Data-Driven Identification of Accident-Prone Zones Using Google Maps and GIS-Based Predictive Modeling

Abstract

Road traffic accidents are a persistent global concern, leading to significant fatalities, injuries, and economic losses annually. Accurate and proactive identification of accident-prone zones is critical for implementing targeted safety measures, optimizing traffic flow, and guiding urban planning initiatives. This paper presents a comprehensive framework for Accidental Prone Zone Identification (APZI), integrating real-time Google Maps traffic data, Geographic Information Systems (GIS), historical accident datasets, and advanced machine learning models. The framework dynamically evaluates road geometry, traffic patterns, environmental conditions, and infrastructural features to compute risk scores for individual road segments. By applying clustering algorithms and predictive analytics, APZI identifies high-risk zones and provides interactive GIS-based visualizations for city planners and traffic authorities. The methodology includes human-in-the-loop validation, ensuring practical applicability and reliability of predictions. Experimental studies conducted across diverse urban and suburban areas demonstrate the framework's effectiveness, with machine learning models achieving F1-scores exceeding 0.85, and successfully uncovering previously unreported accident hotspots. Simulation-based validation using platforms such as SUMO and VISSIM further confirms the accuracy of predicted risk zones under varying traffic scenarios. The integration of real-time traffic data, predictive analytics, GIS overlays, and simulation modeling enables dynamic, data-driven insights that support informed decision-making, preventive interventions, and efficient resource allocation. This research offers a scalable, robust, and practical solution for intelligent transportation management, demonstrating the potential of AI and geospatial technologies in enhancing road safety, reducing accident rates, and fostering safer urban mobility environments. The proposed APZI framework represents a significant advancement toward proactive, evidence-based traffic safety planning and management.