T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.

Recently, accurate traffic flow prediction has become a significant part of intelligent transportation systems, which can not only satisfy citizens' travel need and life satisfaction, but also benefit urban traffic management and control. However, traffic forecasting remains highly challenging...

Full description

Saved in:
Bibliographic Details
Main Authors: Anning Ji, Xintao Ma
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0323787
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160137554100224
author Anning Ji
Xintao Ma
author_facet Anning Ji
Xintao Ma
author_sort Anning Ji
collection DOAJ
description Recently, accurate traffic flow prediction has become a significant part of intelligent transportation systems, which can not only satisfy citizens' travel need and life satisfaction, but also benefit urban traffic management and control. However, traffic forecasting remains highly challenging because of its complexity in both topology structure and time transformation. Inspired by the propagation idea of graph convolutional networks, we propose ripple-propagation-based attentive graph neural networks for traffic flow prediction (T-RippleGNN). Firstly, we adopt Ripple propagation to capture the topology structure of the traffic spatial model. Then, a GRU-based model is used to explore the traffic model through the timeline. Lastly, those two factors are combined and attention scores are assigned to differentiate their influences on the traffic flow prediction. Furthermore, we evaluate our approach with three real-world traffic datasets. The results show that our approach reduces the prediction errors by approximately 2.24%-62,93% compared with state-of-the-art baselines, and the effectiveness of T-RippleGNN in traffic forecasting is demonstrated.
format Article
id doaj-art-e14e520066c441889e27a32e25e7b36a
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-e14e520066c441889e27a32e25e7b36a2025-08-20T02:23:15ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032378710.1371/journal.pone.0323787T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.Anning JiXintao MaRecently, accurate traffic flow prediction has become a significant part of intelligent transportation systems, which can not only satisfy citizens' travel need and life satisfaction, but also benefit urban traffic management and control. However, traffic forecasting remains highly challenging because of its complexity in both topology structure and time transformation. Inspired by the propagation idea of graph convolutional networks, we propose ripple-propagation-based attentive graph neural networks for traffic flow prediction (T-RippleGNN). Firstly, we adopt Ripple propagation to capture the topology structure of the traffic spatial model. Then, a GRU-based model is used to explore the traffic model through the timeline. Lastly, those two factors are combined and attention scores are assigned to differentiate their influences on the traffic flow prediction. Furthermore, we evaluate our approach with three real-world traffic datasets. The results show that our approach reduces the prediction errors by approximately 2.24%-62,93% compared with state-of-the-art baselines, and the effectiveness of T-RippleGNN in traffic forecasting is demonstrated.https://doi.org/10.1371/journal.pone.0323787
spellingShingle Anning Ji
Xintao Ma
T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.
PLoS ONE
title T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.
title_full T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.
title_fullStr T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.
title_full_unstemmed T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.
title_short T-RippleGNN: Predicting traffic flow through ripple propagation with attentive graph neural networks.
title_sort t ripplegnn predicting traffic flow through ripple propagation with attentive graph neural networks
url https://doi.org/10.1371/journal.pone.0323787
work_keys_str_mv AT anningji tripplegnnpredictingtrafficflowthroughripplepropagationwithattentivegraphneuralnetworks
AT xintaoma tripplegnnpredictingtrafficflowthroughripplepropagationwithattentivegraphneuralnetworks