Abstract
The future airports will head toward a highly intelligent direction, like the unmanned check-in services, while the scale and resources allocation of the ground service are tightly related to the air passenger flow. Therefore, forecasting passenger flow accurately will affect the development of future airports and the optimization of service of civil airlines significantly. As a kind of time series, air passenger flow is influenced by multiple factors, particularly, the stochastic part of seasonality, trend and volatility. These will ultimately affect the accuracy of the prediction. Therefore, this paper introduces a prediction model based on a two-phase learning framework. In phase one, various predictors cope with different features of time series in parallel and the prediction results are integrated in phase two. Furthermore, this paper has compared principal error indicators with actual data and results show that the two-phase learning model performs better than current fusion models and owns stable performance.
Similar content being viewed by others
References
SITA: Air transport industry insights: the baggage report of 2019. https://www.sita.aero/resources/type/surveys-reports/baggage-it-insights-2019 (2019). Accessed 10 Aug 2020
Fildes R, Wei Y, Ismail S (2011) Evaluating the forecasting performance of econometric models of air passenger traffic flows using multiple error measures. Int J Forecast 27:902–922. https://doi.org/10.1016/j.ijforecast.2009.06.002
Guo J, Xie Z, Qin Y, Jia L, Wang Y (2019) Short-term abnormal passenger flow prediction based on the fusion of SVR and LSTM. IEEE Access 7:42946–42955. https://doi.org/10.1109/ACCESS.2019.2907739
Box G (2013) Box and Jenkins: time series analysis, forecasting and control. Palgrave Macmillan, London
Williams BM, Durvasula PK, Brown DE (1998) Urban freeway traffic flow prediction: application of seasonal autoregressive integrated moving average and exponential smoothing models. Transp Res Rec 1644(1):132–141. https://doi.org/10.3141/1644-14
Chatfield C (1978) The holt-winters forecasting procedure. Appl Stat. https://doi.org/10.2307/2347162
Chen Y (2017) The research and applications of time series forecasting methods based on machine learning. Ph.D. thesis, Lanzhou University
Qin D, Yu J, Zou G, Yong R, Zhao Q, Zhang B (2019) A novel combined prediction scheme based on CNN and LSTM for urban pm2.5 concentration. IEEE Access 7:20050–20059. https://doi.org/10.1109/ACCESS.2019.289702810.1109/ACCESS.2019.2897028
Smith B, Demetsky M (1994) Short-term traffic flow prediction: neural network approach. Transp Res Rec 1453:98–104
Ke-wu Y (2009) Study on the forecast of air passenger flow based on SVM regression algorithm. In: 2009 First International Workshop on Database Technology and Applications, pp 325–328. https://doi.org/10.1109/DBTA.2009.33
Laik MN, Choy M, Sen P (2014) Predicting airline passenger load: a case study. In: 2014 IEEE 16th Conference on Business Informatics, vol 1, pp 33–38. https://doi.org/10.1109/CBI.2014.39
Lu P, Wei F, Yang L (2019) Military escape parachute price prediction for small sample based on xgboost. In: 2019 16th International Conference on Service Systems and Service Management (ICSSSM), pp 1–5. https://doi.org/10.1109/ICSSSM.2019.8887752
Dietterich TG (2000) Ensemble methods in machine learning. In: Dietterich TG (eds) Proceedings of the 1st international workshop on multiple classifier systems (MCS), Cagliari, Italy, pp 1–15
Nai W, Liu L, Wang S, Dong D (2017) An emd-sarima-based modeling approach for air traffic forecasting. Algorithms. https://doi.org/10.3390/a10040139
Jiang X, Zhang L, Chen XM (2014) Short-term forecasting of high-speed rail demand: a hybrid approach combining ensemble empirical mode decomposition and gray support vector machine with real-world applications in China. Transp Res C Emerg Technol 44:110–127. https://doi.org/10.1016/j.trc.2014.03.016.
Bergmeir C, Hyndman R, Benítez J (2016) Bagging exponential smoothing methods using STL decomposition and Box–Cox transformation. Int J Forecast 32:303–312. https://doi.org/10.1016/j.ijforecast.2015.07.002
Nieto MR, Carmona-Benítez RB (2018) Arima + garch + bootstrap forecasting method applied to the airline industry. J Air Transp Manag 71:1–8. https://doi.org/10.1016/j.jairtraman.2018.05.007.
Sulistyowati R, Suhartono, Kuswanto H, Setiawan, Astuti ET (2018) Hybrid forecasting model to predict air passenger and cargo in Indonesia. In: 2018 International Conference on Information and Communications Technology (ICOIACT), pp 442–447. https://doi.org/10.1109/ICOIACT.2018.8350816
Bi Xy, Li B, Lu Wl, Zhou Xz (2020) Daily runoff forecasting based on data-augmented neural network model. J Hydroinform 22(4):900–915. https://doi.org/10.2166/hydro.2020.017.
Mostafaeipour A, Goli A, Qolipour M (2018) Prediction of air travel demand using a hybrid artificial neural network (ANN) with bat and firefly algorithms: a case study. J Supercomput 74(10):5461–5484. https://doi.org/10.1007/s11227-018-2452-0.
Larabi Marie-Sainte S, Saba T, Alotaibi S (2019) Air passenger demand forecasting using particle swarm optimization and firefly algorithm. J Comput Theor Nanosci 16:3735–3743. https://doi.org/10.1166/jctn.2019.8242
Liu X, Huang X, Chen L, Qiu Z, Chen M (2017) Prediction of passenger flow at Sanya airport based on combined methods. In: Zou B, Li M, Wang H, Song X, Xie W, Lu Z (eds) Data science. Springer Singapore, Singapore, pp 729–740
Guo F, Polak JW, Krishnan R (2018) Predictor fusion for short-term traffic forecasting. Transp Res C Emerg Technol 92:90–100. https://doi.org/10.1016/j.trc.2018.04.025.
Zhao K, Li L, Cai et al S (2020) An optimized time series combined forecasting method based on neural networks. J Supercomput 7:2986–3012. https://doi.org/10.1007/s11227-019-03064-5
Hierons R (1999) Machine learning. Tom M. Mitchell. published by Mcgrawand#x2010;hill, Maidenhead, U.K., International student edition, 1997. ISBN: 0and#x2010;07and#x2010;115467and#x2010;1, 414 pp. price: U.K. andpound;22.99, soft cover. Software Testing, Verification and Reliability 9(3), 191–193
Diaz-Robles L, Ortega Bravo JC, Fu J, Reed G, Chow J, Watson J, Moncada J (2008) A hybrid arima and artificial neural networks model to forecast particulate matter in urban areas: the case of Temuco, Chile. Atmos Environ 42:8331–8340. https://doi.org/10.1016/j.atmosenv.2008.07.020
Elvira L (2002) Annual electrical peak load forecasting methods with measures of prediction error. Diss Abstr Int 62 Section: B
Ruiz-Aguilar J, Turias I, Jiménez-Come M (2014) Hybrid approaches based on sarima and artificial neural networks for inspection time series forecasting. Transp Res E Logist Transp Rev 67:1–13. https://doi.org/10.1016/j.tre.2014.03.009.
Chemali E, Kollmeyer P, Preindl M, Ahmed R, Emadi A (2017) Long short-term memory-networks for accurate state of charge estimation of li-ion batteries. IEEE Trans Ind Electron PP(99):1
Li J, Li X, He D (2019) A directed acyclic graph network combined with CNN and LSTM for remaining useful life prediction. IEEE Access 7:75464–75475. https://doi.org/10.1109/ACCESS.2019.2919566
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
XingFen W, Xiangbin Y, Yangchun M (2018) Research on user consumption behavior prediction based on improved xgboost algorithm. In: 2018 IEEE International Conference on Big Data (Big Data), pp 4169–4175. https://doi.org/10.1109/BigData.2018.8622235
BTS: Passengers (all U.S. carriers-all airports). https://www.bts.gov/ (2019). Accessed 10 June 2019
Chan PK, Stolfo SJ (1997) On the accuracy of meta-learning for scalable data mining. J Intell Inf Syst 8(1):5–28. https://doi.org/10.1023/A:1008640732416.
Acknowledgements
The authors would like to thank the Bureau of Transportation Statistics of the United States Department of Transportation for providing air passenger traffic flow data, and pay special thanks to Sulistyowati et al. as their work provides useful information to this paper.
Funding
This work is supported by the National Natural Science Foundation of China (Grant No. U1933123).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
No potential conflict of interest was reported by the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, X., Xiang, Y., Mao, G. et al. Forecasting air passenger traffic flow based on the two-phase learning model. J Supercomput 77, 4221–4243 (2021). https://doi.org/10.1007/s11227-020-03428-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-020-03428-2