Spatio-Temporal Multi-Graph Convolution Traffic Flow Prediction Model Based on Multi-Source Information Fusion and Attention Enhancement
Source abstract
Abstract
Traffic flow prediction plays a vital role in intelligent transportation systems, directly affecting travel scheduling, road planning, and traffic management efficiency. However, traditional methods often struggle to capture complex spatiotemporal dependencies and integrate heterogeneous data sources. To overcome these challenges, we propose a Spatio-temporal Multi-graph Convolution Traffic Flow Prediction Model based on Multi-source Information Fusion and Attention Enhancement (MIFA-ST-MGCN). The model adopts adaptive data fusion strategies according to spatiotemporal characteristics, achieving effective integration through feature concatenation and multi-graph structure construction. A spatiotemporal attention mechanism is designed to dynamically capture the varying contributions of different adjacency relations and temporal dependencies, thereby enhancing feature representation. In addition, recurrent units are combined with graph convolutional networks to model spatiotemporal data and generate more accurate prediction results. Experiments conducted on a real-world traffic dataset demonstrate that the proposed model achieves superior performance, reducing the mean absolute error by 3.57% compared with mainstream traffic flow prediction models. These results confirm the effectiveness of multi-source fusion and attention enhancement in improving prediction accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic Prediction and Management Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Resources and Environmental Engineering, Wuhan University of Science and Technology, Wuhan 430081, China
Funding
Wuhan Key Research and Development Program
References (37)
Show source-provided references
1. Road accidents and traffic flows: An econometric investigation10.1111/1468-0335.00198 ↗
2. Relationship between traffic volume and accident frequency at intersections10.3390/ijerph17041393 ↗
3. Physical models of traffic safety at crossing streams10.1016/j.physa.2024.129669 ↗
4. A Survey on Highway Traffic Flow Prediction: Methods and Advances
5. Short-term traffic flow prediction studies integrated with external properties
6. Highway Traffic Flow Prediction Based on a Feature Fused Spatio-Temporal Graph Mixed Networks
7. Long Term Prediction on Urban Traffic Flow Based on Multi-source Spatio-temporal Graph Convolutional Neural Network Model
8. AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting10.1109/ACCESS.2021.3062114 ↗
9. Zong, X., Yan, H., and Qi, Y. (Arch. Comput. Methods Eng., 2025). Recent Advances in Multi-source Data Fusion for Traffic Flow Prediction: A Review, Arch. Comput. Methods Eng., Prepublish.10.1007/s11831-025-10336-2 ↗
10. Passenger Flow Prediction of Subway Transfer Stations Based on Nonparametric Regression Model
11. Prediction of functional ARMA processes with an application to traffic data
12. Time series traffic flow prediction with hyper-parameter optimized ARIMA models for intelligent transportation system
13. Time series traffic collision analysis of London hotspots: Patterns, predictions and prevention strategies10.1016/j.heliyon.2024.e25710 ↗
14. Spatiotemporal attention mechanism-based multistep traffic volume prediction model for highway toll stations10.5604/01.3001.0015.8148 ↗
15. Adaptive multi-kernel SVM with spatial–temporal correlation for short-term traffic flow prediction10.1109/TITS.2018.2854913 ↗
16. Multi-view Bayesian spatio-temporal graph neural networks for reliable traffic flow prediction10.1007/s13042-022-01689-2 ↗
17. A novel traffic flow forecasting method based on RNN-GCN and BRB10.1155/2020/7586154 ↗
18. Traffic Flow Prediction at Intersections: Enhancing with a Hybrid LSTM-PSO Approach
19. Zhang, W., Li, X., Li, A., Huang, X., Wang, T., and Gao, H. (2023, January 17–21). Sgru: A high-performance structured gated recurrent unit for traffic flow prediction. Proceedings of the 2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS), Ocean Flower Island, China.10.1109/ICPADS60453.2023.00076 ↗
20. Ma, X., Dai, Z., He, Z., Ma, J., Wang, Y., and Wang, Y. (2017). Learning traffic as images: A deep convolutional neural network for large-scale transportation network speed prediction. Sensors, 17.10.3390/s17040818 ↗
21. Yu, B., Yin, H., and Zhu, Z. (2017). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv.10.24963/ijcai.2018/505 ↗
22. Short-term passenger flow forecast for urban rail transit based on multi-source data10.1186/s13638-020-01881-4 ↗
23. Machine learning-based traffic flow prediction and intelligent traffic management
24. Urban regional function guided traffic flow prediction10.1016/j.ins.2023.03.109 ↗
25. Du, M., Yang, L., and Tu, J. (2021). A novel approach to calculate the spatial–temporal correlation for traffic flow based on the structure of urban road networks and traffic dynamic theory. Sensors, 21.10.3390/s21144725 ↗
26. Chen, M., Yuan, H., Jiang, N., Bao, Z., and Wang, S. (2024, January 21–25). Urban traffic accident risk prediction revisited: Regionality, proximity, similarity and sparsity. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, Boise, ID, USA.10.1145/3627673.3679567 ↗
27. Spatial-temporal feature extraction and evaluation network for citywide traffic condition prediction10.1109/TIV.2023.3324184 ↗
28. Congestion boundary approach for phase transitions in traffic flow
29. Traffic Flow as a Simple Fluid: Toward a Scaling Theory of Urban Congestion10.1177/03611981231179703 ↗
30. Travel time prediction using gated recurrent unit and spatio-temporal algorithm
31. T-GCN: A temporal graph convolutional network for traffic prediction10.1109/TITS.2019.2935152 ↗
32. Tobler’s first law of geography: A big idea for a small world?10.1111/j.1467-8306.2004.09402003.x ↗
33. Li, Y., Yu, R., Shahabi, C., and Liu, Y. (2017). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv.
34. Li, Y., and Xu, W. (2018, January 12–13). Short-term traffic flow forecasting based on SVR. Proceedings of the 2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2018), Dalian, China.10.2991/amcce-18.2018.10 ↗
35. Shao, H., and Soong, B.H. (2016, January 22–25). Traffic flow prediction with long short-term memory networks (LSTMs). Proceedings of the 2016 IEEE Region 10 Conference (TENCON), Singapore.10.1109/TENCON.2016.7848593 ↗
36. Combining weather condition data to predict traffic flow: A GRU-based deep learning approach10.1049/iet-its.2017.0313 ↗
37. Bai, J., Zhu, J., Song, Y., Zhao, L., Hou, Z., Du, R., and Li, H. (2021). A3t-gcn: Attention temporal graph convolutional network for traffic forecasting. ISPRS Int. J. Geo-Inf., 10.10.3390/ijgi10070485 ↗