Deep Autoencoder for Anomaly Detection in Terminal Airspace Operations

Corrado, Samantha J.; Puranik, Tejas G.; Pinon-Fischer, Olivia J.; Mavris, Dimitri N.; Rose, Rodrigo L.; Williams, Jesse; Heidary, Roohollah

doi:10.2514/6.2021-2405

Cited by 7 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Corrado et al [133] introduce a novel framework based on DL methods using autoencoders to identify anomalies in terminal airspace operations. The primary goal is to leverage historical aircraft trajectory data combined with weather and traffic metrics to build an anomaly detection capability.…”

Section: Applications Of Autoencoders In Atmmentioning

confidence: 99%

Deep Learning in Air Traffic Management (ATM): A Survey on Applications, Opportunities, and Open Challenges

et al. 2023

View full text Add to dashboard Cite

Currently, the increasing number of daily flights emphasizes the importance of air transportation. Furthermore, Air Traffic Management (ATM) enables air carriers to operate safely and efficiently through the multiple services provided. Advanced analytic solutions have demonstrated the potential to solve complex problems in several domains, and Deep Learning (DL) has attracted attention due to its impressive results and disruptive capabilities. The adoption of DL models in ATM solutions enables new cognitive services that have never been considered before. The main goal of this research is to present a comprehensive review of state-of-the-art Deep Learning (DL) solutions for Air Traffic Management (ATM). This review focuses on describing applications, identifying opportunities, and highlighting open challenges to foster the evolution of ATM systems. To accomplish this, we discuss the fundamental topics of DL and ATM and categorize the contributions based on different approaches. First, works are grouped based on the DL approach adopted. Then, future directions are identified based on the ATM solution area. Finally, open challenges are listed for both DL applications and ATM solutions. This article aims to support the community by identifying research problems to be faced in the future.

show abstract

Section: Applications Of Autoencoders In Atmmentioning

confidence: 99%

Deep Learning in Air Traffic Management (ATM): A Survey on Applications, Opportunities, and Open Challenges

et al. 2023

View full text Add to dashboard Cite

show abstract

“…ADS-B trajectory data is extracted from the OpenSky Network's [13] historical database for arriving aircraft at a specified airport. Data is extracted, cleaned, and processed using the same procedure described in [6,14,15] for all aircraft arriving within the San Francisco International Airport (KSFO) terminal airspace in 2019. One hour was selected as length of the time intervals to consider due to the tendency of some airspace-level metrics to be computed on an hourly basis.…”

Section: Operational State Representationmentioning

confidence: 99%

Characterizing Terminal Airspace Operational States and Detecting Airspace-Level Anomalies

Corrado

Puranik

Mavris

2021

The 9th OpenSky Symposium

View full text Add to dashboard Cite

Global modernization efforts focus on increasing aviation system capacity and efficiency, while maintaining high levels of safety. To accomplish these objectives, new analysis methods are required that consider Air Traffic Management (ATM) system operations at both the flight level and the airspace level. With the expansion of ADS-B technology, open-source flight tracking data has become more readily available to enable larger-scale analyses of aircraft operations. Specifically, anomaly detection has been identified as being paramount. However, previous analyses of airspace-level operational states have not considered the observation of transitional (transitioning between two distinct airspace-level operational patterns) or anomalous operational states. Therefore, a method is proposed in which the time-series trajectory data of all aircraft operating within a terminal airspace during a specified time period is aggregated to generate a representation of the airspace-level operational states such that a recursive DBSCAN procedure to characterize airspace-level operational states as either nominal, transitional, or anomalous as well as to identify the distinct nominal operational patterns. This method is demonstrated on one year of ADS-B trajectory data for aircraft arriving at San Francisco International Airport (KSFO). Overall, visual inspection of results indicate the method’s promise in assisting ATM system operators, decision-makers, and planners in designing the implementation of new operational concepts.

show abstract

Anomaly Detection for Aviation Cyber-Physical System: Opportunities and Challenges

Ain,

Aftab Ahmed Jilani,

Azhar Butt

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Deep Autoencoder for Anomaly Detection in Terminal Airspace Operations

Cited by 7 publications

References 15 publications

Deep Learning in Air Traffic Management (ATM): A Survey on Applications, Opportunities, and Open Challenges

Deep Learning in Air Traffic Management (ATM): A Survey on Applications, Opportunities, and Open Challenges

Characterizing Terminal Airspace Operational States and Detecting Airspace-Level Anomalies

Anomaly Detection for Aviation Cyber-Physical System: Opportunities and Challenges

Contact Info

Product

Resources

About