We leverage variational autoencoders to generate transient light curves of distant exoplanets and stars in order to demonstrate the efficacy of deep learning techniques for this class of data. The ability to generate accurate light curves with desirable characteristics becomes more and more necessary with the success of recent astronomical missions and upcoming missions and will be a key enabler of the development of future models and research. The first study of its type to date, our initial results indicate a promising new research direction worthy of further development.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Generating Transit Light Curves with Variational Autoencoders


    Contributors:


    Publication date :

    2019-07-01


    Size :

    1059968 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    ENHANCING NEURAL NETWORK EXPLAINABILITY WITH VARIATIONAL AUTOENCODERS

    Tran, Loc / Dolph, Chester / Zhao, Derek | TIBKAT | 2021


    Enhancing Neural Network Explainability with Variational Autoencoders

    Tran, Loc / Dolph, Chester / Zhao, Derek | AIAA | 2021


    Route choice set generation using variational autoencoders

    Yao, Rui / Bekhor, Shlomo | TIBKAT | 2022


    Towards Universal Parameterization: Using Variational Autoencoders to Parameterize Airfoils

    Swannet, Kilian / Varriale, Carmine / Doan, (Nguyen) Anh Khoa | AIAA | 2024