Hostname: page-component-857557d7f7-bkbbk Total loading time: 0 Render date: 2025-12-05T17:16:40.524Z Has data issue: false hasContentIssue false
  • English
  • Français

Sector traffic flow prediction based on the attention-improved graph convolutional transformer network (AGC-T)

Published online by Cambridge University Press:  04 December 2025

J. Zhang Open the ORCID record for J. Zhang [Opens in a new window] ,
X. Dong Open the ORCID record for X. Dong [Opens in a new window] ,
X. Zhu Open the ORCID record for X. Zhu [Opens in a new window] ,
W. Tian ,
Y. Peng ,
Y. Zhong ,
Y. Zhang  and
H. Chen Open the ORCID record for H. Chen [Opens in a new window]
J. Zhang
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
X. Dong*
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
X. Zhu
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
W. Tian
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
Y. Peng
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
Y. Zhong
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
Y. Zhang
Affiliation:
State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
H. Chen
Affiliation:
State Key Laboratory of Air Traffic Management System, Nanjing University of Aeronautics and Astronautics, Nanjing, China
*
Corresponding author: X. Dong; Email: dongxiangning@nuaa.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

The improvement of the accuracy and real-time performance of sector traffic flow prediction is of great significance to air traffic management decision-making. Sectors operate under complex spatial structures and time dimensions. Some neural network methods adopt sequence order to gradually transmit information, which makes it difficult to achieve complete parallel training. Not only does it take too long to train, resulting in low training efficiency, but it is also easy to lose the effective correlation information of long sequence data. To this end, a sector traffic flow prediction method based on attention-improved graph convolutional transformer (AGC-T) network is proposed to improve the current traffic prediction problem for sectors. First, the graph structure information and historical traffic data of the sector are input into the graph convolutional network improved based on the attention mechanism to fully capture the spatial relationship with sectors as nodes. Combined with the transformer’s multi-head self-attention mechanism, it can directly focus on the sequence data at any position without gradually transmitting information. Not only does it improve efficiency through parallel training, but the encoder-decoder structure can also mine the information features in the traffic data, focus on the traffic data features of key nodes and more accurately predict sector traffic. Finally, the operation traffic data of sectors in typical areas in central and southern China are taken as an example to analyse the model. The results show that compared with other prediction models, the AGC-T model $RSME$, $MAE$ and ${R^2}$ are 45.16%, 46.78% and 2.63% higher than the GCN model in the 15-min single-day traffic prediction task, and 41.74%, 35.27% and 1.20% higher than the GRU model. In the single-week traffic prediction task, $RSME$, $MAE$ and ${R^2}$ are 37.12%, 40.54% and 3.55% higher than the GCN model, and 35.15%, 35.17% and 0.65% higher than the GRU model, respectively, showing better prediction performance. This study will help air navigation service providers (ANSP) to make sector traffic predictions more accurately, thereby implementing more scientific and reasonable traffic management measures.

Keywords

air transportationtraffic predictiongraph convolutional networkattention mechanismsector

Information

Type
Research Article
Information
The Aeronautical Journal , First View , pp. 1 - 23
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of Royal Aeronautical Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Zhang, Z., Hao, Z. and Gao, Z. A dynamic adjustment and distribution method of air traffic flow en-route, J. Air Transp. Manag., 2015, 42, pp 15–20, https://doi.org/10.1016/j.jairtraman.2014.07.007 CrossRefGoogle Scholar
Murça, M.C.R. and Hansman, R.J. Predicting and planning airport acceptance rates in metroplex systems for improved traffic flow management decision support, Transp. Res. C Emerg. Technol., 2018, 97, pp 301–323, https://doi.org/10.1016/j.trc.2018.10.020 CrossRefGoogle Scholar
Starita, S., Strauss, A.K., Fei, X., Jovanović, R., Ivanov, N., Pavlović, G. and Fichert, F. Air traffic control capacity planning under demand and capacity provision uncertainty, Transp. Sci., 2020, 54, pp 882–896, https://doi.org/10.1287/trsc.2019.0962 CrossRefGoogle Scholar
Jiang, W., Luo, J., He, M. and Gu, W. Graph neural network for traffic forecasting: The research progress, IJGI, 2023, 12, p 100, 2007, 43, (3), pp 192–236, https://doi.org/10.3390/ijgi12030100 CrossRefGoogle Scholar
Jiang, W. and Luo, J. Graph neural network for traffic forecasting: A survey, Exp. Syst. Appl., 2022, 207, p 117921, https://doi.org/10.1016/j.eswa.2022.117921 CrossRefGoogle Scholar
Hu, Y., Xu, B., Bard, J.F., Chi, H. and Gao, M. Optimization of multi-fleet aircraft routing considering passenger transiting under airline disruption, Comput. Ind. Eng., 2015, 80, pp 132–144, https://doi.org/10.1016/j.cie.2014.11.026 CrossRefGoogle Scholar
Jilkov, V.P., Ledet, J.H. and Li, X.R. Multiple model method for aircraft conflict detection and resolution in intent and weather uncertainty, IEEE Trans. Aerosp. Electron. Syst., 2019, 55, pp 1004–1020, https://doi.org/10.1109/TAES.2018.2867698 CrossRefGoogle Scholar
Matsuno, Y., Tsuchiya, T., Wei, J., Hwang, I. and Matayoshi, N. Stochastic optimal control for aircraft conflict resolution under wind uncertainty, Aerosp. Sci. Technol., 2015, 43, pp 77–88, https://doi.org/10.1016/j.ast.2015.02.018 CrossRefGoogle Scholar
Li, Q., Zhang, Y. and Su, R. A flow-based flight scheduler for en-route air traffic management, IFAC-PapersOnLine, 2016, 49, pp 353–358, https://doi.org/10.1016/j.ifacol.2016.07.059 CrossRefGoogle Scholar
Lin, Y., Zhang, J. and Liu, H. An algorithm for trajectory prediction of flight plan based on relative motion between positions, Front. Inf. Technol. Electron. Eng., 2018, 19, pp 905–916, https://doi.org/10.1631/FITEE.1700224 CrossRefGoogle Scholar
Vardaro, A., Doan, C.T., Chandra, K. and Mehta, V. Graph time-series mixture models for air traffic prediction, In 2013 Integrated Communications, Navigation and Surveillance Conference (ICNS). IEEE, Herndon, VA, USA, 2013, pp 1–19.10.1109/ICNSurv.2013.6548600CrossRefGoogle Scholar
Qiu, F. and Li, Y. Air traffic flow of genetic algorithm to optimize wavelet neural network prediction, In 2014 IEEE 5th International Conference on Software Engineering and Service Science. IEEE, Beijing, China, 2014, pp 1162–1165.10.1109/ICSESS.2014.6933773CrossRefGoogle Scholar
Zhang, H., Jiang, C. and Yang, L. Forecasting traffic congestion status in terminal areas based on support vector machine, Adv. Mech. Eng., 2016, 8, p 1687814016667384, https://doi.org/10.1177/1687814016667384 CrossRefGoogle Scholar
Wang, Z., Liang, M. and Delahaye, D. A hybrid machine learning model for short-term estimated time of arrival prediction in terminal manoeuvring area, Transp. Res. C Emerg. Technol., 2018, 95, pp 280–294, https://doi.org/10.1016/j.trc.2018.07.019 CrossRefGoogle Scholar
Lin, Y., Zhang, J. and Liu, H. Deep learning based short-term air traffic flow prediction considering temporal–spatial correlation, Aerosp. Sci. Technol., 2019, 93, p 105113, https://doi.org/10.1016/j.ast.2019.04.021 CrossRefGoogle Scholar
Liu, H., Lin, Y., Chen, Z., Guo, D., Zhang, J. and Jing, H. Research on the air traffic flow prediction using a deep learning approach, IEEE Access, 2019, 7, pp 148019–148030, https://doi.org/10.1109/ACCESS.2019.2945821 CrossRefGoogle Scholar
Sun, H., Zhang, C. and Ran, B. Interval prediction for traffic time series using local linear predictor, In Proceedings of the 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No. 04TH8749). IEEE, 2004, pp 410–415, https://doi:10.1109/ITSC.2004.1398934 CrossRefGoogle Scholar
Moravčík, M., Schmid, M., Burch, N., Lisý, V., Morrill, D., Bard, N., Davis, T., Waugh, K., Johanson, M. and Bowling, M. DeepStack: Expert-level artificial intelligence in heads-up no-limit poker, Science, 2017, 356, pp 508–513, https://doi.org/10.1126/science.aam6960 CrossRefGoogle ScholarPubMed
Cho, K, Van Merriënboer, B, Gulcehre, C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation, arxiv preprint arxiv:1406.1078, 2014, https://doi.org/10.3115/v1/D14-1179 CrossRefGoogle Scholar
Van Lint, J.W.C., Hoogendoorn, S.P. and Van Zuylen, H.J. Freeway travel time prediction with state-space neural networks: Modeling state-space dynamics with recurrent neural networks, Transp. Res. Rec. J. Transp. Res. Board, 2002, 1811, pp 30–39, https://doi.org/10.3141/1811-04 CrossRefGoogle Scholar
Sun, Q., Zhang, K., Huang, K., Li, X., Zhang, T. and Xu, T. Enhanced graph convolutional network based on node importance for document-level relation extraction, Neural Comput. Appl., 2022, 34, pp 15429–15439, https://doi.org/10.1007/s00521-022-07223-3 CrossRefGoogle Scholar
Wu, L., Chen, Y., Shen, K., Guo, X., Gao, H., Li, S., Pei, J. and Long, B. Graph neural networks for natural language processing: A survey, FNT Mach. Learn., 2023, 16, pp 119–328, https://doi.org/10.1561/2200000096 CrossRefGoogle Scholar
Cao, P, Zhu, Z, Wang, Z, et al. Applications of graph convolutional networks in computer vision, Neural Comput. Appl., 2022, 34, (16), pp 13387–13405, https://doi.org/10.1007/s00521-022-07368-1 CrossRefGoogle Scholar
Han, K, Wang, Y, Guo, J, et al. Vision GNN: An image is worth graph of nodes, Adv. Neural Inform. Process. Syst., 2022, 35, pp 8291–8303, https://arxiv.org/pdf/2206.00272 Google Scholar
Vo, T. An integrated fuzzy neural supervision and attention-based graph neural network for improving network clustering, Neural Comput. Appl., 2023, 35, pp 24015–24035, https://doi.org/10.1007/s00521-023-08974-3 CrossRefGoogle Scholar
Wu, Y. and Tan, H. Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework, arxiv preprint arxiv:1612.01022, 2016, https://arxiv.org/abs/1612.01022 Google Scholar
Kipf, T.N. and Welling, M. Semi-supervised classification with graph convolutional networks, arxiv preprint arxiv:1609.02907, 2016, https://arxiv.org/abs/1609.02907 Google Scholar
Zhao, L., Song, Y., Zhang, C., Liu, Y., Wang, P., Lin, T., Deng, M. and Li, H. T-GCN: A temporal graph convolutional network for traffic prediction, IEEE Trans. Intell. Transport. Syst., 2020, 21, pp 3848–3858, https://doi.org/10.1109/TITS.2019.2935152 CrossRefGoogle Scholar
Li, Z., Xiong, G., Chen, Y., Lv, Y., Hu, B., Zhu, F. and Wang, F.-Y. A hybrid deep learning approach with GCN and LSTM for traffic flow prediction. In 2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE, Auckland, New Zealand, 2019, pp 1929–1933.10.1109/ITSC.2019.8916778CrossRefGoogle Scholar
Du, W., Chen, S., Li, Z., Cao, X. and Lv, Y. A spatial-temporal approach for multi-airport traffic flow prediction through causality graphs, IEEE Trans. Intell. Transport. Syst., 2024, 25, pp 532–544, https://doi.org/10.1109/TITS.2023.3308903 CrossRefGoogle Scholar
Li, B., Li, Z., Chen, J., Yan, Y., Lv, Y., Du, W. MAST-GNN: A multimodal adaptive spatio-temporal graph neural network for airspace complexity prediction, Transp. Res. C Emerg Technol., 2024, 160, p 104521, https://doi.org/10.1016/j.trc.2024.104521 CrossRefGoogle Scholar
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł. and Polosukhin, I. Attention is all you need, 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 2017, pp 1--15.Google Scholar
Zhang, Y., Xu, S., Zhang, L., Jiang, W., Alam, S. and Xue, D. Short-term multi-step-ahead sector-based traffic flow prediction based on the attention-enhanced graph convolutional LSTM network (AGC-LSTM). Neural Comput. Appl., 2025, 37, pp 14869–14888, https://doi.org/10.1007/s00521-024-09827-3 CrossRefGoogle Scholar
Ba, J.L., Kiros, J.R. and Hinton, G.E. Layer Normalization, arxiv preprint arxiv:1607.06450, 2016, http://arxiv.org/abs/1607.06450 Google Scholar