Urban Heat Islands (UHIs) represent a critical challenge for sustainable urban development, contributing to elevated temperatures, increased energy consumption, and adverse health impacts. This study presents a novel approach to Thermal Resilience Mapping through Deep Learning-based Urban Heat Island Forecasting combined with Targeted Green Infrastructure Planning. Leveraging satellite imagery, climate data, and advanced neural network architectures, the proposed model predicts UHI intensity and distribution with high spatial and temporal accuracy. Furthermore, the integration of Geographical Information Systems (GIS) and optimization algorithms enables the strategic placement of green infrastructure to mitigate heat accumulation effectively. This dual-layered approach not only enhances urban climate resilience but also supports policymakers in making data-driven decisions for sustainable urban planning. Our results demonstrate significant potential for reducing peak temperatures and improving thermal comfort in high-risk urban zones.