Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting

Cui, Zhiyong; Henrickson, Kristian; Ke, Ruimin; Wang, Yinhai

doi:10.1109/tits.2019.2950416

Cited by 693 publications

(369 citation statements)

References 34 publications

Supporting

Mentioning

365

Contrasting

Unclassified

Order By: Relevance

“…Later, Li et al (2017) applied a diffusion convolutional recurrent network structure to the prediction of short-term traffic, Yu et al (2017) used gated convolution neural network to predict traffic in urban road networks. Most recently, In Cui et al (2018)'s work, a high-order graph convolutional RNN is proposed for 5-min ahead traffic speed prediction in urban areas. This paper does not work with parking occupancy, but its methodology is closest to our work among all the relevant literature.…”

Section: Literature Reviewmentioning

confidence: 99%

A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources

Yang

et al. 2019

Transportation Research Part C: Emerging Technologies

171

View full text Add to dashboard Cite

A deep learning model is applied for predicting block-level parking occupancy in real time. The model leverages Graph-Convolutional Neural Networks (GCNN) to extract the spatial relations of traffic flow in large-scale networks, and utilizes Recurrent Neural Networks (RNN) with Long-Short Term Memory (LSTM) to capture the temporal features. In addition, the model is capable of taking multiple heterogeneously structured traffic data sources as input, such as parking meter transactions, traffic speed, and weather conditions. The model performance is evaluated through a case study in Pittsburgh downtown area. The proposed model outperforms other baseline methods including multi-layer LSTM and Lasso with an average testing MAPE of 10.6% when predicting block-level parking occupancies 30 minutes in advance. The case study also shows that, in generally, the prediction model works better for business areas than for recreational locations. We found that incorporating traffic speed and weather information can significantly improve the prediction performance. Weather data is particularly useful for improving predicting accuracy in recreational areas.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources

Yang

et al. 2019

Transportation Research Part C: Emerging Technologies

171

View full text Add to dashboard Cite

show abstract

“…[19] and [20] both propose graph NN layers that learn spatiotemporal relationships in traffic networks. [19] propose a "diffusion convolutional" operation with learned coefficients, used to model traffic movements as a random walk along a graph.…”

Section: Neural Network For Traffic Dynamicsmentioning

confidence: 99%

“…[19] propose a "diffusion convolutional" operation with learned coefficients, used to model traffic movements as a random walk along a graph. [20] propose a "traffic graph convolutional" operation that incorporates traffic-theoretic information by clipping adjacency matrices based on whether traffic can feasibly move from one location to another in a time interval, based on the road distance and a prescribed freeflow speed.…”

Section: Neural Network For Traffic Dynamicsmentioning

confidence: 99%

“…In both papers, this graph operation forms the internals of a recurrent neural network (RNN) layer that is iteratively applied to a traffic timeseries to learn an autoregressive model. Their methods are applied to freeway-network-scale traffic measurements in two major U.S. metro areas: Los Angeles in [19] and Seattle in [20].…”

Section: Neural Network For Traffic Dynamicsmentioning

confidence: 99%

See 1 more Smart Citation

Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane Graphs

Wright¹,

Ehlers

Horowitz³

2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear spatiotemporal physics problem of vehicle traffic dynamics. We consider problems of estimating macroscopic quantities (e.g., the queue at an intersection) at a lane level. Firstprinciples modeling at the lane scale has been a challenge due to complexities in modeling social behaviors like lane changes, and those behaviors' resultant macro-scale effects. Following domain knowledge that upstream/downstream lanes and neighboring lanes affect each others' traffic flows in distinct ways, we apply a form of neural attention that allows the neural network layers to aggregate information from different lanes in different manners. Using a microscopic traffic simulator as a testbed, we obtain results showing that an attentional neural network model can use information from nearby lanes to improve predictions, and, that explicitly encoding the lane-to-lane relationship types significantly improves performance. We also demonstrate the transfer of our learned neural network to a more complex road network, discuss how its performance degradation may be attributable to new traffic behaviors induced by increased topological complexity, and motivate learning dynamics models from many road network topologies.

show abstract

“…For instance, it is difficult to predict the chemical properties of a molecule by only looking at its atoms; on the other hand, by explicitly representing the chemical bonds, the description of the molecule becomes more complete, and the learning algorithm can take advantage of that information. Similarly, several other machine learning problems benefit from a graphbased representation, e.g., the understanding of visual scenes [2], the modelling of interactions in physical and multi-agent systems [3], [4], or the prediction of traffic flow [5]. In all these problems (and many others [1]), the dependencies among variables provide a strong prior that has been successfully leveraged to significantly surpass the previous state of the art.…”

Section: Introductionmentioning

confidence: 99%

Autoregressive Models for Sequences of Graphs

Zambon

Grattarola

Livi

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models. A first novelty consists in formalising the AR model for a very general family of graphs, characterised by a variable topology, and attributes associated with nodes and edges. A graph neural network (GNN) is also proposed to learn the AR function associated with the graph-generating process (GGP), and subsequently predict the next graph in a sequence. The proposed method is compared with four baselines on synthetic GGPs, denoting a significantly better performance on all considered problems.

show abstract

Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting

Cited by 693 publications

References 34 publications

A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources

A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources

Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane Graphs

Autoregressive Models for Sequences of Graphs

Contact Info

Product

Resources

About