Water pollution resulting from heavy metals including lead [Pb(II)] is a major health concern for humans, animals, and aquatic life. Pb(II) is a highly hazardous contaminant that must be effectively removed from water before reuse or discharge. In this study, a hybrid electrocoagulation/adsorption system (EC/A) using aluminum electrodes integrated with a novel adsorbent GO@ZIF-7 nanocomposite, was studied for aqueous phase Pb(II) removal. The hybrid EC/A system yielded a near complete Pb(II) removal. The system was optimized using the Response Surface Methodology (RSM) based design of experiments (DOE) technique; specifically using the central composite design (CCD) the study analyzed the impacts of four primary process variables (i.e., current density, Pb(II) initial concentration, dosage of GO@ZIF-7 nanocomposite, and conductivity) on the Pb(II) removal. Notably, the findings show the significant role of current density in the Pb(II) removal process, particularly at a current density of 1.5 mA/cm2. The above-mentioned RSM design along with the analysis of variance (ANOVA) based statistical analysis and optimization, confirmed the suitability of the proposed RSM-based equations for Pb(II) removal modeling. Collectively, the findings of this study indicate that the proposed hybrid EC/A system using aluminum electrodes integrated with a novel GO@ZIF-7 nanocomposite has a significant practical viability as suggested by the remarkably high Pb(II) removal efficiency. Furthermore, this study also presents the effectiveness of three advanced machine learning (ML) based models, i.e., artificial neural network (ANN), eXtreme Gradient Boosting (XGBoost), and Random Forest Regression, for predictingthe Pb(II) removal using the EC/A process.
Read full abstract