The artificial neural network and Box-Behnken design for Cu2+ removal by the pottery sludge from water samples: Equilibrium, kinetic and thermodynamic studies

Copper is a toxic metal to the living beings. The adsorption capacity of a novel, mesoporous, and industrial waste clay mixture was investigated in the laboratory by the batch adsorption experiments. The impacts of several factors such as solution pH, initial Cu2+ concentration, contact time, temperature were examined to test the adsorption process. The critical statistical analysis was applied to find the best-fit isotherm model. Langmuir isotherm better described the experimental data. The thermodynamic study showed the endothermic nature, while pseudo-second-order kinetic of the chemical process confirmed the chemisorption process. Various techniques such as SEM, EDX, FTIR and XRD were used to characterize the material's particles before and after adsorption. The mean crystalline dimension of the pottery sludge was 23.2 nm. A three-layer ANN model with backpropagation algorithm was developed to model the adsorption process. RSM in combination with BBD was used to design, simulate and optimise the adsorption parameters. ANOVA analysis and 3D figures was applied to check the significance of the independent factors and their interactions. The excellent results of the present work verify the effectiveness of pottery sludge as an adsorbent to bind Cu2+ from polluted water.