The problem of heavy metal pollution in wastewater has prompted the demand for more effective and sustainable treatment systems. In the recent decade, the integration of artificial intelligence (AI) in heavy metal adsorption processes has shown tremendous potential in enhancing efficiency and optimizing operational parameters. This study intends to identify global research trends on the application of AI in optimizing heavy metal adsorption processes by a bibliometric method for the period 2010 to 2024. Data were acquired from Google Scholar and filtered to include indexed papers, then analyzed using VOSviewer and Microsoft Excel software to evaluate annual publishing trends, as well as visualization of keyword co-existence. The findings of the investigation showed an impressive move in publications after 2019. The leading terms detected included “machine learning,” “neural networks,” and “optimization.” Despite demonstrating encouraging trends, research in this subject still confronts hurdles such as inadequate large-scale experimental data, minimal integration of AI with Internet of Things (IoT) systems, and lack of industrial-scale applications. This study shows the need of building hybrid AI-IoT systems, using big data analytics, and adaptive predictive models to increase the effectiveness of heavy metal adsorption systems in the future. These findings are likely to be a key reference for researchers and practitioners in creating smart and sustainable waste processing systems.
Afandy et al. (Mon,) studied this question.