Document Type : Original Article
Authors
1
PhD Student in Remote Sensing and GIS, RS and GIS group, Science and Research Branch, Islamic Azad University, Tehran, Iran
2
Associated Professor at Department of Remote Sensing and GIS, Science and Research Branch, Islamic Azad University, Tehran, Iran
3
Associated Professor at Center for Remote Sensing and GIS Research, Faculty of Earth Sciences, Shahid Beheshti University, Tehran, Iran
4
Associate Professor, Department of Surveying Engineering, Faculty of Civil, Water and Environmental Engineering, Shahid Beheshti University, Tehran, Iran
10.22059/eoge.2025.390975.1169
Abstract
Effective urban traffic management relies on a thorough understanding of traffic behavior patterns. Traditional methods often struggle to capture the dynamic and complex nature of modern traffic. This research addresses this challenge by utilizing online traffic data from the Mapbox platform to analyze and forecast traffic behavior patterns in Tehran. Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) time series models were employed to analyze traffic volume, vehicle speed, and travel time data. The models were evaluated using criteria such as the Akaike Information Criterion (AIC) and Root Mean Square Error (RMSE). The results indicate that these models can accurately simulate both temporal and periodic trends. Specifically, the Moving Average (MA) coefficient (ma.L1) shows a positive and significant impact of the first lag (p-value = 0.000). The analysis reveals that the Autoregressive (AR) coefficient (ar.L1) is -0.0270, indicating a negative impact of the first lag; however, a p-value of 0.588 rejects the significance of this impact. On the other hand, the Moving Average (MA) coefficient (ma.L1) is 0.2028, showing a positive and significant impact of the first lag (p-value = 0.000). Furthermore, the AIC and BIC criteria are -18070.697 and -18036.730, respectively. The study's interpretation of negative values indicates a robust model fit and no extra parameters needed. Additionally, this research analyzed traffic behavior in Tehran by examining modeling results across different hours to capture variations in traffic patterns. The study highlights the effectiveness of using online traffic data and time series modeling to identify factors influencing traffic, improve urban traffic management, and support transportation planning. Overall, it promotes detailed traffic analysis and behavior prediction, contributing to intelligent and sustainable transportation systems, enhanced urban resilience, and improved infrastructure and traffic flow.
Keywords
Main Subjects
)