Natural language processing for aviation safety : Extracting knowledge from publicly-available loss of separation reports
(2022) In Open Research Europe p.1-39- Abstract
- Background: The air traffic management (ATM) system has historically
coped with a global increase in traffic demand ultimately leading to
increased operational complexity.
When dealing with the impact of this increasing complexity on system
safety it is crucial to automatically analyse the losses of separation
(LoSs) using tools able to extract meaningful and actionable
information from safety reports.
Current research in this field mainly exploits natural language
processing (NLP) to categorise the reports,with the limitations that the
considered categories need to be manually annotated by experts and
that general taxonomies are seldom exploited.
Methods: To address the current gaps,authors... (More) - Background: The air traffic management (ATM) system has historically
coped with a global increase in traffic demand ultimately leading to
increased operational complexity.
When dealing with the impact of this increasing complexity on system
safety it is crucial to automatically analyse the losses of separation
(LoSs) using tools able to extract meaningful and actionable
information from safety reports.
Current research in this field mainly exploits natural language
processing (NLP) to categorise the reports,with the limitations that the
considered categories need to be manually annotated by experts and
that general taxonomies are seldom exploited.
Methods: To address the current gaps,authors propose to perform
exploratory data analysis on safety reports combining state-of-the-art
techniques like topic modelling and clustering and then to develop an
algorithm able to extract the Toolkit for ATM Occurrence Investigation
(TOKAI) taxonomy factors from the free-text safety reports based on
syntactic analysis.
TOKAI is a tool for investigation developed by EUROCONTROL and its
taxonomy is intended to become a standard and harmonised
approach to future investigations.
Results: Leveraging on the LoS events reported in the public
databases of the Comisi n de Estudio y An lisis de Notificaciones de
Incidentes de Tr nsito A reo and the United Kingdom AirproxBoard,authors show how their proposal is able to automatically
extract meaningful and actionable information from safety
reports,other than to classify their content according to the TOKAI
taxonomy.
The quality of the approach is also indirectly validated by checking the
connection between the identified factors and the main contributor of
the incidents.
Conclusions: Authors' results are a promising first step toward the full
automation of a general analysis of LoS reports supported by results
on real-world data coming from two different sources.
In the future,authors' proposal could be extended to other
taxonomies or tailored to identify factors to be included in the safety
taxonomies.
Keywords
ATM, Safety, Resilience, Natural Language Processing, Losses of
Separation, Safety Reports, TOKAI (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/d586e8ee-5f2b-429f-9ad5-3b8557be18e9
- author
- Buselli, Irene ; Oneto, Luca ; Dambra, Carlo ; Verdonk Gallego, Christian ; Garcia Martinez, Miguel ; Smoker, Anthony LU ; Ike, Nnenna ; Pejovic, Tamara and Martino, Patricia Ruiz
- organization
- publishing date
- 2022-03-21
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Open Research Europe
- pages
- 39 pages
- publisher
- F1000 Research Ltd.
- external identifiers
-
- scopus:85131256017
- pmid:37645142
- ISSN
- 2732-5121
- DOI
- 10.12688/openreseurope.14040.2
- language
- English
- LU publication?
- yes
- id
- d586e8ee-5f2b-429f-9ad5-3b8557be18e9
- date added to LUP
- 2022-03-21 19:08:13
- date last changed
- 2023-09-28 03:00:32
@article{d586e8ee-5f2b-429f-9ad5-3b8557be18e9,
abstract = {{Background: The air traffic management (ATM) system has historically<br/>coped with a global increase in traffic demand ultimately leading to<br/>increased operational complexity.<br/>When dealing with the impact of this increasing complexity on system<br/>safety it is crucial to automatically analyse the losses of separation<br/>(LoSs) using tools able to extract meaningful and actionable<br/>information from safety reports.<br/>Current research in this field mainly exploits natural language<br/>processing (NLP) to categorise the reports,with the limitations that the<br/>considered categories need to be manually annotated by experts and<br/>that general taxonomies are seldom exploited.<br/>Methods: To address the current gaps,authors propose to perform<br/>exploratory data analysis on safety reports combining state-of-the-art<br/>techniques like topic modelling and clustering and then to develop an<br/>algorithm able to extract the Toolkit for ATM Occurrence Investigation<br/>(TOKAI) taxonomy factors from the free-text safety reports based on<br/>syntactic analysis.<br/>TOKAI is a tool for investigation developed by EUROCONTROL and its<br/>taxonomy is intended to become a standard and harmonised<br/>approach to future investigations.<br/>Results: Leveraging on the LoS events reported in the public<br/>databases of the Comisi n de Estudio y An lisis de Notificaciones de<br/>Incidentes de Tr nsito A reo and the United Kingdom AirproxBoard,authors show how their proposal is able to automatically<br/>extract meaningful and actionable information from safety<br/>reports,other than to classify their content according to the TOKAI<br/>taxonomy.<br/>The quality of the approach is also indirectly validated by checking the<br/>connection between the identified factors and the main contributor of<br/>the incidents.<br/>Conclusions: Authors' results are a promising first step toward the full<br/>automation of a general analysis of LoS reports supported by results<br/>on real-world data coming from two different sources.<br/>In the future,authors' proposal could be extended to other<br/>taxonomies or tailored to identify factors to be included in the safety<br/>taxonomies.<br/>Keywords<br/>ATM, Safety, Resilience, Natural Language Processing, Losses of<br/>Separation, Safety Reports, TOKAI}},
author = {{Buselli, Irene and Oneto, Luca and Dambra, Carlo and Verdonk Gallego, Christian and Garcia Martinez, Miguel and Smoker, Anthony and Ike, Nnenna and Pejovic, Tamara and Martino, Patricia Ruiz}},
issn = {{2732-5121}},
language = {{eng}},
month = {{03}},
pages = {{1--39}},
publisher = {{F1000 Research Ltd.}},
series = {{Open Research Europe}},
title = {{Natural language processing for aviation safety : Extracting knowledge from publicly-available loss of separation reports}},
url = {{https://lup.lub.lu.se/search/files/115592953/2022_Buselli_Natural_language_processing_for_aviation_safety_extracting_knowledge_from_publicly_available_loss_of_separation_reports.pdf}},
doi = {{10.12688/openreseurope.14040.2}},
year = {{2022}},
}