Artificial intelligence for water quality monitoring: a PRISMA-based systematic literature review, taxonomy, comparative analysis, and future research directions

Accurate and reliable water quality monitoring (WQM) has become increasingly important due to rapid urbanization, industrialization, climate change, and anthropogenic activities that threaten global freshwater resources. Conventional water quality assessment methods primarily rely on manual sampling and laboratory analysis, which are labour-intensive, time-consuming, costly, and unsuitable for continuous real-time monitoring of large-scale aquatic environments. Recent advances in Artificial Intelligence (AI), the Internet of Things (IoT), and sensing technologies have enabled intelligent, data-driven approaches capable of modelling complex nonlinear relationships, detecting contamination events, and improving predictive decision-making. This study presents a systematic literature review (SLR) of AI-based water quality monitoring using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. A systematic search of IEEE Xplore, Scopus, Web of Science, ScienceDirect, and SpringerLink identified studies published between 2020 and 2026, of which 91 met the predefined inclusion and exclusion criteria. Review and survey articles were excluded from the analytical corpus so that secondary literature was not pooled with primary studies. A structured taxonomy is developed to characterise the strengths, limitations, interpretability and reported applicability of these model families. Because the included studies differ in target variable, dataset, preprocessing and validation protocol, no pooled performance comparison across model categories is reported and no meta-analysis was undertaken. The review identifies key challenges, including heterogeneous datasets, limited model generalization, overfitting, computational complexity, sensor calibration issues, data inconsistency, and the lack of standardized benchmark datasets. Furthermore, emerging research directions comprising Explainable Artificial Intelligence (XAI), Federated Learning, Edge AI, Graph Neural Networks, Digital Twins, Foundation Models, and multimodal environmental intelligence are discussed. The findings provide researchers, practitioners and policymakers with a structured reference to the current evidence base on AI-based water quality monitoring, together with the methodological limitations of that evidence, to inform the development of future monitoring systems for sustainable water resource management.