Prediction of flight departure delays caused by weather conditions adopting data-driven approaches

Journal of Big Data
Seong‐Eun Kim1, Eunil Park2
1Department of Semiconductor and Display Engineering, Sungkyunkwan University, Seoul, 03063, Republic of Korea
2Department of Interaction Science, Sungkyunkwan University, 25-2 Sungkyunkwan-ro, Jongno-gu, Seoul, 03063, Republic of Korea

Tóm tắt

AbstractIn this study, we utilize data-driven approaches to predict flight departure delays. The growing demand for air travel is outpacing the capacity and infrastructure available to support it. In addition, abnormal weather patterns caused by climate change contribute to the frequent occurrence of flight delays. In light of the extensive network of international flights covering vast distances across continents and oceans, the importance of forecasting flight delays over extended time periods becomes increasingly evident. Existing research has predominantly concentrated on short-term predictions, prompting our study to specifically address this aspect. We collected datasets spanning over 10 years from three different airports such as ICN airport in South Korea, JFK and MDW airport in the United States, capturing flight information at six different time intervals (2, 4, 8, 16, 24, and 48 h) prior to flight departure. The datasets comprise 1,569,879 instances for ICN, 773,347 for JFK, and 404,507 for MDW, respectively. We employed a range of machine learning and deep learning approaches, including Decision Tree, Random Forest, Support Vector Machine, K-nearest neighbors, Logistic Regression, Extreme Gradient Boosting, and Long Short-Term Memory, to predict flight delays. Our models achieved accuracy rates of 0.749 for ICN airport, 0.852 for JFK airport, and 0.785 for MDW airport in 2-h predictions. Furthermore, for 48-h predictions, our models achieved accuracy rates of 0.748 for ICN airport, 0.846 for JFK airport, and 0.772 for MDW airport based on our experimental results. Consequently, we have successfully validated the accuracy of flight delay predictions for longer time frames. The implications and future research directions derived from these findings are also discussed.

Từ khóa


Tài liệu tham khảo

Economics-IATA: air passenger market analysis 2014. 2014.

Economics-IATA: air passenger market analysis 2023. 2023. https://www.iata.org/en/iata-repository/publications/economic-reports/air-passenger-market-analysis2/.

Efthymiou M, Njoya ET, Lo PL, Papatheodorou A, Randall D. The impact of delays on customers’ satisfaction: an empirical analysis of the British airways on-time performance at Heathrow airport. J Aerosp Technol Manag. 2018;11:e0219.

Tileagă C, Oprisan O. Flights delay compensation 261/2004: a challenge for airline companies? In: Organizations and Performance in a complex world: 26th international economic conference of Sibiu (IECS) 26. Springer; 2021. p. 335–44.

U.S.D. of transportation, airline on-time performance data. 2023. https://www.transtats.bts.gov/tables.asp?QO_VQ=EFD &QO_anzr=Nv4yv0r.

Sim G-M, Kim Y-S, Jung M-P, Kim J-W, Park M-S, Hong S-H, Kang K-K. Changes in the frequency of abnormal weather events in South Korea in recent years. J Korean Soc Clim Change. 2018;9(4):461–70.

Lee J-W, Yoo H-I, Kim G-H. Analysis of South Korea’s heavy rain characteristics from 2006 to 2015 using AWS data. In: Proceedings of the Korean meteorological society conference. 2016. p. 521–2.

Kim YJ, Choi S, Briceno S, Mavris D. A deep learning approach to flight delay prediction. In: 2016 IEEE/AIAA 35th digital avionics systems conference (DASC). IEEE; 2016. p. 1–6.

Khaksar H, Sheikholeslami A. Airline delay prediction by machine learning algorithms. Scientia Iranica. 2019;26(5):2689–702.

Qu J, Wu S, Zhang J. Flight delay propagation prediction based on deep learning. Mathematics. 2023;11(3):494.

Al-Tabbakh SM, El-Zahed H. Machine learning techniques for analysis of Egyptian flight delay. J Sci Res Sci. 2018;35(part 1):390–9.

Ye B, Liu B, Tian Y, Wan L. A methodology for predicting aggregate flight departure delays in airports based on supervised learning. Sustainability. 2020;12(7):2749.

Atlioğlu MC, Bolat M, Şahin M, Tunali V, Kilinç D. Supervised learning approaches to flight delay prediction. Sakarya Univ J Sci. 2020;24(6):1223–31.

Yazdi MF, Kamel SR, Chabok SJM, Kheirabadi M. Flight delay prediction based on deep learning and Levenberg–Marquart algorithm. J Big Data. 2020;7:1–28.

Lee J, Cha J, Park E. Data-driven approaches into political orientation and news outlet discrimination: the case of news articles in south korea. Telemat Inform. 2023;85: 102066.

Gao Z, Gatpandan MP, Gatpandan PH. Classification decision tree algorithm in predicting students’ course preference. In: 2021 2nd international symposium on computer engineering and intelligent communications (ISCEIC). IEEE; 2021. p. 93–7.

Sharma A, Sharma M, Dwivedi R. Improved decision tree classification (IDT) algorithm for social media data. In: 2021 10th international conference on system modeling & advancement in research trends (SMART). IEEE; 2021. p. 155–7.

Kim E, Ji H, Kim J, Park E. Classifying apartment defect repair tasks in South Korea: a machine learning approach. J Asian Archit Build Eng. 2022;21(6):2503–10.

Soumya A, Kumar GH. Classification of ancient epigraphs into different periods using random forests. In: 2014 fifth international conference on signal and image processing. IEEE; 2014. p. 171–8.

Ardiansyah D, Mantoro T, Syafei WA. Potential classification prediction of solar and wind energy in Indonesia using machine learning with random forest algorithm. In: 2022 5th international conference of computer and informatics engineering (IC2IE). IEEE; 2022. p. 297–302.

Lee J, Park E. D-HRSP: dataset of helpful reviews for service providers. Telemat Inform. 2023;82:102001.

Fadhil IM, Sibaroni Y. Topic classification in Indonesian-language tweets using fast-text feature expansion with support vector machine (SVM). In: 2022 international conference on data science and its applications (ICoDSA). IEEE; 2022. p. 214–9.

Charan PVS, Ramkumar G. Black fungus classification using Adaboost with SVM-based classifier and compare accuracy with support vector machine. In: 2022 5th international conference on contemporary computing and informatics (IC3I). IEEE; 2022. p. 1895–901.

Hwang S, Ahn H, Park E. iMovieRec: a hybrid movie recommendation method based on a user-image-item model. Int J Mach Learn Cybern. 2023;14:3205–16.

Auleria M, Arrahmah AI, Saputra DE. A review on KN nearest neighbour based classification for object recognition. In: 2021 international conference on data science and its applications (ICoDSA). 2021; IEEE. p. 274–80.

Kim S, An C, Cha J, Kim D, Park E. D-visa: a dataset for detecting visual sentiment from art images. In: Proceedings of the IEEE/CVF international conference on computer vision. 2023. p. 3051–9.

Akoulih M, Tigani S, Saadane R, Tazi A. Electrocoagulation based chromium removal efficiency classification using logistic regression. Appl Sci. 2020;10(15):5179.

Guan X, Zhang J, Chen S. Logistic regression based on statistical learning model with linearized kernel for classification. Comput Inform. 2021;40(2):298–317.

Paleczek A, Grochala D, Rydosz A. Artificial breath classification using XGBoost algorithm for diabetes detection. Sensors. 2021;21(12):4187.

Liang H, Li J, Wu H, Li L, Zhou X, Jiang X. Mammographic classification of breast cancer microcalcifications through extreme gradient boosting. Electronics. 2022;11(15):2435.

Lee S, Jeong D, Park E. MultiEmo: multi-task framework for emoji prediction. Knowl-Based Syst. 2022;242: 108437.

Hur Y. Malaysian name-based ethnicity classification using LSTM. KSII Trans Internet Inf Syst. 2022;16(12):3855–67.

Zerrouki N, Houacine A, Harrou F, Bouarroudj R, Cherifi MY, Sun Y. Exploiting deep learning-based LSTM classification for improving hand gesture recognition to enhance visitors’ museum experiences. In: 2022 international conference on innovation and intelligence for informatics, computing, and technologies (3ICT). IEEE; 2022. p. 451–6.

Madanan M, Venugopal A, Velayudhan NC. A hybrid anomaly based intrusion detection methodology using IWD for LSTM classification. In: 2020 IEEE international conference on advanced networks and telecommunications systems (ANTS). IEEE; 2020. p. 1–5.

Lee S, Kim J, Kim D, Kim KJ, Park E. Computational approaches to developing the implicit media bias dataset: assessing political orientations of nonpolitical news articles. Appl Math Comput. 2023;458:128219.

Lee S, Kim J, Park E. Can book covers help predict bestsellers using machine learning approaches? Telemat Inform. 2023;78: 101948.

Park E. CRNet: a multimodal deep convolutional neural network for customer revisit prediction. J Big Data. 2023;10(1):1–10.

Oh S, Ji H, Kim J, Park E, del Pobil AP. Deep learning model based on expectation–confirmation theory to predict customer satisfaction in hospitality service. Inform Technol Tour. 2022;24(1):109–26.

Yu H, Park E. A harmless webtoon for all: an automatic age-restriction prediction system for webtoon contents. Telemat Inform. 2023;76: 101906.

Incheon airport weather. https://data.kma.go.kr/data/air/selectAmosRltmList.do?pgmNo=575 &tabNo=1.

New York City weather. https://www.wunderground.com/history/daily/us/ny/new-york-city/KLGA.

Chicago City weather. https://www.wunderground.com/history/daily/us/il/chicago/KMDW.

Incheon air port flight. https://www.airport.kr/co/ko/cpr/statisticOfDelay.do.

United States Department of Transport. https://www.transtats.bts.gov/tables.asp?QO_VQ=EFD &QO_anzr=Nv4yv0r.

Panda B, Adhikari RK. A method for classification of missing values using data mining techniques. In: 2020 international conference on computer science, engineering and applications (ICCSEA). IEEE; 2020. p. 1–5.

Thông tin
Thông tin xuất bản

Journal of Big Data

Thông tin tác giả