Recent trends and future directions in artificial intelligence (AI) applications for coastal ecosystems Conservation: Insights from a bibliometric analysis

• The field of AI applications in coastal ecosystem conservation has shown a consistent annual growth rate of 5.82% over the past decade, indicating increasing scholarly interest. • China and the United States lead in publication volume and international collaborations, underscoring their investment and influence in advancing AI-driven conservation. • Keyword co-occurrence analysis highlights a transition from traditional environmental sensing to real-time monitoring and predictive modeling using AI tools such as remote sensing, machine learning, and deep learning. • Despite facing critical coastal degradation, many African nations remain underrepresented in the collaboration network, suggesting the need for more inclusive and equitable research partnerships. • The growing integration of computational sciences with conservation efforts signals a shift toward globally adaptive, interdisciplinary, and AI-driven ecosystem management strategies. Coastal ecosystems, such as mangroves, seagrass beds, and coral reefs, provide essential ecological, economic, and social services. However, their capacity to deliver these services is diminishing due to increasing ecosystem disturbances, resource exploitation, and the impacts of climate change. In response, the integration of artificial intelligence (AI) tools into conservation efforts has led to a surge in scholarly publications, highlighting the need for a bibliometric analysis to systematically examine emerging trends and identify future directions in this rapidly evolving and interdisciplinary field. Bibliometric data were sourced from the Scopus database, covering a ten-year period from 2015 to June 2025. The analysis was conducted using Bibliometrix and VOSviewer, complemented by OpenRefine, Microsoft Excel, RStudio, and OriginPro for data cleaning and visualization. Results revealed an annual publication growth rate of 6.61% in the field. The institutions from China and the United States are at the forefront of research outputs and international collaborations, indicating their strong investment and leadership in the application of AI to coastal ecosystem conservation. Keyword co-occurrence analysis identified thematic clusters around AI tools such as remote sensing, machine learning, and deep learning, highlighting a transition from traditional environmental sensing toward real-time monitoring and predictive modeling. There is also a growing presence of multiple countries based on the keyword co-occurrence networks. It indicates increasing global participation, collaboration, and interest in applying AI to ecosystem conservation. Collectively, these findings point to a maturing research landscape with a promising trajectory toward the development of globally adaptive conservation strategies driven by artificial intelligence.