With the proliferation of urban hubs, cities generate vast amounts of data via sensors, IoT devices, GPS, and social media. This necessitates advanced data analysis to extract significant insights for various applications, such as urban planning, disaster management, transportation network research, and climate change studies. Over the years, significant progress has been made in GeoAI, combining Geospatial Information Systems with Artificial Intelligence. GeoAI facilitates the automated examination of extensive spatial data, allowing for identifying patterns and enhancing urban planning procedures in real time. It also facilitates immediate updates and allows prompt responses to environmental alterations. This study introduces a comprehensive process for mapping Land Use and Land Cover (LULC) and extracting spatial information about entities. The study proposes using advanced models to detect features and provide a comprehensive explanation, from data collection to creating practical and effective results. The YOLOv8-SAM-based integrated pipeline is employed for building and vegetation extraction. In contrast, UnetEdge is used for road feature extraction. Both of these pipelines were applied consecutively for LULC preparation. Case studies are also included to illustrate the real-world implementation of this approach. The work emphasizes the importance of the involvement of data-driven approaches in deducing urban insights and implementing applications. Also, it showcases the potential of combining Earth observation data with advanced models to tackle intricate environmental monitoring and management issues.