Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting

Traffic flow prediction is a crucial research area in traffic management. Accurately predicting traffic flow in each area of the city over the long term can enable city managers to make informed decisions regarding the allocation of urban transportation resources in the future. The existing traffic...

Full description

Bibliographic Details
Main Authors: Shuai Lu, Haibo Chen, Yilong Teng
Format: Article
Language:English
Published: MDPI AG 2024-02-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/13/3/71
_version_ 1797240747102044160
author Shuai Lu
Haibo Chen
Yilong Teng
author_facet Shuai Lu
Haibo Chen
Yilong Teng
author_sort Shuai Lu
collection DOAJ
description Traffic flow prediction is a crucial research area in traffic management. Accurately predicting traffic flow in each area of the city over the long term can enable city managers to make informed decisions regarding the allocation of urban transportation resources in the future. The existing traffic flow prediction models either give insufficient attention to the interactions of long-lasting spatio-temporal regions or extract spatio-temporal features in a single scale, which ignores the identification of traffic flow patterns at various scales. In this paper, we present a multi-scale spatio-temporal information fusion model using non-local networks, which fuses traffic flow pattern features at multiple scales in space and time, complemented by non-local networks to construct the global direct dependence relationship between local areas and the entire region of the city in space and time in the past. The proposed model is evaluated through experiments and is shown to outperform existing benchmark models in terms of prediction performance.
first_indexed 2024-04-24T18:12:20Z
format Article
id doaj.art-5bddc668fe07418a927cdcaf66e623cb
institution Directory Open Access Journal
issn 2220-9964
language English
last_indexed 2024-04-24T18:12:20Z
publishDate 2024-02-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj.art-5bddc668fe07418a927cdcaf66e623cb2024-03-27T13:44:51ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-02-011337110.3390/ijgi13030071Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow ForecastingShuai Lu0Haibo Chen1Yilong Teng2School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Sciences, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaTraffic flow prediction is a crucial research area in traffic management. Accurately predicting traffic flow in each area of the city over the long term can enable city managers to make informed decisions regarding the allocation of urban transportation resources in the future. The existing traffic flow prediction models either give insufficient attention to the interactions of long-lasting spatio-temporal regions or extract spatio-temporal features in a single scale, which ignores the identification of traffic flow patterns at various scales. In this paper, we present a multi-scale spatio-temporal information fusion model using non-local networks, which fuses traffic flow pattern features at multiple scales in space and time, complemented by non-local networks to construct the global direct dependence relationship between local areas and the entire region of the city in space and time in the past. The proposed model is evaluated through experiments and is shown to outperform existing benchmark models in terms of prediction performance.https://www.mdpi.com/2220-9964/13/3/71traffic flow predictionmulti-scale spatio-temporal fusionspatio-temporal regional correlationconvolutional LSTMnon-local network
spellingShingle Shuai Lu
Haibo Chen
Yilong Teng
Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting
ISPRS International Journal of Geo-Information
traffic flow prediction
multi-scale spatio-temporal fusion
spatio-temporal regional correlation
convolutional LSTM
non-local network
title Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting
title_full Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting
title_fullStr Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting
title_full_unstemmed Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting
title_short Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting
title_sort multi scale non local spatio temporal information fusion networks for multi step traffic flow forecasting
topic traffic flow prediction
multi-scale spatio-temporal fusion
spatio-temporal regional correlation
convolutional LSTM
non-local network
url https://www.mdpi.com/2220-9964/13/3/71
work_keys_str_mv AT shuailu multiscalenonlocalspatiotemporalinformationfusionnetworksformultisteptrafficflowforecasting
AT haibochen multiscalenonlocalspatiotemporalinformationfusionnetworksformultisteptrafficflowforecasting
AT yilongteng multiscalenonlocalspatiotemporalinformationfusionnetworksformultisteptrafficflowforecasting