| Artificial Intelligence in Modeling and Removal of Dissolved Pollutants in Water and Wastewater: A Review |
| کد مقاله : 1117-IWWA |
| نویسندگان |
|
علی مریدی *، محمد سجاد مفرحی، رضا خلیلی دانشکده عمران، آب و محیط زیست دانشگاه شهید بهشتی |
| چکیده مقاله |
| In recent years, artificial intelligence (AI) has emerged as a transformative framework for modeling, prediction, and optimization in water and wastewater treatment systems. Classical machine learning algorithms such as artificial neural networks (ANNs) and support vector machines (SVMs) have been widely applied to predict pollutant removal efficiency. However, recent research (2020–2025) has demonstrated the superior capability of advanced AI paradigms, including Physics-Informed Neural Networks (PINNs), Graph Neural Networks (GNNs), Reinforcement Learning (RL/DRL), Federated Learning (FL), Explainable AI (XAI), and hybrid Physics–Machine Learning (Hybrid Physics–ML) architectures. These models effectively integrate physical constraints, spatiotemporal dependencies, and distributed learning mechanisms to enhance predictive accuracy, interpretability, and energy efficiency. Deep reinforcement learning and multi-agent control strategies have shown remarkable potential in adaptive aeration and membrane operation, while hybrid GNN–PINN frameworks achieved pollutant concentration prediction accuracies exceeding 95%. This review provides a comprehensive overview of recent advancements in AI-driven modeling for dissolved pollutant removal from aqueous environments, emphasizing emerging challenges, opportunities, and future research directions toward sustainable and intelligent water treatment systems. |
| کلیدواژه ها |
| Keywords: Artificial Intelligence, Machine Learning, Modeling, Pollutant Removal, Water and Wastewater. |
| وضعیت: پذیرفته شده برای ارسال فایل های ارائه پوستر |
