Addressing the need for effective flood risk mitigation strategies and enhanced urban resilience to climate change, we introduce a cloud-computed Green Infrastructure Suitability Index (GISI) methodology. This approach combines remote sensing and geospatial modeling to create a cloud-computed blend that synthesizes land cover classifications, biophysical variables, and flood exposure data to map suitability for green infrastructure (GI) implementation at both street and landscape levels. The GISI methodology provides a flexible and robust tool for urban planning, capable of accommodating diverse data inputs and adjustments, making it suitable for various geographic contexts. Applied within the Wilmington Urban Area Metropolitan Planning Organization (WMPO) in North Carolina, USA, our findings show that residential parcels, constituting approximately 91% of the total identified suitable areas, are optimally positioned for GI integration. This underscores the potential for embedding GI within developed residential urban landscapes to bolster ecosystem and community resilience. Our analysis indicates that 7.19% of the WMPO area is highly suitable for street-level GI applications, while 1.88% is ideal for landscape GI interventions, offering opportunities to enhance stormwater management and biodiversity at larger and more connected spatial scales. By identifying specific parcels with high suitability for GI, this research provides a comprehensive and transferable, data-driven foundation for local and regional planning efforts. The scalability and adaptability of the proposed modeling approach make it a powerful tool for informing sustainable urban development practices. Future work will focus on more spatiallyresolved models of these areas and the exploration of GI's multifaceted benefits at the local level, aiming to guide the deployment of GI projects that align with broader environmental and social objectives.
