Multifidelity surrogates are essential in cases where it is not affordable to have more than a few high-fidelity samples, but it is affordable to have as many low-fidelity samples as needed. In these cases, given a good correlation between the models, the performance of multifidelity models can be outstanding. The first objective of this paper is to discuss progress in creating accurate multifidelity surrogates when they are essential. A more ambiguous situation exists when it may be possible to afford enough high-fidelity samples to construct an accurate surrogate model. In that case, the question is whether a multifidelity surrogate will afford a substantial cost reduction for comparable accuracy. Our the second objective is to see if there are any indications under what circumstances this substantial cost reduction is realized. From the literature, it appears that it is hard to get an idea, in terms of cost savings, of when it is useful to invest the additional effort of creating and using multifidelity surrogates. It is observed that in some cases the inclusion of low-fidelity samples along with the high-fidelity samples in building multifidelity surrogates led to less accurate surrogates than just using the available high-fidelity samples.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Issues in Deciding Whether to Use Multifidelity Surrogates


    Beteiligte:

    Erschienen in:

    AIAA Journal ; 57 , 5 ; 2039-2054


    Erscheinungsdatum :

    01.05.2019




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch






    RELIABLE MULTIDISCIPLINARY DESIGN OF A SUPERSONIC NOZZLE USING MULTIFIDELITY SURROGATES (AIAA 2017-3826)

    Fenrich, Richard W. / Alonso, Juan J. | British Library Conference Proceedings | 2017


    Multifidelity Cross-Validation

    Renganathan, Ashwin / Carlson, Kade | AIAA | 2024


    Multifidelity Bayesian Optimization: A Review

    Do, Bach / Zhang, Ruda | AIAA | 2025