Document Type : Review Article
Authors
Islamic World Science and Technology Monitoring and Citation Institute (ISC), Shiraz, Iran.
Abstract
Recent advances in artificial intelligence (AI) technologies, particularly machine learning, artificial neural networks, decision support systems, and big data analytics, have created new opportunities for monitoring, forecasting, and decision-making in water resources management. Despite the growing body of literature in this field, the intellectual structure and thematic evolution of AI-related research in water resources management have not yet been comprehensively examined through co-word network analysis. Therefore, this study aims to conduct a bibliometric investigation to identify scientific publication trends and map the conceptual landscape of research at the intersection of artificial intelligence and water resources management. This study adopts a descriptive bibliometric approach. The dataset comprised publications indexed in the Scopus database up to May 2025 that addressed the application of artificial intelligence in water resources management within their titles, abstracts, or keywords. Following data extraction and document-type screening, the records were analyzed using VOSviewer software through co-word analysis, thematic clustering, and network visualization techniques. The findings revealed that a total of 3,657 documents were retrieved from Scopus, of which 3,314 journal articles, conference papers, and review articles were selected for the main analysis. Scientific output in this field has experienced marked acceleration since 2014, with 2024 representing the most productive publication year. China, the United States, India, and Iran emerged as the leading contributors to the field, with Iran ranking fourth globally with 319 publications. Co-word analysis identified five major thematic clusters: (1) machine learning and predictive modeling, (2) decision support systems, (3) water resources management, (4) water sustainability, and (5) emerging applications of artificial intelligence. These clusters indicate a clear shift in the knowledge base of the field from the description of water-related challenges toward predictive modeling, optimization, intelligent decision-making, and smart monitoring systems.
Keywords
Subjects
