Detecting spatiotemporal propagation patterns of traffic congestion from fine-grained vehicle trajectory data

Abstract

Traffic congestion on a road segment typically begins as a small-scale spatiotemporal event that can then propagate throughout a road network and produce large-scale disruptions to a transportation system. In current techniques for the analysis of network flow, data is often aggregated to relatively large (e.g. 5 min) discrete time steps that obscure the small-scale spatiotemporal interactions that drive larger-scale dynamics. We propose a new method that handles fine-grained data to better capture those dynamics. Propagation patterns of traffic congestion are represented as spatiotemporally connected events. Each event is captured as a time series at the temporal resolution of the available trajectory data and at the spatial resolution of the network edge. The spatiotemporal propagation patterns of traffic congestion are captured using Dynamic Time Warping and represented as a set of directed acyclic graphs of spatiotemporal events. Results from this method are compared to an existing method using fine-grained data derived from an agent-based model of traffic simulation. Our method outperforms the existing method. Our method also successfully detects congestion propagation patterns that were reported by media news using sparse real-world data derived from taxis.

Keywords:

• Spatiotemporal representation of event propagation
• network dynamics
• traffic congestion

Acknowledgements

The authors thank Dr. May Yuan, Dr. David O’Sullivan and the anonymous reviewers for their constructive comments and suggestions.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and codes availability statement

Data and codes are available at https://doi.org/10.6084/m9.figshare.21511923. For real-world GPS data, we provide a mock dataset because of DiDi’s data policy. Please refer to the running instructions for details in the shared link. Example simulation videos are also available in the shared link.

Additional information

Funding

This work was partially supported financially by the U.S. Department of Transportation’s University Transportation Center Program [69A3551747131].

Notes on contributors

Haoyi Xiong

Haoyi Xiong is a PhD and his research field is GIScience. He is interested in applying the methods in data mining and machine learning to solve geographical problems. He contributed to the study design, literature review, methodology, implementation, data analysis, evaluation and writing.

Xun Zhou

Xun Zhou is an Associate Professor in the Department of Business Analytics, Tippie College of Business at the University of Iowa. His research interests include spatial and spatiotemporal data mining, GeoAI, urban intelligence and business analytics. He contributed to the idea conceptualization, methodology, analysis of real-world data, review and editing of this paper.

David A. Bennett

David A. Bennett is a Professor and department chair in the Department of Geographical and Sustainability Sciences. His research interests lie in GIScience with a focus on agent-based modelling, spatial optimization with application to sustainability and the environment. He contributed to the literature review, analysis of simulated data, review and editing of this paper.