Spatial-Temporal Graph Fusion with Dual-Scale Convolution for Traffic Flow Prediction
Dan Wang1, Mengyi Cui1, Zhenhua Yu1,*, Yukang Liu2
1 College of Artificial Intelligence & Computer Science, Xi’an University of Science and Technology, Xi’an, China
2 China Petroleum Engineering & Construction Corp. Beijing Company, Beijing, China
* Corresponding Author: Zhenhua Yu. Email: 
Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.074308
Received 08 October 2025; Accepted 23 December 2025; Published online 18 March 2026
Abstract
Traffic flow prediction is of great importance in traffic planning, road resource management, and congestion mitigation. However, existing prediction have significant limitations in modeling multi-scale spatial-temporal features, particularly in capturing temporal periodicity and spatial dependency in dynamically evolving traffic networks. This paper proposes a novel framework of traffic flow prediction, referred to as Adaptive Graph Fusion Dual-scale Convolutional Network (AGFDCN), which integrates spatial-temporal dynamic graphs with dual-scale convolutional networks. Specifically, we introduce a Dual-Scale Temporal Network, which combines long- and short-term dilated causal convolutions with a temporal decay-aware attention mechanism to efficiently capture traffic patterns across multiple temporal scales. Furthermore, we design a Dynamic Adaptive Graph Module, which models complex spatial dependencies in traffic networks through an adaptive graph fusion mechanism and a dual-path attention-gated module. Finally, the temporal and spatial representations are integrated by employing a gated fusion mechanism, enhancing the overall prediction performance. Experimental results obtained based on three highway datasets (i.e., PEMS04, PEMS07 and PEMS08) verify that the proposed model outperforms several state-of-the-art baselines in various evaluation metrics. Compared to the spatial-temporal graph model AGCRN with best performance in the baseline models, the proposed model exhibits significant improvements across all datasets: it achieves reduces of MAE by 42.07% and RMSE by 35.43% on PEMS04; MAE by 28.35% and RMSE by 29.28% on PEMS07; and MAE by 30.52% and RMSE by 30.73% on PEMS08, respectively, validating its effectiveness in modeling complex spatial-temporal traffic data and its robustness in handling sudden traffic changes.
Keywords
Dual-scale convolution; dual-path attention-gated module; adaptive graph fusion; spatial-temporal dynamic graph; traffic flow prediction
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
