Data-driven evidence for climate-sensitive air quality decisions: Bridging analytics, uncertainty, and policy translation

Climate change and air quality form an interconnected environmental system that directly influences public health, urban resilience, and sustainable development. Shifting meteorological conditions, rising temperatures, changing atmospheric chemistry, and the growing prevalence of wildfires and dust transport are redefining pollutant dynamics. Moreover, the interaction between air pollutants and the climate system through short-lived climate forcers such as black carbon, ozone, methane precursors, and aerosols further underscores their mutual dependence. In recent years, data-driven methodologies—ranging from machine learning and artificial intelligence to satellite analytics and low-cost sensor networks—have opened new opportunities to analyze, forecast, and manage these interactions. However, despite technological innovation, critical challenges persist regarding data reliability, interpretability, uncertainty communication, and the translation of computational outputs into policy actions. These gaps highlight the pressing need to transform predictive models into decision-relevant evidence for climate-sensitive air quality management.This Research Topic aims to advance the understanding of how data-driven, computational, and artificial intelligence-enabled methods can support effective decision-making at the intersection of climate, air quality, exposure, and public health. It seeks to bring together contributions that demonstrate the application of data and models to real-world decisions—ranging from early warning and exposure reduction to climate adaptation, air quality management, and public health protection. Authors are encouraged to present work that not only describes model development or performance but also addresses interpretability, validation, uncertainty, and the practical pathways through which evidence informs policy. By integrating methodological innovation, applied studies, and governance perspectives, this Research Topic strives to illustrate how computational outputs can be made transparent, reproducible, and actionable to support decisions under uncertainty.The Research Topic encompasses studies that explicitly connect data, modelling approaches, validation frameworks, and uncertainty assessment with decision-oriented applications in climate-sensitive air quality management. Contributions should stay within this boundary, avoiding generic environmental data science. To gather further insights into this intersection, we welcome articles addressing—but not limited to—the following themes:- Decision-oriented forecasting and early warning systems for air pollution and climate-related hazards- Multi-source data integration combining satellite, ground-based, and sensor network observations- Explainable, uncertainty-aware, and physically informed modelling approaches- Climate-sensitive exposure, health vulnerability, and environmental justice analyses- Evidence evaluation for policy, planning, and regulatory interventions- Development and assessment of decision support systems and responsible implementation frameworksSuitable article types: Original Research, Methods, Review, Policy and Practice Reviews, Perspective, and Case Study papers exploring data-driven evidence for climate-sensitive air quality decisions. Topic editors: Anubhav Dwivedi, Dharmendra Kumar SINGH, Akash Biswal Source: https://www.frontiersin.org/research-topics/81954/data-driven-evidence-for-climate-sensitive-air-quality-decisions-bridging-analytics-uncertainty-and-policy-translation