EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Spatiotemporal Framework with Memory and Diffusion Convolution for Traffic Flow Prediction

Xi Chen, Jiajia Chen

Applied Artificial Intelligence Research · 20.07.2026 · 2 (3) · 8-17

DOI: 10.65455/6rkv7629 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Artificial Intelligence Research, online erschienen am 20.07.2026. Verfasst von Xi Chen und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate traffic flow prediction is pivotal for intelligent transportation systems, yet it remains inherently challenging due to dynamic spatial correlations and long-range temporal dependencies. While existing forecasting paradigms predominantly rely on static, pre-defined graph structures, they often overlook the direct functional connections between non-adjacent time steps.This paper proposes a novel spatiotemporal forecasting framework, termed Memory-augmented Diffusion Convolutional LSTM network (MDC-LSTM), which integrates a MemBART-inspired memory mechanism, diffusion convolution, regional attention, and LSTM-based temporal modeling. By synthesizing these components with Long Short-Term Memory (LSTM) units, the proposed model effectively captures both localized spatial patterns and deep inter-temporal relationships. Empirical evaluations conducted on the METR-LA benchmark dataset demonstrate that our framework significantly enhances predictive accuracy across multiple metrics, consistently outperforming several state-of-the-art (SOTA) baselines and exhibiting strong robustness in long-term forecasting scenarios.

Zitieren

APA

Chen, X., & Chen, J. (2026). A Hybrid Spatiotemporal Framework with Memory and Diffusion Convolution for Traffic Flow Prediction. Applied Artificial Intelligence Research, 2(3), 8-17. https://doi.org/10.65455/6rkv7629

Vancouver

Chen X, Chen J. A Hybrid Spatiotemporal Framework with Memory and Diffusion Convolution for Traffic Flow Prediction. Applied Artificial Intelligence Research. 2026;2(3):8-17. doi:10.65455/6rkv7629

BibTeX
@article{Chen2026,
  author = {Chen, Xi and Chen, Jiajia},
  title = {A Hybrid Spatiotemporal Framework with Memory and Diffusion Convolution for Traffic Flow Prediction},
  journal = {Applied Artificial Intelligence Research},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {8--17},
  doi = {10.65455/6rkv7629}
}
Kostenlos starten →