A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks

Abstract Traffic flow prediction is essential for enhancing urban mobility and facilitating effective transportation systems. The rapid increase in traffic data, along with the inherently dynamic characteristics of urban traffic, poses considerable challenges for traditional Machine Learning (ML) mo...

Full description

Saved in:
Bibliographic Details
Main Authors: Mariam Labib Francies, Abeer Twakol Khalil, Hanan M. Amer, Mohamed Maher Ata
Format: Article
Language:English
Published: Springer 2025-08-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-02049-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225775319875584
author Mariam Labib Francies
Abeer Twakol Khalil
Hanan M. Amer
Mohamed Maher Ata
author_facet Mariam Labib Francies
Abeer Twakol Khalil
Hanan M. Amer
Mohamed Maher Ata
author_sort Mariam Labib Francies
collection DOAJ
description Abstract Traffic flow prediction is essential for enhancing urban mobility and facilitating effective transportation systems. The rapid increase in traffic data, along with the inherently dynamic characteristics of urban traffic, poses considerable challenges for traditional Machine Learning (ML) models, which often find it difficult to efficiently handle large-scale datasets. Although Deep Learning (DL) models demonstrate potential, their significant computational requirements and susceptibility to catastrophic forgetting limit their effectiveness in dynamic and real-time contexts, including traffic emergencies or evolving road networks. To address these challenges, this research presents an innovative framework known as the Continual Learning-based Spatial–Temporal Graph Convolutional Recurrent Neural Network (STGNN-CL) for persistent and accurate long-term traffic flow prediction. By utilizing techniques such as Elastic Weight Consolidation (EWC), Memory Aware Synapses (MAS), and Synaptic Intelligence (SI), the proposed model effectively addresses the issue of catastrophic forgetting while simultaneously enhancing its capacity to incrementally assimilate new traffic data streams. An advanced traffic pattern fusion strategy is introduced, utilizing the Kullback–Leibler Divergence (KLD) metric to measure traffic divergence across different scenarios. This approach improves the efficiency of the Continual Learning (CL) process by enabling the model to adapt to new traffic patterns more effectively over time. Extensive experiments conducted on the PeMSD3, PeMSD4, PeMSD7, and PeMSD8 datasets reveal the superiority of the proposed models, STGCN-EWC, STGCN-MAS, and STGCN-SI models achieve significant reductions in error rates compared to baseline methodologies. These results highlight the potential of continual learning in developing efficient, scalable, and adaptive traffic flow prediction systems, paving the way for advancements in transportation management and autonomous driving technologies.
format Article
id doaj-art-85ff97ee803840b79c40319446e3bd35
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2025-08-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-85ff97ee803840b79c40319446e3bd352025-08-24T12:02:23ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-08-01111012810.1007/s40747-025-02049-7A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networksMariam Labib Francies0Abeer Twakol Khalil1Hanan M. Amer2Mohamed Maher Ata3Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura UniversityElectronics and Communications Engineering Department, Faculty of Engineering, Mansoura UniversityElectronics and Communications Engineering Department, Faculty of Engineering, Mansoura UniversitySchool of Computational Sciences and Artificial Intelligence (CSAI) Zewail City of Science and Technology 6th of October CityAbstract Traffic flow prediction is essential for enhancing urban mobility and facilitating effective transportation systems. The rapid increase in traffic data, along with the inherently dynamic characteristics of urban traffic, poses considerable challenges for traditional Machine Learning (ML) models, which often find it difficult to efficiently handle large-scale datasets. Although Deep Learning (DL) models demonstrate potential, their significant computational requirements and susceptibility to catastrophic forgetting limit their effectiveness in dynamic and real-time contexts, including traffic emergencies or evolving road networks. To address these challenges, this research presents an innovative framework known as the Continual Learning-based Spatial–Temporal Graph Convolutional Recurrent Neural Network (STGNN-CL) for persistent and accurate long-term traffic flow prediction. By utilizing techniques such as Elastic Weight Consolidation (EWC), Memory Aware Synapses (MAS), and Synaptic Intelligence (SI), the proposed model effectively addresses the issue of catastrophic forgetting while simultaneously enhancing its capacity to incrementally assimilate new traffic data streams. An advanced traffic pattern fusion strategy is introduced, utilizing the Kullback–Leibler Divergence (KLD) metric to measure traffic divergence across different scenarios. This approach improves the efficiency of the Continual Learning (CL) process by enabling the model to adapt to new traffic patterns more effectively over time. Extensive experiments conducted on the PeMSD3, PeMSD4, PeMSD7, and PeMSD8 datasets reveal the superiority of the proposed models, STGCN-EWC, STGCN-MAS, and STGCN-SI models achieve significant reductions in error rates compared to baseline methodologies. These results highlight the potential of continual learning in developing efficient, scalable, and adaptive traffic flow prediction systems, paving the way for advancements in transportation management and autonomous driving technologies.https://doi.org/10.1007/s40747-025-02049-7Continual LearningGraph Neural NetworkDeep LearningTraffic predictionSmart cities
spellingShingle Mariam Labib Francies
Abeer Twakol Khalil
Hanan M. Amer
Mohamed Maher Ata
A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks
Complex & Intelligent Systems
Continual Learning
Graph Neural Network
Deep Learning
Traffic prediction
Smart cities
title A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks
title_full A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks
title_fullStr A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks
title_full_unstemmed A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks
title_short A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks
title_sort framework for continual learning in real time traffic forecasting utilizing spatial temporal graph convolutional recurrent networks
topic Continual Learning
Graph Neural Network
Deep Learning
Traffic prediction
Smart cities
url https://doi.org/10.1007/s40747-025-02049-7
work_keys_str_mv AT mariamlabibfrancies aframeworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks
AT abeertwakolkhalil aframeworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks
AT hananmamer aframeworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks
AT mohamedmaherata aframeworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks
AT mariamlabibfrancies frameworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks
AT abeertwakolkhalil frameworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks
AT hananmamer frameworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks
AT mohamedmaherata frameworkforcontinuallearninginrealtimetrafficforecastingutilizingspatialtemporalgraphconvolutionalrecurrentnetworks