Artificial neural networks (ANN) approach for modeling of removal of Lanaset Red G on Chara contraria

A three-layer artificial neural network (ANN) was constructed to predict the removal efficiency of Lanaset Red (LR) G on Chara contraria based on 2304 experimental sets. The effects of operating variables (particle size, adsorbent dosage, pH regimes, dye concentration, and contact time) were studied to optimize the sorption conditions of this dye. The operating variables were used as the input to the constructed neural network to predict the dye uptake at any time as the output. This adsorbent was characterized by FTIR. Pseudo second-order model was also fitted to the experimental data. According to values of error analyses and determinations coefficient, the ANN was more appropriate to describe this adsorption process. Result of this model indicated that pH regimes had the highest importance effect (49%) on the dye uptake.

Research highlights
► We examine the sorption of LR G on chara contraria various conditions.
► The ANN model was found to be excellent in representing the sorption kinetics of LR G on the alga.
► ANN model indicated that pH regimes had the highest importance effect on sorption.