Recent advances in data-driven intelligence are transforming how we understand and respond to environmental health challenges. By integrating Earth observation, environmental data, and human activity patterns, these approaches enable improved characterization of exposures related to air pollution, climate extremes, urban heat, and natural disasters. However, key challenges remain, including data quality and uncertainty, spatial and social biases, model interpretability, and translating analytical insights into real-world interventions. This session invites both methodological and applied contributions that use spatial data science and computational approaches to address GeoHealth issues while critically examining their assumptions and limitations. We welcome case studies such as air quality monitoring, heat–health risk mapping, and disaster impact assessment, as well as work evaluating robustness, fairness, and transparency. Contributions integrating multi-source data, developing practical tools, informing policy, or challenging existing paradigms are encouraged. The session aims to foster interdisciplinary dialogue toward actionable and equitable GeoHealth solutions.

• A - Atmospheric Sciences
• GC - Global Environmental Change
• IN - Informatics
• NH - Natural Hazards