Abstract As air traffic demand grows, robust, data-driven methods are required to ensure that aviation systems become safer and more efficient. The terminal airspace is identified as the most critical airspace for both individual flight-level and system-level safety and efficiency. As such, developing data-driven anomaly detection methods to analyze terminal airspace operations has been an active area of research. 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. Generally, the methods developed to detect anomalies in ADS-B trajectory data detect anomalies in either the spatial or energy dimension. These methods distinctly use either spatial metrics or energy metrics, derived from ADS-B trajectory data. Motivated by the limited number of approaches that simultaneously consider both spatial and energy metrics, this paper introduces the concepts of spatial anomalies and energy anomalies and performs a novel investigation into the relationships and interdependencies, if any exist, between the two types of anomalies. To enable this analysis, spatial and energy anomalies are detected in ADS-B trajectory data (and associated derived metrics) using HDBSAN and DBSCAN clustering algorithms, respectively. Four months of ADS-B trajectory data associated with arrivals at San Francisco International Airport is extracted, cleaned and processed. The results that stem from this investigation indicate that if an aircraft is not spatially conforming to an identified set of air traffic flows representing standard spatial operations, then this aircraft is more likely to experience non-conformance to standard operations in its energy metrics. Additionally, this research reveals underlying differences between trajectories that are spatially nominal and energy-anomalous and those trajectories that are spatially anomalous and energy-anomalous. Focusing solely on energy anomalies does not provide insight into potential spatial-related decisions that may have been made to result in off-nominal energy behavior.

    Highlights Introduces the concepts of spatial anomalies to be detected utilizing trajectory data. Builds upon previous work in literature to provide a demonstration of the clustering-based detection of spatial and energy anomalies utilizing open-source ADS-B trajectory data. Leverages ADS-B data for arrivals over a four-month period enabling investigation of the relationship between spatial and energy anomalies detected, finding that, in general, spatial anomalies are more likely to also be energy anomalies, which is valuable information to both ATC and pilot or air crews for a more-informed assessment of risk and mitigation of potentially unsafe operations. Significantly improves over previous similar work in literature in terms of analysis in both the spatial and energy dimensions of trajectory data rather than only one or the other to provide more complete insights.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A clustering-based quantitative analysis of the interdependent relationship between spatial and energy anomalies in ADS-B trajectory data


    Beteiligte:


    Erscheinungsdatum :

    2021-07-26




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Application of Isolation Forest for Detection of Energy Anomalies in ADS-B Trajectory Data

    Kumar, Satvik G. / Corrado, Samantha J. / Puranik, Tejas G. et al. | AIAA | 2022


    Application of Isolation Forest for Detection of Energy Anomalies in ADS-B Trajectory Data

    Kumar, Satvik G. / Corrado, Samantha J. / Puranik, Tejas G. et al. | TIBKAT | 2022


    A Flight Trajectory Prediction Method based on Trajectory Clustering

    Wang, Guangchao / Chen, Hui / Liu, Kun et al. | IEEE | 2019


    AIS Data Pre-Processing for Trajectory Clustering Data Preparation

    Hartawan, I Putu Noven / Widyantara, I Made Oka / Karyawati, A. A. I. N. E. et al. | IEEE | 2021