Skip to main content
SpringerLink
Log in

Flight Delay Prediction Using Deep Convolutional Neural Network Based on Fusion of Meteorological Data

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Nowadays, the civil aviation industry has a high precision demand of flight delay prediction. To make full use of the characteristics of flight data and meteorological data, two flight delay prediction models using deep convolution neural network based on fusion of meteorological data are proposed in this paper. One is DCNN (Dual-channel Convolutional Neural Network), which refers to the ResNet network structure. The other is SE-DenseNet (Squeeze and Excitation-Densely Connected Convolutional Network), combining the advantages of DenseNet and SENet. Firstly, flight data and meteorological data are fused in the model. Then, both DCNN and SE-DenseNet models are used to extract feature automatically based on the fused flight data set. Finally, the softmax classifier is adopted to predict the flight delay level. For proposed DCNN model, both straight channel and convolution channel are designed to guarantee the lossless transmission of the feature matrix and enhance the patency of the deep network. For proposed SE-DenseNet model, a SE module is added after the convolution layer of each DenseNet block, which can not only enhance the transmission of deep information but also achieve feature recalibration in the feature extraction process. The research results indicate that after considering characteristics of meteorological information, the accuracy of the model can be improved 1% compared with only considering the flight information. The two deep convolutional neural networks proposed in this paper, DCNN and SE-DenseNet, can both effectively improve the prediction accuracies, reaching to 92.1% and 93.19%, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. CAAC (2016) Thirteenth five year plan of China’s civil aviation development. http://www.caac.gov.cn/XXGK/XXGK/TZTG/201702/P020170215609468223808.pdf. Accessed 30 Dec 2016

  2. OAG (2018) Punctuality League 2018. http://www.oag.cn/wp-content/uploads/2018/10/Airlines-Sept2018-CN.pdf. Accessed Sep 2018

  3. Zhang D (2018) Google filed flight delay forecast. Available: http://www.caacnews.com.cn/1/88/201802/t20180202_1240124_wap.html. Accessed 02 Feb 2018

  4. Liu YJ (2009) The estimation of flight delay and propagation based on Bayesian networks. Dissertation, Tianjin University

  5. Xu T, Ding JL, Gu B et al (2009) Forecast warning level of flight delays based on incremental ranking support vector machine. Acta Aeronaut et Astronaut Sin 30(7):1256–1263

    Google Scholar 

  6. Baspinar B, Ure NK, Koyuncu E et al (2016) Analysis of delay characteristics of European air traffic through a data-driven airport-centric queuing network model. IFAC-PapersOnLine 49(3):359–364

    Article  Google Scholar 

  7. Xu N, Donohue G, Laskey KB et al (2005) Estimation of delay propagation in the national aviation system using bayesian networks. In: ATM 2005, Baltimore, MD, United states, pp 353–363

  8. Tu Y, Ball MO, Jank WS (2008) Estimating flight departure delay distributions-a statistical approach with long-term trend and short-term pattern. J Am Stat Assoc 103(481):112–125

    Article  MathSciNet  Google Scholar 

  9. Choi S, Kim YJ, Briceno S et al (2016) Prediction of weather-induced airline delays based on machine learning algorithms. In: DASC 2016, Sacramento, CA, USA, pp 1–6

  10. Klein A, Craun C, Lee R (2010) Airport delay prediction using weather-impacted traffic index (WITI) model. In: DASC 2010, Salt Lake City, Utah, USA, pp 2.B.1.1–2.B.1.13

  11. Cao WD, Lin XY (2011) Forecast warning level of flight delays based on incremental ranking support vector machine. Comput Eng Des 32(5):1770–1776

    Google Scholar 

  12. Cheng H, Li YM, Luo Q et al (2014) Study on flight delay with C4.5 decision tree based prediction method. Syst Eng Theory Pract 34(S1):239–247

    Google Scholar 

  13. Luo YQ, Chen ZJ, Tang JH et al (2015) Flight delay prediction using support vector machine regression. J Transp Syst Eng Inf Technol 15(1):143–149

    Google Scholar 

  14. Chen HY, Wang JD, Tang BG (2009) Early warning model of flight delay based on SVM with incorporated prior knowledge. J Nanjing Univ Aeronaut Astronaut 41(2):243–247

    Google Scholar 

  15. Alonso H,. Loureiro A (2014) Predicting flight departure delay at porto airport: a preliminary study. In: IJCCI 2015, Lisbon, Portugal, pp 93–98

  16. Rebollo JJ, Balakrishnang H (2014) Characterization and prediction of air traffic delays. Transp Res Part C Emerg Technol 44(3):231–241

    Article  Google Scholar 

  17. Gopalakrishnan K, Hamsa BA (2017) A comparative analysis of models for predicting delays in air traffic networks. In: ATM 2017, Seattle, WA, United states

  18. Khanmohammadi S, Tutun S, Kucuk Y (2016) A new multilevel input layer artificial neural network for predicting flight delays at JFK airport. Complex adaptive systems. Los Angeles, USA, pp 237–244

    Google Scholar 

  19. Kim YJ, Choi S, Briceno S et al (2016) A deep learning approach to flight delay prediction. In: DASC 2016, Sacramento, CA, USA, pp 67–72

  20. Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Article  Google Scholar 

  21. Goodfellow LJ, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial networks. https://arxiv.org/pdf/1406.2661.pdf. Accessed 10 Jun 2014

  22. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Neural Inf Process Syst 25(2):1097–1105

    Google Scholar 

  23. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. https://arxiv.org/pdf/1409.1556.pdf. Accessed 10 Apr 2015

  24. Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: CVPR 2015, Boston, MA, United states, pp 1–9

  25. Olaf R, Philipp F, Thomas B (2015) U-Net: Convolutional networks for biomedical image segmentation. https://arxiv.org/pdf/1505.04597.pdf. Accessed 18 May 2015

  26. He K, Zhang X, Ren S (2016) Deep residual learning for image recognition. In: CVPR 2016, Las Vegas, NV, United states, pp 770–778

  27. Huang G, Liu Z, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR 2017, Honolulu, HI, United states, pp 2261–2269

  28. Hu J, Li S, Gang S (2018) Squeeze-and-excitation networks. https://arxiv.org/pdf/1709.01507.pdf. Accessed 25 Oct 2018

  29. Tsoia A-C, Tan S-H (1997) Recurrent neural networks: a constructive algorithm, and its properties. Neuro Comput 15(3–4):309–326

    Google Scholar 

  30. Hochreiter S, Schmmidhuber J (1997) Long short-term memory. Neuro Comput 9(8):1735–1780

    Google Scholar 

  31. Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: AISTATS 2011, Fort Lauderdale, FL, United states, pp 315–323

  32. Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. https://arxiv.org/pdf/1507.06228.pdf. Accessed 23 Oct 2015

  33. Loffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML 2015, Lile, France, pp 448–456

  34. Dumoulin V, Visin F (2018) A guide to convolution arithmetic for deep learning. https://arxiv.org/pdf/1603.07285.pdf. Accessed 11 Jan 2018

  35. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(9):533–536

    Article  Google Scholar 

  36. Shen L, Lin ZC, Huang QM (2016) Relay backpropagation for effective learning of deep convolutional neural networks. In: ECCV 2016, Fort Lauderdale, Amsterdam, The Netherlands, pp 467–482

  37. Mirkhan M, Meybodi MR (2018) Restricted convolutional neural networks. Neural Process Lett. https://doi.org/10.1007/s11063-018-9954-x

    Article  Google Scholar 

  38. Lin J, Yao Y (2019) A fast algorithm for convolutional neural networks using tile-based fast fourier transforms. Neural Process Lett. https://doi.org/10.1007/s11063-019-09981-z

    Article  Google Scholar 

  39. Zoph B, Vasudevan V, Shlens J, et al (2018) Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8697–8710

  40. Chen Y, Li J, Xiao H, et al (2017) Dual path networks. In: Advances in neural information processing systems, pp 4467–4475

  41. Zhang P (2019) Preliminary quantitative study of thunderstorm induced flight delays. Civil Aviation Flight University of China

  42. Tan M, Le QV (2019) Rethinking model scaling for deep convolutional neural networks. In: ICML 2019. https://arxiv.org/pdf/1905.11946.pdf

  43. Xie S, Girshick RB, Dollár P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: CVPR 2017. https://arxiv.org/pdf/1611.05431.pdf

  44. Duta I C, Liu L, Zhu F, Shao L (2020) Improved residual networks for image and video recognition. In: CVPR 2020. https://arxiv.org/abs/2004.04989.pdf

Download references

Acknowledgements

This work was supported by the Natural Science Foundation of China (U1833105), Tianjin Natural Science Foundation (19JCYBJC15900) and the Fundamental Research Funds for the Central Universities (3122019185).

Author information

Authors and Affiliations

  1. Tianjin Key Laboratory of Advanced Signal Processing, Civil Aviation University of China, Tianjin, 300300, China

    Jingyi Qu, Ting Zhao, Meng Ye & Chao Liu

  2. Qingdao Air Traffic Management Station of Civil Aviation of China, East China Air Traffic Control Bureau, Qingdao, 266000, China

    Jiayi Li

Authors
  1. Jingyi Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ting Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Meng Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiayi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jingyi Qu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qu, J., Zhao, T., Ye, M. et al. Flight Delay Prediction Using Deep Convolutional Neural Network Based on Fusion of Meteorological Data. Neural Process Lett 52, 1461–1484 (2020). https://doi.org/10.1007/s11063-020-10318-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-020-10318-4

Keywords

Search

Navigation