Spacecraft are not only eye-catching because they go up riding loud rockets spitting fire. Spacecraft are also remarkable data sources. The sea of data they generate is what essentially allows them to be reliably teleoperated. Spacecraft are time-series data goldmines thanks to a network of on-board computers and sensors that create a tide of multivariate information to be consumed. The question is: to be consumed by whom? Only by humans with a functioning brain capable of “connecting the dots”? This has been the approach for the last 64 years since Sputnik 1. Can’t algorithms connect those dots? This chapter dives into how algorithms must be equipped with the nuances needed to understand the dynamic of the processes hidden behind the numbers, and how those numbers and figures relate with each other.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Satellites and Machine Learning


    Beteiligte:

    Erschienen in:

    Space Technology ; Kapitel : 7 ; 87-97


    Erscheinungsdatum :

    08.06.2023


    Format / Umfang :

    11 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    FAULT PREDICTION IN SATELLITES USING MACHINE LEARNING TECHNIQUES

    Latkar, Archit / Koul, Abhinav / Raghavan, Dharini et al. | TIBKAT | 2022


    Application of Machine Learning to Investigation of Arcing on Geosynchronous Satellites

    Plis, Sergey M. / Ferguson, Dale C. / Plis, Elena A. | Springer Verlag | 2022



    Satellites Harming Other Satellites

    P. C. Hughes | NTIS | 1991


    SILO: A Machine Learning Dataset of Synthetic Ground-Based Observations of LEO Satellites

    Werth, Michael / Lucas, Jacob / Kyono, Trent et al. | IEEE | 2020