Artificial neural network-genetic algorithm based optimization for the adsorption of phenol red (PR) onto gold and titanium dioxide nanoparticles loaded on activated carbon

The artificial neural network (ANN) model based on application of Levenberg–Marquardt algorithm (LMA) composed of linear transfer function (purelin) at output layer and tangent sigmoid transfer function (tansig) at hidden layer with 15 and 19 neurons for Au-NP-AC and TiO2-NP-AC, respectively was applied for optimization and prediction of adsorption system behavior. The judgment about applicability of this model was criterion such as mean squared error (MSE) (3.19e−04) and coefficient of determination (R2) 0.9962 were found for removal efficiency of Au-NP-AC. For TiO2-NP-AC, the obtained values for MSE and R2 were 0.0022 and 0.9729, respectively. It was seen that a good agreement between the experimental data and predicted values based on ANN model was found. The novel approximately green adsorbents with unique advantages such as low cost, locally available and relatively new are applicable for the removal of dyes from aqueous solutions. The optimization has been carried out by fitting the experimental parameters including initial pH, dye concentration, sorbent dosage and contact time to ANN. At initial pH lower than 2 the removal percentage and adsorption of dye on both adsorbent was complete that suggest and confirm their suitability for removal of this dye from complicated real matrices. The isothermal data for adsorption followed the Freundlich and Langmuir models with high monolayer adsorption capacity in short time that confirm their applicability and suggest their attractive candidates for removal of under study dye.