Highly efficient removal of heavy metals from wastewater by MnO2-NP-CPC and γ-Fe2O3-NP-CPC nanomaterials: modeling and optimization with machine learning (Artificial Neural Network).

Abstract In this study, two nanomaterials with excellent adsorption capacities were developed to remove chromium (VI) and cobalt (II) heavy metals efficiently from wastewater. MnO2-NP-CPC and γ-Fe2O3-NP-CPC nanomaterials were successfully synthesized using an agricultural waste which is cassava peels, and characterized by different techniques namely FTIR, XRD, BET, SEM, and EDX analysis. The experimental tests for the adsorption process were done in a batch system, and the influence of various parameters such as temperature, initial concentration, pH, and contact time on the biosorption of cobalt (II) and chromium (VI) were fully investigated. Furthermore, the Qmax were 546,32 mg/g and 349,59 mg/g for chromium (VI) and cobalt (II) respectively. The results fitted well the monolayer Langmuir with the pseudo-second-order model, revealing that chemisorption controls heavy metals removal, while the thermodynamic sorption was an endothermic and spontaneous reaction. Artificial Neural Network (ANN) model was developed to predict as well as to simulate the experimental results, for this purpose, the proposed model was based on five independent inputs or variables and one output or response which is the predicted adsorbed amount of Cr (VI) and Co (II), the predicted results were in good agreement with the experimental values, indeed the proposed ANN model showed an appreciable prediction accuracy with high optimization ability for chromium (VI) and cobalt (II) removal. Hence the present work has great potential for the industrial and environmental applications of biochar and nanomaterials especially in wastewater treatment and green chemistry.