Hybrid Machine Learning in Water Systems Resilience Under Climate Change: A Bibliometric Perspective.

Water resource management has been negatively affected by the dual process of rapid urbanisation and climate change. Advances in machine learning have led to the development of new forecasting models that improve the accuracy and robustness of predicting water systems' resilience to climate change.   The main objective of the bibliometric study was to map the intellectual landscape of Hybrid Machine Learning in the context of water resilience. The study provided insights into the research outputs of the Scopus database, collaborative networks, and keyword co-occurrence. The study used the VOSviewer software to perform the metric analysis. The data used covered 2021 to June 2026, and a total of 86 publications were retrieved. The availability of relevant publications in the Scopus database determined the selection of the period from 2021 to June 2026. The publication trends showed sharp growth in research output from 2021 onward. The analysis of the document types shows that journal articles were the most dominant, indicating a higher level of research maturity. The bibliometric analyses show that combinations of ML with classical analytical methods, regression, and remote sensing have consistently dominated research in water system resilience.  The co-authorship analysis shows the key role of China and India, as research hubs of international collaboration, facilitating knowledge diffusion. The journal Water (Switzerland) was the most popular outlet for the field. The most prolific author was Ramana D.B.V with a total of two publications. At the institutional level, the Indian Research Council was the leading organisation contributing to the field.  The pattern of country contributions highlights the concentration of research activities in a handful of countries. The analysis indicates that Hybrid machine learning research in water systems resilience under climate change is increasingily sustainability driven as evidenced by the keyword co-occurrence map where clusters around machine learning, climate change, and water resources converge with themes of sustainable development and transformative adaptation. Future research must emphasize deeper integration of socio-economic data, real-time monitoring, and embedding predictive insights into governance frameworks.