Original scientific paper
https://doi.org/10.7307/ptt.v38i5.1300
A Multi-Level Dynamic GCN-Transformer Framework with Spatio-Temporal Interaction for Traffic Flow Prediction
Guan Lian
; School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin, China
*
Caihua Huang
; School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin, China
Qi Sun
; School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin, China
Wenyong Li
; Guangxi Key Laboratory of Intelligent Transportation, Guilin University of Electronic Technology, Guilin, China
Yingzi Wu
; School of Civil Engineering and Transportation, Northeast Forestry University, Harbin, China
* Corresponding author.
Abstract
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.
Keywords
traffic flow prediction; graph convolutional network; transformer model; gated fusion; spatio-temporal modelling
Hrčak ID:
347517
URI
Publication date:
27.5.2026.
Visits: 0 *