交通运输工程与信息学报2026，Vol.24Issue(1)：64-79,16.DOI:10.19961/j.cnki.1672-4747.2025.02.018
基于ResNet-GCN-Transformer的多时间粒度地铁短时客流预测
ResNet-GCN-Transformer-based prediction of short-time passenger flow for multi-time granularity subway
摘要
Abstract
[Background]With the acceleration of urbanization,the pressure on urban rail transit is increasing.The accurate prediction of subway passenger flow plays an important role in optimizing train schedules,reducing congestion during peak hours,improving the service level of subway sys-tems,and providing subway freight.[Objective]To comprehensively consider the spatiotemporal characteristics of subway passenger flows,fully utilize the multi-time-granularity passenger-flow da-ta,and improve the accuracy of larger time-granularity passenger-flow prediction tasks.[Method]The correlation between subway passenger-flow data with different time granularities is analyzed,a multi-time granularity fusion mechanism is determined,and a ResNet-GCN-Transformer model is proposed.Graph convolutional network(GCN)is used to extract the spatial correlation of passenger flows at different stations,and a deep convolutional neural network is constructed with residual blocks.Data with different time granularities are aggregated in the order of small to large time granu-larities to obtain multichannel feature graphs with multi-time granularity.A transformer encoder is used to model the long-term dependence of the passenger-flow data,and the prediction results are output through multiple prediction heads composed of fully connected layers.Besides,hyperparame-ter optimization is performed based on the Optuna framework to obtain the optimal combination of hyperparameters.[Data]Noise reduction is performed on the Hangzhou Metro card swipe dataset,and subway passenger-flow datasets with different time granularities are constructed.The model is verified based on 10 min and 30 min datasets.[Result]For the two datasets with different target time granularities,the mean absolute percentage error(MAPE)of the ResNet-GCN-Transformer model is found to be 12.62％and 10.61％,respectively.Both values are lower than the MAPE of the six base-line models,which indicates that the proposed model has higher prediction accuracy.This demon-strates the importance of integrating multi-time granularity features in metro passenger-flow predic-tion tasks.The model can fully capture these features,and also the connectivity characteristics and time-dependent relationships of subway stations so that the passenger-flow prediction effect can be significantly improved.关键词
城市交通/客流预测/多时间粒度/图卷积神经网络/残差网络/TransformerKey words
urban traffic/passenger flow prediction/multi-time granularity/graph convolutional neural network/residual network/Transformer分类
交通工程引用本文复制引用
杜姿晨,郑长江,郑树康,马庚华,陆野..基于ResNet-GCN-Transformer的多时间粒度地铁短时客流预测[J].交通运输工程与信息学报,2026,24(1):64-79,16.基金项目
国家自然科学基金项目(72471083) （72471083）
