Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention

Spatiotemporal forecasting of traffic flow data represents a typical problem for urban traffic management, involving complex interactions, nonlinearities, and long-range dependencies due to the interwoven nature of the temporal and spatial dimensions. Traditional statistical and machine learning met...

Full description

Saved in:
Bibliographic Details
Main Authors: Yash Jakhmola, Madhurima Panja, Nitish Kumar Mishra, Kripabandhu Ghosh, Uttam Kumar, Tanujit Chakraborty
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10794773/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846113887711133696
author Yash Jakhmola
Madhurima Panja
Nitish Kumar Mishra
Kripabandhu Ghosh
Uttam Kumar
Tanujit Chakraborty
author_facet Yash Jakhmola
Madhurima Panja
Nitish Kumar Mishra
Kripabandhu Ghosh
Uttam Kumar
Tanujit Chakraborty
author_sort Yash Jakhmola
collection DOAJ
description Spatiotemporal forecasting of traffic flow data represents a typical problem for urban traffic management, involving complex interactions, nonlinearities, and long-range dependencies due to the interwoven nature of the temporal and spatial dimensions. Traditional statistical and machine learning methods struggle to handle both temporal and spatial dependencies in such datasets. While graph convolutional networks and multi-head attention mechanisms have been widely adopted in this field, they often fail to accurately model dynamic temporal patterns and effectively differentiate noise from signals in traffic datasets, leading to potential overfitting. This paper proposes a wavelet-based temporal attention model, namely a wavelet dynamic spatiotemporal aware graph neural network (W-DSTAGNN), for tackling the traffic forecasting problem. A key feature of W-DSTAGNN is the use of wavelets that can effectively separate noise and capture multi-resolution temporal patterns. Wavelet decomposition can help by decomposing the signal into components that can be analyzed independently, reducing the impact of non-stationarity and handling long-range dependencies of traffic flow datasets. These enable our proposal to generate more robust and accurate forecasts of complex and dynamic traffic dependencies than commonly used spatiotemporal deep learning models. Benchmark experiments using three popularly used statistical metrics confirm that our proposal efficiently captures spatiotemporal correlations and outperforms eleven state-of-the-art models (including both temporal and spatiotemporal benchmarks) on three publicly available traffic datasets. Our proposed approach can better handle dynamic temporal and spatial dependencies, delivering reliable long-term forecasts, and generating interval forecasts to enhance probabilistic forecasting of traffic datasets.
format Article
id doaj-art-b270aa6ee4024c6eafe765374d6d89a5
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-b270aa6ee4024c6eafe765374d6d89a52024-12-21T00:01:10ZengIEEEIEEE Access2169-35362024-01-011218879718881210.1109/ACCESS.2024.351619510794773Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal AttentionYash Jakhmola0https://orcid.org/0009-0005-1068-886XMadhurima Panja1https://orcid.org/0009-0004-7467-2456Nitish Kumar Mishra2https://orcid.org/0009-0009-1088-7139Kripabandhu Ghosh3https://orcid.org/0000-0002-8130-1221Uttam Kumar4https://orcid.org/0000-0002-0822-7993Tanujit Chakraborty5https://orcid.org/0000-0002-3479-2187Department of Mathematics and Statistics, Indian Institute of Science, Education and Research, Kolkata, IndiaCenter for Data Science, International Institute of Information Technology, Bangalore, Bengaluru, IndiaDepartment of Mathematics and Statistics, Indian Institute of Science, Education and Research, Kolkata, IndiaDepartment of Computational and Data Sciences, Indian Institute of Science, Education and Research, Kolkata, IndiaCenter for Data Science, International Institute of Information Technology, Bangalore, Bengaluru, IndiaSAFIR, Sorbonne University Abu Dhabi, Abu Dhabi, United Arab EmiratesSpatiotemporal forecasting of traffic flow data represents a typical problem for urban traffic management, involving complex interactions, nonlinearities, and long-range dependencies due to the interwoven nature of the temporal and spatial dimensions. Traditional statistical and machine learning methods struggle to handle both temporal and spatial dependencies in such datasets. While graph convolutional networks and multi-head attention mechanisms have been widely adopted in this field, they often fail to accurately model dynamic temporal patterns and effectively differentiate noise from signals in traffic datasets, leading to potential overfitting. This paper proposes a wavelet-based temporal attention model, namely a wavelet dynamic spatiotemporal aware graph neural network (W-DSTAGNN), for tackling the traffic forecasting problem. A key feature of W-DSTAGNN is the use of wavelets that can effectively separate noise and capture multi-resolution temporal patterns. Wavelet decomposition can help by decomposing the signal into components that can be analyzed independently, reducing the impact of non-stationarity and handling long-range dependencies of traffic flow datasets. These enable our proposal to generate more robust and accurate forecasts of complex and dynamic traffic dependencies than commonly used spatiotemporal deep learning models. Benchmark experiments using three popularly used statistical metrics confirm that our proposal efficiently captures spatiotemporal correlations and outperforms eleven state-of-the-art models (including both temporal and spatiotemporal benchmarks) on three publicly available traffic datasets. Our proposed approach can better handle dynamic temporal and spatial dependencies, delivering reliable long-term forecasts, and generating interval forecasts to enhance probabilistic forecasting of traffic datasets.https://ieeexplore.ieee.org/document/10794773/Traffic forecastingwavelet transformationtemporal attentionspatiotemporal datacomputational complexity
spellingShingle Yash Jakhmola
Madhurima Panja
Nitish Kumar Mishra
Kripabandhu Ghosh
Uttam Kumar
Tanujit Chakraborty
Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention
IEEE Access
Traffic forecasting
wavelet transformation
temporal attention
spatiotemporal data
computational complexity
title Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention
title_full Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention
title_fullStr Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention
title_full_unstemmed Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention
title_short Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention
title_sort spatiotemporal forecasting of traffic flow using wavelet based temporal attention
topic Traffic forecasting
wavelet transformation
temporal attention
spatiotemporal data
computational complexity
url https://ieeexplore.ieee.org/document/10794773/
work_keys_str_mv AT yashjakhmola spatiotemporalforecastingoftrafficflowusingwaveletbasedtemporalattention
AT madhurimapanja spatiotemporalforecastingoftrafficflowusingwaveletbasedtemporalattention
AT nitishkumarmishra spatiotemporalforecastingoftrafficflowusingwaveletbasedtemporalattention
AT kripabandhughosh spatiotemporalforecastingoftrafficflowusingwaveletbasedtemporalattention
AT uttamkumar spatiotemporalforecastingoftrafficflowusingwaveletbasedtemporalattention
AT tanujitchakraborty spatiotemporalforecastingoftrafficflowusingwaveletbasedtemporalattention