Abstract
This work describes an experimental and machine learning approach for the prediction of selenite removal on chemically modified zeolite for water treatment. Breakthrough curves were constructed using iron-coated zeolite adsorbent and the adsorption behavior was evaluated as a function of an initial contaminant concentration as well as the ionic strength. An elevated selenium concentration in water threatens human health and aquatic life. The migration of this metalloid from the contaminated sites and the problems associated with its high releases into the water has become a major environmental concern. The mobility of this emerging metalloid in the contaminated water prompted the development of an efficient, cost-effective adsorbent for its removal. Selenite [Se(IV)] removal from aqueous solutions was studied in laboratory-scale continuous and packed-bed adsorption columns using iron-coated natural zeolite adsorbents. The proposed adsorbent combines iron oxide and natural zeolite's ability to bind contaminants. Breakthrough curves were initially obtained under variable experimental conditions, including the change in the initial concentration of Se (IV), and the ionic strength of solutions. Investigating the effect of these parameters will enhance selenite mobility retardation in contaminated water. Continuous adsorption experiment findings will evaluate the efficiency of this economical and naturally-based adsorbent for selenite removal and fate in water. Multilinear and non-linear regressions approaches were utilized, yet low coefficients of determination values were respectively obtained. Then, a comparative analysis of five boosted regression tree algorithms for a selenite breakthrough curve prediction was performed. AdaBoost, Gradient boosting, XGBoost, LightGBM, and CatBoost models were analyzed using the experimental data of the packed-bed columns. The performance of these models for the breakthrough curve prediction under different operation conditions, such as initial selenite concentration and ionic strength, was discussed. The applicability of these models was evaluated using performance metrics (i.e., Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R-2). The CatBoost model provided the best fit for a breakthrough prediction with a coefficient of determination R-2 equal to 99.57. The k-fold cross-validation technique and the statistical metrics verify this model's accurateness. A feature importance assessment indicated that Se (IV) initial concentration was the most influential experimental variable, while the ionic strength had the least effect. This finding was consistent with the column transport results, which observed Se (IV) sorption dependency on its inlet concentration; simultaneously, the ionic strength effect was negligible. This work proposes implementing machine learning-based approaches for predicting water remediation-associated processes. The significance of this work was to provide an alternative method for investigating selenite adsorption behavior and predicting the breakthrough curves using a machine-based approach. This work also highlighted the importance of management practices of adsorption processes involved in water remediation.