A bibliometric review of advances in copula modelling of extreme air pollution events

Abstract Copula models offer a flexible statistical framework for describing complex dependence structures between variables by linking marginal distributions to a joint distribution. In recent years, they have attracted growing interest in air pollution research due to their ability to capture nonlinear relationships and extreme dependencies among pollutants. This study presents a bibliometric and content analysis of research applying copula models in air pollution studies using data retrieved from the Scopus database for the period 2005–2026. The review examines publication trends, leading contributors, and emerging research directions. A synthesis matrix for the relevant publications, allowed the identification of methodological developments and key research themes. The results showed increasing scholarly attention to modelling pollutant interdependence and environmental risk. Three main thematic areas were identified: dependence structure modelling of air pollutants, copula-based forecasting and hybrid machine learning approaches, and risk assessment of extreme pollution events. Recent studies show a methodological shift toward more advanced techniques like vine copulas, hybrid AI-copula frameworks, and spatiotemporal dependence models, which enhance predictive performance and interpretability. Overall, the review highlights the expanding role of copula models in air pollution analysis and emphasizes the need for methodological consistency, and stronger integration with public health and climate resilience research.