Urban Traffic Flow Forecasting Based on Graph Structure Learning

The transportation system is a complex dynamic giant system which integrates and intertwines the elements of people, vehicles, roads, and the environment. The city-level traffic flow forecasting can effectively reflect the flow changes of the traffic system and provide practical guidance for the for...

Full description

Saved in:
Bibliographic Details
Main Authors: Guangyu Huo, Yong Zhang, Yimei Lv, Hao Ren, Baocai Yin
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/atr/7878081
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850076235842977792
author Guangyu Huo
Yong Zhang
Yimei Lv
Hao Ren
Baocai Yin
author_facet Guangyu Huo
Yong Zhang
Yimei Lv
Hao Ren
Baocai Yin
author_sort Guangyu Huo
collection DOAJ
description The transportation system is a complex dynamic giant system which integrates and intertwines the elements of people, vehicles, roads, and the environment. The city-level traffic flow forecasting can effectively reflect the flow changes of the traffic system and provide practical guidance for the formulation of traffic rules. Recent city-level traffic flow forecasting works rely on accurate prior knowledge of graphs (i.e., the spatial relationships between roads), which hinders their effectiveness and application in the real world. We propose a novel framework for urban traffic flow forecasting, which simultaneously infers and utilizes the relationship between time series. In our model, the graph structure learning module dynamically captures the correlation and causation between the different time series and infers a potentially fully connected graph. At the same time, the temporal convolution network captures the temporal correlation between a single time series. The graph neural network uses the graph for forecasting. Our model no longer relies on accurate graph priors and achieves better forecasting results than previous work. Experiments on two public datasets verify that the proposed model is very competitive.
format Article
id doaj-art-da32eb7dc80f4cee810b3ccae792e4ce
institution DOAJ
issn 2042-3195
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-da32eb7dc80f4cee810b3ccae792e4ce2025-08-20T02:46:04ZengWileyJournal of Advanced Transportation2042-31952024-01-01202410.1155/atr/7878081Urban Traffic Flow Forecasting Based on Graph Structure LearningGuangyu Huo0Yong Zhang1Yimei Lv2Hao Ren3Baocai Yin4School of Information Science and TechnologyBeijing Key Laboratory of Multimedia and Intelligent Software TechnologyQingdao Engineering Vocational CollegeChina Electronics Technology Group Taiji Co. Ltd.Beijing Key Laboratory of Multimedia and Intelligent Software TechnologyThe transportation system is a complex dynamic giant system which integrates and intertwines the elements of people, vehicles, roads, and the environment. The city-level traffic flow forecasting can effectively reflect the flow changes of the traffic system and provide practical guidance for the formulation of traffic rules. Recent city-level traffic flow forecasting works rely on accurate prior knowledge of graphs (i.e., the spatial relationships between roads), which hinders their effectiveness and application in the real world. We propose a novel framework for urban traffic flow forecasting, which simultaneously infers and utilizes the relationship between time series. In our model, the graph structure learning module dynamically captures the correlation and causation between the different time series and infers a potentially fully connected graph. At the same time, the temporal convolution network captures the temporal correlation between a single time series. The graph neural network uses the graph for forecasting. Our model no longer relies on accurate graph priors and achieves better forecasting results than previous work. Experiments on two public datasets verify that the proposed model is very competitive.http://dx.doi.org/10.1155/atr/7878081
spellingShingle Guangyu Huo
Yong Zhang
Yimei Lv
Hao Ren
Baocai Yin
Urban Traffic Flow Forecasting Based on Graph Structure Learning
Journal of Advanced Transportation
title Urban Traffic Flow Forecasting Based on Graph Structure Learning
title_full Urban Traffic Flow Forecasting Based on Graph Structure Learning
title_fullStr Urban Traffic Flow Forecasting Based on Graph Structure Learning
title_full_unstemmed Urban Traffic Flow Forecasting Based on Graph Structure Learning
title_short Urban Traffic Flow Forecasting Based on Graph Structure Learning
title_sort urban traffic flow forecasting based on graph structure learning
url http://dx.doi.org/10.1155/atr/7878081
work_keys_str_mv AT guangyuhuo urbantrafficflowforecastingbasedongraphstructurelearning
AT yongzhang urbantrafficflowforecastingbasedongraphstructurelearning
AT yimeilv urbantrafficflowforecastingbasedongraphstructurelearning
AT haoren urbantrafficflowforecastingbasedongraphstructurelearning
AT baocaiyin urbantrafficflowforecastingbasedongraphstructurelearning