AI-DRIVEN URBAN HEAT ISLAND MAPPING FOR GREEN BUILDING DESIGN AND SUSTAINABLE INFRASTRUCTURE PLANNING

The Urban Heat Island (UHI) effect intensifies rising temperatures in cities, leading to increased building cooling demand, reduced outdoor thermal comfort, and environmental stress on urban infrastructure. This study presents an Artificial Intelligence–driven framework to support green building design and sustainable infrastructure planning through high-resolution thermal mapping. The proposed model integrates ground-based temperature observations, Sentinel-2 and Landsat satellite imagery, local weather parameters, and urban built-form indicators such as vegetation cover, surface reflectivity, and construction density. Machine learning techniques are employed to generate fine-scale spatial predictions of heat exposure across urban regions and to quantify the influence of green infrastructure and high-albedo materials on local temperature patterns. The resulting thermal suitability assessment enables identification of heat-vulnerable construction zones and potential locations for green roofs, reflective roofing systems, and vegetative buffers. These insights assist planners, architects, and policymakers in adopting heat-resilient building strategies that reduce energy consumption and improve urban microclimatic conditions. The framework is scalable and adaptable to different cities using open geospatial datasets, supporting data-driven decision making for sustainable urban development. By linking AI-based thermal analysis with green building interventions, the study provides a practical planning support tool for climate-responsive infrastructure and contributes to the advancement of environmentally responsible construction practices in rapidly urbanizing regions.