Experimental design,machine learning approaches for the optimization and modeling of caffeine adsorption

In the current research, the sorption of caffeine on fresh and calcined Cu–Al layered double hydroxide was comparatively studied based on adsorption parameters, adsorption kinetics, and adsorption isotherm. Response surface methodology (RSM), support vector machine (SVM) and artificial neural network (ANN), as data mining methods, were applied to develop models by considering various operating variables. Different characterization methods were exploited to conduct a comprehensive analysis of the characteristics of HDL in order to acquire a thorough understanding of its structural and functional features. The Langmuir model was employed to accurately describe the maximum monolayer adsorption capacity for calcined sample (q_max) of 152.99 mg/g mg/g with R² = 0.9977. The pseudo-second order model precisely described the adsorption phenomenon (R² = 0.999). The thermodynamic analysis also reveals a favorable and spontaneous process. The ANN model predicts adsorption efficiency result with R² = 0.989. The five-fold cross-validation was achieved to evaluate the validity of the SVM. The predication results revealed approximately 99.9% accuracy for test datasets and 99.63% accuracy for experiment data. Moreover, ANOVA analysis employing the central composite design-response surface methodology (CCD-RSM) indicated a good agreement between the quadratic equation predictions and the experimental data, which results in R² of 0.9868 and the highest removal percentages in optimized step were obtained for RSM (pH 5.05, mass of adsorbent 20 mg, time of 72 min, and caffeine concentrations of 22 mg/L). On the whole, the findings confirm that the proposed machine learning models provided reliable and robust computer methods for monitoring and simulating the adsorption of pollutants from aqueous solutions by Cu–Al–LDH.