Graph-Based Dynamic Modeling and Traffic Prediction of Urban Road Network

Based on various on-road sensor observations, dynamic modeling and analysis of urban road networks becomes an important task of an intelligent transportation system. The major difficulty of this task is that traffic states vary dynamically in both spatial and temporal domains. In this paper, we propose a novel urban road network modeling approach. A road network is described by a weighted undirected graph composed of vertices and edges denoting, respectively, traffic intersections and their pairwise connections. Given the topology of the network, an effective weight estimation algorithm is proposed to extract spatial correlations among adjacent traffic intersections from physical sensor observations. Graph weights can be regularly updated to capture the dynamic essence of traffic states over time. On the basis of weight estimation, we further develop a dynamic spatio-temporal traffic prediction model by using the spatio-temporal autoregressive integrated moving average (STARIMA) model. The effectiveness of the proposed graph-based STARIMA is validated by a series of numerical experiments.

Automated summary

This paper introduces a novel urban road network modeling approach based on a weighted undirected graph, which extracts spatial correlations from physical sensor observations and utilizes the STARIMA model for dynamic spatio-temporal traffic prediction. The effectiveness of the proposed graph-based STARIMA model is validated through a series of numerical experiments, addressing the challenges of dynamic modeling and analysis of urban road networks in intelligent transportation systems.