SASTGCN: Semantic-Augmented Spatio-temporal graph convolutional network for subway flow prediction

Deep learning based subway passenger flow prediction was widely employed to promote prediction accuracy, which is crucial for subway management and commercial infrastructure planning. However, the existing work ignored the semantic similarity inherent in the subway stations function, which can extra...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiyuan Jin, Changfeng Jing, Sheng Yao, Yushan Zhang, Pu Zhao, Jinlong Zhang
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225001773
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning based subway passenger flow prediction was widely employed to promote prediction accuracy, which is crucial for subway management and commercial infrastructure planning. However, the existing work ignored the semantic similarity inherent in the subway stations function, which can extract passengers and enhance prediction accuracy. In this work, a Semantic-Augmented Spatio-temporal Graph Convolutional Network (SASTGCN) model was proposed, which considered semantic similarity, spatiotemporal correlations and spatial heterogeneity to realize the passenger inflow and outflow prediction. The station function was derived from travel characteristics of passengers by data-driven method. The spatiotemporal block including Topology Adaptive Graph Convolutional Network (TAGCN) and ConvNeXt, constructed adaptive spatial topology, depthwise separable convolution and expanded receptive fields to capture spatiotemporal correlations and spatial heterogeneity. The SASTGCN model was validated with the card swiping data in Shanghai, the prediction ability and error analysis results demonstrated the performance outperform nine baseline methods, and the accuracy was improved by approximately 21%. The proposed model can provide inspiration for the follow-up research of passenger flow prediction, traffic pattern recognition and dynamic scheduling.
ISSN:1569-8432