|Table of Contents|

Graph neural network-based subway passenger flow prediction considering time periods(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2025年2期
Page:
154-164
Research Field:
交通工程
Publishing date:

Info

Title:
Graph neural network-based subway passenger flow prediction considering time periods
Author(s):
QIAN Han-qiang1; 2;  SHI Yue1; 2;  CHEN Yan-yan1; 2;  WANG Jia-chen3
(1. School of Metropolitan Transportation, Beijing University of Technology, Beijing 100124, China; 2. Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, China; 3. School of Engineering, Brown University, Providence 02912, Rhode Island, USA)
Keywords:
traffic engineering;  passenger flow prediction;  graph neural network;  subway;  deep learning
PACS:
U491.14
DOI:
10.19721/j.cnki.1671-8879.2025.02.013
Abstract:
To achieve precise subway passenger entry and exit flows prediction, a deep learning-based for subway passenger flow pediction graph neural spatio-temporal network(GNSTNet), was proposed. Historical 24-hour subway entry and exit flow data, weather and time labels were taken into account as inputs, and they were used to predict the hourly passenger entry and exit flows for every station in the entire network for the next hour. A subway passenger flow spatio-temporal graph were constructed using the hourly station entry and exit flows and subway network adjacency matrix. In the GNSTNet model, a graph neural network was used to extract the spatial features at each time step. The Fourier transform was used to extract the potential periodicity in the time series, and a convolutional neural network was used to extract the temporal features. The research results show that on a dataset from the Beijing Subway in June 2021, the graph neural network-based subway passenger flow prediction model outperforms six benchmark models, with an average reduction of 14.97% in the mean absolute error and 13.35% in the root mean squared error compared to the most accurate benchmark model. The graph neural networks-based subway passenger flow prediction model effectively improves the accuracy of predicting the passenger entry and exit flow for the entire subway network compared to traditional algorithms by integrating graph neural network, Fourier transform and convolutional neural network.2 tabs, 9 figs, 25 refs.

References:

[1] 中国城市轨道交通协会.2023年中国内地城轨交通线路概况[J].城市轨道交通,2024(1):8-9.
China Association of Metros.General situation of urban rail transit lines in China in 2023[J].China Metros,2024(1):8-9.
[2]雷 斌,张 源,郝亚睿,等.城市轨道交通短期客流预测研究进展[J].长安大学学报(自然科学版),2022,42(1):79-96.
LEI Bin,ZHANG Yuan,HAO Ya-rui,et al.Research progress on short-term passenger flow forecast model of urban rail transit[J].Journal of Chang'an University(Natural Science Edition),2022,42(1):79-96.
[3]马超群,李培坤,朱才华,等.基于不同时间粒度的城市轨道交通短时客流预测[J].长安大学学报(自然科学版),2020,40(3):75-83.
MA Chao-qun,LI Pei-kun,ZHU Cai-hua,et al.Short-term passenger flow forecast of urban rail transit based on different time granularities[J].Journal of Chang'an University(Natural Science Edition),2020,40(3):75-83.
[4]MILENKOVIC M,VADLENKA L,MELICHAR V,et al.SARIMA modelling approach for railway passenger flow forecasting[J].Transport,2018,33(5):1113-1120.
[5]马超群,李培坤,朱才华,等.基于不同时间粒度的城市轨道交通短时客流预测[J].长安大学学报(自然科学版),2020,40(3):75-83.
MA Chao-qun,LI Pei-kun,ZHU Cai-hua,et al.Short-term passenger flow forecast of urban rail transit based on different time granularities[J].Journal of Chang'an University(Natural Science Edition),2020,40(3):75-83.
[6]李得伟,颜艺星,曾险峰.城市轨道交通进站客流量短时组合预测模型[J].都市快轨交通,2017,30(1):54-58,64.
LI De-wei,YAN Yi-xing,ZENG Xian-feng.Combined short-term prediction model of station entry flow in urban rail transit[J].Urban Rapid Rail Transit,2017,30(1):54-58,64.
[7]WILLIAMS B M,HOEL L A.Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process:Theoretical basis and empirical results[J].Journal of Transportation Engineering,2003,129(6):664-672.
[8]SUN P,ALJERI N,BOUKERCHE A.Machine learning-based models for real-time traffic flow prediction in vehicular networks[J].IEEE Network,2020,34(3):178-185.
[9]王 莹,韩宝明,张 琦,等.基于SARIMA模型的北京地铁进站客流量预测[J].交通运输系统工程与信息,2015,15(6):205-211.
WANG Ying,HAN Bao-ming,ZHANG Qi,et al.Forecasting of entering passenger flow volume in Beijing subway based on SARIMA model[J].Journal of Transportation Systems Engineering and Information Technology,2015,15(6):205-211.
[10]孙晓黎,马超群,朱才华.基于XGBoost的轨道交通短时客流预测精度分析[J].交通科技与经济,2021,23(1):54-58.
SUN Xiao-li,MA Chao-qun,ZHU Cai-hua.XGBoost-based analysis of prediction accuracy for short-term passenger flow in rail transit[J].Technology and Economy in Areas of Communications,2021,23(1):54-58.
[11]ZHAO Y Y,REN L,MA Z L,et al.Novel three-stage framework for prioritizing and selecting feature variables for short-term metro passenger flow prediction[J].Transportation Research Record,2020(2674):192-205.
[12]KANG L L,HU G J,HUANG H,et al.Urban traffic travel time short-term prediction model based on spatio-temporal feature extraction[J].Journal of Advanced Transportation,2020,2020:3247847.
[13]VAN LINT J W C,VAN HINSBERGEN C.Short-term traffic and travel time prediction models[J].Artificial Intelligence Applications to Critical Transportation Issues,2012,22(1):22-41.
[14]CHAN K Y,DILLON T S,SINGH J,et al.Neural-network-based models for short-term traffic flow forecasting using a hybrid exponential smoothing and Levenberg-Marquardt algorithm[J].IEEE Transactions on Intelligent Transportation Systems,2011,13(2):644-654.
[15]ZHENG W Z,LEE D H,SHI Q X.Short-term freeway traffic flow prediction:Bayesian combined neural network approach[J].Journal of Transportation Engineering,2006,132(2):114-121.
[16]MA X L,ZHANG J Y,DU B W,et al.Parallel architecture of convolutional bi-directional LSTM neural networks for network-wide metro ridership prediction[J].IEEE Transactions on Intelligent Transportation Systems,2018,20(6):2278-2288.
[17]HAO S Y,LEE D H,ZHAO D.Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system[J].Transportation Research Part C:Emerging Technologies,2019,107:287-300.
[18]谢昊阳.基于图卷积网络的城市轨道交通多站点客流预测研究[D].兰州:兰州交通大学,2023.
XIE Hao-yang.Research on multi-station passenger flow forecast of urban rail transit based on graph-convolution network[D].Lanzhou:Lanzhou Jiatong University,2023.
[19]孙凤美.基于图注意力神经网络的地铁短时客流量预测[D].大连:大连海事大学,2023.
SUN Feng-mei.Short-term passenger flow forecast of subway based on graph attention neural network[D].Dalian:Dalian Maritime University,2023.
[20]WU Z H,PAN S R,CHEN F W,et al.A comprehensive survey on graph neural networks[J].IEEE Transactions on Neural Networks and Learning Systems,2021,32(1):4-24.
[21]YU B,YIN H T,ZHU Z X,et al.Spatio-temporal graph convolutional networks[C]//ACM.Proceedings of the 27th International Joint Conference on Artificial Intelligence.Stockholm:ACM,2018:3634-3640.
[22]刘晓磊,段征宇,余 庆,等.基于图卷积循环神经网络的城市轨道客流预测[J].华南理工大学学报(自然科学版),2022,50(3):21-27.
LIU Xiao-lei,DUAN Zheng-yu,YU Qing,et al.Passenger flow forecast of urban rail transit based on graph convolution and recurrent neural network[J].Journal of South China University of Technology(Natural Science Edition),2022,50(3):21-27.
[23]ILBEIGI M,ASHURI B,JOUKAR A.Time-series analysis for forecasting asphalt-cement price[J].Journal of Management in Engineering,2017,33(1):04016030.
[24]ZHOU H Y,ZHANG S H,PENG J Q,et al.Informer:Beyond efficient transformer for long sequence time-series forecasting[C]//Assoc Advancement Artificial Intelligence.Proceedings of the AAAI-21 Technical Tracks 12.Los Angeles:Assoc Advancement Artificial Intelligence,2021:11106-11115.
[25]WU H X,HU T G,LIU Y,et al.TimesNet:Temporal 2D-variation modeling for general time series analysis[EB/OL].(2022-10-05)[2025-03-05].https://arxiv.org/abs/2210.02186v3.

Memo

Memo:
-
Last Update: 2025-04-01