Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2025.072147
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

State Space Guided Spatio-Temporal Network for Efficient Long-Term Traffic Prediction

Guangyu Huo, Chang Su, Xiaoyu Zhang*, Xiaohui Cui, Lizhong Zhang
School of Information Science and Technology, School of Artificial Intelligence, Beijing Forestry University, Beijing, 100083, China
* Corresponding Author: Xiaoyu Zhang. Email: email
(This article belongs to the Special Issue: Advancing Network Intelligence: Communication, Sensing and Computation)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2025.072147

Received 20 August 2025; Accepted 24 September 2025; Published online 27 October 2025

Abstract

Long-term traffic flow prediction is a crucial component of intelligent transportation systems within intelligent networks, requiring predictive models that balance accuracy with low-latency and lightweight computation to optimize traffic management and enhance urban mobility and sustainability. However, traditional predictive models struggle to capture long-term temporal dependencies and are computationally intensive, limiting their practicality in real-time. Moreover, many approaches overlook the periodic characteristics inherent in traffic data, further impacting performance. To address these challenges, we introduce ST-MambaGCN, a State-Space-Based Spatio-Temporal Graph Convolution Network. Unlike conventional models, ST-MambaGCN replaces the temporal attention layer with Mamba, a state-space model that efficiently captures long-term dependencies with near-linear computational complexity. The model combines Chebyshev polynomial-based graph convolutional networks (GCN) to explore spatial correlations. Additionally, we incorporate a multi-temporal feature capture mechanism, where the final integrated features are generated through the Hadamard product based on learnable parameters. This mechanism explicitly models short-term, daily, and weekly traffic patterns to enhance the network’s awareness of traffic periodicity. Extensive experiments on the PeMS04 and PeMS08 datasets demonstrate that ST-MambaGCN significantly outperforms existing benchmarks, offering substantial improvements in both prediction accuracy and computational efficiency for long-term traffic flow prediction.

Keywords

State space model; long-term traffic flow prediction; graph convolutional network; multi-time scale analysis; emerging applications at intelligent networks

  • 661

    View

  • 442

    Download

  • 0

    Like

Related articles
Copyright© 2025 Tech Science Press
© 1997-2025 TSP (Henderson, USA) unless otherwise stated

Share Link