Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flow

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations


Related Research Unit(s)


Original languageEnglish
Journal / PublicationIEEE Transactions on Intelligent Transportation Systems
Online published14 Mar 2022
Publication statusOnline published - 14 Mar 2022


Short-term forecasting of passenger flow is critical for transit management and crowd regulation. Spatial dependencies, temporal dependencies, inter-station correlations driven by other latent factors, and exogenous factors bring challenges to the short-term forecasts of passenger flow of urban rail transit networks. An innovative deep learning approach, MultiGraph Convolutional-Recurrent Neural Network (MGC-RNN) is proposed to forecast passenger flow in urban rail transit systems to incorporate these complex factors. We propose to use multiple graphs to encode the spatial and other heterogenous inter-station correlations. The temporal dynamics of the interstation correlations are also modeled via the proposed multigraph convolutional-recurrent neural network structure. Inflow and outflow of all stations can be collectively predicted with multiple time steps ahead via a sequence to sequence(seq2seq) architecture. The proposed method is applied to the shortterm forecasts of passenger flow in Shenzhen Metro, China. The experimental results show that MGC-RNN outperforms the benchmark algorithms in terms of forecasting accuracy. Besides, it is found that the inter-station driven by network distance, network structure, and recent flow patterns are significant factors for passenger flow forecasting. Moreover, the architecture of LSTM-encoder-decoder can capture the temporal dependencies well. In general, the proposed framework could provide multiple views of passenger flow dynamics for fine prediction and exhibit a possibility for multi-source heterogeneous data fusion in the spatiotemporal forecast tasks.

Research Area(s)

  • Correlation, Forecasting, inter-station correlation, multi-graph-convolution., Predictive models, Rails, Short-term forecasting of passenger flow, spatiotemporal dependencies, Spatiotemporal phenomena, Time series analysis, Transportation