All Issue

2025 Vol.1, Issue 2 Preview Page

Article

Analysis of Aircraft Connection Delay Factors on the Jeju–Gimpo Route Using LIME and SHAP: Impacts of Slot Utilization, Turnaround Time, and Leg Count

LIME·SHAP 기법을 활용한 제주–김포 노선 항공기 연결 지연 요인 분석: 슬롯 사용률, 연결 시간, 구간 수의 영향

Jinseong Ko1
,
Suhyun Lee2
,
Kihan Song3*
고 진성1
,
이 수현2
,
송 기한3*
1Undergraduate’s Course, Department of Civil Engineering, Seoul National University of Science and Technology
2Master’s Course, Department of Civil Engineering, Seoul National University of Science and Technology
3Professor, Department of Civil Engineering, Seoul National University of Science and Technology
1서울과학기술대학교 건설시스템공학과 학부과정
2서울과학기술대학교 건설시스템공학과 석사과정
3서울과학기술대학교 건설시스템공학과 교수
*Corresponding Author
31 December 2025. pp. 98-113
PDF XML Citation
Abstract

This study analyzes the effects of three key factors—slot utilization, turnaround time (TAT), and leg count (LEG)—on aircraft connection delays for the Jeju–Gimpo route using an XGBoost-based prediction model combined with LIME and SHAP techniques. The results show that slot utilization was the most influential factor in most airlines and time periods, while leg count and short turnaround times were identified as major risk factors for low-cost carriers (LCCs). Moreover, slot saturation had a pronounced impact during peak morning and late-night hours, whereas reduced turnaround efficiency was more evident in certain afternoon periods. These findings provide practical insights for developing tailored delay mitigation strategies, including time period- and airline-specific schedule adjustments and ensuring sufficient turnaround buffers.

Keywords
Connection Delay
LIME
SHAP
Turnaround Time
Flight-Leg Count
Slot Saturation

본 연구는 제주–김포 노선의 항공기 연결 지연을 대상으로 슬롯 사용률, 연결 시간(TAT), 구간 수(leg count, LEG 수) 등 세 가지 주요 요인의 영향을 XGBoost 기반 예측 모델과 LIME·SHAP 기법으로 분석하였다. 분석 결과, 대부분의 항공사와 시간대에서 슬롯 사용률이 지연 발생에 가장 큰 기여 요인으로 나타났으며, LCC에서는 구간 수와 짧은 연결 시간이 주요 위험 요인으로 확인되었다. 또한 혼잡도가 높은 오전·야간에는 슬롯 포화의 영향이, 오후 일부 시간대에는 회전율 저하의 영향이 두드러졌다. 이러한 결과는 시간대별·항공사별 맞춤형 스케쥴 조정과 연결 시간 완충 확보 등 지연 완화 전략 수립에 실질적 근거를 제공한다.

키워드
연결 지연
LIME
SHAP
항공기 연결 시간
항공기 구간 수
슬롯 사용률
References
1

항공정보포털시스템 항공통계자료, https://www.airportal.go.kr/stats/transport/totalData.do, 2025.08.26.

2

EUROCONTROL (2023), All-Causes Delays to Air Transport in Europe – Annual 2022, Brussels: EUROCONTROL Central Office for Delay Analysis (CODA).

3

IATA (2023), “Worldwide Airport Slot Guidelines”, p.6.

4

Atallah S., Hotle S. (2022), Evaluation of Airport Size and Delay Causal Factor Effects on Delay Propagation Dissipation, Transportation Research Record, 2676(3), p.608-620.

10.1177/03611981211055663
5

Zheng Z., Wei W., Hu M. (2021), A Comparative Analysis of Delay Propagation on Departure and Arrival Flights for a Chinese Case Study, Aerospace, 8(8), p.212.

10.3390/aerospace8080212
6

Rodríguez-Sanz Á., Comendador F. G., Valdés R. A., Pérez-Castán J. A. (2018), Characterization and Prediction of the Airport Operational Saturation, Journal of Air Transport Management, 69, p.147-172.

10.1016/j.jairtraman.2018.03.002
7

Hao L., Hansen M., Zhang Y., Post J. (2014), New York, New York: Two Ways of Estimating the Delay Impact of New York Airports, Transportation Research Part E: Logistics and Transportation Review, 70, p.245-260.

10.1016/j.tre.2014.07.004
8

Fricke H., Schultz M. (2009, June), Delay Impacts onto Turnaround Performance, In ATM Seminar.

9

Yıldız S., Aydemir O., Memiş A., Varlı S. (2022), A Turnaround Control System to Automatically Detect and Monitor the Time Stamps of Ground Service Actions in Airports: A Deep Learning and Computer Vision Based Approach, Engineering Applications of Artificial Intelligence, 114, p.105032.

10.1016/j.engappai.2022.105032
10

AhmadBeygi S., Cohn A., Guan Y., Belobaba P. (2008), Analysis of the Potential for Delay Propagation in Passenger Airline Networks, Journal of Air Transport Management, 14(5), p.221-236.

10.1016/j.jairtraman.2008.04.010
11

Wu C. L., Caves R. E. (2003), Flight Schedule Punctuality Control and Management: A Stochastic Approach, Transportation Planning and Technology, 26(4), p.313-330.

10.1080/03081060310001635869
12

Rebollo J. J., Balakrishnan H. (2014), Characterization and Prediction of Air Traffic Delays, Transportation Research Part C: Emerging Technologies, 44, p.231-241.

10.1016/j.trc.2014.04.007
13

Fleurquin P., Ramasco J. J., Eguiluz V. M. (2013), Systemic Delay Propagation in the US Airport Network, Scientific Reports, 3(1), p.1159.

10.1038/srep0115923362459PMC3557445
14

Ma Z., Jørgensen B. N., Ma Z. G. (2023, October), A Novel Hybrid Feature Importance and Feature Interaction Detection Framework for Predictive Optimization in Industry 4.0 Applications, In IECON 2023-49th Annual Conference of the IEEE Industrial Electronics Society (p.1-6), IEEE.

10.1109/IECON51785.2023.10312491
15

Santhiya P., Jebadurai I. J., Paulraj G. L., Kirubakaran S. S., Keren L. R. (2024), Explainable Artificial Intelligence for Traffic Signal Detection Using LIME Algorithm, International Journal of Informatics and Communication Technology (IJ-ICT), 13(3), p.527.

10.11591/ijict.v13i3.pp527-536
16

Brito L. C., Susto G. A., Brito J. N., Duarte M. A. (2022), An Explainable Artificial Intelligence Approach for Unsupervised Fault Detection and Diagnosis in Rotating Machinery, Mechanical Systems and Signal Processing, 163, p.108105.

10.1016/j.ymssp.2021.108105
17

Hatıpoğlu I., Tosun O. (2024), Predictive Modeling of Flight Delays at an Airport Using Machine Learning Methods, Applied Sciences, 14(13), p.5472.

10.3390/app14135472
18

Jmoona W., Ahmed M. U., Islam M. R., Barua S., Begum S., Ferreira A., Cavagnetto N. (2023, June), Explaining the Unexplainable: Role of XAI for Flight Take-Off Time Delay Prediction, In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp.81-93), Cham: Springer Nature Switzerland.

10.1007/978-3-031-34107-6_7
19

Xie Y., Pongsakornsathien N., Gardi A., Sabatini R. (2021), Explanation of Machine-Learning Solutions in Air-Traffic Management, Aerospace, 8(8), p.224.

10.3390/aerospace8080224
20

Lee C., Kim D., Kim H., Baik H. (2022), Correlation Analysis between Delay and Turnaround Time at Jeju International Airport, Journal of the Korean Society for Aviation and Aeronautics, 30(1), p.1-11.

10.12985/ksaa.2022.30.1.001
21

Choi S., Kim S. H., Lee S. H., Suh W., Elkosantini S., Lee S. M., Song K. H. (2025), How the Pandemic Changes the Factors Influencing Aircraft Utilization: The Case of Korea, Applied Sciences, 15(15), p.8405.

10.3390/app15158405
22

Ribeiro M. T., Singh S., Guestrin C. (2016, August), “Why Should I Trust You?” Explaining the Predictions of Any Classifier, In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (p.1135-1144).

10.1145/2939672.2939778
23

Lundberg S. M., Lee S. I. (2017), A Unified Approach to Interpreting Model Predictions, Advances in Neural Information Processing Systems, 30.

24

Van den Broeck G., Lykov A., Schleich M., Suciu D. (2022), On the Tractability of SHAP Explanations, Journal of Artificial Intelligence Research, 74, p.851-886.

10.1613/jair.1.13283
Information
  • Publisher :The Korean Society of Airport
  • Publisher(Ko) :한국공항학회
  • Journal Title :Journal of the Korean Society of Airport
  • Journal Title(Ko) :한국공항학회지
  • Volume : 1
  • No :2
  • Pages :98-113
  • Received Date : 2025-08-08
  • Revised Date : 2025-11-28
  • Accepted Date : 2025-12-19
  • DOI :https://doi.org/10.23379/jkosap.1.2.98
Journal Informaiton Journal of the Korean Society of Airport Journal of the Korean Society of Airport
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • KCI 문헌 유사도 검사
  • orcid
  • open access
Journal Informaiton Journal Informaiton - close