Urban change detection is essential for effective urban planning, environmental monitoring, and sustainable development. With the advent of deep learning, traditional change detection method for urban areas have been significantly enhanced, offering improved accuracy and efficiency. This review focuses on the application of deep learning techniques in urban change detection, highlighting recent advancements and methodologies. Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and other deep learning architectures are explored for their roles in analyzing high-resolution satellite imagery and temporal data. The review also examines the integration of these techniques with Geographic Information Systems (GIS) and remote sensing technologies to monitor urban sprawl, infrastructure development, and land use changes. A comprehensive bibliographic analysis of seminal works and contemporary studies is presented, showcasing the evolution of deep learning applications in this field. The findings indicate that deep learning not only enhances the precision of urban change detection but also facilitates real-time monitoring and large-scale analysis, providing valuable insights for policymakers and urban planners aiming for sustainable urban development. In this review paper, the bibliometric analysis gives a broad overview of the application and worldwide developments of deep learning-based urban change detection. This would assist the researchers in examining the most pertinent studies, analyses, and identification of research gaps in accordance with their needs.