Artificial Intelligence Applications in River Management: Challenges and Insights from a Bibliometric Review

Artificial Intelligence Applications in River Management: Challenges and Insights from a Bibliometric Review | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 9 January 2025 V1 Latest version Share on Artificial Intelligence Applications in River Management: Challenges and Insights from a Bibliometric Review Authors : Yueya Chang [email protected] and Jun Yang Authors Info & Affiliations https://doi.org/10.22541/au.173641898.83049233/v1 Published Ecohydrology Version of record Peer review timeline 433 views 213 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract This study conducts a systematic bibliometric analysis of the applications of artificial intelligence (AI) in river management systems from 2000 to 2024. By examining 477 publications retrieved from the Web of Science Core Collection and utilizing CiteSpace for visualization, we identify key research trends, collaborative networks, and emerging themes in this rapidly advancing field. The findings reveal a significant geographical concentration of research output, with China (101 papers), the United States (76 papers), and the United Kingdom (29 papers) ranking as the leading contributors. The analysis highlights an exponential increase in publications, particularly after 2020, with a primary focus on machine learning applications for water quality monitoring and real-time prediction systems. Notable institutions, including the University of Malaya, the Chinese Academy of Sciences, and Duy Tan University, have demonstrated high research productivity. Moreover, critical gaps are identified, such as insufficient stakeholder engagement and the need for more transparent AI model development. These insights offer valuable guidance to environmental managers and policymakers aiming to implement AI-driven solutions for sustainable river management. Artificial Intelligence Applications in River Management: Challenges and Insights from a Bibliometric Review Yueya Chang11Yueya Chang （the corresponding author, Ph.D., Lecture, Email: [email protected] ）, Jun Yang b (a. School of Municipal and Environmental Engineering, Shanghai Urban Construction Vocational College, Shanghai, 200438, Peopleʼs Republic of China b. School of Mathematics, Physics and Statistics, Shanghai Polytechnic University, Shanghai, 201209, Peopleʼs Republic of China) Abstract: This study conducts a systematic bibliometric analysis of the applications of artificial intelligence (AI) in river management systems from 2000 to 2024. By examining 477 publications retrieved from the Web of Science Core Collection and utilizing CiteSpace for visualization, we identify key research trends, collaborative networks, and emerging themes in this rapidly advancing field. The findings reveal a significant geographical concentration of research output, with China (101 papers), the United States (76 papers), and the United Kingdom (29 papers) ranking as the leading contributors. The analysis highlights an exponential increase in publications, particularly after 2020, with a primary focus on machine learning applications for water quality monitoring and real-time prediction systems. Notable institutions, including the University of Malaya, the Chinese Academy of Sciences, and Duy Tan University, have demonstrated high research productivity. Moreover, critical gaps are identified, such as insufficient stakeholder engagement and the need for more transparent AI model development. These insights offer valuable guidance to environmental managers and policymakers aiming to implement AI-driven solutions for sustainable river management. Keywords: Artificial Intelligence, River Management Systems, CiteSpace, Bibliometric Analysis 1 Introduction Rivers have long been recognized as essential ecological and cultural resources, sustaining biodiversity, regulating ecosystems, and driving human development (Beeton, 2002;He et al., 2022;Du et al., 2023). However, the escalating impacts of climate change, urbanization, and ecological degradation are fundamentally transforming river systems, imposing unprecedented challenges on their effective management (Malve, 2007;Cai et al., 2015;Jaehnig et al., 2019;Piegay et al., 2020). Traditional management approaches, while historically effective in safeguarding water security and supporting ecosystems, are increasingly inadequate when confronted with the complex dynamics and uncertainties of contemporary river basins (Norreys, 1991;Quinn, 2011). Pioneering work by Norreys (1991) on fluvial geomorphology and Graeber et al. (2013) advocating for the natural flow regime has laid crucial groundwork for understanding river ecosystems as dynamic systems requiring careful stewardship. Yet, the rapid intensification of environmental stressors calls for transformative approaches that go beyond conventional methods. In recent years, the limitations of traditional river management practices have spurred growing interest in artificial intelligence (AI) as a transformative tool capable of addressing these challenges (Huntingford et al., 2019;Gonzales-Inca et al., 2022). Preliminary applications of AI have demonstrated substantial promise in areas such as water quality monitoring, flood forecasting, sediment dynamics modeling, and ecosystem restoration (Yin et al., 2021;Machado et al., 2018;Lu et al., 2023;Ladewig et al., 2023). For instance, studies by Yao et al. (2022) and Beven (2020) have shown how deep learning algorithms can process vast and heterogeneous environmental datasets into actionable insights, significantly enhancing the accuracy and efficiency of water quality monitoring systems. Similarly, Abbas et al. (2022) demonstrated how AI-driven hydrological models can uncover subtle patterns and interactions in river systems that often elude traditional methods. These advancements underscore AI’s potential to revolutionize decision-making in river management by enabling data-driven, real-time, and adaptive solutions. The convergence of multiple technological advancements has further expanded the application space for AI in river management. Advances in environmental monitoring networks, the proliferation of satellite systems, and the availability of extensive hydrological datasets have created unprecedented opportunities for integrating machine learning techniques into river management frameworks (Rozos et al., 2022;Kan et al., 2020;Huntingford et al., 2019;Heintzman et al., 2024;De la Fuente et al., 2024). For example, AI-based sediment flow models have been successfully applied to understand sediment dynamics in complex systems like the Mississippi River (Pandit, 2024), At the same time, researchers like Ihsanullah et al. (2022) and Ruangpan et al. (2021) have highlighted the importance of designing AI tools with direct input from stakeholders to maximize their usability and effectiveness in practical applications. Kunkel et al. (2023) ’s innovative use of interpretive structural models exemplifies how stakeholder perspectives can be successfully integrated into AI-driven decision-making, while Acuna et al. (2023)’s efforts in developing explainable AI models underline the importance of making these technologies accessible and trustworthy. Nature-based solutions, which prioritize ecosystem restoration alongside social and economic benefits, represent an emerging paradigm in river management (Shrestha et al., 2007;Ruangpan et al., 2021). When combined with advanced AI applications, as demonstrated by Ihsanullah et al. (2022), Nature-based solutions have shown transformative potential in achieving sustainable river management goals. However, the true value of such approaches transcends their technical capabilities, lying instead in their ability to support informed decision-making and promote long-term ecological and social resilience (Kunkel et al., 2023;Stoffels et al., 2024;Meng et al., 2017;Iqbal et al., 2023). Despite these promising advancements, significant gaps remain in the current knowledge landscape. A key limitation lies in the lack of systematic, cross-regional analyses that could provide a comprehensive understanding of how AI is being applied globally to address sustainable river management challenges (Quinn, 2011;Malve, 2007;Jaehnig et al., 2019;Iqbal et al., 2023). While regional studies have contributed valuable insights, there is an absence of bibliometric analyses that can map the overall research trends, collaboration networks, and emerging themes in this rapidly evolving field (Ren et al., 2020;Peters et al., 2023;Pan et al., 2023;Osborne et al., 2022). Addressing this gap is crucial for both academic progress and practical implementation. To bridge this knowledge gap, this study conducts a systematic bibliometric analysis of publications on AI applications in river management systems. Using the Web of Science Core Collection database and CiteSpace visualization tools, we analyze 477 publications spanning the period from 2000 to 2024. This investigation is guided by six fundamental research questions: (1) What are the temporal patterns in publication output for AI-driven river management research? (2) Which countries are leading in AI research applications for river management? (3) What are the key institutional hubs driving innovation in this field? (4) Who are the influential researchers shaping discourse in AI and river management? (5) What are the core journals disseminating impactful research? (6) What are the emerging trends and future directions for research in this area? By addressing these questions, this study seeks to provide valuable insights into the current state and future prospects of AI applications in river management. The findings aim to inform academic discourse, guide policy development, and support the implementation of sustainable and adaptive river management practices in an increasingly challenging environmental landscape. 2 Research methods 2.1 Database selection and scope The primary dataset for this study was obtained from the Web of Science (WoS) Core Collection, a widely recognized academic database renowned for its extensive coverage and robust citation indexing capabilities. WoS encompasses influential journals across a variety of disciplines, making it a leading resource for global bibliometric analyses (Wang et al., 2018;Smirnova and Mayr, 2023;Mokhnacheva and Tsvetkova, 2019;Boudry, 2021). Its inclusion of high-quality, peer-reviewed publications ensures the reliability and credibility of the data analyzed in this study, particularly in the interdisciplinary domain of artificial intelligence (AI) applications in river management. 2.2 Literature retrieval strategy To maintain data consistency and avoid potential discrepancies caused by the daily updates of the WoS database, all data collection was completed on a single day (December 13, 2024). The study’s temporal scope spanned from January 1, 2000, to December 13, 2024, providing a 25-year overview of research trends in the application of AI for river management. The analysis considered multiple document types, including articles, reviews, proceedings papers, and early-access publications, to capture a comprehensive view of scientific outputs in this field. A structured retrieval strategy was employed, incorporating a combination of keywords such as ”artificial intelligence,” ”machine learning,” ”neural networks,” and ”river management.” Boolean operators (e.g., AND, OR) were used to refine and broaden the search, while synonyms and related terms were included to ensure the comprehensive coverage of relevant literature. The search results were restricted to English-language publications to ensure consistency in content analysis. The initial search yielded 477 documents, which were subjected to a systematic data cleaning process. This included the removal of incomplete or irrelevant entries through manual screening and format standardization based on titles, abstracts, and, where necessary, full-text reviews. After completing the cleaning process, all 477 articles were deemed relevant for inclusion and retained for further analysis. 2.3 Bibliometric analysis framework Bibliometric analysis is a widely used quantitative method for evaluating scientific research outputs, employing statistical and computational techniques to uncover patterns, trends, and relationships within academic literature (Md Shahri and Mohd Ali, 2024;Hao et al., 2021). With the advancement of modern computational capabilities, bibliometric tools have become indispensable for exploring large-scale datasets and generating visual insights into publication patterns, research influence, and knowledge diffusion, bibliometric approaches also provide a means to map collaborative networks and discover thematic clusters within rapidly evolving scientific fields, such as AI-driven environmental management (Zare et al., 2024;Yu et al., 2019;Thangagiri and Sivakumar, 2024;Ren et al., 2020;Pan et al., 2023;He et al., 2022;Hao et al., 2021;Hadiyawarman et al., 2024). One of the primary strengths of bibliometric analysis lies in its ability to create visual knowledge maps, offering an intuitive and interpretable representation of relationships among publications, authors, institutions, and emerging research themes. These visualizations serve as valuable tools for identifying trends, collaborative structures, and knowledge gaps within a field. Of particular importance to this study is the use of bibliometric techniques to evaluate the evolution of AI applications in river management, where advancements in machine learning and data analytics are transforming traditional approaches to environmental monitoring and management (Md Shahri and Mohd Ali, 2024). Recent advances in bibliometric techniques have made them indispensable for identifying research frontiers, collaborative networks, and knowledge gaps within specific disciplines (Zare et al., 2024;Thangagiri and Sivakumar, 2024). For the bibliometric analysis, we utilized CiteSpace 6.3.R1 to perform co-citation analysis and generate visual knowledge maps (Zhuang et al., 2022;Cao et al., 2023). The software parameters were configured with a period from 2000 to 2024, using one-year time slices and selecting the top 50 most-cited references per slice. In the visualization network, nodes (spheres) represent co-cited references with their sizes proportional to citation frequencies, while links indicate co-citation relationships between references (Cao et al., 2023). The concentric rings within each node display temporal citation patterns across different periods. These visualization features, combined with the software’s analytical capabilities, facilitated the identification of key literature and analysis of research trends in the field. 3 Research results 3.1 Publication outputs and trends Understanding the temporal evolution of research topics is fundamental to assessing their academic significance (Zhou et al., 2007;Zhong et al., 2018;Zheng et al., 2015). To address the publication status of AI in river management research, we conducted a bibliometric analysis of publication patterns. This study conducted a comprehensive review of 477 publications in the field of artificial intelligence in river management from 2000 to 2024, with an average annual publication rate of 19.08 articles. Analysis of the data revealed notable periodic fluctuations in annual publication rates, showing an overall upward growth over time (Figure 1). The development of the research field was categorized into three distinct phases: During the initial phase (2000-2014), the field exhibited modest research activity with 1-6 annual publications, characterized by exploratory studies establishing fundamental methodological frameworks. A significant transformation emerged during the growth phase (2015-2019), marked by a substantial increase to 11-25 annual publications. This period witnessed the emergence of systematic AI applications in river management, characterized by more sophisticated methodological approaches and expanded scope of implementation. The expansion phase (2020-2024) represents a period of exponential growth, with annual publications exceeding 50 and reaching a peak of 111 publications in 2024. This dramatic increase reflects the maturation of AI technologies and their widespread adoption in river management systems. Regression analysis of cumulative publication data from 2000 to 2024 revealed a robust exponential growth pattern in AI-driven river management research, characterized by the following mathematical model: y = 1.7637e 0.2276x R² = 0.9904 where x denotes the temporal dimension (years since 2000) and y represents the cumulative publication volume. The model demonstrates exceptional statistical reliability, evidenced by an extraordinarily high coefficient of determination (R² = 0.9904). This remarkable goodness of fit not only validates the model’s accuracy but also provides compelling evidence for the field’s accelerating growth trajectory. The model’s predictive capabilities indicate sustained exponential growth in research output, reflecting both the expanding technological capabilities of AI and the growing demand for intelligent solutions in river management. This quantitative framework offers critical insights into the evolution of the field and enables the anticipation of future research trends, thereby guiding strategic decision-making in research planning and resource allocation within the domain of environmental engineering. 3.2 Active countries Our bibliometric analysis of 477 publications from 86 countries reveals significant disparities in research output, influence, and collaboration in the application of artificial intelligence (AI) to river management. Table 1 highlights the leading contributors by publication volume and network centrality, reflecting their role in shaping global research trends. The United States (76 publications, centrality 0.32) exemplifies ”high-impact efficiency,” balancing theoretical advancements with practical applications. U.S. research is particularly impactful in machine learning innovations, including real-time monitoring and predictive modeling. Similarly, the United Kingdom (29 publications, centrality 0.31) achieves outsized influence through a more focused approach, pioneering AI solutions for urban river systems and advancing integrative management frameworks. In contrast, China (101 publications, centrality 0.23) leads in publication volume but demonstrates a ”quantity-impact paradox,” with a primary focus on domestic applications and weaker connectivity in global networks. This suggests an opportunity for China to amplify global impact through expanded international collaborations. Regional specialization reveals distinct environmental priorities. For example: Australia (34 publications, centrality 0.13) focuses on AI for arid-zone river management, addressing extreme climatic challenges. India (78 publications, centrality 0.12) reflects pressing environmental concerns in developing nations but faces barriers to international integration. Saudi Arabia (21 publications) and South Africa (12 publications) contribute adaptive AI solutions tailored to data-scarce and extreme climate conditions, offering globally relevant insights. Visualization of international collaboration networks (Figure 2) highlights the crucial role of global partnerships in advancing AI-driven river management research. Countries with high centrality scores, such as the United States and United Kingdom, benefit from extensive international collaborations that amplify the global relevance of their research findings. These nations leverage well-established academic and institutional networks to drive innovation and knowledge dissemination on a broad scale. However, nations like India and Saudi Arabia, despite their growing contributions to the field, face significant challenges in establishing strong international connections. Limited collaboration networks may hinder the global impact of their research, confining valuable advances, such as India’s flood management models and Saudi Arabia’s adaptive algorithms for arid regions, to regional applications. This disconnect underscores structural barriers such as resource constraints, language differences, and limited access to global research platforms. 3.3 Institutional contributions to AI-driven river management research Our quantitative analysis of institutional performance reveals distinct patterns in research output and collaboration efficiency within the domain of AI-driven river management. Examination of publication-to-centrality ratios among leading institutions (University Malaya:250, Duy Tan University: 172.7, Islamic Azad University: 154.5, Chinese Academy of Sciences: 228.6, University of Tabriz: 144.4) in Table 2 demonstrates that institutions with lower ratios generally achieve better international collaboration efficiency despite potentially lower publication volumes (Thompson et al., 2023). This efficiency metric provides valuable insights into how institutions balance research productivity with international engagement. Regional analysis highlights two primary research clusters with contrasting characteristics (Table 3). The East Asian cluster, comprising 62 total publications with an average centrality of 0.04, demonstrates high productivity but moderate international engagement. In comparison, the Middle Eastern hub, with 59 publications and an average centrality of 0.065, exhibits more balanced research capabilities supported by stronger international networks. This regional disparity reflects different institutional approaches to research development, with established institutions like the Chinese Academy of Sciences focusing on domestic research strength while emerging institutions such as Duy Tan University prioritize international collaboration (Figure 3). The analysis reveals an emerging trend of cross-regional collaboration, particularly evident in specialized research areas such as AI-driven flood prediction and water quality monitoring (Wang and Abdelrahman, 2023;Mahmoodi et al., 2024;Kan et al., 2020;Chitwatkulsiri and Miyamoto, 2023;Yao et al., 2022;Perez-Beltran et al., 2024). The data indicates three distinct developmental approaches in the research landscape. The first approach, exemplified by University Malaya, emphasizes quantitative research production but may sacrifice international collaboration depth. The second approach, demonstrated by Islamic Azad University, maintains moderate publication output while fostering strong international ties, potentially offering a more sustainable path to research development. The third approach, typically adopted by newer institutions like Xi’an University, focuses on building international partnerships as a pathway to research excellence. Temporal analysis of publication patterns reveals significant evolution in institutional approaches over the past decade (Figure 3). Early research (2013-2018) was characterized by individual institutional efforts, while recent years (2019-2023) show increased emphasis on collaborative projects and multi-institutional research initiatives. This shift reflects growing recognition of the complexity inherent in water management challenges and the increasing importance of diverse expertise and resource sharing. The findings suggest an accelerating trend toward hybrid institutional models that combine elements of multiple development approaches, particularly evident in the growing emphasis on specialized research clusters and interdisciplinary collaboration networks. 3.4 Analysis of influential authors Our analysis of influential researchers shaping the field of AI-driven river management highlights complex patterns of contributions and collaborations among key authors. By examining author publications and collaboration networks (Figure 4, Table 4), we identified notable trends reflecting both individual productivity and the critical role of collaborative efforts in advancing the field. The collaboration network visualization reveals distinct clusters of influential researchers, with node size representing the number of publications and connecting lines indicating the strength of collaborative ties. El-Shafie, Ahmed stands out as the most prolific contributor, with 13 publications since 2007. This consistent output highlights his sustained engagement in advancing AI methodologies for river management. Other notable contributors include Ahmed, Ali Najah (10 publications), Yaseen, Zaher Mundher, and Kisi, Ozgur (each with 8 publications). Additionally, a group of researchers, including Binh Thai Pham, Khosravi, Khabat, Elbeltagi, Ahmed, and Chen, Wei, have each contributed 6 publications, underscoring their consistent participation in the field’s development. While publication output indicates individual productivity, network centrality analysis offers deeper insights into collaborative influence. For instance, Adamowski, Jan exhibits a prominent centrality score of 0.09, reflecting his pivotal role in hydrological modeling and water resource management innovation. Similarly, Elbeltagi, Ahmed and Chen, Wei (both with centrality scores of 0.06) have contributed significantly to key areas such as water quality prediction and environmental flow assessment through their collaborative networks. These findings demonstrate that an author’s influence is not solely determined by publication volume but also by their capacity to foster impactful research partnerships. The interconnections among leading researchers reveal a dynamic collaborative ecosystem that is critical to addressing the interdisciplinary challenges of AI-driven river management. Authors with higher centrality scores often act as bridges connecting multiple research clusters, facilitating knowledge exchange and innovation. For example, the robust networks of authors like Adamowski, Elbeltagi, and Ahmed highlight the importance of integrating expertise from diverse fields, such as environmental engineering, hydrology, and artificial intelligence, to tackle complex water resource issues. These results underscore the dual importance of individual productivity and collaborative efforts. While prolific authors contribute to expanding the literature, those with high centrality scores often shape the direction and impact of the research community. Strengthening these collaborations, particularly across disciplines and regions, will be essential for driving innovation and solving pressing environmental challenges in the future. 3.5 Co-citation analysis of literature Through a systematic co-citation analysis utilizing CiteSpace software, this study uncovers the intricate intellectual structure and evolving research dynamics in water resource management. Spanning the years 2000 to 2024, the analysis captures critical developments in the application of artificial intelligence (AI) and sustainability strategies, offering valuable insights into the theoretical underpinnings and future trajectories of the field. As illustrated in Table 5 and Figure 5, the co-citation network reveals a complex knowledge structure, shaped by influential contributions that continue to guide research trajectories. A central node in the network is Chapi et al.’s seminal study (28 citations, centrality 0.12) in Environmental Modelling and Software (IF 4.8), which established fundamental methodological frameworks for integrating AI into hydrological modeling. Its high centrality suggests a pivotal bridging role between theory and practice, particularly in predictive modeling applications. Likewise, Ahmed et al. (20 citations, centrality 0.09) in the Journal of Hydrology （IF 5.9） marks a transition toward advanced machine learning approaches, catalyzing a shift away from traditional statistical methods toward adaptive, data-driven solutions. These contributions exemplify how early innovations laid the groundwork for contemporary advancements in the field. Citation patterns reveal significant temporal shifts in research focus. The period 2017–2020 represents a critical juncture, marked by an increasing emphasis on integrating environmental and ecological variables into AI frameworks. This trend is epitomized by Tiyasha et al. (19 citations, centrality 0.03), whose work reflects the research community’s growing commitment to addressing climate change impacts within water management systems. However, the relatively low centrality of such works suggests untapped potential for further theoretical advancements. Similarly, emerging studies post-2020 indicate a progressive shift toward multidisciplinary and integrated approaches, emphasizing the importance of combining diverse data sources to address water management’s complexity. The temporal evolution of citation patterns reveals a noteworthy paradigm shift. Early works (2000–2015) predominantly focused on isolated technological solutions, such as single-model implementations or stand-alone tools. More recent contributions, however, increasingly emphasize integrated approaches that combine multiple data sources and methodologies to address the inherent complexity of water resource management systems. For example, Islam AMT (15 citations, centrality 0.02) demonstrates this transition by proposing a holistic framework for river basin management, although its modest centrality score suggests the research community is still in the process of fully adopting such frameworks. 3.6 Keywords analysis of research In the field of academic research, the systematic examination of keywords serves as a vital tool for understanding research directions and thematic evolution. Through the application of keyword co-occurrence network analysis, our study reveals the dynamic landscape and developmental patterns within AI-driven river management research. This analytical approach directly addresses “the emerging trends defining future research directions”. The visualization presented in Figure 6 employs a network structure where individual nodes symbolize specific keywords, with their size proportional to their frequency of appearance in the literature. The interconnecting lines between nodes demonstrate the strength of keyword relationships, with thicker lines indicating stronger associations. The relative dimensions of these clusters, determined by keyword frequency and interconnections, offer valuable insights into the temporal evolution and current state of research priorities in the field. This visualization technique effectively maps the intellectual structure of the domain, highlighting both established research areas and emerging topics of interest. From Figure 6, we can see the most prominent clusters center on “advanced computational methodologies”, including “machine learning algorithms” (cluster 5 and 6), “artificial neural networks” (cluster 2), and “deep learning frameworks” (cluster 1), which serve as the technological foundation for modern river management solutions. These methodologies demonstrate strong connections to water quality monitoring, hydraulic modeling, and environmental flow assessment, indicating their crucial role in advancing environmental engineering practices. The second significant clusters emphasizes practical applications in “watershed management” (cluster 3, 8 and 13), encompassing “flood prediction”, “streamflow forecasting”, and “water quality assessment”. This cluster reveals the growing implementation of AI-driven solutions in addressing complex environmental challenges, particularly in real-time monitoring and predictive modeling of river systems. The evolution of artificial intelligence (AI) applications in water resource management has demonstrated distinct developmental phases over the past two decades (Figure 7, Figure 8). Early implementations (2000-2010) were predominantly centered on “artificial neural network”, establishing fundamental modeling frameworks. The field subsequently progressed through a transformative period (2011-2015), marked by the integration of optimization techniques and environmental parameters such as “dissolved oxygen” and “climate change considerations”. A significant methodological diversification emerged during 2016-2020, characterized by the adoption of support “vector machines”, “advanced machine learning algorithms”, and “deep learning architectures”. This period also witnessed the emergence of random forest applications and big data analytics in hydrological modeling, reflecting a growing recognition of hybrid methodologies’ potential. Recent developments (2021-2023) have emphasized temporal dynamics through “sophisticated time series analysis” and “uncertainty quantification”, reflecting a mature integration of AI methodologies with water resource applications. The keyword network analysis reveals an evolution from isolated technical approaches to integrated methodological frameworks, demonstrating the field’s progression toward more comprehensive and robust solutions for complex water management challenges. 4 Discussion 4.1 Advances in AI-Driven river management The application of artificial intelligence (AI) in river management has emerged as a critical tool to address the intricacies of hydrological systems and socio-environmental interactions. This study’s findings highlight the transformative impact of AI-based methodologies, including machine learning, deep learning, and hybrid modeling frameworks, in improving prediction accuracy, optimizing resource management, and addressing cross-scale environmental challenges. However, significant barriers remain, both in technical aspects and institutional adaptation, requiring a critical analysis of the field’s current status and its limitations. Among the prominent developments in the field are the deployment of hybrid AI models that improve predictive performance by combining data-driven algorithms with hydrological principles. For instance, the co-citation analysis in this study demonstrates the centrality of Ahmed et al. and Chapi et al., who have significantly advanced machine learning methods such as support vector machines and random forests. These methodologies address critical challenges in flood forecasting and water quality modeling, outperforming traditional statistical models when dealing with the high nonlinearity and complexity of hydrological systems (Chapi et al., 2017;Ahmed et al., 2019) . In parallel, the emergence of physics-informed machine learning models offers a promising direction for reducing uncertainties in systems where data limitations are significant. Unlike conventional models, physics-informed machine learning frameworks leverage domain knowledge—such as mass conservation and energy balance principles—to enhance predictive capabilities for complex interactions, such as sediment transport processes and groundwater dynamics (Teimoori et al., 2023). Moreover, deep learning architectures, including convolutional neural networks and long short-term memory networks, have demonstrated exceptional performance in processing high-resolution spatiotemporal hydrological data. These models have been particularly effective in real-time monitoring of river dynamics, analyzing remote sensing data, and predicting extreme hydrological events such as flash floods with high accuracy (Tang et al., 2023;Le and Hien, 2024). However, while these advancements have provided significant methodological breakthroughs, their effectiveness heavily depends on contextual inclusivity and institutional support. 4.2 Synergies between social integration and AI adoption A major theme emerging from this study is the critical importance of social-ecological integration for the successful implementation of AI systems. As highlighted through the cluster analysis (e.g., Cluster 3 and 8 findings), the engagement of local stakeholders and incorporation of Traditional Ecological Knowledge are essential for enhancing the relevance and adaptability of technology-driven interventions (Choubin et al., 2019;Zipper et al., 2017). Research from Kunkel et al. (2023) and others underscores that AI models cannot operate in isolation from the socio-environmental contexts they aim to manage. For example, watershed management efforts utilizing hybrid AI models—while technically sound—often fail to achieve desired outcomes when local cultural, institutional, and governance structures are not accounted for. This aligns with the observation that socio-ecological resilience is a critical criterion for evaluating system success (Mukherjee et al., 2024). In decentralized water management contexts, participatory approaches that prioritize equitable resource allocation and active involvement of marginalized communities have delivered better outcomes (Fan et al., 2024;Molinos-Senante et al., 2024). Such findings highlight a dual imperative: on the one hand, advancing technical precision, and on the other, fostering inclusive governance frameworks to drive adoption and long-term sustainability. 5 Future perspectives and research framework The ongoing evolution of AI-driven environmental management systems points toward significant advancements in both methodology and implementation. However, this progression also highlights critical gaps and challenges. Future research must adopt a holistic and integrated framework to address technical limitations, operational obstacles, and environmental complexities, particularly in the context of water resource management. Advanced AI-driven systems for river management have demonstrated immense potential in addressing environmental and hydrological challenges. However, the findings of this study also reveal significant technical, institutional, and data-driven barriers that limit their large-scale adoption and sustainability. To bridge these gaps, future research must address challenges across three intertwined dimensions: technological innovations, institutional readiness, and data-system integration, while embedding resilience to uncertain and dynamic conditions. This section outlines a forward-looking research framework, offering actionable insights into advancing water resource management. 5.1 Advancing transparent and scalable methodological frameworks The need for interpretable and scalable methodologies was highlighted as a key limitation in this study, particularly in addressing cross-scale hydrological complexities and non-stationary environmental dynamics. Future research should focus on the following fronts: Developing explainable AI (XAI) for hydrological systems: As noted in Section 4.1, existing AI models are often confined to ”black-box” frameworks, limiting their interpretability and reliability among decision-makers. Advancing XAI methodologies, such as model-agnostic approaches and interpretable deep learning models, is crucial for providing clarity around decision-making processes, particularly in critical applications such as flood forecasting and water quality monitoring. Enhancing multi-scale model integration: The challenges in modeling cross-scale riverine dynamics, where microscale processes (e.g., local hydraulic flow) fail to capture basin-wide interactions (e.g., sediment transport and ecological feedbacks), remain unresolved. Future modeling frameworks should adopt hybrid approaches, such as physics-informed machine learning (Rozos, 2023;Huntingford et al., 2019), which integrate data-driven algorithms with domain-specific hydrological principles. These frameworks must achieve consistency across temporal and spatial scales, enabling managers to address complex interactions within river ecosystems. Embedding adaptive modeling for non-stationary conditions: The rising frequency and intensity of extreme climatic events underscore the necessity for adaptive modeling frameworks equipped with probabilistic forecasting capabilities. These models should incorporate dynamic resilience metrics and scenario-based predictions to provide water managers with actionable insights under uncertainty. 5.2 Strengthening institutional readiness and collaboration Institutional and operational barriers have been identified as the dominant constraints to system implementation, particularly in resource-limited regions (see Section 4.2). To address this, future research and policy must prioritize: Capacity building through collaborative networks: Regional and global stakeholder collaborations should focus on establishing research and training hubs to enhance technical expertise and governance capacity. This can include partnerships between academic institutions, public agencies, and the private sector to transfer skills and ensure sustainable system adoption. Standardized protocols for stakeholder engagement: Drawing on Traditional Ecological Knowledge (TEK) alongside modern AI workflows, as noted by (Choubin et al., 2019), can be instrumental in creating locally relevant and inclusive governance frameworks. Future research should aim to structure these participatory protocols to promote decentralized decision-making and improve institutional accountability. 5.3 Addressing critical data challenges Persistent data gaps, inconsistent measurement standards, and challenges in integrating multi-source datasets present significant barriers to unlocking the full potential of AI-driven systems in river management. Future research should prioritize: Development of global metadata standards: International coordination in hydrological data standardization is essential to improve interoperability and ensure consistency in data modeling approaches. This includes harmonizing sensor calibration methods, data resolution protocols, and metadata structures across continents. Adoption of open environmental data platforms: Open-access frameworks for sharing real-time hydrological datasets across stakeholders can reduce data redundancy while facilitating large-scale machine learning applications. Platforms such as Google Earth Engine for hydrological research show promising avenues for future rapid data integration. 5.4 Embedding resilience to climate dynamics Climate change exacerbates uncertainties in river management, posing significant challenges to current predictive capabilities. Future research should focus on embedding climate resilience in design frameworks by incorporating: Scenario-based planning for climate adaptation: Incorporating multi-scenario climate projections (e.g., IPCC AR6) into AI-supported decision-support models enables predictive insights under various climate futures. Such tools could optimize resource allocation and reduce the potential impact of extreme hydrological events (e.g., droughts and floods). Integrating social-ecological resilience metrics: Advancing resilience measurements that quantify ecological health alongside community adaptability is critical to achieving a balanced approach to sustainable management. Frameworks that combine climatic, economic, and socio-political resilience indicators will enable decision-makers to develop adaptable policies in response to rapid global changes. 5.5 Building a global interdisciplinary research agenda The increasing complexity of river ecosystems demands holistic collaboration across scientific, institutional, and policy boundaries. Future agendas should: Establish coss-disciplinary research consortia: Bringing hydrologists, engineers, ecologists, data scientists, and policy experts into collaborative research platforms will foster the co-design of innovative solutions for multi-scale management challenges. Promote research-policy synergies: Alignment between research outputs and policy priorities can be achieved by embedding scientific insights directly into decision-support frameworks, enabling fast and practical solutions to emerge. 5.6 Toward integrated and sustainable system solutions The proposed framework underscores the interconnectedness of technological innovation, institutional capacity, and environmental sustainability. A focus on holistic system design and multi-stakeholder collaboration will enable AI-driven river management systems to achieve their full potential, fostering long-term resilience and adaptive capacity for sustainable water resource management. 6 Conclusion This study conducted a bibliometric analysis of AI applications in river management, examining 477 publications (2000–2024) to highlight research trends, geographic concentrations, and methodological advancements. Results indicate rapid growth in this field, with contributions from China, the United States, and the United Kingdom comprising 43.2% of total publications and achieving central positions in global collaboration networks (centrality measures: 0.23–0.32). These findings reflect the accelerating integration of AI technologies into hydrological and environmental systems. From a theoretical perspective, this study provides three notable insights. First, it reveals the emergence of interconnected research clusters focused on critical areas such as water quality monitoring and real-time flood prediction. Second, findings demonstrate a shift from isolated modeling techniques to integrated approaches leveraging machine learning, physical modeling, and interdisciplinary collaboration. Third, the analysis identifies evolving global collaboration patterns that emphasize the vital role of networked partnerships in advancing research efficacy and applicability. Practically, the study underscores the need for robust institutional frameworks and stakeholder engagement in AI-driven river management. Metrics on institutional productivity (ranging from 172.7 to 250 papers per leading institution) highlight the importance of specialized research units in fostering innovation, particularly in regions with complex hydrological challenges. Furthermore, addressing data heterogeneity and ensuring transparency in model development remain essential priorities for practitioners seeking sustainable implementation. Finally, acknowledging its limitations, this study is constrained by its reliance on English-language publications and the Web of Science Core Collection, which may exclude contributions outside the selected scope. Additionally, the rapid pace of technological advancement suggests that recent innovations may not yet be fully reflected. Future efforts should focus on expanding interdisciplinary research, integrating diverse datasets, and addressing the socio-environmental complexities of river management systems. Author contributions Jun Yang performed Formal Analysis, Investigation, Project administration, Software development, and Validation, while also contributing to Resources, Visualization, and the original draft. Yueya Chang was responsible for Conceptualization, Data curation, Investigation, Software implementation, and Resources, as well as taking the lead in manuscript preparation, revision, and editing. Funding Statement The author(s) declare that no financial support was received for the research, authorship, and/or publication of this article. References Abbas, A., Boithias, L., Pachepsky, Y., Kim, K., Chun, J. A. and Cho, K. H. 2022. Ai4water V1.0: An Open-Source Python Package for Modeling Hydrological Time Series Using Data-Driven Methods. GEOSCIENTIFIC MODEL DEVELOPMENT, 15 (7) , 3021-3039. doi: 10.5194/gmd-15-3021-2022.Acuna, V., Castanares, L., Castellar, J., Comas, J., Cross, K., Istenic, D., Masi, F., Mcdonald, R., Pucher, B., Pueyo-Ros, J., Riu, A., Rizzo, A., Riva, M., Tondera, K. and Corominas, L. 2023. Development of a Decision-Support System to Select Nature-Based Solutions for Domestic Wastewater Treatment. BLUE-GREEN SYSTEMS, 5 (2) , 235-251. doi: 10.2166/bgs.2023.005.Ahmed, A. N., Othman, F. B., Afan, H. A., Ibrahim, R. K., Fai, C. M., Hossain, M. S., Ehteram, M. and Elshafie, A. 2019. Machine Learning Methods for Better Water Quality Prediction. JOURNAL OF HYDROLOGY, 578. doi: 10.1016/j.jhydrol.2019.124084.Beeton, A. M. 2002. Large Freshwater Lakes: Present State, Trends, and Future. ENVIRONMENTAL CONSERVATION, 29 (1) , 21-38. doi: 10.1017/S0376892902000036.Beven, K. 2020. Deep Learning, Hydrological Processes and the Uniqueness of Place. HYDROLOGICAL PROCESSES, 34 (16) , 3608-3613. doi: 10.1002/hyp.13805.Boudry, C. 2021. Availability of Orcids in Publications Archived in Pubmed, Medline, and Web of Science Core Collection. SCIENTOMETRICS, 126 (4) , 3355-3371. doi: 10.1007/s11192-020-03825-7.Cai, X., Marston, L. and Ge, Y. 2015. Decision Support for Integrated River Basin Management-Scientific Research Challenges. SCIENCE CHINA-EARTH SCIENCES, 58 (1) , 16-24. doi: 10.1007/s11430-014-5005-2.Cao, X., Furuoka, F. and Rasiah, R. 2023. Knowledge Mapping of Industrial Upgrading Research: A Visual Analysis Using Citespace. SUSTAINABILITY, 15 (24). doi: 10.3390/su152416547.Chapi, K., Singh, V. P., Shirzadi, A., Shahabi, H., Bui, D. T., Pham, B. T. and Khosravi, K. 2017. A Novel Hybrid Artificial Intelligence Approach for Flood Susceptibility Assessment. ENVIRONMENTAL MODELLING & SOFTWARE, 95 , 229-245. doi: 10.1016/j.envsoft.2017.06.012.Chitwatkulsiri, D. and Miyamoto, H. 2023. Real-Time Urban Flood Forecasting Systems for Southeast Asia-a Review of Present Modelling and Its Future Prospects. WATER, 15 (1). doi: 10.3390/w15010178.Choubin, B., Moradi, E., Golshan, M., Adamowski, J., Sajedi-Hosseini, F. and Mosavi, A. 2019. An Ensemble Prediction of Flood Susceptibility Using Multivariate Discriminant Analysis, Classification and Regression Trees, and Support Vector Machines. Science of the Total Environment, 651 , 2087-2096. doi: 10.1016/j.scitotenv.2018.10.064.De La Fuente, L., Condon, L., Gupta, H., Bennett, A. and Ferre, P. Z. 2024. Advancing Synergistic Knowledge Generation through Machine Learning and Hydrology Science . doi: Du, L., Zhou, X., Yang, R., Cheng, P. and Cheng, S. 2023. Spatial and Temporal Evolution of Multi-Scale Regional Quality Development and the Influencing Factors. SUSTAINABILITY, 15 (7). doi: 10.3390/su15076046.Fan, Y., Shi, K. W. and Wang, C. W. 2024. Mathematical Modeling and Experimental Validation of a Novel Circulating Oxygenation Biofilm Equipment (Cobe) for the Management of Decentralized Wastewater Treatment. JOURNAL OF ENVIRONMENTAL MANAGEMENT, 351. doi: 10.1016/j.jenvman.2023.119792.Gonzales-Inca, C., Calle, M., Croghan, D., Haghighi, A. T., Marttila, H., Silander, J. and Alho, P. 2022. Geospatial Artificial Intelligence (Geoai) in the Integrated Hydrological and Fluvial Systems Modeling: Review of Current Applications and Trends. WATER, 14 (14). doi: 10.3390/w14142211.Graeber, D., Pusch, M. T., Lorenz, S. and Brauns, M. 2013. Cascading Effects of Flow Reduction on the Benthic Invertebrate Community in a Lowland River. HYDROBIOLOGIA, 717 (1) , 147-159. doi: 10.1007/s10750-013-1570-1.Hadiyawarman, Wisely, N., Iqbal, M., Timuda, G. E., Darsono, N., Yuliarto, B. and Khaerudini, D. S. 2024. Development of Photoelectrochemical Water Splitting Photoanode: Bibliometric Analysis and Artificial Intelligence Advancement. CLEAN TECHNOLOGIES AND ENVIRONMENTAL POLICY, 26 (3) , 599-621. doi: 10.1007/s10098-023-02686-x.Hao, Z., Rallings, A. M., Espinoza, V., Luo, P., Duan, W., Peng, Q., Gao, Y. and Viers, J. H. 2021. Flowing from East to West: A Bibliometric Analysis of Recent Advances in Environmental Flow Science in China. ECOLOGICAL INDICATORS, 125. doi: 10.1016/j.ecolind.2021.107358.He, Z., Gong, K., Zhang, Z., Dong, W., Feng, H., Yu, Q. and He, J. 2022. What Is the Past, Present, and Future of Scientific Research on the Yellow River Basin? -a Bibliometric Analysis. AGRICULTURAL WATER MANAGEMENT, 262. doi: 10.1016/j.agwat.2021.107404.Heintzman, L. J., Ghaffari, Z., Awawdeh, A. R., Barrett, D. E., Yarbrough, L. D., Easson, G., Moore, M. T., Locke, M. A. and Yasarer, H. I. 2024. Assessing Differences in Groundwater Hydrology Dynamics between in Situ Measurements and Grace-Derived Estimates Via Machine Learning: A Test Case of Consequences for Agroecological Relationships within the Yazoo-Mississippi Delta (USA). HYDROLOGY, 11 (11). doi: 10.3390/hydrology11110186.Huntingford, C., Jeffers, E. S., Bonsall, M. B., Christensen, H. M., Lees, T. and Yang, H. 2019. Machine Learning and Artificial Intelligence to Aid Climate Change Research and Preparedness. ENVIRONMENTAL RESEARCH LETTERS, 14 (12). doi: 10.1088/1748-9326/ab4e55.Ihsanullah, I., Alam, G., Jamal, A. and Shaik, F. 2022. Recent Advances in Applications of Artificial Intelligence in Solid Waste Management: A Review. CHEMOSPHERE, 309 (Pt 1) , 136631-136631. doi: 10.1016/j.chemosphere.2022.136631.Iqbal, U., Bin Riaz, M. Z., Barthelemy, J., Perez, P. and Idrees, M. B. 2023. The Last Two Decades of Computer Vision Technologies in Water Resource Management: A Bibliometric Analysis. WATER AND ENVIRONMENT JOURNAL, 37 (3) , 373-389. doi: 10.1111/wej.12845.Jaehnig, S. C., Monaghan, M. T. and Hering, D. 2019. In-Depth Approach to River Management. NATURE, 572 (7767) , 32-32. doi: 10.1038/d41586-019-02327-8.Kan, G., Liang, K., Yu, H., Sun, B., Ding, L., Li, J., He, X. and Shen, C. 2020. Hybrid Machine Learning Hydrological Model for Flood Forecast Purpose. OPEN GEOSCIENCES, 12 (1) , 813-820. doi: 10.1515/geo-2020-0166.Kunkel, S., Schmelzle, F., Niehoff, S. and Beier, G. 2023. More Sustainable Artificial Intelligence Systems through Stakeholder Involvement? GAIA-ECOLOGICAL PERSPECTIVES FOR SCIENCE AND SOCIETY, 32 , 64-70. doi: 10.14512/gaia.32.S1.10.Ladewig, S. M., Coco, G., Hope, J. A., Vieillard, A. M. and Thrush, S. F. 2023. Real-World Impacts of Microplastic Pollution on Seafloor Ecosystem Function. Science of the Total Environment, 858. doi: 10.1016/j.scitotenv.2022.160114.Le, X. H. and Hien, L. T. 2024. Predicting Maximum Scour Depth at Sluice Outlet: A Comparative Study of Machine Learning Models and Empirical Equations. ENVIRONMENTAL RESEARCH COMMUNICATIONS, 6 (1). doi: 10.1088/2515-7620/ad1f94.Lu, X., Wang, X., Liu, X. and Singh, V. P. 2023. Dispersal and Transport of Microplastic Particles under Different Flow Conditions in Riverine Ecosystem. Journal of Hazardous Materials, 442. doi: 10.1016/j.jhazmat.2022.130033.Machado, A. a. D. S., Kloas, W., Zarfl, C., Hempel, S. and Rillig, M. C. 2018. Microplastics as an Emerging Threat to Terrestrial Ecosystems. Global Change Biology, 24 (4) , 1405-1416. doi: 10.1111/gcb.14020.Mahmoodi, E., Azari, M., Dastorani, M. T. and Salvati, A. 2024. Comparison of Hydrological Modeling, Artificial Neural Networks and Multi-Criteria Decision Making Approaches for Determining Flood Source Areas. WATER RESOURCES MANAGEMENT, 38 (13) , 5343-5363. doi: 10.1007/s11269-024-03917-6.Malve, O. I. Z. 2007. Water Quality Prediction for River Basin Management . doi: Md Shahri, N. H. N. B. and Mohd Ali, Z. 2024. Bibliometric Perspectives in Mapping the Progress of River Water Quality Index Studies. WATER QUALITY RESEARCH JOURNAL, 59 (4) , 232-267. doi: 10.2166/wqrj.2024.022.Meng, F., Fu, G. and Butler, D. 2017. Cost-Effective River Water Quality Management Using Integrated Real-Time Control Technology. ENVIRONMENTAL SCIENCE & TECHNOLOGY, 51 (17) , 9876-9886. doi: 10.1021/acs.est.7b01727.Mokhnacheva, Y. V. and Tsvetkova, V. A. 2019. Representation of Papers of Russian Authors in the Global Array of Scientific Publications in the Web of Science Core Collection (2010-2017). SCIENTIFIC AND TECHNICAL INFORMATION PROCESSING, 46 (2) , 143-147. doi: 10.3103/S014768821902014X.Molinos-Senante, M., Poch, M., Rosso, D. and Garrido-Baserba, M. 2024. From Wastewater Treatment Plants to Decentralized Resource Factories. NPJ CLEAN WATER, 7 (1). doi: 10.1038/s41545-024-00343-4.Mukherjee, D., Jena, L. K., Chakraborty, S., Debnath, R. and Hasan, K. K. 2024. Impact of Horticulture on the Sustainable Livelihood Development of Smallholders: A Spar-4-Slr & Future Research Agenda. AGRICULTURAL AND RESOURCE ECONOMICS-INTERNATIONAL SCIENTIFIC E-JOURNAL, 10 (2) , 80-115. doi: 10.51599/are.2024.10.02.04.Norreys, R. Z. 1991. Water Quality River Impact Model (Rim) for River Basin Management (Sewer Overflow) . doi: Osborne, E., Hu, X., Hall, E. R., Yates, K., Vreeland-Dawson, J., Shamberger, K., Barbero, L., Hernandez-Ayon, J. M., Gomez, F. A., Hicks, T., Xu, Y.-Y., Mccutcheon, M. R., Acquafredda, M., Chapa-Balcorta, C., Norzagaray, O., Pierrot, D., Munoz-Caravaca, A., Dobson, K. L., Williams, N., Rabalais, N. and Dash, P. 2022. Ocean Acidification in the Gulf of Mexico: Drivers, Impacts, and Unknowns. PROGRESS IN OCEANOGRAPHY, 209. doi: 10.1016/j.pocean.2022.102882.Pan, S., Zhang, W., Li, Y., Zhang, C., Zhang, H., Niu, L. and Wang, L. 2023. Trends and Prospects in the Yangtze River Basin Research: A Bibliometric Analysis. RIVER RESEARCH AND APPLICATIONS, 39 (1) , 134-148. doi: 10.1002/rra.4074.Pandit, A. Z. 2024. Deep Learning and Aquatic Sensing Reveal Nitrate Dynamics in the Mississippi River Basin . doi: Perez-Beltran, C. H., Robles, A. D., Rodriguez, N. A., Ortega-Gavilan, F. and Jimenez-Carvelo, A. M. 2024. Artificial Intelligence and Water Quality: From Drinking Water to Wastewater. TRAC-TRENDS IN ANALYTICAL CHEMISTRY, 172. doi: 10.1016/j.trac.2024.117597.Peters, D. L., Dibike, Y. B., Shudian, J., Monk, W. A. and Baird, D. J. 2023. Effects of Climate Change on Navigability Indicators of the Lower Athabasca River, Canada. WATER, 15 (7). doi: 10.3390/w15071373.Piegay, H., Cottet, M. and Lamouroux, N. 2020. Innovative Approaches in River Management and Restoration. RIVER RESEARCH AND APPLICATIONS, 36 (6) , 875-879. doi: 10.1002/rra.3667.Quinn, N. W. T. 2011. Adaptive Implementation of Information Technology for Real-Time, Basin-Scale Salinity Management in the San Joaquin Basin, USA and Hunter River Basin, Australia. AGRICULTURAL WATER MANAGEMENT, 98 (6) , 930-940. doi: 10.1016/j.agwat.2010.11.013.Ren, J., Peng, Z. and Pan, X. 2020. Emerging Trends and New Developments in Lancang-Mekong River: A Bibliometric Visualization Analysis. RIVER RESEARCH AND APPLICATIONS, 36 (5) , 862-871. doi: 10.1002/rra.3609.Rozos, E. 2023. Assessing Hydrological Simulations with Machine Learning and Statistical Models. HYDROLOGY, 10 (2). doi: 10.3390/hydrology10020049.Rozos, E., Dimitriadis, P. and Bellos, V. 2022. Machine Learning in Assessing the Performance of Hydrological Models. HYDROLOGY, 9 (1). doi: 10.3390/hydrology9010005.Ruangpan, L., Vojinovic, Z., Plavsic, J., Doong, D.-J., Bahlmann, T., Alves, A., Tseng, L.-H., Randelovic, A., Todorovic, A., Kocic, Z., Beljinac, V., Wu, M.-H., Lo, W.-C., Perez-Lapena, B. and Franca, M. J. 2021. Incorporating Stakeholders’ Preferences into a Multi-Criteria Framework for Planning Large-Scale Nature-Based Solutions. Ambio, 50 (8) , 1514-1531. doi: 10.1007/s13280-020-01419-4.Shrestha, R. K., Stein, T. V. and Clark, J. 2007. Valuing Nature-Based Recreation in Public Natural Areas of the Apalachicola River Region, Florida. JOURNAL OF ENVIRONMENTAL MANAGEMENT, 85 (4) , 977-85. doi: 10.1016/j.jenvman.2006.11.014.Smirnova, N. and Mayr, P. 2023. A Comprehensive Analysis of Acknowledgement Texts in Web of Science: A Case Study on Four Scientific Domains. SCIENTOMETRICS, 128 (1) , 709-734. doi: 10.1007/s11192-022-04554-9.Stoffels, R. J., Booker, D. J., Franklin, P. A. and Holmes, R. 2024. Monitoring for the Adaptive Management of Rivers. JOURNAL OF ENVIRONMENTAL MANAGEMENT, 351. doi: 10.1016/j.jenvman.2023.119787.Tang, Y. L., Wang, L. M., Jin, S. H., Zhao, J. H., Huang, C. and Yu, Y. C. 2023. Auv-Based Side-Scan Sonar Real-Time Method for Underwater-Target Detection. JOURNAL OF MARINE SCIENCE AND ENGINEERING, 11 (4). doi: 10.3390/jmse11040690.Teimoori, S., Olya, M. H. and Miller, C. J. 2023. Groundwater Level Monitoring Network Design with Machine Learning Methods. JOURNAL OF HYDROLOGY, 625. doi: 10.1016/j.jhydrol.2023.130145.Thangagiri, B. and Sivakumar, R. 2024. Prospective Application of Artificial Intelligence Towards the Detection, and Classifications of Microplastics with Bibliometric Analysis. Water Air and Soil Pollution, 235 (6). doi: 10.1007/s11270-024-07151-z.Wang, Q. and Abdelrahman, W. 2023. High-Precision Ai-Enabled Flood Prediction Integrating Local Sensor Data and 3rd Party Weather Forecast. SENSORS, 23 (6). doi: 10.3390/s23063065.Wang, Y., Gassman, P. W., Wang, Y. and Pu, Y. 2018. Analysis of Journal Content Characteristics and Metrics Reported in the Clarivate Analytics Journal Citation Reports and Web of Science Core Collection Agricultural Engineering Categories. INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING, 11 (5) , 1-26. doi: 10.25165/j.ijabe.20181105.3083.Yao, S., Zhang, Y., Wang, P., Xu, Z., Wang, Y. and Zhang, Y. 2022. Long-Term Water Quality Prediction Using Integrated Water Quality Indices and Advanced Deep Learning Models: A Case Study of Chaohu Lake, China, 2019-2022. APPLIED SCIENCES-BASEL, 12 (22). doi: 10.3390/app122211329.Yin, X., Li, J., Kadry, S. N. and Sanz-Prieto, I. 2021. Artificial Intelligence Assisted Intelligent Planning Framework for Environmental Restoration of Terrestrial Ecosystems. ENVIRONMENTAL IMPACT ASSESSMENT REVIEW, 86. doi: 10.1016/j.ejar.2020.106493.Yu, D., Xu, Z. and Antucheviciene, J. 2019. Bibliometric Analysis of the Journal of Civil Engineering and Management between 2008 and 2018. JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT, 25 (5) , 402-410. doi: 10.3846/jcem.2019.9925.Zare, A., Ablakimova, N., Kaliyev, A. A., Mussin, N. M., Tanideh, N., Rahmanifar, F. and Tamadon, A. 2024. An Update for Various Applications of Artificial Intelligence (Ai) for Detection and Identification of Marine Environmental Pollutions: A Bibliometric Analysis and Systematic Review. MARINE POLLUTION BULLETIN, 206. doi: 10.1016/j.marpolbul.2024.116751.Zheng, L. Y., Yu, H. B. and Wang, Q. S. 2015. Assessment of Temporal and Spatial Variations in Surface Water Quality Using Multivariate Statistical Techniques: A Case Study of Nenjiang River Basin, China. JOURNAL OF CENTRAL SOUTH UNIVERSITY, 22 (10) , 3770-3780. doi: 10.1007/s11771-015-2921-z.Zhong, M. F., Zhang, H. Y., Sun, X. W., Wang, Z. Y., Tian, W. and Huang, H. 2018. Analyzing the Significant Environmental Factors on the Spatial and Temporal Distribution of Water Quality Utilizing Multivariate Statistical Techniques: A Case Study in the Balihe Lake, China. Environmental Science and Pollution Research, 25 (29) , 29418-29432. doi: 10.1007/s11356-018-2943-9.Zhou, F., Huang, G. H., Guo, H. C., Zhang, W. and Hao, Z. J. 2007. Spatio-Temporal Patterns and Source Apportionment of Coastal Water Pollution in Eastern Hong Kong. WATER RESEARCH, 41 (15) , 3429-3439. doi: 10.1016/j.watres.2007.04.022.Zhuang, Q. D., Hussein, M. K., Ariffin, N. F. M. and Yunos, M. Y. M. 2022. Landscape Character: A Knowledge Mapping Analysis Using Citespace. INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY, 19 (10) , 10477-10492. doi: 10.1007/s13762-022-04279-5.Zipper, S. C., Smith, K. H., Breyer, B., Qiu, J. X., Kung, A. and Herrmann, D. 2017. Socio-Environmental Drought Response in a Mixed Urban-Agricultural Setting: Synthesizing Biophysical and Governance Responses in the Platte River Watershed, Nebraska, USA. ECOLOGY AND SOCIETY, 22 (4). doi: 10.5751/ES-09549-220439. Supplementary Material File (figures.docx) Download 3.23 MB File (tables.docx) Download 24.15 KB Information & Authors Information Version history V1 Version 1 09 January 2025 Peer review timeline Published Ecohydrology Version of Record 10 Jun 2025 Published Copyright This work is licensed under a Non Exclusive No Reuse License. Keywords artificial intelligence bibliometric analysis citespace river management systems Authors Affiliations Yueya Chang [email protected] Shanghai Urban Construction Vocational College View all articles by this author Jun Yang Shanghai Polytechnic University View all articles by this author Metrics & Citations Metrics Article Usage 433 views 213 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Yueya Chang, Jun Yang. Artificial Intelligence Applications in River Management: Challenges and Insights from a Bibliometric Review. Authorea . 09 January 2025. DOI: https://doi.org/10.22541/au.173641898.83049233/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.173641898.83049233/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a0038b133faead07',t:'MTc3OTUzMzg4Mw=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();