This paper discusses the prediction of sector capacity in the United States’ National Airspace System (NAS) using sector complexity features as input. Sector capacity prediction is critical for safe operation of aircraft in the NAS. Among other uses, a sector’s capacity is the basis of flow decisions designed to limit a sector’s traffic to that which can be safely separated. In this paper we use Machine Learning techniques with features from the Sector Complexity literature to predict capacity. We present the accuracy of the calculation, insights into input sensitivity, and recommendations for future studies.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Using Sector Complexity Metrics to Predict Sector Capacity


    Beteiligte:
    Rebollo, Juan (Autor:in) / Khater, Shaymaa (Autor:in) / Wieland, Frederick (Autor:in)


    Erscheinungsdatum :

    2023-10-01


    Format / Umfang :

    1224734 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Validating airspaceAnalyzer Metrics for En Route ATC Sector Complexity

    Niedringhaus, William P | Online Contents | 2012


    Requirements for metrics of aircraft separation and sector capacity

    Smith, K. / Knecht, W. R. / Cranfield University | British Library Conference Proceedings | 1997


    Predicting Sector Complexity Using Machine Learning

    Wieland, Frederick / Rebollo, Juan / Gibbs, Mary et al. | TIBKAT | 2022


    Predicting Sector Complexity Using Machine Learning

    Wieland, Frederick / Rebollo, Juan / Gibbs, Mary et al. | AIAA | 2022