A spatio-temporal self-supervised meta-learning network with dynamic graph learning for traffic flow forecasting
PLOS One · 27.03.2026 · 21 (3) · e0342520
DOI: 10.1371/journal.pone.0342520 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 27.03.2026. Verfasst von Qian Qiu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Traffic and Transportation, Guangxi Transport Vocational And Technical College, Nanning, China. Hauptthemen laut MEDLINE: Transportation. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key R&D projects in Guangxi.
Abstract (Originalsprache)
Accurate traffic flow prediction is essential for alleviating urban congestion, improving road network efficiency, and sup-porting sustainable transportation systems. Existing spatio-temporal graph neural networks, however, often struggle to capture dynamically evolving spatial dependencies, effectively integrate spatio-temporal features, and generalize across diverse traffic scenarios. To address the challenges of accurately modeling complex spatio-temporal dependencies in traffic flow forecasting, this study proposes a Spatio-Temporal Self-Supervised Meta-Learning Network (SSML-Net), the model comprises spatial- and temporal-level learners, and integrates self-supervised meta-learning with meta-learning-driven feature fusion and gated coupling mechanisms to enhance spatio-temporal interaction and generalization capabilities. Comprehensive experiments on the PeMS datasets demonstrate that SSML-Net clearly outperforms traditional statistical approaches, deep temporal models, and spatio-temporal graph-based networks. The ablation study validated the effective-ness and necessity of the model’s core components, whilst the small-sample experiments demonstrated its robustness and generalisation capabilities under extreme data conditions. Concurrently, we expanded our training and evaluation experi-ments based on METR-LR and Beijing traffic data, further validating the model’s exceptional transfer learning capability and generalisation performance in cross-domain traffic forecasting scenarios. This approach not only achieved superior prediction accuracy but also substantially reduced model training costs. These results indicate that SSML-Net adapts to varying data scales and dynamic urban scenarios, providing a robust, adaptive, and high-precision spatio-temporal traffic flow prediction framework.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Traffic and Transportation, Guangxi Transport Vocational And Technical College, Nanning, China.
- Guangxi Comprehensive Transportation Safety and Management Innovation Team, Nanning, China.
- Guangxi Transportation Industry Safety and Emergency Response Technology Key Laboratory, Guangxi Transport Vocational And Technical College, Nanning, China.
- Nanning Architectural Planning and Design Group Co., Ltd., Nanning, China.
ORCID-Profile: Qian Qiu
Förderung
- Key R&D projects in Guangxi
Zitieren
APA
Qiu, Q., Huang, Y., Huang, X., & Zhou, W. (2026). A spatio-temporal self-supervised meta-learning network with dynamic graph learning for traffic flow forecasting. PLOS One, 21(3), e0342520. https://doi.org/10.1371/journal.pone.0342520
Vancouver
Qiu Q, Huang Y, Huang X, Zhou W. A spatio-temporal self-supervised meta-learning network with dynamic graph learning for traffic flow forecasting. PLOS One. 2026;21(3):e0342520. doi:10.1371/journal.pone.0342520
BibTeX
@article{Qiu2026,
author = {Qiu, Qian and Huang, Yong and Huang, Xiaoting and Zhou, Wei},
title = {A spatio-temporal self-supervised meta-learning network with dynamic graph learning for traffic flow forecasting},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {3},
pages = {e0342520},
doi = {10.1371/journal.pone.0342520}
}
EUVIMED