2025, Vol. 6, Issue 2, Part A

The increasing contamination of water resources by heavy metals necessitates the development of efficient and sustainable methods for their removal. In this study, we explored the use of artificial intelligence (AI)-driven optimization for the synthesis of nanoparticles aimed at enhancing heavy metal removal from wastewater. The primary objective was to design an AI-based framework that could optimize nanoparticle synthesis conditions—such as precursor ratios, temperature, and reaction time—to achieve maximum adsorption efficiency while maintaining nanoparticle stability and reusability. To achieve this, we utilized Bayesian optimization and metaheuristics to guide the synthesis of metal-based nanoparticles (Fe?O?, ZnO-MXene, rGO-titanate) for Pb²?, Cd²?, As(V), and Cr(VI) removal from synthetic wastewater.

The experimental results revealed that the AI-optimized nanoparticles exhibited significantly improved adsorption capacities compared to control materials synthesized using traditional methods. The maximum adsorption capacities (q_max) for Pb²?, Cd²?, As(V), and Cr(VI) were 212.6, 185.4, 156.8, and 244.1 mg/g, respectively. Additionally, AI-optimized nanoparticles demonstrated excellent selectivity in multi-ion systems and retained over 90% of their initial adsorption capacity after five regeneration cycles, outperforming control nanoparticles. Statistical analyses confirmed that these improvements were statistically significant (p < 0.05).

The AI-driven optimization framework demonstrated significant advantages in nanoparticle synthesis, offering higher efficiency, selectivity, and regeneration compared to traditional approaches. These results suggest that AI-driven methodologies can provide an efficient and sustainable solution for heavy metal removal from wastewater. Future studies should focus on scaling these AI-based processes and further exploring their real-world applications in wastewater treatment systems.