Inbound Passenger Flow Prediction of Spatio-temporal Graph Convolutional Neural Network for Urban Rail Transit Based on Spatio-temporal Correlation

Abstract

Objective Accurate short term passenger flow prediction is of great significance to improve the operation and management efficiency of the ultra-large scale of urban rail transit network. However, the current research on deep exploration of the spatio-temporal correlations is still insufficient. Therefore, according to the spatio-temporal law of short term passenger flow, a STGCN (spatio-temporal graph convolutional neural network) model based on spatio-temporal correlation characteristics of passenger flow is proposed. Method Firstly, the spatial correlation of ultra-large scale urban rail transit network is captured by ChebyNet （Chebyshev graph convolutional network）, and the temporal correlation of the passenger flow under multi-temporal correlation characteristics is explored with the help of GRU (gated recurrent unit). Secondly, the correlation of the historical passenger flow data of the station to be predicted and that of OD (origin-destination) passenger flow data are analyzed to extract the spatio-temporal correlation deeply. Finally, a STGCN model is established in combination with the spatio-temporal correlation characteristics of the passenger flow. Result & Conclusion Taking Jiangsu Road Station of Shanghai Metro Line as an example, a short-term inbound passenger flow prediction is conducted. The result shows that the prediction accuracy with spatio-temporal correlation characteristic parameters is 16% higher than that without the parameters, indicating a better prediction effect.