Urban areas globally face escalating challenges from Urban Heat Islands (UHI), characterized by elevated temperatures in urban regions compared to surrounding areas. This paper addresses the urgent need for comprehensive UHI analysis and mitigation strategies by harnessing advanced Artificial Intelligence (AI) and Computer Vision techniques. The primary objectives encompass leveraging high-resolution satellite imagery and semantic segmentation algorithms for accurate UHI detection through detailed land cover classification. Additionally, the study integrates weather information application programming interfaces (APIs) to correlate real-time and historical weather data with UHI intensity, providing a holistic understanding of UHI effects. Our proposed methodology involves a twofold architectural design, comprising the preprocessing of satellite images using patchify-ing and semantic segmentation for land cover classification. Experimental results demonstrate the model's ability to differentiate between urban and rural areas, showcasing its potential for automated UHI detection. The research emphasizes the importance of acquiring ample satellite data to enhance accuracy and resolution, acknowledging current limitations in the available dataset. In conclusion, this paper underscores the necessity of a holistic approach to UHI, combining AI and Computer Vision for precise detection and comprehensive analysis. While presenting a case study for a single city, the outlined pipeline provides essential steps for detecting UHI effects in any area equipped with necessary satellite imagery and temperature data, contributing to the broader understanding and mitigation of UHI in urban environments.