Journal of the Korean Society for Aeronautical & Space Sciences (한국항공우주학회지)

The Korean Society for Aeronautical and Space Sciences (한국항공우주학회)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning Based Capacity Prediction Model of Terminal Maneuvering Area

기계학습 기반 접근관제구역 수용량 예측 모형

  • Received : 2021.11.29
  • Accepted : 2022.02.17
  • Published : 2022.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of air traffic flow management is to balance demand and capacity in the national airspace, and its performance relies on an accurate capacity prediction of the airport or airspace. This paper developed a regression model that predicts the number of aircraft actually departing and arriving in a terminal maneuvering area. The regression model is based on a boosting ensemble learning algorithm that learns past aircraft operational data such as time, weather, scheduled demand, and unfulfilled demand at a specific airport in the terminal maneuvering area. The developed model was tested using historical departure and arrival flight data at Incheon International Airport, and the coefficient of determination is greater than 0.95. Also, the capacity of the terminal maneuvering area of interest is implicitly predicted by using the model.

항공교통흐름관리의 목적은 공항 및 공역의 수용량 안에서 항공교통 수요를 만족시키는 것이다. 그러므로 수용량을 정확하게 예측하는 것은 항공교통흐름관리의 성능에 많은 영향을 준다. 본 논문은 특정 공항의 예상 출·도착 수요, 시각, 기상 및 실제 처리한 항공기 대수 등 과거의 항공기운항 데이터를 기계학습의 한 방법론인 부스팅 앙상블 알고리즘으로 학습하여 시간당 출·도착하는 항공기의 수를 예측하는 회귀모형을 개발하였다. 기계학습을 통해 도출된 모델은 실제 인천국제공항의 출·도착 항공편 데이터를 이용해 검증하였으며, 결정계수가 0.95 이상으로 나타났다. 이 모델을 이용하여 접근관제구역의 수용량을 간접적으로 예측할 수 있었다.

Keywords

Acknowledgement

본 연구는 국토교통부/국토교통과학기술진흥원의 '데이터기반 항공교통관리 기술개발' 과제의 지원으로 수행되었습니다(과제번호 21DATM-C163373-01).

References

  1. "Air Transport, Registered Carrier Departures Worldwide," World Bank Group, retrieved 22 November 2021. https://data.worldbank.org/indicator/IS.AIR.DPRT?end=2019&start=2009
  2. Pearce, B., "COVID-19: An almost full recovery of air travel in prospect," IATA, 26 May 2021. https://www.iata.org/en/iata-repository/publications/economic-reports/an-almost-full-recovery-of-air-travel-in-prospect/
  3. "Manual on Collaborative Air Traffic Flow Management (ATFM)," ICAO Doc 9971, 3rd Ed., 2018.
  4. Yang, H. and Kim, B., "Capacity Model for Terminal Control Area," Journal of Korean Society of Transportation, Vol. 12, No. 3, 1994, pp. 15~27.
  5. Kim, Y. and Shin, H., "Fundamental Study for Improving the Safety and Efficiency in Korea Airspace," Korea Transport Institute, November 2002.
  6. Juricic, B., Skurla Babic, R. and Francetic, I., "Zagreb Terminal Airspace Capacity Analysis," Promet-Traffic & Transportation, Vol. 23, No. 5, 2011, pp. 367~375.
  7. Cetek, F. A., Kantar, Y. M. and Cavcar, A., "A Regression Model for Terminal Airspace Delays," The Aeronautical Journal, Vol. 121, No. 1239, 2017, pp. 680~692. https://doi.org/10.1017/aer.2017.19
  8. Zhang, M., Shan, L., Zhang, M., Liu, K., Yu, H. and Yu, J., "Terminal Airspace Sector Capacity Estimation Method Based on the ATC Dynamical Model," Kybernetes, Vol. 45, No. 6, 2016, pp. 884~899. https://doi.org/10.1108/K-12-2014-0308
  9. Jones, J., DeLaura, R., Pawlak, M., Troxel, S. and Underhill, N., "Predicting & Quantifying Risk in Airport Capacity Profile Selection for Air Traffic Management," USA/Europe Air Traffic Management Research and Development Seminar (ATM2017), Seattle, WA, June 2017.
  10. "LightGBM's Documentation," Microsoft Corporation, retrieved 24 November 2021. https:// lightgbm.readthedocs.io/en/latest/
  11. Duan, T., Avati, A., Ding, D. Y., Basu, S., Ng, A. and Schuler, A., "NGBoost: Natural Gradient Boosting for Probabilistic Prediction," retrieved 24 November 2021. https://stanfordmlgroup.github.io/projects/ngboost/
  12. Hawkins, D. M., "The problem of Overfitting," Journal of Chemical Information and Computer Sciences, Vol. 44, No. 1, 2004, pp. 1~12. https://doi.org/10.1021/ci0342472