Conference Paper2021Cited by 48

Unified spatio-temporal modeling for traffic forecasting using graph neural network

Amit Roy, Kashob Kumar Roy, Amin Ahsan Ali, M Ashraful Amin, AKM Mahbubur Rahman

2021 International Joint Conference on Neural Networks (IJCNN)

IEEE, pp. 1–8

  • Sustainable Cities and Communities — Relevance: 45%
DOI: 10.1109/ijcnn52387.2021.9533319Open AccessURL

Abstract

Research in deep learning models to forecast traffic intensities has gained great attention in recent years due to their capability to capture the complex spatio-temporal relationships within the traffic data. However, most state-of-the-art approaches have designed spatial-only (e.g. Graph Neural Networks) and temporal-only (e.g. Recurrent Neural Networks) modules to separately extract spatial and temporal features. However, we argue that it is less effective to extract the complex spatiotemporal relationship with such factorized modules. Besides, most existing works predict the traffic intensity of a particular time interval only based on the traffic data of the previous one hour of that day. And thereby ignores the repetitive daily/weekly pattern that may exist in the last hour of data. Therefore, we propose a Unified Spatio-Temporal Graph Convolution Network (USTGCN) for traffic forecasting that performs both spatial and temporal aggregation through direct information propagation across different timestamp nodes with the help of spectral graph convolution on a spatio-temporal graph. Furthermore, it captures historical daily patterns in previous days and current-day patterns in current-day traffic data. Finally, we validate our work's effectiveness through experimental analysis11Code is available at github.com/AmitRoy7781/USTGCN, which shows that our model USTGCN can outperform state-of-the-art performances in three popular benchmark datasets from the Performance Measurement System (PeMS). Moreover, the training time is reduced significantly with our proposed USTGCN model.

Keywords

  • spectral graph convolution
  • traffic prediction
  • graph neural networks
  • spatio-temporal graph convolutional network
  • spatio-temporal graph
  • PeMS dataset

CCDS Authors

Amit Roy
Amit Roy

Amit Roy

  • Alumni, CCDS

  • PhD Student

    Purdue University, USA

  • BSc

    University of Dhaka, Bangladesh

Published at

PAKDD, IJCNN

Kashob Kumar Roy
Kashob Kumar Roy

Kashob Kumar Roy

  • Alumni, CCDS

  • PhD Student

    University of Illinois Urbana-Champaign, USA

  • BSc

    University of Dhaka, Bangladesh

Published at

PAKDD, IJCNN

Prof. Amin Ahsan Ali, PhD
Amin Ahsan Ali, PhD

Prof. Amin Ahsan Ali, PhD

  • Director, AI/ML Wing
  • Supervisor, ComBio Wing

  • Professor

    Department of Computer Science and Engineering

    Independent University, Bangladesh (IUB)

Published at

ACL, CHI, UbiComp, ECCV, IJCAI, ECAI, WACV, IPSN, PAKDD, LREC, IJCNN, ICPR, ICIP, BEA, BLP, ICMLA, Scientific Reports, Scientific Data, Pattern Recognition, Information Sciences, Ad Hoc Networks, Drug and Alcohol Dependence, PLOS ONE

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, Pattern Recognition, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

AKM Mahbubur Rahman, PhD
AKM Mahbubur Rhman, PhD

AKM Mahbubur Rahman, PhD

  • Director, DS & IPT Wings

  • Associate Professor

    Department of Computer Science and Engineering

    Independent University, Bangladesh (IUB)

Published at

CHI, ECCV, WACV, PAKDD, LREC, IJCNN, ICPR, ICIP, HCII, BEA, Scientific Reports, Information Sciences

References

  1. 1.Chen, Tianyu, Wang, Zeyu, Li, Lin, Li, Ding, Li, Zongyang, Chang, Xiaoning, Bian, Pan, Liang, Guangtai, Wang, Qianxiang, Xie, Tao. (2025). Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories. Dagstuhl Research Online Publication Server[10.4230/lipics.ecoop.2025.6]
  2. 2.Michaël Defferrard. (2016). Convolutional Neural Networks On Graphs With Fast Localized Spectral Filtering (Gdl Seminar). Figshare[10.5281/zenodo.1318397]
  3. 3.Bing Yu, Haoteng Yin, Zhanxing Zhu. (2018). Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. , 3634–3640[10.24963/ijcai.2018/505]
  4. 4.Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li. (2019). T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems, 21(9), 3848–3858[10.1109/tits.2019.2935152]
  5. 5.Shengnan Guo, Youfang Lin, Ning Feng, Chao Song, Huaiyu Wan. (2019). Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 922–929[10.1609/aaai.v33i01.3301922]
  6. 6.Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang. (2019). Graph WaveNet for Deep Spatial-Temporal Graph Modeling. , 1907–1913[10.24963/ijcai.2019/264]
  7. 7.Billy M. Williams, L A Hoel. (2003). Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results. Journal of Transportation Engineering, 129(6), 664–672[10.1061/(asce)0733-947x(2003)129:6(664)]
  8. 8.Chih-Hsien Wu, Jan-Ming Ho, Dong-Hyun Lee. (2004). Travel-Time Prediction With Support Vector Regression. IEEE Transactions on Intelligent Transportation Systems, 5(4), 276–281[10.1109/tits.2004.837813]
  9. 9.Iwao Okutani, Yorgos J. Stephanedes. (1984). Dynamic prediction of traffic volume through Kalman filtering theory. Transportation Research Part B Methodological, 18(1), 1–11[10.1016/0191-2615(84)90002-x]
  10. 10.Chao Chen, Karl Petty, Alexander Skabardonis, Pravin Varaiya, Zhanfeng Jia. (2001). Freeway Performance Measurement System: Mining Loop Detector Data. Transportation Research Record Journal of the Transportation Research Board, 1748(1), 96–102[10.3141/1748-12]
  11. 11.Rongzhou Huang, Chuyin Huang, Yubao Liu, Genan Dai, Weiyang Kong. (2020). LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks. , 2355–2361[10.24963/ijcai.2020/326]
  12. 12.Cen Chen, Kenli Li, Sin G. Teo, Xiaofeng Zou, Kang Wang, Jie Wang, Zeng Zeng. (2019). Gated Residual Recurrent Graph Neural Networks for Traffic Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 485–492[10.1609/aaai.v33i01.3301485]
  13. 13.Shen Fang, Qi Zhang, Gaofeng Meng, Shiming Xiang, Chunhong Pan. (2019). GSTNet: Global Spatial-Temporal Network for Traffic Flow Prediction. , 2286–2293[10.24963/ijcai.2019/317]
  14. 14.Cheonbok Park, Chunggi Lee, Hyojin Bahng, Yunwon Tae, Seungmin Jin, Ki-Hwan Kim, Sungahn Ko, Jaegul Choo. (2020). ST-GRAT: A Novel Spatio-temporal Graph Attention Networks for Accurately Forecasting Dynamically Changing Road Speed. , 1215–1224[10.1145/3340531.3411940]
  15. 15.Cheonbok Park, Chunggi Lee, Hyojin Bahng, Taeyun won, Kihwan Kim, Seungmin Jin, Sungahn Ko, Jaegul Choo. (2019). STGRAT: A Spatio-Temporal Graph Attention Network for Traffic Forecasting.. arXiv (Cornell University)[link]
  16. 16.William L. Hamilton, Rex Ying, Jure Leskovec. (2017). Inductive Representation Learning on Large Graphs. arXiv (Cornell University), 30, 1024–1034[10.48550/arxiv.1706.02216]
  17. 17.Yaguang Li, Rose Yu, Cyrus Shahabi, Yan Liu. (2017). Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic\n Forecasting. arXiv (Cornell University)[10.48550/arxiv.1707.01926]
  18. 18.Mingxing Xu, Wenrui Dai, Chunmiao Liu, Xing Gao, Weiyao Lin, Guo-Jun Qi, Hongkai Xiong. (2020). Spatial-Temporal Transformer Networks for Traffic Flow Forecasting. arXiv (Cornell University)[10.48550/arxiv.2001.02908]

Cited By

  1. 1.Saeed Rahmani, Asiye Baghbani, Nizar Bouguila, Zachary Patterson. (2023). Graph Neural Networks for Intelligent Transportation Systems: A Survey. IEEE Transactions on Intelligent Transportation Systems, 24(8), 8846–8885[10.1109/tits.2023.3257759]
  2. 2.Yingjie Tian, Xiaoxi Zhao, Wei Huang. (2022). Meta-learning approaches for learning-to-learn in deep learning: A survey. Neurocomputing, 494, 203–223[10.1016/j.neucom.2022.04.078]
  3. 3.Qinyao Luo, Silu He, Xing Han, Yuhan Wang, Haifeng Li. (2024). LSTTN: A Long-Short Term Transformer-based spatiotemporal neural network for traffic flow forecasting. Knowledge-Based Systems, 293, 111637[10.1016/j.knosys.2024.111637]
  4. 4.Yuyan Annie Pan, Fuliang Li, Anran Li, Zhiqiang Niu, Zhen Liu. (2025). Urban intersection traffic flow prediction: A physics-guided stepwise framework utilizing spatio-temporal graph neural network algorithms. Multimodal Transportation, 4(2), 100207[10.1016/j.multra.2025.100207]
  5. 5.Senwen Li, Liang Ge, Yongquan Lin, Bo Zeng. (2022). Adaptive Spatial-Temporal Fusion Graph Convolutional Networks for Traffic Flow Forecasting. 2022 International Joint Conference on Neural Networks (IJCNN), 1–8[10.1109/ijcnn55064.2022.9892326]
  6. 6.Hojat Behrooz, Yeganeh M. Hayeri. (2022). Machine Learning Applications in Surface Transportation Systems: A Literature Review. Applied Sciences, 12(18), 9156[10.3390/app12189156]
  7. 7.Yun Li, Dazhou Yu, Zhenke Liu, Minxing Zhang, Xiaoyun Gong, Liang Zhao. (2024). Graph Neural Network for Spatiotemporal Data: Methods and Applications. SSRN Electronic Journal[10.2139/ssrn.4725185]
  8. 8.Xu Huang, Bowen Zhang, Shanshan Feng, Yunming Ye, Xutao Li. (2023). Interpretable local flow attention for multi-step traffic flow prediction. Neural Networks, 161, 25–38[10.1016/j.neunet.2023.01.023]
  9. 9.Rui Feng, Heqi Cui, Qiang Feng, Sixuan Chen, Xiaoning Gu, Baozhen Yao. (2023). Urban Traffic Congestion Level Prediction Using a Fusion-Based Graph Convolutional Network. IEEE Transactions on Intelligent Transportation Systems, 24(12), 14695–14705[10.1109/tits.2023.3304089]
  10. 10.Alkilane Khaled, Alfateh M. Tag Elsir, Pengfei Wang, Yanming Shen, Qiang Zhang. (2024). A graph-based approach for traffic prediction using similarity and causal relations between nodes. Knowledge-Based Systems, 296, 111913[10.1016/j.knosys.2024.111913]
  11. 11.Hao Huang, Zhiqun Hu, Yueting Wang, Zhaoming Lu, Xiangming Wen, Bin Fu. (2023). Train a central traffic prediction model using local data: A spatio-temporal network based on federated learning. Engineering Applications of Artificial Intelligence, 125, 106612[10.1016/j.engappai.2023.106612]
  12. 12.Ziming Xu, Juliana Y. Leung. (2024). Shale Gas Production Forecasting with Well Interference Based on Spatial-Temporal Graph Convolutional Network. SPE Journal, 29(10), 5120–5131[10.2118/215056-pa]
  13. 13.Yuanqi Du, Xiaojie Guo, Hengning Cao, Yanfang Ye, Liang Zhao. (2022). Disentangled Spatiotemporal Graph Generative Models. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6541–6549[10.1609/aaai.v36i6.20607]
  14. 14.Vandana Singh, Sudip Kumar Sahana, Vandana Bhattacharjee. (2024). Integrated Spatio-Temporal Graph Neural Network for Traffic Forecasting. Applied Sciences, 14(24), 11477[10.3390/app142411477]
  15. 15.Shuai Liu, Xiaoyuan Feng, Yilong Ren, Han Jiang, Haiyang Yu. (2023). DCENet: A dynamic correlation evolve network for short-term traffic prediction. Physica A Statistical Mechanics and its Applications, 614, 128525[10.1016/j.physa.2023.128525]
  16. 16.Tianli Tang, Jiannan Mao, Ronghui Liu, Zhiyuan Liu, Yiran Wang, Di Huang. (2024). Origin-Destination Matrix Prediction in Public Transport Networks: Incorporating Heterogeneous Direct and Transfer Trips. IEEE Transactions on Intelligent Transportation Systems, 25(12), 19889–19903[10.1109/tits.2024.3447611]
  17. 17.Atkia Akila Karim, Naushin Nower. (2024). Probabilistic spatio-temporal graph convolutional network for traffic forecasting. Applied Intelligence, 54(11-12), 7070–7085[10.1007/s10489-024-05562-3]
  18. 18.Xiyuan Jin, Jing Wang, Shengnan Guo, Tonglong Wei, Yiji Zhao, Youfang Lin, Huaiyu Wan. (2023). Spatial–temporal uncertainty-aware graph networks for promoting accuracy and reliability of traffic forecasting. Expert Systems with Applications, 238, 122143[10.1016/j.eswa.2023.122143]
  19. 19.Xiao Wu, Hua Huang, Tong Zhou, Yudan Tian, Shisen Wang, Jingting Wang. (2025). An urban road traffic flow prediction method based on multi-information fusion. Scientific Reports, 15(1), 5568[10.1038/s41598-025-88429-y]
  20. 20.Yuen Hoi Lau, Raymond Chi-Wing Wong. (2021). Spatio-Temporal Graph Convolutional Networks for Traffic Forecasting. ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS), 427–430[10.1145/3474717.3484207]
  21. 21.Nooshin Yousefzadeh, Rahul Sengupta, Yashaswi Karnati, Anand Rangarajan, Sanjay Ranka. (2025). Graph Attention Network for Lane-Wise and Topology-Invariant Intersection Traffic Simulation. IEEE Transactions on Intelligent Transportation Systems, 26(4), 5082–5093[10.1109/tits.2025.3546810]
  22. 22.Shuai Liu, Haiyang Yu, Han Jiang, Zhenliang Ma, Zhiyong Cui, Yilong Ren. (2024). MuGIL: A Multi-Graph Interaction Learning Network for Multi-Task Traffic Prediction. Knowledge-Based Systems, 306, 112709[10.1016/j.knosys.2024.112709]
  23. 23.Hongfan Mu, Noura Aljeri, Azzedine Boukerche. (2024). Spatio-Temporal Feature Engineering for Deep Learning Models in Traffic Flow Forecasting. IEEE Access, 12, 76555–76578[10.1109/access.2024.3403516]
  24. 24.Jian Yang, Jinhong Li, Lu Wei, Lei Gao, Fuqi Mao. (2022). Spatiotemporal DeepWalk Gated Recurrent Neural Network: A Deep Learning Framework for Traffic Learning and Forecasting. Journal of Advanced Transportation, 2022, 1–11[10.1155/2022/4260244]
  25. 25.Junhao Zhang, Juncheng Jin, Junjie Tang, Zehui Qu. (2023). FPTN: Fast Pure Transformer Network for Traffic Flow Forecasting. Lecture notes in computer science, 382–393[10.1007/978-3-031-44223-0_31]
  26. 26.Shihao Zhao, Shuli Xing, Guojun Mao. (2022). An Attention and Wavelet Based Spatial-Temporal Graph Neural Network for Traffic Flow and Speed Prediction. Mathematics, 10(19), 3507[10.3390/math10193507]
  27. 27.Vongani Chabalala, Craig Rudolph, Karabo Mosala, Edward Khomotso Nkadimeng, Chuene Mosomane, Thuso Mathaha, Pallab Basu, Muhammad Ahsan Mahboob, Jude Kong, Nicola Bragazzi, Iqra Atif, Mukesh Kumar, Bruce Mellado. (2026). Spatiotemporal Graph Neural Networks for PM2.5 Concentration Forecasting. Air, 4(1), 2[10.3390/air4010002]
  28. 28.Dimuthu Lakmal, Kushani Perera, Renata Borovica-Gajic, Shanika Karunasekera. (2024). Spatial-Temporal Bipartite Graph Attention Network for Traffic Forecasting. Lecture notes in computer science, 68–80[10.1007/978-981-97-2253-2_6]
  29. 29.Yunke Zhang, Tong Li, Yuan Yuan, Fengli Xu, Fan Yang, Funing Sun, Yong Li. (2023). Demand-driven Urban Facility Visit Prediction. ACM Transactions on Intelligent Systems and Technology, 15(2), 1–24[10.1145/3625233]
  30. 30.Tianbao Zhang, Hongbin Wang, Dan Niu, Chunlei Shi, Xisong Chen, Yulong Jin. (2023). MMSTP: Multi-modal Spatiotemporal Feature Fusion Network for Precipitation Prediction. International Symposium on Autonomous Systems (ISAS), 1–5[10.1109/isas59543.2023.10164452]
  31. 31.Shaokang Cheng, Nada Osman, Shiru Qu, Lamberto Ballan. (2025). DSP-ST: Dynamic Structural Prior Spatiotemporal Graph Attention Networks for Traffic Speed Prediction. IEEE Intelligent Transportation Systems Magazine, 17(5), 20–35[10.1109/mits.2024.3512861]
  32. 32.Valerio Bellandi, Paolo Ceravolo, Samira Maghool, Margherita Pindaro, Stefano Siccardi. (2022). Pattern Matching Algorithm in Event Graphs. IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), 1–7[10.1109/dasc/picom/cbdcom/cy55231.2022.9927860]
  33. 33.Shijia Liu, Yong Wang, Sen Li, Yuming Liu. (2025). MADRL-based bitrate allocation for QoE fairness in 360° video streaming with viewport prediction. Multimedia Systems, 31(5)[10.1007/s00530-025-01920-4]
  34. 34.Parthapratim Deuri, Lindy Nongmaithem, Ningrinla Marchang. (2025). Missing Data Inference in Spatio-Temporal Mobile Crowd Sensing Using Graph Neural Network. IEEE Guwahati Subsection Conference (GCON), 1–6[10.1109/gcon65540.2025.11173307]
  35. 35.Jiali Yang, Kehua Yang, Fanzi Zeng, Qixuan Cheng, Zhu Xiao, Hongbo Jiang. (2024). Dear: vehicle mobility prediction using diffusion-expanded attention network based on IoV trajectory data. Neural Computing and Applications, 37(20), 14813–14827[10.1007/s00521-024-10641-0]
  36. 36.Lei Yao, Da Guo, Xing Wang, Lin Zhu, Junlan Feng, Yong Zhang. (2023). A double-layer attentive graph convolution networks based on transfer learning for dynamic graph classification. International Journal of Machine Learning and Cybernetics, 15(3), 863–877[10.1007/s13042-023-01944-0]
  37. 37.Jian Yang, Jinhong Li, Lu Wei, Lei Gao, Fuqi Mao. (2022). ST-AGRNN: A Spatio-Temporal Attention-Gated Recurrent Neural Network for Traffic State Forecasting. Journal of Advanced Transportation, 2022, 1–17[10.1155/2022/2806183]
  38. 38.Gamal Hossam Ragab, Aly Khalifa, Ahmed Elliethy. (2026). Similarity-Aware Server-Side Aggregation for Federated Cross-City Traffic Prediction. , 1–6[10.1109/iicc69623.2026.11581912]
  39. 39.G N Karthik Rajan, S Kabilan, K Nithya. (2026). AI-Driven Traffic Congestion Prediction and Adaptive Signal Control Using Spatial–Temporal Graph Neural Networks. , 1–6[10.1109/icdsaai69492.2026.11505063]
  40. 40.Chang Liu, Lihu Pan. (2026). STAGAT: Spatio-Temporal Aggregation Graph Attention Network for Traffic Prediction. Communications in computer and information science, 144–158[10.1007/978-981-95-5294-8_11]
  41. 41.Xin Zhao, Manchun Li, Keyu Lu, Ying Zhou, Lipeng Zheng. (2026). An Enhanced Graph Convolutional Network With Multispatial Relationships for Urban Village Identification. IEEE Transactions on Geoscience and Remote Sensing, 64, 3002711[10.1109/tgrs.2026.3722841]
  42. 42.Haifeng Huang, Yijun Xiong, Kai Xu, Mo Chen. (2026). Fusion State Space Model with Mixed Graph Learner for Long‐Term Traffic Flow Prediction. IET Intelligent Transport Systems, 20(1)[10.1049/itr2.70315]
  43. 43.Shehal Shah, Prince Doshi, Shlok Mangle, Prachi Tawde, Vinaya Sawant. (2024). Traffic Forecasting with Spatio-Temporal Graph Neural Networks. Communications in computer and information science, 183–197[10.1007/978-3-031-73477-9_13]
  44. 44.Ruoyi Wen, Daoyu Liang. (2024). Spatio-Temporal Traffic Prediction Under Multi-Scale Dynamic Convolution. International Conference on Computer and Communications (ICCC), 2042–2046[10.1109/iccc62609.2024.10942072]
  45. 45.Ji Feng, Jiashuang Huang, Chang Guo, Zhenquan Shi. (2024). MSA-GCN: Multistage Spatio-Temporal Aggregation Graph Convolutional Networks for Traffic Flow Prediction. Mathematics, 12(21), 3338[10.3390/math12213338]
  46. 46.Alfateh M. Tag Elsir, Alkilane Khaled, Yanming Shen. (2023). Triplet-contrastive Periodical Siamese Graph Networks for Travel Time Estimation. , 28, 1–8[10.1109/ijcnn54540.2023.10191875]
  47. 47.Bing Ba, Qi Fu, Chongjing Hang, YunXia Jiang. (2022). MixHop Graph WaveNet for Traffic Forecasting. Communications in computer and information science, 117–131[10.1007/978-981-19-8152-4_8]
  48. 48.Jiawei Zhang, Youfa Liu, Yongyong Chen, Yulong Wang. (2022). Recent Graph Neural Networks: A Survey. Lecture notes in electrical engineering, 1470–1480[10.1007/978-981-19-6901-0_155]
← All publications