A deep neural network approach for prediction of aircraft top of descent
An arrival flight starts to transit from the cruise phase to the descent phase at the top of descent (TOD). Pilots get to know the TOD locations via onboard devices, while controllers can estimate the TOD locations with the help of radar surveillance and simple rules. In order to help controllers to...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/162777 https://www.jstage.jst.go.jp/browse/iwac/list/-char/en |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-162777 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1627772022-12-17T23:30:24Z A deep neural network approach for prediction of aircraft top of descent Ang, Haojie Cai, Qing Alam, Sameer School of Mechanical and Aerospace Engineering International Workshop on ATM/CNS (IWAC 2022) Air Traffic Management Research Institute Engineering::Aeronautical engineering Air Traffic Management Deep Learning An arrival flight starts to transit from the cruise phase to the descent phase at the top of descent (TOD). Pilots get to know the TOD locations via onboard devices, while controllers can estimate the TOD locations with the help of radar surveillance and simple rules. In order to help controllers to get a better situation awareness of the traffic surrounding an aerodrome, it is of great operational importance to get an accurate prediction of the TOD locations for arrival flights. In this paper, we propose to apply deep learning for TOD location prediction for arrival flights. To do so, a TOD-specific feature engineering is suggested and applied to historical flight trajectories. Then the simple yet effective multilayer perceptron neural network model is adopted for TOD prediction. A case study on the arrival flights to Singapore Changi airport with respect to one-month historical trajectory data is carried out. Experiments demonstrate that the adopted deep learning method is effective for TOD location prediction. When compared against several typical machine learning models for regression, the adopted model yields a mean square error of 0.0039, which is smaller than the error achieved by the comparison models. Meanwhile, the adopted deep learning model yields TOD location prediction errors of 0.29 nautical miles (NM) on average with a standard deviation of 46.88 NM. Civil Aviation Authority of Singapore (CAAS) National Research Foundation (NRF) Submitted/Accepted version This research is supported by the National Research Foundation, Singapore, and the Civil Aviation Authority of Singapore, under the Aviation Transformation Programme. 2022-12-16T05:54:31Z 2022-12-16T05:54:31Z 2022 Conference Paper Ang, H., Cai, Q. & Alam, S. (2022). A deep neural network approach for prediction of aircraft top of descent. International Workshop on ATM/CNS (IWAC 2022), 208-215. https://dx.doi.org/10.57358/iwac.1.0_208 https://hdl.handle.net/10356/162777 10.57358/iwac.1.0_208 https://www.jstage.jst.go.jp/browse/iwac/list/-char/en 208 215 en © 2022 Electronic Navigation Research Institute (ENRI). All rights reserved. This paper was published in the Proceedings of International Workshop on ATM/CNS (IWAC 2022) and is made available with permission of Electronic Navigation Research Institute (ENRI). application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Aeronautical engineering Air Traffic Management Deep Learning |
spellingShingle |
Engineering::Aeronautical engineering Air Traffic Management Deep Learning Ang, Haojie Cai, Qing Alam, Sameer A deep neural network approach for prediction of aircraft top of descent |
description |
An arrival flight starts to transit from the cruise phase to the descent phase at the top of descent (TOD). Pilots get to know the TOD locations via onboard devices, while controllers can estimate the TOD locations with the help of radar surveillance and simple rules. In order to help controllers to get a better situation awareness of the traffic surrounding an aerodrome, it is of great operational importance to get an accurate prediction of the TOD locations for arrival flights. In this paper, we propose to apply deep learning for TOD location prediction for arrival flights. To do so, a TOD-specific feature engineering is suggested and applied to historical flight trajectories. Then the simple yet effective multilayer perceptron neural network model is adopted for TOD prediction. A case study on the arrival flights to Singapore Changi airport with respect to one-month historical trajectory data is carried out. Experiments demonstrate that the adopted deep learning method is effective for TOD location prediction. When compared against several typical machine learning models for regression, the adopted model yields a mean square error of 0.0039, which is smaller than the error achieved by the comparison models. Meanwhile, the adopted deep learning model yields TOD location prediction errors of 0.29 nautical miles (NM) on average with a standard deviation of 46.88 NM. |
author2 |
School of Mechanical and Aerospace Engineering |
author_facet |
School of Mechanical and Aerospace Engineering Ang, Haojie Cai, Qing Alam, Sameer |
format |
Conference or Workshop Item |
author |
Ang, Haojie Cai, Qing Alam, Sameer |
author_sort |
Ang, Haojie |
title |
A deep neural network approach for prediction of aircraft top of descent |
title_short |
A deep neural network approach for prediction of aircraft top of descent |
title_full |
A deep neural network approach for prediction of aircraft top of descent |
title_fullStr |
A deep neural network approach for prediction of aircraft top of descent |
title_full_unstemmed |
A deep neural network approach for prediction of aircraft top of descent |
title_sort |
deep neural network approach for prediction of aircraft top of descent |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/162777 https://www.jstage.jst.go.jp/browse/iwac/list/-char/en |
_version_ |
1753801096099266560 |