RESUMEN
Two machine learning approach (i.e. Radial Basis Function Neural Network (RBF-NN) and Random Forest (RF) was developed and evaluated against a quadratic response surface model to predict the maximum removal efficiency of brilliant green (BG) from aqueous media in relation to BG concentration (4-20mgL-1), sonication time (2-6min) and ZnS-NP-AC mass (0.010-0.030g) by ultrasound-assisted. All three (i.e. RBF network, RF and polynomial) model were compared against the experimental data using four statistical indices namely, coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE) and absolute average deviation (AAD). Graphical plots were also used for model comparison. The obtained results using RBF network and RF exhibit a better performance in comparison to classical statistical model for both dyes. The significant factors were optimized using desirability function approach (DFA) combined central composite design (CCD) and genetic algorithm (GA) approach. The obtained optimal point was located in the valid region and the experimental confirmation tests were conducted showing a good accordance between the predicted optimal points and the experimental data. The properties of ZnS-NPs-AC were identified by X-ray diffraction; field emission scanning electron microscopy, energy dispersive X-ray spectroscopy (EDS) and Fourier transformation infrared spectroscopy. Various isotherm models for fitting the experimental equilibrium data were studied and Langmuir model was chosen as an efficient model. Various kinetic models for analysis of experimental adsorption data were studied and pseudo second order model was chosen as an efficient model. Moreover, ZnS nanoparticles loaded on activated carbon efficiently were regenerated using methanol and after five cycles the removal percentage do not change significantly.
RESUMEN
Analytical chemists apply statistical methods for both the validation and prediction of proposed models. Methods are required that are adequate for finding the typical features of a dataset, such as nonlinearities and interactions. Boosted regression trees (BRTs), as an ensemble technique, are fundamentally different to other conventional techniques, with the aim to fit a single parsimonious model. In this work, BRT, artificial neural network (ANN) and response surface methodology (RSM) models have been used for the optimization and/or modeling of the stirring time (min), pH, adsorbent mass (mg) and concentrations of MB and Cd2+ ions (mg L-1) in order to develop respective predictive equations for simulation of the efficiency of MB and Cd2+ adsorption based on the experimental data set. Activated carbon, as an adsorbent, was synthesized from walnut wood waste which is abundant, non-toxic, cheap and locally available. This adsorbent was characterized using different techniques such as FT-IR, BET, SEM, point of zero charge (pHpzc) and also the determination of oxygen containing functional groups. The influence of various parameters (i.e. pH, stirring time, adsorbent mass and concentrations of MB and Cd2+ ions) on the percentage removal was calculated by investigation of sensitive function, variable importance rankings (BRT) and analysis of variance (RSM). Furthermore, a central composite design (CCD) combined with a desirability function approach (DFA) as a global optimization technique was used for the simultaneous optimization of the effective parameters. The applicability of the BRT, ANN and RSM models for the description of experimental data was examined using four statistical criteria (absolute average deviation (AAD), mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R2)). All three models demonstrated good predictions in this study. The BRT model was more precise compared to the other models and this showed that BRT could be a powerful tool for the modeling and optimizing of removal of MB and Cd(ii). Sensitivity analysis (calculated from the weight of neurons in ANN) confirmed that the adsorbent mass and pH were the essential factors affecting the removal of MB and Cd(ii), with relative importances of 28.82% and 38.34%, respectively. A good agreement (R2 > 0.960) between the predicted and experimental values was obtained. Maximum removal (R% > 99) was achieved at an initial dye concentration of 15 mg L-1, a Cd2+ concentration of 20 mg L-1, a pH of 5.2, an adsorbent mass of 0.55 g and a time of 35 min.
