Multi dynamic temporal representation graph convolutional network for traffic flow prediction

Abstract Traffic flow prediction is fundamental to the dynamic control and application of Intelligent Transportation Systems (ITS), which play a crucial role in alleviating road congestion. However, existing approaches have not fully exploited the inherent dynamic and multifaceted spatiotemporal fea...

Full description

Saved in:
Bibliographic Details
Main Authors: Zuojun Wu, Xiaojun Liu, Xiaoling Zhang
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01157-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850273528277893120
author Zuojun Wu
Xiaojun Liu
Xiaoling Zhang
author_facet Zuojun Wu
Xiaojun Liu
Xiaoling Zhang
author_sort Zuojun Wu
collection DOAJ
description Abstract Traffic flow prediction is fundamental to the dynamic control and application of Intelligent Transportation Systems (ITS), which play a crucial role in alleviating road congestion. However, existing approaches have not fully exploited the inherent dynamic and multifaceted spatiotemporal features within traffic data, posing significant challenges in achieving accurate traffic flow predictions. To address this issue, we propose a novel Multi Dynamic Temporal Representation Graph Convolutional Network (MDTRGCN). Specifically, we introduce a dynamic graph construction method that learns the time‒space dependencies specific to road segments. On the basis of this method, we develop a dynamic graph convolution module that aggregates the hidden states of neighboring nodes to a focal node by propagating messages across a dynamic adjacency matrix. Moreover, a multiaspect fusion module is presented, which combines auxiliary hidden states learned from traffic volume with primary hidden states derived from traffic speed. Finally, we propose a temporal representation module that infers the content of masked subsequences from small portions of unmasked subsequences and their temporal context. The experimental results on real-world datasets demonstrate that the proposed method not only achieves state-of-the-art predictive performance but also provides clear and interpretable insights into the dynamic spatial relationships of road segments.
format Article
id doaj-art-ab294a32d23a4cffaf90ba873693d1c7
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ab294a32d23a4cffaf90ba873693d1c72025-08-20T01:51:28ZengNature PortfolioScientific Reports2045-23222025-05-0115111310.1038/s41598-025-01157-1Multi dynamic temporal representation graph convolutional network for traffic flow predictionZuojun Wu0Xiaojun Liu1Xiaoling Zhang2College of Intelligent Manufacturing and Control Engineering, Shandong Institute of Petroleum and Chemical TechnologyCollege of Intelligent Manufacturing and Control Engineering, Shandong Institute of Petroleum and Chemical TechnologyCollege of Intelligent Manufacturing and Control Engineering, Shandong Institute of Petroleum and Chemical TechnologyAbstract Traffic flow prediction is fundamental to the dynamic control and application of Intelligent Transportation Systems (ITS), which play a crucial role in alleviating road congestion. However, existing approaches have not fully exploited the inherent dynamic and multifaceted spatiotemporal features within traffic data, posing significant challenges in achieving accurate traffic flow predictions. To address this issue, we propose a novel Multi Dynamic Temporal Representation Graph Convolutional Network (MDTRGCN). Specifically, we introduce a dynamic graph construction method that learns the time‒space dependencies specific to road segments. On the basis of this method, we develop a dynamic graph convolution module that aggregates the hidden states of neighboring nodes to a focal node by propagating messages across a dynamic adjacency matrix. Moreover, a multiaspect fusion module is presented, which combines auxiliary hidden states learned from traffic volume with primary hidden states derived from traffic speed. Finally, we propose a temporal representation module that infers the content of masked subsequences from small portions of unmasked subsequences and their temporal context. The experimental results on real-world datasets demonstrate that the proposed method not only achieves state-of-the-art predictive performance but also provides clear and interpretable insights into the dynamic spatial relationships of road segments.https://doi.org/10.1038/s41598-025-01157-1Traffic flow predictionGraph convolutional networksGraph constructionSpatiotemporal characteristics
spellingShingle Zuojun Wu
Xiaojun Liu
Xiaoling Zhang
Multi dynamic temporal representation graph convolutional network for traffic flow prediction
Scientific Reports
Traffic flow prediction
Graph convolutional networks
Graph construction
Spatiotemporal characteristics
title Multi dynamic temporal representation graph convolutional network for traffic flow prediction
title_full Multi dynamic temporal representation graph convolutional network for traffic flow prediction
title_fullStr Multi dynamic temporal representation graph convolutional network for traffic flow prediction
title_full_unstemmed Multi dynamic temporal representation graph convolutional network for traffic flow prediction
title_short Multi dynamic temporal representation graph convolutional network for traffic flow prediction
title_sort multi dynamic temporal representation graph convolutional network for traffic flow prediction
topic Traffic flow prediction
Graph convolutional networks
Graph construction
Spatiotemporal characteristics
url https://doi.org/10.1038/s41598-025-01157-1
work_keys_str_mv AT zuojunwu multidynamictemporalrepresentationgraphconvolutionalnetworkfortrafficflowprediction
AT xiaojunliu multidynamictemporalrepresentationgraphconvolutionalnetworkfortrafficflowprediction
AT xiaolingzhang multidynamictemporalrepresentationgraphconvolutionalnetworkfortrafficflowprediction