<![CDATA[The rapid advancement of artificial intelligence (AI) has opened new opportunities for developing hydrological models that are more adaptive, accurate, and efficient. This study aims to examine the research trends and directions concerning the application of AI in hydrological modeling using bibliometric analysis. A total of 136 relevant articles published between 2015 and 2025 were retrieved from the Semantic Scholar database using the Publish or Perish software. These records were then analyzed with VOSviewer to map keyword relationships and identify current research focuses. The results reveal a consistent upward trend in AI-based hydrological modeling publications, particularly since 2020. Among the top 15 cited articles, a total of 2,316 citations were recorded, averaging 17.03 citations per article. Keywords such as “LSTM,” “RNN,” “streamflow,” and “hydrological forecasting” appeared with the highest frequency and recentness, signifying a shift toward more adaptive and predictive modeling approaches. Furthermore, density visualization highlights a strong focus on deep learning models particularly LSTM and Support Vector Machines while showing opportunities for further exploration in hybrid models and climate resilience applications. Although limited to a single database, the study provides a methodologically robust overview of the current research landscape. The findings underscore the transformative role of AI, not merely as a computational tool, but as a key enabler for designing hydrological models that are data-driven, responsive, and capable of supporting sustainable water resource management in the face of environmental uncertaintie.]]>
Copyrights © 2025
