Spatial-Temporal Traffic Flow Pattern Identification and Anomaly Detection with Dictionary-based Compression Theory in a Large-Scale Urban Network

Traffic flow pattern identification, as well as anomaly detection, is an important component for traffic operations and control. To reveal the characteristics of regional traffic flow patterns in large road networks, this paper employs dictionary-based compression theory to identify the features of both spatial and temporal patterns by analyzing the multi-dimensional traffic-related data. An anomaly index is derived to quantify the network traffic in both spatial and temporal perspectives. Both pattern identifications are conducted in three different geographic levels: detector, intersection, and sub-region. From different geographic levels, this study finds several important features of traffic flow patterns, including the geographic distribution of traffic flow patterns, pattern shifts at different times-of-day, pattern fluctuations over different days, etc. Both spatial and temporal traffic flow patterns defined in this study can jointly characterize pattern changes and provide a good performance measure of traffic operations and management. The proposed method is further implemented in a case study for the impact of a newly constructed subway line. The before-and-after study identifies the major changes of surrounding road traffic near the subway stations. It is found that new metro stations attract more commute traffic in weekdays as well as entertaining traffic during weekends. 1 Introduction Studies on traffic flow patterns within a scale of road facilities have aroused increasing attentions in recent years. The traffic flow patterns can be taken as those characteristics of vehicle groups passing a point or a short segment during a specified span or traveling over longer sections of highway (Lan et al., 2008). The spatiotemporal features of traffic flow, occupancy, and speed over different time scales can provide insights into traffic operation and control, urban planning, incident management, etc. The time-of-day and day-of-week features of traffic flow or occupancy reveal the fluctuations of the jammed conditions and traffic operations of road links, intersections or even networks and can serve different research purposes. For instance, White et al., (2007) focused on the impact of the daily visitor transportation on the public infrastructures and suggested approaches to improve the environmental sustainability of national parks; Ramaswami et al. (1996) studied the network traffic patterns to design the logical topology and the routing algorithm so as to minimize the network congestion; Cassidy et al. (1999) investigated the characteristics of freeway traffic flow patterns and their findings have practical implications for freeway traffic planning and management; Lee et al.(2014) proposed a method to identify the congestion …