Standard

Predicting abnormal runway occupancy times and observing related precursors. / Herrema, F.F.; Curran, R.; Visser, Hendrikus G.; Vincent, Treve; Bruno, Desart.

In: Journal of Aerospace Information Systems (online), Vol. 15, No. 1, 2018, p. 10-21.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Herrema, FF, Curran, R, Visser, HG, Vincent, T & Bruno, D 2018, 'Predicting abnormal runway occupancy times and observing related precursors' Journal of Aerospace Information Systems (online), vol. 15, no. 1, pp. 10-21. https://doi.org/10.2514/1.I010548

APA

Herrema, F. F., Curran, R., Visser, H. G., Vincent, T., & Bruno, D. (2018). Predicting abnormal runway occupancy times and observing related precursors. Journal of Aerospace Information Systems (online), 15(1), 10-21. https://doi.org/10.2514/1.I010548

Vancouver

Herrema FF, Curran R, Visser HG, Vincent T, Bruno D. Predicting abnormal runway occupancy times and observing related precursors. Journal of Aerospace Information Systems (online). 2018;15(1):10-21. https://doi.org/10.2514/1.I010548

Author

Herrema, F.F. ; Curran, R. ; Visser, Hendrikus G. ; Vincent, Treve ; Bruno, Desart. / Predicting abnormal runway occupancy times and observing related precursors. In: Journal of Aerospace Information Systems (online). 2018 ; Vol. 15, No. 1. pp. 10-21.

BibTeX

@article{b90c0fa295454fa1a3a32d0507fc810e,
title = "Predicting abnormal runway occupancy times and observing related precursors",
abstract = "Accidents on the runway triggered the development and implementation of mitigation strategies. Therefore, the airline industry is moving toward proactive risk management, which aims to identify and predict risk precursors and to mitigate risks before accidents occur. For certain predictions machine learning techniques can be used. Although many studies have explored and applied novel machine learning techniques on different radar and A-SMGCS data, the identification and prediction of abnormal runway occupancy times and the observation of related precursors are not well developed. In our previous papers, three existing methods were introduced, lasso, multi-layer perception, and neural networks, to predict the taxi-out time on the taxiway and the time to fly and true airspeed profile on final approach. This paper presents a new machine learning method where the existing machine learning techniques are combined for predicting the abnormal runway occupancy times of unique radar data patterns. Additionally the regression tree method is used in this study to observe the key related precursors extracted from the top 10 features. Compared with existing methods, the new method no longer requires predefined criteria or domain knowledge. Tests were conducted using final approach radar data and A-SMGCS runway data consisting of 78,321 flights at Paris Charles de Gaulle airport and were benchmarked against 500,000 flights at Vienna airport.",
author = "F.F. Herrema and R. Curran and Visser, {Hendrikus G.} and Treve Vincent and Desart Bruno",
year = "2018",
doi = "10.2514/1.I010548",
language = "English",
volume = "15",
pages = "10--21",
journal = "Journal of Aerospace Information Systems (online)",
issn = "2327-3097",
number = "1",

}

RIS

TY - JOUR

T1 - Predicting abnormal runway occupancy times and observing related precursors

AU - Herrema, F.F.

AU - Curran, R.

AU - Visser, Hendrikus G.

AU - Vincent, Treve

AU - Bruno, Desart

PY - 2018

Y1 - 2018

N2 - Accidents on the runway triggered the development and implementation of mitigation strategies. Therefore, the airline industry is moving toward proactive risk management, which aims to identify and predict risk precursors and to mitigate risks before accidents occur. For certain predictions machine learning techniques can be used. Although many studies have explored and applied novel machine learning techniques on different radar and A-SMGCS data, the identification and prediction of abnormal runway occupancy times and the observation of related precursors are not well developed. In our previous papers, three existing methods were introduced, lasso, multi-layer perception, and neural networks, to predict the taxi-out time on the taxiway and the time to fly and true airspeed profile on final approach. This paper presents a new machine learning method where the existing machine learning techniques are combined for predicting the abnormal runway occupancy times of unique radar data patterns. Additionally the regression tree method is used in this study to observe the key related precursors extracted from the top 10 features. Compared with existing methods, the new method no longer requires predefined criteria or domain knowledge. Tests were conducted using final approach radar data and A-SMGCS runway data consisting of 78,321 flights at Paris Charles de Gaulle airport and were benchmarked against 500,000 flights at Vienna airport.

AB - Accidents on the runway triggered the development and implementation of mitigation strategies. Therefore, the airline industry is moving toward proactive risk management, which aims to identify and predict risk precursors and to mitigate risks before accidents occur. For certain predictions machine learning techniques can be used. Although many studies have explored and applied novel machine learning techniques on different radar and A-SMGCS data, the identification and prediction of abnormal runway occupancy times and the observation of related precursors are not well developed. In our previous papers, three existing methods were introduced, lasso, multi-layer perception, and neural networks, to predict the taxi-out time on the taxiway and the time to fly and true airspeed profile on final approach. This paper presents a new machine learning method where the existing machine learning techniques are combined for predicting the abnormal runway occupancy times of unique radar data patterns. Additionally the regression tree method is used in this study to observe the key related precursors extracted from the top 10 features. Compared with existing methods, the new method no longer requires predefined criteria or domain knowledge. Tests were conducted using final approach radar data and A-SMGCS runway data consisting of 78,321 flights at Paris Charles de Gaulle airport and were benchmarked against 500,000 flights at Vienna airport.

UR - http://www.scopus.com/inward/record.url?scp=85040352753&partnerID=8YFLogxK

U2 - 10.2514/1.I010548

DO - 10.2514/1.I010548

M3 - Article

VL - 15

SP - 10

EP - 21

JO - Journal of Aerospace Information Systems (online)

T2 - Journal of Aerospace Information Systems (online)

JF - Journal of Aerospace Information Systems (online)

SN - 2327-3097

IS - 1

ER -

ID: 37382375