ANOMALY DETECTION IN APPROACH OPERATIONS AT SAO PAULO/GUARULHOS INTERNATIONAL AIRPORT¶
Abstract¶
THE PURSUIT OF STRINGENT TARGETS ON OPERATIONAL SAFETY AND EFFICIENCY IN AN INCREASINGLY COMPLEX AVIATION SYSTEM HAS BEEN DRIVING THE DEVELOPMENT OF NOVEL ANALYTICS CAPABILITIES FOR MORE PROACTIVE AVIATION PERFORMANCE MANAGEMENT. ANOMALY DETECTION IN FLIGHT OPERATIONS DATA IS A PROMINENT APPROACH TO DELIVERING ACTIONABLE INFORMATION, AS ANOMALIES ARE OFTEN RELATED TO CRITICAL SAFETY EVENTS OR INEFFICIENT OPERATIONS. IN THIS PAPER, WE APPLY MACHINE LEARNING TECHNIQUES TO AIRCRAFT SURVEILLANCE DATA FOR OFFLINE ANOMALY DETECTION AND EXPLANATION IN APPROACH OPERATIONS AT SAO PAULO/GUARULHOS INTERNATIONAL AIRPORT (SBGR). FIRST, WE BUILD AN AUTOENCODER CLASSIFIER FOR THE AUTOMATIC IDENTIFICATION OF ANOMALOUS APPROACH PERFORMANCE FROM FLIGHT TRAJECTORY DATA. THEN, WE EXTEND OUR ANALYSIS WITH RUNWAY CONFIGURATION AND WEATHER INFORMATION TO DEVELOP MODELS FOR ANOMALY EXPLANATION. WE FOUND THAT THE AUTOENCODER CLASSIFIER WAS ABLE TO DETECT OPERATIONALLY RELEVANT ANOMALIES, WHILE THE EXPLANATORY MODELS PROVIDED NOVEL INSIGHTS ABOUT CONTRIBUTING FACTORS TO THE ANOMALIES IDENTIFIED. WE LEARNED THAT ANOMALOUS FLIGHT TRAJECTORIES ARE MORE LIKELY TO BE ASSOCIATED WITH LANDING OPERATIONS ON RUNWAY 27 UNDER WIND SCENARIOS, WITH AN INCREASE IN THE ODDS RATIO OF 63% AND 48% FOR TAILWINDS AND HEADWINDS, RESPECTIVELY. IN ADDITION, WE ALSO OBSERVED A POSITIVE ASSOCIATION BETWEEN ANOMALIES AND WIND GUSTS SITUATIONS.
Download¶
Citing¶
@inproceedings{SIT231,
author = {LUCAS COELHO E SILVA; MAYARA CONDÉ ROCHA MURÇA},
title = {ANOMALY DETECTION IN APPROACH OPERATIONS AT SAO PAULO/GUARULHOS INTERNATIONAL AIRPORT},
booktitle = {Proceedings of the 2022 Air Transportation Symposium},
series = {SITRAER 2022},
year = {2022},
pages = {174-184},
publisher = {SBTA - Brazilian Air Transportation Research Society},
address = {São José dos Campos, Brazil,}
}
License¶
The contents of this article can be used given that the authors are cited. The reproduction of the whole article in any medium is forbidden, unless authorized by the authors.