Enhanced metal ion adsorption using ZnO-MXene nanocomposites with machine learning-based performance prediction

The efficacy of ZnO-MXene nanocomposites as extremely effective adsorbents for the removal of metal ions from wastewater is investigated in this work. The two-step chemical method used to create composites showed how temperature affected their shape. In the adsorption studies, a high removal efficiency of 97% for chromium, 91% for cadmium, 97% for lead, and 96% for arsenic were observed. While isotherm studies showed a stronger fit with the Freundlich model, indicating heterogeneous adsorption, adsorption kinetics followed a pseudo-second-order model. The spontaneity and viability of adsorption, which is dominated by chemisorption mechanisms, were validated by thermodynamic studies. Furthermore, adsorption performance was well predicted by machine learning models such as Random Forest (RF) and Support Vector Machine (SVM), with RF showing the highest accuracy. These results demonstrate that ZnO-MXene is a promising and reasonably priced nano adsorbent that can satisfy WHO water quality requirements. A sustainable wastewater treatment solution is provided by the combination of both experimental and predictive modelling techniques, which yield important insights into adsorption mechanisms.