Standard

Evaluation of feasible machine learning techniques for predicting the time to fly and aircraft speed profile on final approach : Predictive dynamic support tool on final approach. / Herrema, Floris; Treve, V; Curran, Richard; Visser, H.G.

7th International Conference on Research in Air Transportation: Philadelphia, USA. ed. / D. Lovell; H. Fricke. 2016.

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Harvard

Herrema, F, Treve, V, Curran, R & Visser, HG 2016, Evaluation of feasible machine learning techniques for predicting the time to fly and aircraft speed profile on final approach: Predictive dynamic support tool on final approach. in D Lovell & H Fricke (eds), 7th International Conference on Research in Air Transportation: Philadelphia, USA. 7th International Conference on Research in Air Transportation, Philadelphia, United States, 20/06/16.

APA

Vancouver

Author

BibTeX

@inproceedings{77d3739bcfb348f7aaf4a789328104e1,
title = "Evaluation of feasible machine learning techniques for predicting the time to fly and aircraft speed profile on final approach: Predictive dynamic support tool on final approach",
abstract = "currently, at many airports, the runway throughput is the limiting factor for the overall capacity. Among the most important constraining parameters is the separation minima expressed in distance. On the top of these minima, the difference of the leader and follower aircraft speed profiles imposes to consider buffer to cope with compression effect. Currently, Air Traffic Control Officers (ATCO’s) take these buffers on the basis of their training and experience. However, this experience will not be sufficient to safety deploy advanced concepts, like pair-wise separations, that increase variability in the separations to be delivered and therefore in the compression buffer to be considered. Systematic analysis of years of radar tracks has allowed to better predict the buffers to apply by characterising the time to fly (T2F) given a separation distance and True Airspeed (TAS) profile as a function of meteorological parameters.This paper presents how Machine Learning (ML) techniques may be used for predicting the T2F and TAS profile on final approach. Different ML techniques will be assessed on their forecast performance, computational time and amount of data needed for delivering a reliable prediction. The techniques will be applied on 2 different major European airports traffic and will be benchmarked against Optimized Runway Delivery (ORD) study using a Model Based Approach (MBA) for deriving the T2F and TAS. As a result the most efficient ML techniques will be applied on two case studies for predicting the T2F and TAS.",
keywords = "T2F, TAS, ML, ensemble",
author = "Floris Herrema and V Treve and Richard Curran and H.G. Visser",
year = "2016",
language = "English",
editor = "D. Lovell and H. Fricke",
booktitle = "7th International Conference on Research in Air Transportation",

}

RIS

TY - GEN

T1 - Evaluation of feasible machine learning techniques for predicting the time to fly and aircraft speed profile on final approach

T2 - Predictive dynamic support tool on final approach

AU - Herrema, Floris

AU - Treve, V

AU - Curran, Richard

AU - Visser, H.G.

PY - 2016

Y1 - 2016

N2 - currently, at many airports, the runway throughput is the limiting factor for the overall capacity. Among the most important constraining parameters is the separation minima expressed in distance. On the top of these minima, the difference of the leader and follower aircraft speed profiles imposes to consider buffer to cope with compression effect. Currently, Air Traffic Control Officers (ATCO’s) take these buffers on the basis of their training and experience. However, this experience will not be sufficient to safety deploy advanced concepts, like pair-wise separations, that increase variability in the separations to be delivered and therefore in the compression buffer to be considered. Systematic analysis of years of radar tracks has allowed to better predict the buffers to apply by characterising the time to fly (T2F) given a separation distance and True Airspeed (TAS) profile as a function of meteorological parameters.This paper presents how Machine Learning (ML) techniques may be used for predicting the T2F and TAS profile on final approach. Different ML techniques will be assessed on their forecast performance, computational time and amount of data needed for delivering a reliable prediction. The techniques will be applied on 2 different major European airports traffic and will be benchmarked against Optimized Runway Delivery (ORD) study using a Model Based Approach (MBA) for deriving the T2F and TAS. As a result the most efficient ML techniques will be applied on two case studies for predicting the T2F and TAS.

AB - currently, at many airports, the runway throughput is the limiting factor for the overall capacity. Among the most important constraining parameters is the separation minima expressed in distance. On the top of these minima, the difference of the leader and follower aircraft speed profiles imposes to consider buffer to cope with compression effect. Currently, Air Traffic Control Officers (ATCO’s) take these buffers on the basis of their training and experience. However, this experience will not be sufficient to safety deploy advanced concepts, like pair-wise separations, that increase variability in the separations to be delivered and therefore in the compression buffer to be considered. Systematic analysis of years of radar tracks has allowed to better predict the buffers to apply by characterising the time to fly (T2F) given a separation distance and True Airspeed (TAS) profile as a function of meteorological parameters.This paper presents how Machine Learning (ML) techniques may be used for predicting the T2F and TAS profile on final approach. Different ML techniques will be assessed on their forecast performance, computational time and amount of data needed for delivering a reliable prediction. The techniques will be applied on 2 different major European airports traffic and will be benchmarked against Optimized Runway Delivery (ORD) study using a Model Based Approach (MBA) for deriving the T2F and TAS. As a result the most efficient ML techniques will be applied on two case studies for predicting the T2F and TAS.

KW - T2F

KW - TAS

KW - ML

KW - ensemble

UR - http://resolver.tudelft.nl/uuid:77d3739b-cfb3-48f7-aaf4-a789328104e1

M3 - Conference contribution

BT - 7th International Conference on Research in Air Transportation

A2 - Lovell, D.

A2 - Fricke, H.

ER -

ID: 8959677