Multi-fidelity surrogate modeling for time-series outputs - Archive ouverte HAL Access content directly
Journal Articles SIAM/ASA Journal on Uncertainty Quantification Year : 2023

Multi-fidelity surrogate modeling for time-series outputs


This paper considers the surrogate modeling of a complex numerical code in a multifidelity framework when the code output is a time series. Using an experimental design of the low-and high-fidelity code levels, an original Gaussian process regression method is proposed. The code output is expanded on a basis built from the experimental design. The first coefficients of the expansion of the code output are processed by a co-kriging approach. The last coefficients are collectively processed by a kriging approach with covariance tensorization. The resulting surrogate model taking into account the uncertainty in the basis construction is shown to have better performance in terms of prediction errors and uncertainty quantification than standard dimension reduction techniques.
Fichier principal
Vignette du fichier
20m1386694.pdf (1.56 Mo) Télécharger le fichier
AS_LowFi.pdf (9.7 Ko) Télécharger le fichier
AS_highFi.pdf (9.62 Ko) Télécharger le fichier
HighFiData.pdf (10.57 Ko) Télécharger le fichier
InterationBetweenCodes3.pdf (19.84 Ko) Télécharger le fichier
InterationBetweenCodesAll.pdf (28.15 Ko) Télécharger le fichier
Q2mean40_10_100.pdf (21.96 Ko) Télécharger le fichier
VarianceMean.pdf (6.25 Ko) Télécharger le fichier
curve12_100_1.pdf (7.15 Ko) Télécharger le fichier
curve12_100_2.pdf (7.01 Ko) Télécharger le fichier
kerleguer2023A01.pdf (736.73 Ko) Télécharger le fichier
lowFiData.pdf (11.07 Ko) Télécharger le fichier
pendulum.png (54.79 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)

Dates and versions

hal-03350472 , version 1 (22-09-2021)
hal-03350472 , version 2 (22-02-2022)
hal-03350472 , version 3 (22-11-2023)



Baptiste Kerleguer. Multi-fidelity surrogate modeling for time-series outputs. SIAM/ASA Journal on Uncertainty Quantification, 2023, 11 (2), pp.514-539. ⟨10.1137/20M1386694⟩. ⟨hal-03350472v3⟩
138 View
87 Download



Gmail Facebook X LinkedIn More