A probabilistic model for aircraft in climb using monotonic functional Gaussian process emulators
dc.contributor.author | Pepper, N | |
dc.contributor.author | Thomas, M | |
dc.contributor.author | De Ath, G | |
dc.contributor.author | Oliver, E | |
dc.contributor.author | Cannon, R | |
dc.contributor.author | Everson, R | |
dc.contributor.author | Dodwell, T | |
dc.date.accessioned | 2023-03-27T08:46:50Z | |
dc.date.issued | 2023-03-22 | |
dc.date.updated | 2023-03-25T12:13:05Z | |
dc.description.abstract | Ensuring vertical separation is a key means of maintaining safe separation between aircraft in congested airspace. Aircraft trajectories are modelled in the presence of significant epistemic uncertainty, leading to discrepancies between observed trajectories and the predictions of deterministic models, hampering the task of planning to ensure safe separation. In this paper, a probabilistic model is presented, for the purpose of emulating the trajectories of aircraft in climb and bounding the uncertainty of the predicted trajectory. A monotonic, functional representation exploits the spatio-temporal correlations in the radar observations. Through the use of Gaussian process emulators, features that parameterize the climb are mapped directly to functional outputs, providing a fast approximation, while ensuring that the resulting trajectory is monotonic. The model was applied as a probabilistic digital twin for aircraft in climb and baselined against the base of aircraft data, a deterministic model widely used in industry. When applied to an unseen test dataset, the probabilistic model was found to provide a mean prediction that was 20.56% more accurate, as measured by the mean absolute error, with data-driven credible intervals that were 9.54% sharper. | en_GB |
dc.description.sponsorship | Engineering and Physical Sciences Research Council (EPSRC) | en_GB |
dc.description.sponsorship | UKRI Turing AI Fellowship | en_GB |
dc.identifier.citation | Vol. 479 (2271), article 20220607 | en_GB |
dc.identifier.doi | 10.1098/rspa.2022.0607 | |
dc.identifier.grantnumber | EP/V056522/1 | en_GB |
dc.identifier.grantnumber | 2TAFFP\100007 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/132783 | |
dc.identifier | ORCID: 0000-0003-4909-0257 (De Ath, George) | |
dc.identifier | ScopusID: 57205564689 (De Ath, George) | |
dc.identifier | ResearcherID: AAP-8110-2021 (De Ath, George) | |
dc.identifier | ORCID: 0000-0002-3964-1150 (Everson, Richard) | |
dc.identifier | ScopusID: 7006615147 (Everson, Richard) | |
dc.language.iso | en | en_GB |
dc.publisher | Royal Society | en_GB |
dc.rights | © 2023 The Author(s). Published by the Royal Society. This version is made available under the CC-BY 4.0 license: https://creativecommons.org/licenses/by/4.0/ | en_GB |
dc.subject | trajectory prediction | en_GB |
dc.subject | probabilistic machine learning | en_GB |
dc.subject | functional data analysis | en_GB |
dc.subject | Gaussian process emulators | en_GB |
dc.subject | monotonicity | en_GB |
dc.title | A probabilistic model for aircraft in climb using monotonic functional Gaussian process emulators | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2023-03-27T08:46:50Z | |
dc.identifier.issn | 1471-2946 | |
dc.description | This is the author accepted manuscript. The final version is available from the Royal Society via the DOI in this record | en_GB |
dc.description | Data accessibility: This article has no additional data. | en_GB |
dc.identifier.journal | Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences | en_GB |
dc.relation.ispartof | Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 479(2271) | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en_GB |
dcterms.dateAccepted | 2023-03-01 | |
dcterms.dateSubmitted | 2022-09-15 | |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2023-03-22 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2023-03-27T08:43:26Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2023-03-27T08:46:54Z | |
refterms.panel | B | en_GB |
refterms.dateFirstOnline | 2023-03-22 |
Files in this item
This item appears in the following Collection(s)
Except where otherwise noted, this item's licence is described as © 2023 The Author(s). Published by the Royal Society. This version is made available under the CC-BY 4.0 license: https://creativecommons.org/licenses/by/4.0/