A Traffic Data Imputation Method Based on Spatial-temporal Synchronous Graph Recovery Neural Network

Chaolong Jia; Zigao Huang; Wenhui Li; Rong Wang; Yunpeng Xiao

doi:10.1145/3807952

journal article Apr 10, 2026

A Traffic Data Imputation Method Based on Spatial-temporal Synchronous Graph Recovery Neural Network

Chaolong Jia

ACM Transactions on Knowledge Discovery from Data · Association for Computing Machinery (ACM)

View at Publisher Save 10.1145/3807952

Abstract

Due to comprehensive considerations regarding demand and cost control in traffic management, the performance indicators for checkpoint sensors can differ depending on the section of road. Consequently, some traffic data collected at checkpoints may be incomplete, which complicates data analysis. To address this issue, we propose using a neural network based on embedding synchronised spatio-temporal map data. Firstly, we designed a trajectory vectorisation algorithm using word embedding techniques, modelling the road network with vehicle trajectories to capture spatial correlations among road checkpoints. Secondly, we constructed a spatio-temporal synchronisation graph recovery neural network (STSGRN) that uses graph convolutional networks (GCNs) and gated recurrent units (GRUs) to account for the spatio-temporal characteristics of traffic data and fill in missing data across multiple dimensions. Finally, we developed an attention mechanism module for the spatio-temporal graph to extract dynamic dependencies at the spatio-temporal level. This architecture enhances the flexibility of the STSGRN in processing complex data with missing values. Experimental results demonstrate that the model effectively identifies spatial and temporal correlations in traffic data, enabling the accurate imputation of missing values. Compared to existing methods, it demonstrates significant improvements and superior generalisation performance.

Topics

No keywords indexed for this article. Browse by subject →

References

32

[1]

Fourth-Order Dimension Preserved Tensor Completion With Temporal Constraint for Missing Traffic Data Imputation

Hong Chen, Mingwei Lin, Liang Zhao et al.

IEEE Transactions on Intelligent Transportation Sy... 10.1109/tits.2025.3531221

[2]

10.1109/itsc55140.2022.9922425

[3]

10.1109/jiot.2022.3172447

[4]

10.1016/j.neunet.2023.03.009

[5]

10.1016/j.neunet.2024.106549

[6]

10.1109/tvt.2024.3423348

[7]

10.1155/int/3715086

[8]

10.1016/j.dcan.2020.03.002

[9]

10.1016/j.eswa.2024.125531

[10]

10.1109/tits.2022.3161792

[11]

10.1016/j.asoc.2023.110814

[12]

10.1109/jas.2024.124611

[13]

10.1016/j.neucom.2024.128948

[14]

10.1016/j.ins.2023.119972

[15]

10.1109/tits.2022.3203791

[16]

10.1016/j.neucom.2023.02.017

[17]

10.1109/cac.2017.8244105

[18]

10.1109/tits.2022.3233890

[19]

Yiming Wang, Hao Peng, Senzhang Wang, Haohua Du, Chunyang Liu, Jia Wu, and Guanlin Wu. 2025. STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation. arXiv preprint arXiv:2506.08054 (2025).

[20]

10.1016/j.knosys.2023.111325

[21]

10.1109/tkde.2024.3396158

[22]

10.1016/j.neucom.2025.129575

[23]

Jinjian Xiao, Yingna Xie, and Yubo Wen. 2021. The short-time traffic flow prediction at ramp junction based on wavelet neural network. In 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Vol. 5. IEEE, 664–667.

[24]

10.1016/j.neunet.2024.106365

[25]

10.1016/j.measurement.2024.116274

[26]

10.1109/tits.2025.3555449

[27]

10.1109/tits.2025.3541448

[28]

10.1109/tits.2024.3478816

[29]

10.1109/tits.2019.2935152

[30]

10.1109/tits.2023.3249409

[31]

10.1016/j.inffus.2024.102703

[32]

10.1049/iet-its.2018.5114

Metrics

0

Citations

32

References

Details

Published: Apr 10, 2026

Authors

C

Chaolong Jia