Urbanization has rapidly transformed cities, leading to increased traffic congestion and a surge in road accidents. With more people migrating to urban areas in search of better opportunities, the growing interaction between vehicles and pedestrians has become a pressing concern for urban planners and safety officials. Understanding the underlying causes of traffic accidents is crucial for mitigating risks and enhancing public safety. This study focuses on analyzing accident causation and urban safety using advanced techniques such as machine learning and Geographic Information Systems (GIS). The relationship between land use, urban planning, and road safety is well-established, with factors such as land use changes, accessibility, road design, and driver behavior playing significant roles in accident occurrences. However, existing studies often overlook the dynamic nature of land use, particularly how land use and land cover (LULC) changes over time influence accident rates. By integrating behavioral, demographic, and engineering factors with LULC changes, this study aims to provide a more comprehensive understanding of accident causation. The research also explores the potential of hybrid models, combining traditional statistical approaches with machine learning techniques, to improve accident prediction accuracy. The study focuses on Vizianagaram, a rapidly urbanizing city in Andhra Pradesh, India, using satellite imagery and GIS tools to analyze land use patterns from 2017 to 2023. Through this analysis, the report aims to identify key patterns in accident causation and provide insights for urban safety and traffic management strategies. This research contributes to developing more effective prevention measures to ensure safer urban environments.