A machine learning model to predict runway exit at Vienna airport

Floris Herrema; Ricky Curran; Sander Hartjes; Mohamed Ellejmi; Steven Bancroft; Michael Schultz

doi:10.1016/j.tre.2019.10.002

A machine learning model to predict runway exit at Vienna airport

Floris Herrema^*, Ricky Curran, Sander Hartjes, Mohamed Ellejmi, Steven Bancroft, Michael Schultz

^*Corresponding author for this work

Air Transport & Operations

Research output: Contribution to journal › Article › Scientific › peer-review

28 Citations (Scopus)

Abstract

Runway utilisation is a function of actual yearly runway throughput and annual capacity. The aim of the analysis in this project is to find data driven prediction models based on the features and relevant scenarios that might impact runway utilisation. The Gradient Boosting machine learning method will be assessed on their forecast performance and computational time for predicting the procedural and non-procedural runway exit to be utilised after the landing rollout. The Gradient Boosting method obtained an accuracy of 79% and was used to observe key related precursors of unique data patterns. Tests were conducted using runway and final approach data consisting of 54,679 arrival flights at Vienna airport.

Original language	English
Pages (from-to)	329-342
Number of pages	14
Journal	Transportation Research Part E: Logistics and Transportation Review
Volume	131
DOIs	https://doi.org/10.1016/j.tre.2019.10.002
Publication status	Published - 1 Nov 2019

Keywords

Component
Gradient boosting
Runway capacity
Runway occupancy time
Runway utilisation

Access to Document

10.1016/j.tre.2019.10.002

Cite this

@article{3f33fb2ccf9a4795beda564fd5803762,

title = "A machine learning model to predict runway exit at Vienna airport",

abstract = "Runway utilisation is a function of actual yearly runway throughput and annual capacity. The aim of the analysis in this project is to find data driven prediction models based on the features and relevant scenarios that might impact runway utilisation. The Gradient Boosting machine learning method will be assessed on their forecast performance and computational time for predicting the procedural and non-procedural runway exit to be utilised after the landing rollout. The Gradient Boosting method obtained an accuracy of 79% and was used to observe key related precursors of unique data patterns. Tests were conducted using runway and final approach data consisting of 54,679 arrival flights at Vienna airport.",

keywords = "Component, Gradient boosting, Runway capacity, Runway occupancy time, Runway utilisation",

author = "Floris Herrema and Ricky Curran and Sander Hartjes and Mohamed Ellejmi and Steven Bancroft and Michael Schultz",

year = "2019",

month = nov,

day = "1",

doi = "10.1016/j.tre.2019.10.002",

language = "English",

volume = "131",

pages = "329--342",

journal = "Transportation Research Part E: Logistics and Transportation Review",

issn = "1366-5545",

publisher = "Elsevier",

}

TY - JOUR

T1 - A machine learning model to predict runway exit at Vienna airport

AU - Herrema, Floris

AU - Curran, Ricky

AU - Hartjes, Sander

AU - Ellejmi, Mohamed

AU - Bancroft, Steven

AU - Schultz, Michael

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Runway utilisation is a function of actual yearly runway throughput and annual capacity. The aim of the analysis in this project is to find data driven prediction models based on the features and relevant scenarios that might impact runway utilisation. The Gradient Boosting machine learning method will be assessed on their forecast performance and computational time for predicting the procedural and non-procedural runway exit to be utilised after the landing rollout. The Gradient Boosting method obtained an accuracy of 79% and was used to observe key related precursors of unique data patterns. Tests were conducted using runway and final approach data consisting of 54,679 arrival flights at Vienna airport.

AB - Runway utilisation is a function of actual yearly runway throughput and annual capacity. The aim of the analysis in this project is to find data driven prediction models based on the features and relevant scenarios that might impact runway utilisation. The Gradient Boosting machine learning method will be assessed on their forecast performance and computational time for predicting the procedural and non-procedural runway exit to be utilised after the landing rollout. The Gradient Boosting method obtained an accuracy of 79% and was used to observe key related precursors of unique data patterns. Tests were conducted using runway and final approach data consisting of 54,679 arrival flights at Vienna airport.

KW - Component

KW - Gradient boosting

KW - Runway capacity

KW - Runway occupancy time

KW - Runway utilisation

UR - http://www.scopus.com/inward/record.url?scp=85073714898&partnerID=8YFLogxK

U2 - 10.1016/j.tre.2019.10.002

DO - 10.1016/j.tre.2019.10.002

M3 - Article

AN - SCOPUS:85073714898

SN - 1366-5545

VL - 131

SP - 329

EP - 342

JO - Transportation Research Part E: Logistics and Transportation Review

JF - Transportation Research Part E: Logistics and Transportation Review

ER -

A machine learning model to predict runway exit at Vienna airport

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this