Batch adsorption studies of the removal of methyl violet 2B by soya bean waste: isotherm, kinetics and artificial neural network modelling

Batch adsorption experiment of methyl violet 2B was studied using soya bean waste. Isotherm, kinetics and thermodynamics aspects of the study were investigated to provide better understanding of the adsorption process. The effects of pH and ionic strengths provide insights to the involvement of electrostatic attraction and hydrophobic–hydrophobic interactions. Kinetics data best-fitted the pseudo-second-order model indicating rate-limiting step may be controlled by chemical processes. The Weber–Morris model suggested intraparticle diffusion is not the rate-limiting step. The thermodynamics studies showed that the adsorption process was endothermic in nature. The Langmuir isotherm model best fitted with the experimental data compared to other isotherm models studied, with the Langmuir’s maximum adsorption capacity of 180.7 mg g⁻¹ at 25 °C. An artificial neural network (ANN) model was used to predict the adsorption capacity of the adsorbent under different conditions. The high value of correlation coefficient of 0.9946 indicated that the ANN model provided a very good predictive performance for the adsorption system.