Railway Delay Prediction with Spatial-Temporal Graph Convolutional Networks

Cascading delays that propagate from a primary source along a railway network are an immediate concern for British railway systems. Complex nonlinear interactions between various spatio-temporal variables govern the propagation of these delays which can quickly spread throughout railway networks, causing further severe disruptions. To better understand the effects of these nonlinear interactions, we present a novel, graph-based formulation of a subset of the British railway network. Using this graph-based formulation, we apply the Spatial-Temporal Graph Convolutional Network (STGCN) model to predict cascading delays throughout the railway network. We find that this model outperforms other statistical models which do not explicitly account for interactions on the rail network, thus showing the value of a Graph Neural Network (GNN) approach in predicting delays for the British railway system.

[1]  Pierre Vandergheynst,et al.  Wavelets on Graphs via Spectral Graph Theory , 2009, ArXiv.

[2]  Nils O. E. Olsson,et al.  Method of analysis for delay propagation in a single-track network , 2017, J. Rail Transp. Plan. Manag..

[3]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[4]  Davide Anguita,et al.  Advanced Analytics for Train Delay Prediction Systems by Including Exogenous Weather Data , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[5]  Boris Cule,et al.  Mining Train Delays , 2011, IDA.

[6]  Ren Wang,et al.  Data Driven Approaches for Passenger Train Delay Estimation , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[7]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[8]  Irina Stipanovič.  Big data in railway operations : Using artificial neural networks to predict train delay propagation , 2016 .

[9]  Yuxiang Yang,et al.  Statistical delay distribution analysis on high-speed railway trains , 2019, Journal of Modern Transportation.

[10]  Thorsten Büker,et al.  Stochastic modelling of delay propagation in large networks , 2012, J. Rail Transp. Plan. Manag..

[11]  Hamsa Balakrishnan,et al.  A comparative analysis of models for predicting delays in air traffic networks , 2017 .

[12]  Pu Wang,et al.  Train delay analysis and prediction based on big data fusion , 2019, Transportation Safety and Environment.

[13]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[14]  Davide Anguita,et al.  Train Delay Prediction Systems: A Big Data Analytics Perspective , 2017, Big Data Res..

[15]  Abhishek Dubey,et al.  On the Data-Driven Prediction of Arrival Times for Freight Trains on U.S. Railroads , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[16]  Rob M.P. Goverde,et al.  A delay propagation algorithm for large-scale railway traffic networks , 2010 .

[17]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[18]  Harshad Khadilkar.  Modelling the impact of control strategy on stochastic delay propagation in transportation networks , 2016, 2016 European Control Conference (ECC).

[19]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[20]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.