Cities concentrate environmental exposures, infrastructure vulnerabilities, and social inequalities, making them key sites for understanding and strengthening climate resilience. Rapid advances in geospatial computation, including geospatial AI, machine learning, remote sensing, street-view imagery, spatial statistics, and multi-source data fusion, are transforming how urban environments can be observed, modeled, and evaluated at policy-relevant scales. This session invites contributions using geo-computational approaches to examine urban environmental challenges and support more resilient communities. We welcome studies that develop or apply spatially explicit, high-resolution, and data-driven methods to address urban heat and heat mitigation, green infrastructure and nature-based solutions, flooding and extreme weather, air quality and exposure, energy vulnerability and climate resilience, infrastructure risk, and spatial inequalities in environmental conditions and adaptive capacity. We also encourage work on new urban datasets, benchmarking and validation, interpretable and hybrid machine learning frameworks, and computational tools that connect environmental observations with planning, governance, and community resilience.

• B - Biogeosciences
• GC - Global Environmental Change
• NH - Natural Hazards