Water is essential for sustainable development, but it is a limited resource. The universal demand for quality water, be it for purposes of drinking, industrial use, sanitation, etc., has been rising exponentially, but the increasing world population and climate change have given rise to an alarming decline of freshwater resources and their availability. Monitoring the quality of ground and surface water is essential because these sources are the primary suppliers of water for home and industrial purposes. Water bodies are being impacted by emerging contaminants, which can infiltrate the ecosystem and have negative effects on human health and the environment. Machine learning (ML) and deep learning are commonly employed artificial intelligence (AI) methodologies. They demonstrate a logical approach based on evidence rather than relying on knowledge, which forms the basis of most fields in physical science. The utilization of AI approaches in water purification and wastewater treatment processes offers substantial benefits due to the ability to automate these facilities, resulting in streamlined and cost-effective operations, as well as a considerable decrease in human errors. This review provides a comprehensive overview of recent progress and findings in different AI technologies used for determining the quality of source water, coagulation/flocculation, disinfection, membrane filtration, desalination, modeling wastewater treatment plants, predicting membrane fouling, removing heavy metals, and monitoring levels of biological oxygen demand and chemical oxygen demand. The evaluation of the efficacy of several AI technologies in this review demonstrates the effective integration of these technologies in water treatment applications. Additionally, it emphasizes the constraints that impede their application in practical water treatment systems. This article provides a detailed summary of the progress of ML applications in both natural and engineered water systems, considering the promising future of ML. This review offers citations for addressing a broader spectrum of water-related issues and provides other perspectives on the intelligent advancement of water science.
Keshri et al. (Fri,) studied this question.