交通信息与安全2024，Vol.42Issue(1)：150-160,11.DOI:10.3963/j.jssn.1674-4861.2024.01.017
基于动态图神经常微分方程的地铁短时客流预测方法
Forecasting for Short-term Passenger Flow of Subway Based on Dynamic Graph Neural Ordinary Differential Equations
摘要
Abstract
With the rapid expansion of urban rail transit networks,accurate forecasting for passenger flows has be-come paramount for optimizing operational services.To solve the issue of the inadequate mining for the spatiotem-poral characteristics in the forecasting of current subway passenger flow forecasting and to further enhance accuracy and efficiency of forecasting methods,a forecasting method for short-term subway passenger flow based on multi-variate time series with dynamic graph neural ordinary differential equations(MTGODE)is proposed.The method constructs a dynamic topological graph structure by learning the dynamic correlation strength between subway sta-tions.Continuous graph propagation is performed on the learned dynamic graph to transmit spatiotemporal informa-tion and capture the dependencies of passenger flows.Moreover,residual convolution is employed to extract period-ic patterns at multiple time scales,enabling continuous representation of spatiotemporal dynamics between stations and overcoming the limitations of traditional graph convolutional network models in capturing dynamic spatial de-pendencies.Furthermore,to fully uncover the spatiotemporal patterns of passenger flow distribution among differ-ent stations,a multi-source fusion model for passenger flow forecasting is developed by comprehensively utilizing data from the Beijing subway's automatic fare collection system,weather data,air quality data,and surrounding land use attributes of stations.The proposed model was tested by forecasting inbound passenger flow and origin-des-tination flow using historical data from Beijing Station and Jishuitan Station-Dongzhimen Station.The experimental results demonstrate that the proposed model achieves superior performance compared to multiple benchmark mod-els across three metrics:mean absolute error(MAE),root mean square error(RMSE),and mean absolute percentage error(MAPE).Compared to the best-performing benchmark model,the diffusion convolutional recurrent neural net-work(DCRNN),the proposed model reduces MAE,RMSE,and MAPE by 9.93%,12.30%,and 9.23%,respective-ly.It exhibits a better fit to the spatiotemporal distribution of subway passenger flows and possesses improved pre-diction accuracy,stability,and fitting capability.关键词
轨道交通/地铁客流/动态图神经网络/MTGODE模型/深度学习Key words
rail transit/subway passenger flow/dynamic graph neural network/MTGODE model/deep learning分类
交通工程引用本文复制引用
彭颢,贺玉龙,宋太龙,武继壮..基于动态图神经常微分方程的地铁短时客流预测方法[J].交通信息与安全,2024,42(1):150-160,11.基金项目
国家自然科学基金项目(61876011)资助 （61876011）
