On Inferring the Time-Varying Traffic Connectivity Structures of an Urban Environment

Abstract

Road networks shape traffic mobility in a city. These dynamics are often represented as traffic flows in and out of defined urban travel zones. The functional dynamics of traffic zones can be represented by time-dependant correlations between time series of traffic flows in and out of these zones. In this paper we address the question: given the dense timevarying functional correlations of traffic flow in a city, how can we derive a sparse representation that explains the timevarying structural connectivity of traffic zones in a city? We call this sparse representation the time-varying effective traffic connectivity of the city. We formulate an optimization problem to infer the sparse effective traffic network from dense functional correlations of traffic flow for arbitrary levels of temporal granularity, and demonstrate the results for the city of Doha, Qatar on data collected from several hundred bluetooth sensors deployed across the city to record vehicular activity through the city’s traffic zones. Preliminary experiments suggest that our framework can be used by urban transportation experts and policy specialists to take a real time data-driven approach towards urban planning and real time traffic planning in the city, especially at the level of administrative zones of a city.