A Spatial-Temporal Approach for Multi-Airport Traffic Flow Prediction Through Causality Graphs
Pages 532 - 544
Abstract
Accurate airport traffic flow estimation is crucial for the secure and orderly operation of the aviation system. Recent advances in machine learning have achieved promising prediction results in the single-airport scenario. However, these works overlook the variational spatial interactions hidden among airports and show limited performances on the traffic flow prediction task for the aviation system which is composed of several airports. In this paper, we consider the multi-airport scenario and propose a novel spatio-temporal hybrid deep learning model to efficiently capture spatial correlations as well as temporal dependencies in a parallelized way. Specifically, we introduce the causal inference among airports to model their interactions and thus construct adaptive causality graphs in a data-driven manner to address the heterogeneity of airports. Furthermore, given that multi-source features are not applicable for all airports, a feature mask module is designated to adaptively select the features in spatial information mining. Extensive experiments are conducted on the real data of top-30 busiest airports in China. The results show that our spatio-temporal deep learning approach is superior to state-of-the-art methodologies and the improvement ratio is up to 4.7% against benchmarks. Ablation studies emphasize the power of the proposed adaptive causality graph and the feature mask module. All of these prove the effectiveness of the proposed methodology.
References
[1]
T. H. Oum, C. Yu, and X. Fu, “A comparative analysis of productivity performance of the world’s major airports: Summary report of the ATRS global airport benchmarking research report—2002,” J. Air Transp. Manage., vol. 9, no. 5, pp. 285–297, Sep. 2003. 10.1016/S0969-6997(03)00037-1.
[2]
W.-B. Du, M.-Y. Zhang, Y. Zhang, X.-B. Cao, and J. Zhang, “Delay causality network in air transport systems,” Transp. Res. E, Logistics Transp. Rev., vol. 118, pp. 466–476, Oct. 2018. 10.1016/j.tre.2018.08.014.
[3]
European Air Traffic Control Delays Loom over Summer Air Travel. Accessed: Oct. 11, 2022. [Online]. Available: https://www.iata.org/en/pressroom/pr/2018-07-18-01/
[4]
(2013). Challenges of Growth 2013: The Effect of Air Traffic Network Congestion in 2035. EUROCONTROL, Brussels, Belgium. [Online]. Available: https://www.eurocontrol.int/sites/default/files/content/documents/officialdocuments/reports/201306-challenges-of-growth-2013-summary-report.pdf
[5]
R. Kicinger, J.-T. Chen, M. Steiner, and J. Pinto, “Airport capacity prediction with explicit consideration of weather forecast uncertainty,” J. Air Transp., vol. 24, no. 1, pp. 18–28, Jan. 2016. 10.2514/1.D0017.
[6]
M. C. R. Murça and R. J. Hansman, “Predicting and planning airport acceptance rates in metroplex systems for improved traffic flow management decision support,” Transp. Res. C, Emerg. Technol., vol. 97, pp. 301–323, Dec. 2018. 10.1016/j.trc.2018.10.020.
[7]
D. Guo, E. Q. Wu, Y. Wu, J. Zhang, R. Law, and Y. Lin, “FlightBERT: Binary encoding representation for flight trajectory prediction,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 2, pp. 1828–1842, Feb. 2023. 10.1109/TITS.2022.3219923.
[8]
Y. Lin, L. Deng, Z. Chen, X. Wu, J. Zhang, and B. Yang, “A real-time ATC safety monitoring framework using a deep learning approach,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 11, pp. 4572–4581, Nov. 2020. 10.1109/TITS.2019.2940992.
[9]
C. Yang, J. Mao, X. Qian, and P. Wei, “Designing robust air transportation networks via minimizing total effective resistance,” IEEE Trans. Intell. Transp. Syst., vol. 20, no. 6, pp. 2353–2366, Jun. 2019. 10.1109/TITS.2018.2868955.
[10]
L. Zhaoet al., “T-GCN: A temporal graph convolutional network for traffic prediction,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 9, pp. 3848–3858, Sep. 2020. 10.1109/TITS.2019.2935152.
[11]
C. Zhao, Y. Lv, J. Jin, Y. Tian, J. Wang, and F.-Y. Wang, “DeCAST in TransVerse for parallel intelligent transportation systems and smart cities: Three decades and beyond,” IEEE Intell. Transp. Syst. Mag., vol. 14, no. 6, pp. 6–17, Nov. 2022. 10.1109/MITS.2022.3199557.
[12]
W. Zhanget al., “AdapGL: An adaptive graph learning algorithm for traffic prediction based on spatiotemporal neural networks,” Transp. Res. C, Emerg. Technol., vol. 139, Jun. 2022, Art. no. 10.1016/j.trc.2022.103659.
[13]
Z. Li, G. Xiong, Z. Wei, Y. Lv, N. Anwar, and F.-Y. Wang, “A semisupervised end-to-end framework for transportation mode detection by using GPS-enabled sensing devices,” IEEE Internet Things J., vol. 9, no. 10, pp. 7842–7852, May 2022. 10.1109/JIOT.2021.3115239.
[14]
Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang, “Traffic flow prediction with big data: A deep learning approach,” IEEE Trans. Intell. Transp. Syst., vol. 16, no. 2, pp. 865–873, Apr. 2015. 10.1109/TITS.2014.2345663.
[15]
J. Ke, S. Feng, Z. Zhu, H. Yang, and J. Ye, “Joint predictions of multi-modal ride-hailing demands: A deep multi-task multi-graph learning-based approach,” Transp. Res. C, Emerg. Technol., vol. 127, Jun. 2021, Art. no. 10.1016/j.trc.2021.103063.
[16]
J. Tang, J. Liang, F. Liu, J. Hao, and Y. Wang, “Multi-community passenger demand prediction at region level based on spatio-temporal graph convolutional network,” Transp. Res. C, Emerg. Technol., vol. 124, Mar. 2021, Art. no. 10.1016/j.trc.2020.102951.
[17]
M. Xu, Y. Di, H. Yang, X. Chen, and Z. Zhu, “Multi-task supply-demand prediction and reliability analysis for docked bike-sharing systems via transformer-encoder-based neural processes,” Transp. Res. C, Emerg. Technol., vol. 147, Feb. 2023, Art. no. 10.1016/j.trc.2023.104015.
[18]
W.-B. Du, X.-L. Zhou, O. Lordan, Z. Wang, C. Zhao, and Y.-B. Zhu, “Analysis of the Chinese airline network as multi-layer networks,” Transp. Res. E, Logistics Transp. Rev., vol. 89, pp. 108–116, May 2016. 10.1016/j.tre.2016.03.009.
[19]
K. Cai, Y. Li, Y.-P. Fang, and Y. Zhu, “A deep learning approach for flight delay prediction through time-evolving graphs,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 8, pp. 11397–11407, Aug. 2022. 10.1109/TITS.2021.3103502.
[20]
Y. Jianget al., “Spatial–temporal graph data mining for IoT-enabled air mobility prediction,” IEEE Internet Things J., vol. 9, no. 12, pp. 9232–9240, Jun. 2022. 10.1109/JIOT.2021.3090265.
[21]
B. Li, W. Du, Y. Zhang, J. Chen, K. Tang, and X. Cao, “A deep unsupervised learning approach for airspace complexity evaluation,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 8, pp. 11739–11751, Aug. 2022. 10.1109/TITS.2021.3106779.
[22]
T. H. Oum and C. Yu, “Measuring airports’ operating efficiency: A summary of the 2003 ATRS global airport benchmarking report,” Transp. Res. E, Logistics Transp. Rev., vol. 40, no. 6, pp. 515–532, Nov. 2004. 10.1016/j.tre.2004.08.002.
[23]
C. A. Provan, L. Cook, and J. Cunningham, “A probabilistic airport capacity model for improved ground delay program planning,” in Proc. IEEE/AIAA 30th Digit. Avionics Syst. Conf., Seattle, WA, USA, Oct. 2011, pp. 2B6-1–2B6-12. 10.1109/DASC.2011.6095990.
[24]
P.-C.-B. Liu, M. Hansen, and A. Mukherjee, “Scenario-based air traffic flow management: From theory to practice,” Transp. Res. B, Methodol., vol. 42, nos. 7–8, pp. 685–702, Aug. 2008. 10.1016/j.trb.2008.01.002.
[25]
G. Buxi and M. Hansen, “Generating probabilistic capacity profiles from weather forecast: A design-of-experiment approach,” in Proc. 9th USA/Europe Air Traffic Manage. Res. Develop. Seminar, Berlin, Germany, Jun. 2011, pp. 1–10.
[26]
Á. Rodríguez-Sanz, F. G. Comendador, R. A. Valdés, J. Pérez-Castán, R. B. Montes, and S. C. Serrano, “Assessment of airport arrival congestion and delay: Prediction and reliability,” Transp. Res. C, Emerg. Technol., vol. 98, pp. 255–283, Jan. 2019. 10.1016/j.trc.2018.11.015.
[27]
M. Li, “Moving beyond the linear regression model,” J. Manage., vol. 41, no. 1, pp. 71–98, Jan. 2015. 10.1177/0149206314551963.
[28]
Y. Wang, “Prediction of weather impacted airport capacity using RUC-2 forecast,” in Proc. IEEE/AIAA 31st Digit. Avionics Syst. Conf. (DASC), Williamsburg, VA, USA, Oct. 2012, pp. 3C3-1–3C3-12. 10.1109/DASC.2012.6382312.
[29]
S.-L. A. Tien, C. Taylor, E. Vargo, and C. Wanke, “Using ensemble weather forecasts for predicting airport arrival capacity,” J. Air Transp., vol. 26, no. 3, pp. 123–132, Jul. 2018. 10.2514/1.D0105.
[30]
M. C. R. Murça, R. J. Hansman, L. Li, and P. Ren, “Flight trajectory data analytics for characterization of air traffic flows: A comparative analysis of terminal area operations between New York, Hong Kong and Sao Paulo,” Transp. Res. C, Emerg. Technol., vol. 97, pp. 324–347, Dec. 2018. 10.1016/j.trc.2018.10.021.
[31]
M. C. R. Murça and R. J. Hansman, “Identification, characterization, and prediction of traffic flow patterns in multi-airport systems,” IEEE Trans. Intell. Transp. Syst., vol. 20, no. 5, pp. 1683–1696, May 2019. 10.1109/TITS.2018.2833452.
[32]
Y. Wang, “Estimate weather impacted airport capacity using ensemble learning,” in Proc. IEEE/AIAA 30th Digit. Avionics Syst. Conf., Seattle, WA, USA, Oct. 2011, pp. 1–13. 10.1109/DASC.2011.6096196.
[33]
L. J. G. Andy, S. Alam, R. Piplani, N. Lilith, and I. Dhief, “A decision-tree based continuous learning framework for real-time prediction of runway capacities,” in Proc. Integr. Commun. Navigat. Surveill. Conf. (ICNS), Dulles, VA, USA, Apr. 2021, pp. 1–14. 10.1109/ICNS52807.2021.9441617.
[34]
A. Churchill, W. J. Coupe, and Y. C. Jung, “Predicting arrival and departure runway assignments with machine learning,” in Proc. AIAA Aviation Forum, Aug. 2021, p. 2400. https://doi.org/10.2514/6.2021-2400
[35]
S. El Hihi and Y. Bengio, “Hierarchical recurrent neural networks for long-term dependencies,” in Proc. 8th Int. Conf. Neural Inf. Process. Syst., Cambridge, MA, USA, Nov. 1995, pp. 493–499.
[36]
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997. 10.1162/neco.1997.9.8.1735.
[37]
C. Zhang, F. Zhu, X. Wang, L. Sun, H. Tang, and Y. Lv, “Taxi demand prediction using parallel multi-task learning model,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 2, pp. 794–803, Feb. 2022. 10.1109/TITS.2020.3015542.
[38]
J. Guet al., “Recent advances in convolutional neural networks,” Pattern Recognit., vol. 77, pp. 354–377, May 2018. 10.1016/j.patcog.2017.10.013.
[39]
Y. Wang and Y. Zhang, “Prediction of runway configurations and airport acceptance rates for multi-airport system using gridded weather forecast,” Transp. Res. C, Emerg. Technol., vol. 125, Apr. 2021, Art. no. 10.1016/j.trc.2021.103049.
[40]
M. Schultz, S. Reitmann, and S. Alam, “Predictive classification and understanding of weather impact on airport performance through machine learning,” Transp. Res. C, Emerg. Technol., vol. 131, Oct. 2021, Art. no. 10.1016/j.trc.2021.103119.
[41]
S. Choi and Y. J. Kim, “Artificial neural network models for airport capacity prediction,” J. Air Transp. Manage., vol. 97, Oct. 2021, Art. no. 10.1016/j.jairtraman.2021.102146.
[42]
Z. Weiet al., “STGSA: A novel spatial–temporal graph synchronous aggregation model for traffic prediction,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 1, pp. 226–238, Jan. 2023.
[43]
B. Liaoet al., “Deep sequence learning with auxiliary information for traffic prediction,” in Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, London, U.K., Jul. 2018, pp. 537–546. 10.1145/3219819.3219895.
[44]
Y. Seo, M. Defferrard, P. Vandergheynst, and X. Bresson, “Structured sequence modeling with graph convolutional recurrent networks,” in Proc. Int. Conf. Neural Inf. Process., Long Beach, CA, USA, Nov. 2018, pp. 362–373.
[45]
Y. Li, R. Yu, C. Shahabi, and Y. Liu, “Diffusion convolutional recurrent neural network: Data-driven traffic forecasting,” in Proc. Int. Conf. Learn. Represent., 2018, pp. 1–16. [Online]. Available: https://openreview.net/forum?id=SJiHXGWAZ
[46]
G. Jin, F. Li, J. Zhang, M. Wang, and J. Huang, “Automated dilated spatio-temporal synchronous graph modeling for traffic prediction,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 8, pp. 8820–8830, Aug. 2023. 10.1109/TITS.2022.3195232.
[47]
Z. Liet al., “A multi-stream feature fusion approach for traffic prediction,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 2, pp. 1456–1466, Feb. 2022. 10.1109/TITS.2020.3026836.
[48]
Y. Lin, J.-W. Zhang, and H. Liu, “Deep learning based short-term air traffic flow prediction considering temporal–spatial correlation,” Aerosp. Sci. Technol., vol. 93, Oct. 2019, Art. no. 10.1016/j.ast.2019.04.021.
[49]
Z. Yan, H. Yang, F. Li, and Y. Lin, “A deep learning approach for short-term airport traffic flow prediction,” Aerospace, vol. 9, no. 1, p. 11, Dec. 2021. 10.3390/aerospace9010011.
[50]
M. Zanin, S. Belkoura, and Y. Zhu, “Network analysis of Chinese air transport delay propagation,” Chin. J. Aeronaut., vol. 30, no. 2, pp. 491–499, Apr. 2017. 10.1016/j.cja.2017.01.012.
[51]
S. Chen, W. Du, R. Liu, and X. Cao, “Finding spatial and temporal features of delay propagation via multi-layer networks,” Phys. A, Stat. Mech. Appl., vol. 614, Mar. 2023, Art. no. 10.1016/j.physa.2023.128526.
[52]
M. Zhanget al., “Propagation index on airport delays,” Transp. Res. Rec., vol. 2673, no. 8, pp. 536–543, Apr. 2019. 10.1177/0361198119844240.
[53]
Z. Weiet al., “Recurrent attention unit: A simple and effective method for traffic prediction,” in Proc. IEEE Int. Intell. Transp. Syst. Conf. (ITSC), Sep. 2021, pp. 1272–1277. 10.1109/ITSC48978.2021.9564984.
[54]
K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification,” in Proc. Int. Conf. Comput. Vis., Santiago, Chile, Dec. 2015, pp. 1026–1034.
[55]
X. Daiet al., “DeepTrend 2.0: A light-weighted multi-scale traffic prediction model using detrending,” Transp. Res. C, Emerg. Technol., vol. 103, pp. 142–157, Jun. 2019. 10.1016/j.trc.2019.03.022.
[56]
Y. Wang, M. Z. Li, K. Gopalakrishnan, and T. Liu, “Timescales of delay propagation in airport networks,” Transp. Res. E, Logistics Transp. Rev., vol. 161, May 2022, Art. no. 10.1016/j.tre.2022.102687.
[57]
L. Zeng, B. Wang, T. Wang, and Z. Wang, “Research on delay propagation mechanism of air traffic control system based on causal inference,” Transp. Res. C, Emerg. Technol., vol. 138, May 2022, Art. no. 10.1016/j.trc.2022.103622.
[58]
Z. Guo, M. Hao, B. Yu, and B. Yao, “Detecting delay propagation in regional air transport systems using convergent cross mapping and complex network theory,” Transp. Res. E, Logistics Transp. Rev., vol. 157, Jan. 2022, Art. no. 10.1016/j.tre.2021.102585.
[59]
M. Paluš and M. Vejmelka, “Directionality of coupling from bivariate time series: How to avoid false causalities and missed connections,” Phys. Rev. E, Stat. Phys. Plasmas Fluids Relat. Interdiscip. Top., vol. 75, no. 5, May 2007, Art. no. 10.1103/PhysRevE.75.056211.
[60]
R. Vicente, M. Wibral, M. Lindner, and G. Pipa, “Transfer entropy—A model-free measure of effective connectivity for the neurosciences,” J. Comput. Neurosci., vol. 30, no. 1, pp. 45–67, Feb. 2011. 10.1007/s10827-010-0262-3.
[61]
M. Defferrard, X. Bresson, and P. Vandergheynst, “Convolutional neural networks on graphs with fast localized spectral filtering,” in Proc. Adv. Neural Inf. Process. Syst., 2016, pp. 3844–3852.
[62]
W. Du, S. Chen, H. Li, Z. Li, X. Cao, and Y. Lv, “Airport capacity prediction with multisource features: A temporal deep learning approach,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 1, pp. 615–630, Jan. 2023. 10.1109/TITS.2022.3213029.
[63]
W. Du, B. Li, J. Chen, Y. Lv, and Y. Li, “A spatiotemporal hybrid model for airspace complexity prediction,” IEEE Intell. Transp. Syst. Mag., vol. 15, no. 2, pp. 217–224, Mar. 2023. 10.1109/MITS.2022.3204099.
Index Terms
- A Spatial-Temporal Approach for Multi-Airport Traffic Flow Prediction Through Causality Graphs
Index terms have been assigned to the content through auto-classification.
Recommendations
Airport Choice in Multi-airport Regions: An Empirical Study for Chinese Metropolitan Area
ICICTA '08: Proceedings of the 2008 International Conference on Intelligent Computation Technology and Automation - Volume 02In this paper, a multinomial logit (MNL) model is constructed to predict airport choice in a multiple-airport region and estimated using passenger data from Chinese metropolitan area. Four explanatory variables were investigated, namely, access time to ...
Research on Ergonomic Evaluation of Remote Air Traffic Control Tower of Hangzhou Jiande Airport
Engineering Psychology and Cognitive ErgonomicsAbstractRemote air traffic control (ATC) tower technology has been applied in six locations in China, and has achieved good application effects in recent years. When utilizing the technology, the ergonomic evaluation is an important work to ensure the ...
Comments
Information & Contributors
Information
Published In
1558-0016 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Press
Publication History
Published: 04 September 2023
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 27 Jul 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in