Smart City Gnosys

Smart city article details

Title	Spatial-Temporal Attention Graph Wavenet For Traffic Forecasting
ID_Doc	52507
Authors	Liu S.; Zhu J.; Lei W.; Zhang P.
Year	2023
Published	2023 5th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2023
DOI	http://dx.doi.org/10.1109/DOCS60977.2023.10294485
Abstract	Accurately predicting road traffic conditions is critical for travel planning and efficient allocation of resources, making it a major research focus within smart cities. However, traffic forecasting poses significant challenges due to the complex spatial correlations and nonlinear temporal dependencies inherent to real-time traffic networks. Existing approaches for modeling spatial dependencies have primarily relied on a fixed graph structure, assuming that the relationships between roads are predetermined and static. In contrast, real-world transportation networks exhibit more dynamic interactions that evolve over time. To address this issue, we propose a Spatial-Temporal Attention Graph WaveNet (STAGWN) model for complex traffic network modeling. STAGWN utilizes self-attention network to capture dynamic spatial dependencies. Additionally, long time series are processed via temporal convolution module consisting of stacked dilated casual convolutions in STAGWN. Furthermore, STAGWN incorporates spatial and temporal embeddings to capture spatial-temporal heterogeneity. The proposed model is evaluated using two real-world datasets and compared with 10 baseline methods. Results indicate our approach attains state-of-the-art for 30 and 60 minutes ahead forecasts, demonstrating efficacy on longer prediction horizons. © 2023 IEEE.
Author Keywords	attention; deep learning; graph neutral network; traffic prediction

Similar Articles

Id	Similarity	Authors	Title	Published
52517	0.943	Huang X.; Pan Z.; Zhao G.	Spatial-Temporal Interactive Graph Convolutional Networks For Traffic Forecasting	2024 4th International Conference on Electronic Information Engineering and Computer Technology, EIECT 2024 (2024)
35590	0.939	Remmouche B.; Boukraa D.; Zakharova A.; Bouwmans T.; Taffar M.	Long-Term Spatio-Temporal Graph Attention Network For Traffic Forecasting	Expert Systems with Applications, 288 (2025)
32052	0.934	Qiu Z.; Xie Z.; Ji Z.; Liu X.; Wang G.	Integrating Query Data For Enhanced Traffic Forecasting: A Spatio-Temporal Graph Attention Convolution Network Approach With Delay Modeling	Knowledge-Based Systems, 301 (2024)
11045	0.929	Yin S.; Wang J.; Cui Z.; Wang Y.	Attention-Enabled Network-Level Traffic Speed Prediction	2020 IEEE International Smart Cities Conference, ISC2 2020 (2020)
38047	0.929	Yang S.; Wu Q.; Wang Y.; Zhou Z.	Mstdfgrn: A Multi-View Spatio-Temporal Dynamic Fusion Graph Recurrent Network For Traffic Flow Prediction	Computers and Electrical Engineering, 123 (2025)
53044	0.927	Meng X.; Xie W.; Cui J.	Stmgfn: Spatio-Temporal Multi-Graph Fusion Network For Traffic Flow Prediction	Lecture Notes in Computer Science, 15291 LNCS (2025)
36944	0.927	Tian R.; Wang C.; Hu J.; Ma Z.	Mfstgn: A Multi-Scale Spatial-Temporal Fusion Graph Network For Traffic Prediction	Applied Intelligence, 53, 19 (2023)
29828	0.926	Dai R.; Xu S.; Gu Q.; Ji C.; Liu K.	Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction With Navigation Data	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2020)
4883	0.926	Cao S.; Wu L.; Wu J.; Wu D.; Li Q.	A Spatio-Temporal Sequence-To-Sequence Network For Traffic Flow Prediction	Information Sciences, 610 (2022)
11043	0.924	He Q.; Xia D.; Li J.; Yang J.; Hu Y.; Li Y.; Li H.	Attention-Based Spatiotemporal Adaptive Graph Diffusion Convolutional Network For Traffic Flow Prediction	Transportation Research Record (2025)