFACE METHODOLOGY AND ARTIFICIAL NEURAL NETWORK APPROACH FOR METHYLENE BLUE REMOVAL BY ADSORPTION ONTO WATER HYACINTH

The release of coloured effluents from various dying industries are of great concern due to the challenge involved in the treatment process. In present work, response surface methodology (RSM) and artificial neural network (ANN) were used to predict the color removal using adsorption process. Water hyacinth (WH) was used as an economical adsorbent for color removal from aqueous solution in a batch system. The individual effect of influential parameter viz. initial pH, MB (dye) concentration, and the adsorbent dose were studied using the central composite design of RSM. The RSM result was used as an input data along with final pH (non-controllable parameter) after adsorption to train the ANN model. Color removal of 96.649% was obtained experimentally at the optimized condition. A comparison between the experimental data and model results shows a high correlation coefficient (R2RSM = 0.99 and R2ANN = 0.98) and showed that the two models predicted MB removal indicating WH can be used as an adsorbent for color removal from dye wastewater.