[1]张震,刘博,李卓,等.面向交通流量预测的自适应时空图卷积网络[J].郑州大学学报(工学版),2027,48(XX):1-9.[doi:10.13705/j.issn.1671-6833.2025.05.011]
　ZHANG Zhen,LIU Bo,LI Zhuo,et al.Adaptive Spatial-temporal Graph Convolutional Network for Traffic Forecasting[J].Journal of Zhengzhou University (Engineering Science),2027,48(XX):1-9.[doi:10.13705/j.issn.1671-6833.2025.05.011]
点击复制

面向交通流量预测的自适应时空图卷积网络()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
48
期数:
2027年XX
页码:
1-9
栏目:
出版日期:
2027-12-10

文章信息/Info

Title:
Adaptive Spatial-temporal Graph Convolutional Network for Traffic Forecasting
作者:
张震1,2, 刘博1, 李卓2, 张学忠3
1. 郑州大学 河南先进技术研究院,河南 郑州 450001;2. 郑州大学 电气与信息工程学院,河南 郑州 450001;3. 国网周口供电公司,河南 周口 466000
Author(s):
ZHANG Zhen1,2, LIU Bo1, LI Zhuo2, ZHANG Xuezhong3
1. School of Henan Institute of Advanced Technology, Zhengzhou University, Zhengzhou 450001, China; 2. School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China; 3. State Grid Zhoukou Power Supply Company, Zhoukou 466000, China
关键词:
交通流量预测;  自适应图结构;  节点属性;  图卷积网络;  时空相关性
Keywords:
traffic flow prediction;  adaptive graph structure;  node attributes;  graph convolutional network;  spatiotemporal correlation
分类号:
TP391
DOI:
10.13705/j.issn.1671-6833.2025.05.011
文献标志码:
A
摘要:
针对现有交通流量预测方法未能充分利用节点属性指导图结构学习，以及在捕获复杂时空相关性方面存在局限性等问题，提出了一种结合自适应图结构学习和时空卷积架构的自适应时空图卷积网络（AdpSTGCN）。首先，设计一种基于节点属性的自适应图结构学习方法，从全局和局部两个视角动态学习道路网络的空间关系；其次，提出一种专用的时空卷积网络架构，有效地捕获交通流量中的时空相关性，进一步提升模型对复杂时空关系的建模能力，同时引入递进式训练策略来解决模型训练中可学习参数过多和数据稀疏性问题；最后，在高速公路交通数据集 METR-La、PEMS-Bay 进行了 15、30、60 min 的交通流量预测实验。实验结果表明：AdpSTGCN 模型相较于多个基线模型，在 MAE、RMSE、MAPE 3 个预测误差指标上均表现最优。这说明该模型在未来短期和长期交通流量预测任务上均具有更优的建模能力，为城市交通疏导提供了理论依据。
Abstract:
To address the limitations of existing traffic flow prediction methods in fully utilizing node attributes to guide graph structure learning and capturing complex spatio-temporal dependencies, this study proposes an Adaptive Spatio-Temporal Graph Convolutional Network (AdpSTGCN) integrating adaptive graph structure learning with spatio-temporal convolutional architecture. Firstly, an adaptive graph structure learning method based on node attributes is designed to dynamically capture spatial relationships in road networks from both global and local perspectives. Secondly, a dedicated spatio-temporal convolutional architecture was developed to effectively model spatio-temporal correlations in traffic flow patterns, further enhancing the model’s capability to handle complex spatio-temporal relationships. A progressive training strategy is introduced to address challenges of excessive learnable parameters and data sparsity during model training. Finally, experimental evaluations on highway traffic datasets (METR-LA and PEMS-Bay) demonstrate the model’s performance in 15, 30, and 60 minutes traffic flow prediction tasks. Experimental results showed that the AdpSTGCN model achieved the best performance among multiple baseline models in terms of three prediction error metrics: MAE, RMSE, and MAPE. These findings indicate the model’s superior modeling capabilities for both short-term and long-term traffic flow prediction tasks, providing a theoretical foundation for urban traffic management strategies.

参考文献/References:

[1] 王佳昊, 黎文斌, 郭仕尧, 等. 基于全局时空图卷积神经网络的城市交通流量预测[J]. 计算机科学, 2024, 51(S2): 534-542.Wang Jiahao, Li Wenbin, Guo Shiyao, et al. Urban traffic flow prediction based on global spatiotemporal graph convolutional neural network [J]. Computer Science, 2024, 51(S2): 534-542.
[2] 杨高飞, 徐睿, 秦鸣, 等. 基于ARMA和卡尔曼滤波的短时交通预测[J]. 郑州大学学报(工学版), 2017, 38(2): 36-40.Yang Gaofei, Xu Rui, Qin Ming, et al. Short-term traffic volume forecasting based on ARMA and Kalman filter [J]. Journal of Zhengzhou University (Engineering Science), 2017, 38(2): 36-40.
[3] Yan He, Zhang Tianan, Qi Yong, et al. Short-term traffic flow prediction based on a hybrid optimization algorithm[J]. Applied Mathematical Modelling, 2022, 102: 385-404.
[4] Lin Guancen, Lin Aijing, Gu Danlei. Using support vector regression and K-nearest neighbors for short-term traffic flow prediction based on maximal information coefficient[J]. Information Sciences, 2022, 608: 517-531.
[5] Zhang Si, Tong Hanghang, Xu Jiejun, et al. Graph convolutional networks: a comprehensive review[J]. Computational Social Networks, 2019, 6: 11.
[6] Li Yaguang, Yu R, Shahabi C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[P/OL]. arXiv: 1707-06, 2019. https://doi.org/10.48550/arXiv.1707.01926.
[7] Yu Bing, Yin Haoteng, Zhan Zhanxing. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[P/OL]. arXiv: 1807-12, 2018. https://doi.org/10.48550/arXiv.1709.04875.
[8] Guo Shengnan, Lin Youfang, Feng Ning, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 922-929.
[9] Zheng Chuanpan, Fan Xiaoliang, Wang Cheng, et al. GMAN: a graph multi-attention network for traffic prediction[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(1): 1234-1241.
[10] Zhang Wei, Zhu Fenghua, Lv Yisheng, et al. AdapGL: an adaptive graph learning algorithm for traffic prediction based on spatiotemporal neural networks[J]. Transportation Research Part C: Emerging Technologies, 2022, 139: 103659.
[11] Wu Zonghan, Pan Shirui, Long Guodong, et al. Graph WaveNet for deep spatial-temporal graph modeling[P/OL]. arXiv: 1906-00121, 2019. https://doi.org/10.48550/arXiv.1906.00121.
[12] Bai Lei, Bai Lei, Yao Lina, et al. Adaptive graph convolutional recurrent network for traffic forecasting[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York: ACM, 2020: 17804-17815.
[13] Lin Junpeng, Li Ziyue, Li Zhishuai, et al. Dynamic causal graph convolutional network for traffic prediction[C]//Proceedings of the 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE). Piscataway: IEEE, 2023: 1-8.
[14] Diao Zuliang, Wang Xin, Zhang Dafang, et al. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 890-897.
[15] Lyu Mingqi, Hong Zhaoxiong, Chen Ling, et al. Temporal multi-graph convolutional network for traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(6): 3337-3348.
[16] Zhang Hong, Wang Hongyan, Chen Linlong, et al. Traffic flow forecasting based on transformer with diffusion graph attention network[J]. International Journal of Automotive Technology, 2024, 25(3): 455-468.
[17] Liu Haiyang, Zhu Chunjiang, Zhang Detian, et al. Attention-based spatial-temporal graph convolutional recurrent networks for Traffic forecasting[C]//Advanced data mining and applications. Cham: Springer Nature Switzerland, 2023: 630-645.
[18] Weng Wenchao, Fan Jin, Wu Huifeng, et al. A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting[J]. Pattern Recognition, 2023, 142: 109670.
[19] Kong Xiangyuan, Xing Weiwei, Wei Xiang, et al. STGAT: spatial-temporal graph attention networks for traffic flow forecasting[J]. IEEE Access, 2020, 8: 134363-134372.
[20] Sha Ning, Wu Xiaochun, Wen Jinpeng, et al. Adaptive spatio-temporal graph convolutional network with attention mechanism for mobile edge network traffic prediction[J]. Cluster Computing, 2024, 27(9): 13257-13272.
[21] Li Yaguang, Shahabi C. A brief overview of machine learning methods for short-term traffic forecasting and future directions[J]. SIGSPATIAL Special, 2018, 10(1): 3-9.
[22] Pan Bei, Demiryurek U, Shahabi C. Utilizing real-world transportation data for accurate traffic prediction[C]//Proceedings of the 2012 IEEE 12th International Conference on Data Mining. Piscataway: IEEE, 2012: 595-604.
[23] Sutskever I, Sutskever I, Vinyals O, et al. Sequence to sequence learning with neural networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. New York: ACM, 2014: 3104-3112.
[24] Han Liangzhe, Du Bowen, Sun Leilei, et al. Dynamic and multi-faceted spatio-temporal deep learning for traffic speed forecasting[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. New York: ACM, 2021: 547-555.
[25] Shin Y, Yoon Y. PGCN: progressive graph convolutional networks for spatial-temporal traffic forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(7): 7633-7644.

备注/Memo

备注/Memo:
收稿日期:2026-01-22;修订日期:2026-03-23
基金项目:河南省重点研发专项(231111211600)
作者简介:张震(1966— ) ,男,河南郑州人,郑州大学教授,博士,博士生导师,主要从事计算机视觉、交通流量预测的研究,E-mail:zhangzhen66@126.com。
更新日期/Last Update: 2026-04-22