EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Multi-Level Dynamic GCN-Transformer Framework with Spatio-Temporal Interaction for Traffic Flow Prediction

Guan LIAN, Caihua HUANG, Qi SUN, Wenyong LI, Yingzi WU

Promet - Traffic&Transportation · 27.05.2026 · 38 (5) · 1173-1191

DOI: 10.7307/ptt.v38i5.1300 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Promet - Traffic&Transportation, online erschienen am 27.05.2026. Verfasst von Guan LIAN und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a core task of intelligent transportation systems, traffic flow prediction is characterised by high spatio-temporal complexity. Due to the limitations of existing methods in modelling complex spatio-temporal dependencies, particularly regarding medium- to long-term prediction accuracy and generalisation capabilities, this paper proposes a combination prediction model based on a multi-level dynamic GCN-Transformer framework (DGTFormer), to enhance the accuracy of short- and long-term traffic flow predictions. DGTFormer adopts a dual-stream architecture to achieve spatio-temporal decoupling modelling. The spatio-temporal dynamic graph convolutional network processes dynamic changes in the road network structure, and the temporal transformer encoder processes temporal information related to traffic flow. A spatio-temporal gated fusion mechanism is introduced to deeply couple spatial and temporal information. Experimental results on three real-world traffic datasets (PeMSD4, PeMSD7 and PeMSD8) demonstrate that DGTFormer significantly outperforms mainstream baseline models on multiple key evaluation metrics. Compared with advanced baseline methods, DGTFormer achieves performance improvements of up to 8.61% and 9.15% in RMSE and MAE, respectively. Furthermore, the coefficient of determination, R², remains stable at an excellent level above 0.9 across different prediction time steps, which fully validates that the DGTFormer model possesses superior predictive performance and generalisation capabilities.

Zitieren

APA

LIAN, G., HUANG, C., SUN, Q., LI, W., & WU, Y. (2026). A Multi-Level Dynamic GCN-Transformer Framework with Spatio-Temporal Interaction for Traffic Flow Prediction. Promet - Traffic&Transportation, 38(5), 1173-1191. https://doi.org/10.7307/ptt.v38i5.1300

Vancouver

LIAN G, HUANG C, SUN Q, LI W, WU Y. A Multi-Level Dynamic GCN-Transformer Framework with Spatio-Temporal Interaction for Traffic Flow Prediction. Promet - Traffic&Transportation. 2026;38(5):1173-1191. doi:10.7307/ptt.v38i5.1300

BibTeX
@article{LIAN2026,
  author = {LIAN, Guan and HUANG, Caihua and SUN, Qi and LI, Wenyong and WU, Yingzi},
  title = {A Multi-Level Dynamic GCN-Transformer Framework with Spatio-Temporal Interaction for Traffic Flow Prediction},
  journal = {Promet - Traffic&Transportation},
  year = {2026},
  volume = {38},
  number = {5},
  pages = {1173--1191},
  doi = {10.7307/ptt.v38i5.1300}
}
Kostenlos starten →