Automated Extraction of Roads Traffic Flow from Open Google Maps Data

This study explores the practical utilization of open data to analyze and improve urban transportation systems, focusing on leveraging real-time Google Traffic maps (GTM) data for automatic extraction of road traffic delay patterns. The research began by defining the study area geographically for data extraction from open street maps. A specialized extraction procedure, executed via the "r.tikrit" R code deployed on a server, tailored extraction intervals considering server constraints and area dimensions. The resulting traffic delay values were transformed into a spatial object table, enabling Geographic Information System (GIS) data analysis and visualization. The dataset, stored as daily tabular records, with hourly data input, accompanied by contextual raster images, facilitated comprehensive analysis. The methodological framework comprises three primary phases: firstly, defining the study area and segmenting roads; secondly, setting up the r.tikrit code; and thirdly, conducting data analysis and extracting traffic flow patterns. Throughout the developmental phases, Generative AI tools played a pivotal role as assistants, aiding in the development of analysis codes, streamlining the extraction process, and facilitating the literature survey. Subsequent research phases involved testing multiple applications: 1)Traffic Flow and Commuting Delay: Calculating traffic delay, peak hours and roads congestion situation 2) Spatial-Temporal Semi-Stationary Traffic Flow: Identifying unusual delays in selected roads segments that might be linked to external factors like accidents or natural hazards. 3) Traffic Flow Delay - Rainfall Relationship: Evaluating the impact of rainfall events on traffic networks and traffic delay. The approach's strength lies in its ability to generate high-resolution spatial and temporal road traffic delay data continuously. However, acknowledging inherent limitations of Google Traffic mapssuch as inactive roads and discrepancies with open street mapsis vital. Despite these limitations, This methodology serves as an indispensable tool for researchers aiming to gain comprehensive insights into the complex status of urban traffic congestion patterns. Furthermore, it facilitates extended research into understanding the correlations between urban traffic and the ambient environment, enabling a deeper exploration of their impacts.