STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast

The characteristics of multivariate heterogeneity in traffic flow forecasting exhibit significant variation, heavily influenced by spatio-temporal dynamics and unforeseen events. To address this challenge, we propose a spatio-temporal fusion graph neural network based on dynamic sparse graph convolu...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiahao Chang, Jiali Yin, Yanrong Hao, Chengxin Gao
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160576674660352
author Jiahao Chang
Jiali Yin
Yanrong Hao
Chengxin Gao
author_facet Jiahao Chang
Jiali Yin
Yanrong Hao
Chengxin Gao
author_sort Jiahao Chang
collection DOAJ
description The characteristics of multivariate heterogeneity in traffic flow forecasting exhibit significant variation, heavily influenced by spatio-temporal dynamics and unforeseen events. To address this challenge, we propose a spatio-temporal fusion graph neural network based on dynamic sparse graph convolution GRU for traffic flow forecast (STFDSGCN), which incorporates a spatio-temporal attention fusion scheme with a gating mechanism. The dynamic sparse graph convolution gated recurrent unit (DSGCN-GRU) in this model is a novel component that integrates adaptive dynamic sparse graph convolution into the gated recurrent network to simulate the diffusion of information within a dynamic spatial structure. This approach effectively captures the heterogeneous and local features of spatial data, further reflecting the irregularities and dynamic variability inherent in spatial information. By leveraging spatio-temporal attention through the gating mechanism, the model enhances its understanding of both local and global spatio-temporal characteristics. This enables a unified representation of multi-scale and long-range spatio-temporal patterns and strengthens the model’s ability to respond to long-term traffic flow forecasting and traffic emergencies. Extensive experiments on two real-world datasets demonstrate that, compared to advanced methods that lack sufficient multivariate heterogeneous feature extraction and do not account for traffic emergencies, the STFDSGCN model improves the average absolute error (MAE), root mean square error (RMSE), and average absolute percentage error (MAPE) by 4.01%, 1.33%, and 1.03%, respectively, achieving superior performance.
format Article
id doaj-art-746bdb3ca3d5446ba5d4000615a57637
institution OA Journals
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-746bdb3ca3d5446ba5d4000615a576372025-08-20T02:23:07ZengMDPI AGSensors1424-82202025-05-012511344610.3390/s25113446STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow ForecastJiahao Chang0Jiali Yin1Yanrong Hao2Chengxin Gao3College of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaSchool of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaCollege of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Software, Taiyuan University of Technology, Taiyuan 030024, ChinaThe characteristics of multivariate heterogeneity in traffic flow forecasting exhibit significant variation, heavily influenced by spatio-temporal dynamics and unforeseen events. To address this challenge, we propose a spatio-temporal fusion graph neural network based on dynamic sparse graph convolution GRU for traffic flow forecast (STFDSGCN), which incorporates a spatio-temporal attention fusion scheme with a gating mechanism. The dynamic sparse graph convolution gated recurrent unit (DSGCN-GRU) in this model is a novel component that integrates adaptive dynamic sparse graph convolution into the gated recurrent network to simulate the diffusion of information within a dynamic spatial structure. This approach effectively captures the heterogeneous and local features of spatial data, further reflecting the irregularities and dynamic variability inherent in spatial information. By leveraging spatio-temporal attention through the gating mechanism, the model enhances its understanding of both local and global spatio-temporal characteristics. This enables a unified representation of multi-scale and long-range spatio-temporal patterns and strengthens the model’s ability to respond to long-term traffic flow forecasting and traffic emergencies. Extensive experiments on two real-world datasets demonstrate that, compared to advanced methods that lack sufficient multivariate heterogeneous feature extraction and do not account for traffic emergencies, the STFDSGCN model improves the average absolute error (MAE), root mean square error (RMSE), and average absolute percentage error (MAPE) by 4.01%, 1.33%, and 1.03%, respectively, achieving superior performance.https://www.mdpi.com/1424-8220/25/11/3446traffic flow forecastinggraph neural networks (GNN)gated recurrent units (GRUs)dynamic sparse graph convolutionspatio-temporal attention
spellingShingle Jiahao Chang
Jiali Yin
Yanrong Hao
Chengxin Gao
STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast
Sensors
traffic flow forecasting
graph neural networks (GNN)
gated recurrent units (GRUs)
dynamic sparse graph convolution
spatio-temporal attention
title STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast
title_full STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast
title_fullStr STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast
title_full_unstemmed STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast
title_short STFDSGCN: Spatio-Temporal Fusion Graph Neural Network Based on Dynamic Sparse Graph Convolution GRU for Traffic Flow Forecast
title_sort stfdsgcn spatio temporal fusion graph neural network based on dynamic sparse graph convolution gru for traffic flow forecast
topic traffic flow forecasting
graph neural networks (GNN)
gated recurrent units (GRUs)
dynamic sparse graph convolution
spatio-temporal attention
url https://www.mdpi.com/1424-8220/25/11/3446
work_keys_str_mv AT jiahaochang stfdsgcnspatiotemporalfusiongraphneuralnetworkbasedondynamicsparsegraphconvolutiongrufortrafficflowforecast
AT jialiyin stfdsgcnspatiotemporalfusiongraphneuralnetworkbasedondynamicsparsegraphconvolutiongrufortrafficflowforecast
AT yanronghao stfdsgcnspatiotemporalfusiongraphneuralnetworkbasedondynamicsparsegraphconvolutiongrufortrafficflowforecast
AT chengxingao stfdsgcnspatiotemporalfusiongraphneuralnetworkbasedondynamicsparsegraphconvolutiongrufortrafficflowforecast