Multivariate Correlation-aware Spatio-temporal Graph Convolutional Networks for Multi-scale Traffic Prediction
Authors:
Open Access
- 18 January 2022
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 13 (3) , 1-22
Abstract
Traffic flow prediction based on vehicle trajectories collected from the installed GPS devices is critically important to Intelligent Transportation Systems (ITS). One limitation of existing traffic prediction models is that they mostly focus on predicting road-segment level traffic conditions, which can be considered as a fine-grained prediction. In many scenarios, however, a coarse-grained prediction, such as predicting the traffic flows among different urban areas covering multiple road links, is also required to help government have a better understanding on traffic conditions from the macroscopic point of view. This is especially useful in the applications of urban planning and public transportation planning. Another limitation is that the correlations among different types of traffic-related features are largely ignored. For example, the traffic flow and traffic speed are usually negatively correlated. Existing works regard these traffic-related features as independent features without considering their correlations. In this article, we for the first time study the novel problem of multivariate correlation-aware multi-scale traffic flow predicting, and we propose a feature correlation-aware spatio-temporal graph convolutional networks named MC-STGCN to effectively address it. Specifically, given a road graph, we first construct a coarse-grained road graph based on both the topology closeness and the traffic flow similarity among the nodes (road links). Then a cross-scale spatial-temporal feature learning and fusion technique is proposed for dealing with both the fine- and coarse-grained traffic data. In the spatial domain, a cross-scale GCN is proposed to learn the multi-scale spatial features jointly and fuse them together. In the temporal domain, a cross-scale temporal network that is composed of a hierarchical attention is designed for effectively capturing intra- and inter-scale temporal correlations. To effectively capture the feature correlations, a feature correlation learning component is also designed. Finally, a structural constraint is introduced to make the predictions on the two scale traffic data consistent. We conduct extensive evaluations over two real traffic datasets, and the results demonstrate the superior performance of the proposal on both fine- and coarse-grained traffic predictions.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (NZ2020014)
- National Natural Science Foundation of China (62072282 and 62172443)
- Industrial Internet Innovation and Development Project in 2019 of China
- shandong provincial key research and development program (2019JZZY010105)
- NSF (III-1763325, III-1909323, and SaTC-1930941)
This publication has 33 references indexed in Scilit:
- Community structure in traffic zones based on travel demandPhysica A: Statistical Mechanics and its Applications, 2016
- The rise of big data on urban studies and planning practices in China: Review and open research issuesJournal of Urban Management, 2015
- Traffic zone division based on big data from mobile phone base stationsTransportation Research Part C: Emerging Technologies, 2015
- Regression conformal prediction with random forestsMachine Learning, 2014
- Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditionsExpert Systems with Applications, 2009
- A tutorial on spectral clusteringStatistics and Computing, 2007
- Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical ResultsJournal of Transportation Engineering, 2003
- Vector Autoregressive Models for Multivariate Time Series2003
- Multivariate Vehicular Traffic Flow Prediction: Evaluation of ARIMAX ModelingTransportation Research Record: Journal of the Transportation Research Board, 2001
- Traffic Flow Forecasting: Comparison of Modeling ApproachesJournal of Transportation Engineering, 1997