A Non-Autoregressive Spatiotemporal Framework for Offline Full-Matrix Origin–Destination Forecasting in Large-Scale Metro Networks
Applied Sciences · 26.05.2026 · 16 (11) · 5333
DOI: 10.3390/app16115333 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 26.05.2026. Verfasst von Seung Ha Kim und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Technology Evaluation and Planning, T-money Welfare Foundation.
Abstract (Originalsprache)
Origin–destination (OD) matrix forecasting is essential for urban railway operations because it enables simultaneous understanding of the direction and magnitude of passenger flows. However, OD matrices in large-scale subway networks are difficult to predict owing to their high dimensionality and sparsity, and existing approaches often rely on station-level predictions or complex structural designs. This study addresses the offline full-matrix OD forecasting problem, where complete historical OD sequences are available at prediction time, and proposes Metro-GATF, a spatiotemporal forecasting framework that jointly models railway topology and dynamic OD interactions. The model employs a GATv2-based spatial encoder to learn static inter-station relationships and encodes time-varying interactions using sparse OD graphs. A non-autoregressive transformer decoder generates future multi-step node representations in parallel, whereas origin–destination factorization and sparsity-aware gating are used to reconstruct the full OD matrix. Experiments on minute-level AFC-based OD data from a 637-station metropolitan subway network demonstrated that Metro-GATF achieved the lowest sMAPE among the compared full-matrix models. These results indicate that the proposed framework effectively captures complex spatiotemporal OD patterns and offers a practical end-to-end framework for forecasting urban railway demand.
Förderung
- Korea Institute of Energy Technology Evaluation and Planning
- T-money Welfare Foundation
Zitieren
APA
Kim, S. H., Jeong, H. J., Shin, S. I., & Kwon, J. W. (2026). A Non-Autoregressive Spatiotemporal Framework for Offline Full-Matrix Origin–Destination Forecasting in Large-Scale Metro Networks. Applied Sciences, 16(11), 5333. https://doi.org/10.3390/app16115333
Vancouver
Kim SH, Jeong HJ, Shin SI, Kwon JW. A Non-Autoregressive Spatiotemporal Framework for Offline Full-Matrix Origin–Destination Forecasting in Large-Scale Metro Networks. Applied Sciences. 2026;16(11):5333. doi:10.3390/app16115333
BibTeX
@article{Kim2026,
author = {Kim, Seung Ha and Jeong, Hoe Jun and Shin, Seong il and Kwon, Jang Woo},
title = {A Non-Autoregressive Spatiotemporal Framework for Offline Full-Matrix Origin–Destination Forecasting in Large-Scale Metro Networks},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {11},
pages = {5333},
doi = {10.3390/app16115333}
}
EUVIMED