Estimation of American Air Passenger Miles Using the LSTM Model

Abstract

The Covid-19 epidemic, which emerged in China in 2019, spread all over the world in a short time. Due to the epidemic, many sectors around the world have been adversely affected. Airline passenger transport is also one of the sectors most heavily affected by the Covid-19 outbreak. Airline passenger mile is a frequently used metric in the aviation industry and is obtained by multiplying the number of miles flown by the number of passengers. With the airline passenger mile metric, mobility in the sector can be measured. In this study, a total of 259 data for the American airline passenger mile metric taken from the United Reserve Economic Data (FRED) system between 2000 and 2021 were used. Since the data set used has an upward trend, it does not show a static feature. In addition, it has been observed that it has a seasonality that increases in some seasons of the year and decreases in some seasons, on the contrary. Long Short-Term Memory (LSTM) architecture of Recurrent Neural Networks (RNN), which is one of the deep learning methods, was preferred in this study because it can work with non-stationary data set and can take seasonal effects into account. In order to observe the effect of the sudden change in the trend of the data set during the Covid-19 period on the performance of the LSTM architecture, two separate estimations were made with both the data set containing the Covid-19 period data and the data set not containing the Covid-19 period, and the results were compared. According to the findings, it was seen that the performance of the LSTM architecture was much higher in the predictions made with the data set that did not include the Covid-19 period. The same data set was also estimated with the Autoregressive Model and compared with the performance of the LSTM architecture. Finally, with the LSTM architecture, which gives more successful results, estimations were made with the number of passengers in Turkey between the years 1960-2020.

Keywords

• LSTM
• Airline passenger mile
• Time Series
• Havayolu yolcu mili LSTM modeli Zaman serileri

Amerika Havayolu Yolcu Milinin LSTM ve AR Modeli Kullanılarak Tahmini

Abstract

2019 yılında Çin’de ortaya çıkan Covid-19 salgını kısa sürede tüm Dünya’da yayılmıştır. Salgın sebebiyle küresel çapta birçok sektör olumsuz etkilenmiştir. Havayolu yolcu taşımacılığı da Covid-19 salgınından en yoğun etkilenen sektörlerden biridir. Havayolu yolcu mili havacılık sektöründe sıkça kullanılan bir metrik olup toplam uçulan mil ile toplam yolcu sayısının çarpımı ile elde edilir. Havayolu yolcu mili metriği ile sektördeki hareketlilik ölçülebilmektedir. Bu çalışmada Amerika Birleşik Rezerv Ekonomik Veri (FRED) sisteminden alınan Amerika havayolu yolcu mili metriğine ait 2000 ile 2021 yılları arasında toplam 259 veri kullanılmıştır. Kullanılan veri seti yukarı doğru artış eğilimi barındırdığı için durağan özellik göstermemektedir. Bunun yanında yılın bazı mevsimlerinde artan, bazı mevsimlerinde de tam tersine azalan bir yapıya yani, mevsimselliğe sahip olduğu gözlemlenmiştir. Derin öğrenme metotlarından Tekrarlayan Sinir Ağlarının (RNN) Uzun Kısa Dönem Hafıza (LSTM) mimarisinin durağan olmayan veri seti ile çalışabilmesi ve mevsimsellik etkilerini hesaba katabiliyor olmasından ötürü bu çalışmada tercih edilmiştir. Covid-19 döneminde veri setinin eğiliminde meydana gelen ani değişimin LSTM mimarisinin performansına etkisini gözlemleyebilmek amacıyla hem Covid-19 dönemi verilerini içeren veri seti hem de Covid-19 dönemini içermeyen veri seti ile iki ayrı tahmin yapılmış ve sonuçlar kıyaslanmıştır. Bulgulara göre, Covid-19 dönemini içermeyen veri seti ile yapılan tahminlerde LSTM mimarisinin performansının çok daha yüksek olduğu görülmüştür. Aynı veri setinin Otoregresif Model (AR) ile de tahmini yapılmış ve LSTM mimarisinin performansı ile kıyaslanmıştır. Son olarak daha başarılı sonuçlar veren LSTM mimarisi ile 1960-2020 yılları arasında Türkiye’ye ait yolcu sayısı verileri ile tahmin yapılmıştır.

Keywords

• LSTM
• Havayolları yolcu mili
• Zamaan serileri

References

1. Abbasimehr, H., Shabani & M., Yousefi, M. (2020). An optimized model using LSTM network for demand forecasting. Computers & Industrial Engineering, 143 (2020), 106435. Doi: https://doi.org/10.1016/j.cie.2020.106435
2. Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., Makarenkov, V. & Nahavandi, S. (2021). A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information Fusion, 76 (2021), 243-297. Doi: https://doi.org/10.1016/j.inffus.2021.05.008
3. Alassafi, M. O., Jarrah, M. & Alotaibi, R. (2021). Time series predicting of COVID-19 based on deep learning. Neurocomputing, 468 (2022), 335-344. Doi: https://doi.org/10.1016/j.neucom.2021.10.035
4. Bi, J-W., Li, H. & Fan, Z-P. (2021). Tourism demand forecasting with time series imaging: A deep learning model. Annals of Tourism Research, 90 (2021), 103255. Doi: https://doi.org/10.1016/j.annals.2021.103255
5. Brown, R. S. & Kline, W. A. (2020). Exogenous shocks and managerial preparedness: A study of U.S. airlines’ environmental scanning before the onset of the COVID-19 pandemic. Journal of Air Transport Management, 89 (2020), 101899. Doi: https://doi.org/10.1016/j.jairtraman.2020.101899
6. Cao, W., Sun, S. & Li, H. (2021). A new forecasting system for high-speed railway passenger demand based on residual component disposing. Measurement, 183 (2021), 109762. Doi: https://doi.org/10.1016/j.measurement.2021.109762
7. Chimmula, V. K. R. & Zhang, L. (2020). Time series forecasting of COVID-19 transmission in Canada using LSTM networks. Chaos, Solitons and Fractal, 153 (2020), 109864. Doi: https://doi.org/10.1016/j.chaos.2020.109864
8. Choi, S. & Kim, Y. J. (2021). Artificial neural network models for airport capacity prediction. Journal of Air Transport Management, 97 (2021), 102146. Doi: https://doi.org/10.1016/j.jairtraman.2021.102146

9. Grosche, T., Rothlauf, F. & Heinzl, A. (2007). Gravity models for airline passenger volume estimation. Journal of Air Transport Management, 13 (2007), 175-183. Doi: https://doi.org/10.1016/j.jairtraman.2007.02.001
10. Hanson, D., Delibasi, T. T., Gatti, M. & Cohen, S. (2021). How do changes in economic activity affect air passenger traffic? The use of state-dependent income elasticities to improve aviation forecast. Journal of Air Transport Management, 98 (2022), 102147. Doi: https://doi.org/10.1016/j.jairtraman.2021.102147
11. Hotle, S. & Mumbower, S. (2021). The impact of COVID-19 on domestic U.S. air travel operations and commercial airport service. Transportation Research Interdisciplinary Perspectives, 9 (2021), 100277. Doi: https://doi.org/10.1016/j.trip.2020.100277
12. Iacus, S. M., Natale, F., Santamaria, C., Spyratos, S. & Vespe, M. (2020). Estimating and projecting air passenger traffic during the COVID-19 coronavirus outbreak and its socio-economic impact. Safety Science, 129 (2020), 104791. Doi: https://doi.org/10.1016/j.ssci.2020.104791
13. İç, Y. T. & Civelek, H. (2021). Development of a new model of gross domestic product forecasting. Journal of Turkish Operations Management, 5 (1), 564-575. Erişim adresi: https://dergipark.org.tr/en/pub/jtom/issue/63460/883089
14. İncekara, Ç. Ö. (2020). Türkiye’nin elektrik üretiminde doğalgaz talep tahminleri. Journal of Turkish Operations Management, 4 (2), 494-508. Erişim adresi: https://dergipark.org.tr/en/pub/jtom/issue/59336/851882
15. Karami, Z. & Kashef, R. (2020). Smart transportation planning: Data, models, and algorithms. Transportation Engineering, 2 (2020), 100013. Doi: https://doi.org/10.1016/j.treng.2020.100013
16. Luo, J., Zhang, Z., Fu, Y., & Rao, F. (2021). Time series prediction of COVID-19 transmission in America using LSTM and XGBoost algorithms. Results in Physics, 27 (2021), 104462. Doi: https://doi.org/10.1016/j.rinp.2021.104462
17. Singh, B. (2021). Predicting airline passengers’ loyalty using artificial neural network theory. Journal of Air Transport Management, 94 (2021), 102080. Doi: https://doi.org/10.1016/j.jairtraman.2021.102080
18. Solvoll, G., Mathisen, T. A. & Welde, M. (2020). Forecasting air traffic demand for major infrastructure changes. Research in Transportation Economics, 82 (2020), 100873. Doi: https://doi.org/10.1016/j.retrec.2020.100873
19. Somu, N., Raman M R, G. & Ramamritham, K. (2020). A hybrid model for building energy consumption forecasting using long short term memory networks. Applied Energy, 261 (2020), 114131. Doi: https://doi.org/10.1016/j.apenergy.2019.114131
20. Truong, D. (2021). Estimating the impact of COVID-19 on air travel in the medium and long-term using neural network and Monte Carlo simulation. Journal of Air Transport Management, 96 (2021), 102126. Doi: https://doi.org/10.1016/j.jairtraman.2021.102126
21. Ünsal, M. G. & Kasap, R. (2020). Investigating Covid 19 data for G20, EU and OECD countries via using time series analysis & cluster analysis. Journal of Turkish Operations Management, 4 (2), 424-432. Erişim adresi: https://dergipark.org.tr/en/pub/jtom/issue/59336/851834
22. Yang, Z., Tang, R., Zeng, W., Lu, J. & Zhang, Z. (2021). Short-term prediction of airway congestion index using machine learning methods. Transportation Research Part C, 125 (2021), 103040. Doi: https://doi.org/10.1016/j.trc.2021.103040
23. Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50 (2003), 159–175. Doi: https://doi.org/10.1016/S0925-2312(01)00702-0