Exploring the Recent Trends, Progresses, and Challenges in the Application of Artificial Intelligence in Water Quality Assessment and Monitoring in Nigeria: A Systematic Review

In recent decades, machine learning (MLMachine learning (ML)) artificial intelligenceArtificial intelligence (AI) has found wide application in water quality monitoring and prediction due to the complexity of water quality data as a result of increasing variations in anthropogenic activities and seasonal fluctuations. In this study, a systematic literature review (SLR) was carried out to explore the trend in the application of ML models in water quality monitoring and prediction in Nigeria for the last two decades (2003–2023) through an in-depth comparative assessment of progress from the present well-observed trends to more hypothetical and advanced ML model simulation. To achieve this, the study integrated the bibliometric coupling and meta-analysis technique for data extraction and visualization. Two databases- Scopus and Web of Science (WoS)- were considered in the search for articles published from 2003 to 2023. After the analysis of the abstract, title, and full texts, 40 articles were considered for the SLR. Bibliographic coupling and visualization were then carried out based on the selected articles using the VOSviewer tool (version 1.6.18). Experimental results showed that the use of hybrid ML models in water quality prediction has not been well explored globally; a majority of the prediction has been based on the use of artificial neural networks (ANN). Among the ANN algorithms, the adaptive neuro-fuzzy inference system (ANFIS), and Wavelet-Adaptive Neural Fuzzy Interference System (W-ANFIS) hybrid models are the most accurate in prediction; with temperature, dissolved oxygen (DO), pH, conductivity (EC), and total dissolved solids (TDS) among the most frequently predicted parameters. China and the United States had the highest number of publications concerning the application of ML in water quality prediction; while Nigeria appears among the countries grossly lacking behind. Based on the sources of contaminants in aquatic systems in Nigeria, heavy metalsHeavy metals (Pb, Cd, Cu, Cr, and Zinc) were reported in more publications; linked majorly to mining activities. It is therefore proposed that more focus on future water quality prediction in Nigeria be placed on theDrinking water quality rapidly evolving field of machine learningMachine learning (ML).