The present document discloses a computer-implemented method for predicting a conjunction parameter from conjunction data messages and the respective method for training a transformer-based machine-learning model for predicting a conjunction parameter. It is also disclosed a device comprising a computer-readable medium comprising the trained transformer-based machine-learning model and a computer configured to carry out the training method of the transformer-based machine-learning model.


    Access

    Download


    Export, share and cite



    Title :

    METHOD AND DEVICE FOR TRAINING AND PREDICTING A CONJUNCTION PARAMETER FROM CONJUNCTION DATA MESSAGES


    Additional title:

    VERFAHREN UND VORRICHTUNG ZUM TRAINIEREN UND VORHERSAGEN EINES VERBINDUNGSPARAMETERS AUS VERBUNDENEN DATENNACHRICHTEN
    PROCÉDÉ ET DISPOSITIF D'APPRENTISSAGE ET DE PRÉDICTION D'UN PARAMÈTRE DE CONJONCTION À PARTIR DE MESSAGES DE DONNÉES DE CONJONCTION



    Publication date :

    2025-07-23


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B64G Raumfahrt , COSMONAUTICS




    JAC Software, Dedicated to the Analysis of Conjunction Messages (AIAA 2014-1774)

    Laporte, F. / American Institute of Aeronautics and Astronautics | British Library Conference Proceedings | 2014


    Actionability and Persistence of Conjunction Data

    Vallado, David A. / Alfano, Salvatore / Oltrogge, Daniel et al. | Springer Verlag | 2025


    Actionability and Persistence of Conjunction Data

    Vallado, David A. / Alfano, Salvatore / Oltrogge, Daniel et al. | Springer Verlag | 2025


    Peak Pc Prediction in Conjunction Analysis: Conjunction Assessment Risk Analysis

    Vallejo, J.J. / Hejduk, M.D. / Stamey, J. D. | NTRS | 2015