Modelling traffic as multi-graph signals: Using domain knowledge to enhance the network-level passenger flow prediction in metro systems

Abstract

Network-level metro passenger flow prediction has always been one of the most important but most challenging scientific problems in intelligent transportation systems (ITS). However, conventional methods ignore the multi-dimensional topological relationships in the subway system or directly learn from the physical topological structure and fail to explore the spatial-temporal evolution of passenger flow fully. Moreover, due to the highly punctual operation feature, the metro system has high-degree controllability and regularity, which is usually not considered in the traditional model. To address this problem, we model a metro system based on various topological structures and propose a novel spatial-temporal multi-graph convolutional wavelet network (ST-MGCWN) with unique metro system state characteristics. The core of this approach is to combine the domain knowledge of transportation and deep learning models. To be precise, there are three main modules in the proposed framework: (i). The graph wavelet convolution captures the dynamic spatial dependence between nodes on the established multiple graphs and synthesizes topological features through the graph fusion module. (ii). The various approaches based on the gated recurrent model are designed to capture the long-term periodicity and short-term trends. (iii). The transformation of the metro state characteristics reflects the change of the train density on the operation diagram, which is approximated by the distribution of the local peaks of passenger flow. Experimental results show that our proposed model achieves up to about 5% improvement over the state-of-the-art approach for the network-level passenger flow prediction task. In addition, we conduct a detailed analysis of the contribution of each component to enhance interpretability and reliability.