Railway Passenger Flow Forecasting by Integrating Passenger Flow Relationship and Spatiotemporal Similarity

Railway passenger f low forecasting can help to develop sensible railway schedules, make full use of railway resources, and meet the travel demand of passengers. The structure of passenger f low in railway networks and the spatiotemporal relationship of passenger f low among stations are two distinctive features of railway passenger f low. Most of the previous studies used only a single feature for prediction and lacked correlations, resulting in suboptimal performance. To address the above-mentioned problem, we proposed the railway passenger f low prediction model called Flow-Similarity Attention Graph Convolutional Network (F-SAGCN). First, we constructed the passenger f low relations graph (RG) based on the Origin-Destination (OD). Second, the Passenger Flow Fluctuation Similarity (PFFS) algorithm is used to measure the similarity of passenger f low between stations, which helps construct the spatiotemporal similarity graph (SG). Then, we determine the weights of the mutual inf luence of different stations at different times through an attention mechanism and extract spatiotemporal features through graph convolution on the RG and SG. Finally, we fused the spatiotemporal features and the original temporal features of stations for prediction. The comparison experiments on a railway bureau’s accurate railway passenger f low data show that the proposed F-SAGCN method improved the prediction accuracy and reduced the mean absolute percentage error (MAPE) of 46 stations to 7.93%.