Spatiotemporal Virtual Graph Convolution Network for Key Origin-Destination Flow Prediction in Metro System

Abstract

Short-term Origin-Destination (OD) flow prediction plays a major part in the realization of Smart Metro. It can help traffic managers implement dynamic control strategies to improve operation safety. Also, it can assist passengers in making reasonable travel plans to improve the passenger experience. However, there are problems that the dimension of OD short-term traffic prediction is much higher than the base number of metro stations and the OD matrix is sparse. To resolve the above two problems, a threshold-based method is proposed to extract key OD pairs first. OD passenger flow contains the attribute information of the Origin-Destination station and exhibits similar time evolution characteristics, so the spatial and temporal correlation needs to be considered in the prediction. Pearson correlation matrix is used to build a virtual graph and model the virtual connection between OD pairs. A spatiotemporal virtual graph convolutional network (ST-VGCN), which combines the advantages of a graph neural network and gated recurrent neural network, is proposed to identify spatial associations and temporal patterns simultaneously. The proposed method is evaluated on 39 days of real-world data from Shenzhen Metro, which outperforms other benchmarks. The research in this work can contribute to the development of short-term OD flow forecasts and help to provide ideas for the research on real-time operation and management of rail transit. Furthermore, it can help to establish passenger flow prediction and early warning mechanisms to quickly evacuate a large number of passengers in case of emergency.

Model Generation and Origin - Destination(OD) Matrix Forecasting for metro systems

“…These graphs are incorporated into a Graph Convolution Gated Recurrent Unit (GC-GRU) to learn spatiotemporal relationships and apply them to a Fully-Connected Gated Recurrent Unit (FC-GRU) to find the global evolution trend, for later prediction. There are others that follow the same trend [9]- [12], although we can highlight a recent one [15] in which not only these spatio-temporal dependencies are used for forecasting through multigraph convolutions but also the same method is applied to perform a parallel IO prediction (multi-task forecasting) so that this, likewise, improves the OD prediction.…”

Passenger Flow Path Prediction Based on Urban Rail Transit AFC Data: An Example of Chengdu, China

“…Moreover, in the last two years of research, passenger fow forecasting, especially OD passenger fow forecasting, has been studied further, revealing that there are indeed urgent problems in this area in the current period. Terefore, current research mainly tends to employ data mining algorithms for OD passenger fow prediction in urban rail transit, considering spatiotemporal correlation factors [1,2,[8][9][10][11][12][13].…”