PFNet: Large-Scale Traffic Forecasting With Progressive Spatio-Temporal Fusion

Traffic flow forecasting on a large-scale sensor network is of great practical significance for policy decision-making, urban management, and transport planning. Recently, several prediction methods based on graph convolution have been put forward. However, they are limited to small-scale analyses b...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent transportation systems 2023-12, Vol.24 (12), p.14580-14597
Main Authors: Wang, Chen, Zuo, Kaizhong, Zhang, Shaokun, Lei, Hanwen, Hu, Peng, Shen, Zhangyi, Wang, Rui, Zhao, Peize
Format: Article
Language:English
Subjects:
attention mechanism
Convolution
Convolutional neural networks
Correlation
Forecasting
graph embedding
Hidden Markov models
Large-scale traffic forecasting
Predictive models
road network distance
Roads
Traffic flow
Transportation networks
Transportation planning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traffic flow forecasting on a large-scale sensor network is of great practical significance for policy decision-making, urban management, and transport planning. Recently, several prediction methods based on graph convolution have been put forward. However, they are limited to small-scale analyses because of high computation complexity and fail to integrate spatial-temporal dependencies sufficiently between sensors with a large topological distance in multiple time steps. To address these issues, we propose a novel deep framework called PFNet to perform large-scale traffic forecasting. PFNet captures temporal correlations using deep multi-view sequence encoders (DMVSE) and spatial correlations using graph embedding technologies on transportation networks. Spatial-temporal dependencies are more comprehensively fused using cascaded progressive attention (CPA) modules due to the full use of latent temporal and spatial representation. Experiments are conducted on two large-scale traffic datasets (LondonHW and ManchesterHW) from England Highway. The results demonstrate that PFNet outperforms several existing state-of-the-art approaches.
ISSN:1524-9050
1558-0016
DOI:10.1109/TITS.2023.3296697