Adaptive spatial-temporal graph attention networks for traffic flow forecasting

Traffic flow forecasting, which requires modelling involuted spatial and temporal dependence and uncertainty regarding road networks and traffic conditions, is a challenge for intelligent transportation systems (ITS). Recent studies have mainly focused on modelling spatial-temporal dependence throug...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2022-03, Vol.52 (4), p.4300-4316
Main Authors: Kong, Xiangyuan, Zhang, Jian, Wei, Xiang, Xing, Weiwei, Lu, Wei
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Science
Forecasting
Intelligent transportation systems
Machines
Manufacturing
Mechanical Engineering
Modelling
Processes
Roads
Spatial dependencies
Traffic flow
Traffic models
Traffic speed
Transportation networks
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, which requires modelling involuted spatial and temporal dependence and uncertainty regarding road networks and traffic conditions, is a challenge for intelligent transportation systems (ITS). Recent studies have mainly focused on modelling spatial-temporal dependence through a fixed weighted graph based on prior knowledge. However, collecting up-to-date and accurate road information is costly. Moreover, is a single fixed graph enough to describe the correlation between sensors? The fixed weighted graph cannot directly relate to prediction tasks, which may result in considerable biases. To tackle this issue, in this paper, we propose a novel deep learning model framework: an adaptive spatial-temporal graph attention network (ASTGAT). Our ASTGAT simultaneously learns the dynamic graph structure and spatial-temporal dependency for traffic flow forecasting. Specifically, our framework consists of two joint training parts: a Network Generator model that generates a discrete graph with the Gumbel-Softmax technique and a Spatial-Temporal model that utilizes the generated network to predict traffic speed. Our Network Generator can adaptively infer the hidden correlations from data. Moreover, we propose a graph talking-heads attention layer (GTHA) for capturing spatial dependencies and design a gate temporal convolution (GTCN) layer for handling long temporal sequences. We evaluated our ASTGAT on two public datasets: METR-LA is collected in Los Angeles and PEMS-BAY is collected in California. Experimental results indicate that our ASTGAT outperforms the state-of-the-art (SOTA) baselines. Finally, to further describe our model, we visualize the forecasting results and the generated graph.
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-021-02648-0