Print Email Facebook Twitter Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flow Title Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flow Author He, Yuxin (Shenzhen Technology University) Li, L. (TU Delft Air Transport & Operations) Zhu, X. (TU Delft Air Transport & Operations; City University of Hong Kong) Tsui, Kwok Leung (Virginia Tech) Date 2022 Abstract 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, Multi-Graph 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 inter-station correlations are also modeled via the proposed multi-graph 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 short-term 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. Subject CorrelationForecastinginter-station correlationmulti-graph-convolution.Predictive modelsRailsShort-term forecasting of passenger flowspatiotemporal dependenciesSpatiotemporal phenomenaTime series analysisTransportation To reference this document use: http://resolver.tudelft.nl/uuid:d59efa06-be2f-4a68-9f20-1162678569ae DOI https://doi.org/10.1109/TITS.2022.3150600 Embargo date 2023-07-01 ISSN 1524-9050 Source IEEE Transactions on Intelligent Transportation Systems, 23 (10), 18155-18174 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2022 Yuxin He, L. Li, X. Zhu, Kwok Leung Tsui Files PDF Multi_Graph_Convolutional ... r_Flow.pdf 8.69 MB Close viewer /islandora/object/uuid:d59efa06-be2f-4a68-9f20-1162678569ae/datastream/OBJ/view