EUVIMEDEUVIMED entdecken
Crossref

GLOBAL SENSITIVITY ANALYSIS USING DERIVATIVE-BASED SPARSE POINCARÉ CHAOS EXPANSIONS

Nora Lüthen, Olivier Roustant, Fabrice Gamboa, Bertrand Iooss, Stefano Marelli, Bruno Sudret

International Journal for Uncertainty Quantification · 2023 · 13 (6) · 57-82

DOI: 10.1615/int.j.uncertaintyquantification.2023043593 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal for Uncertainty Quantification, 2023. Verfasst von Nora Lüthen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 64 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Variance-based global sensitivity analysis, in particular Sobol' analysis, is widely used for determining the importance of input variables to a computational model. Sobol' indices can be computed cheaply based on spectral methods like polynomial chaos expansions (PCE). Another choice are the recently developed Poincare chaos expansions (PoinCE), whose orthonormal tensor-product basis is generated from the eigenfunctions of one-dimensional Poincaré differential operators. In this paper, we show that the Poincaré basis is the unique orthonormal basis with the property that partial derivatives of the basis again form an orthogonal basis with respect to the same measure as the original basis. This special property makes PoinCE ideally suited for incorporating derivative information into the surrogate modeling process. Assuming that partial derivative evaluations of the computational model are available, we compute spectral expansions in terms of Poincaré basis functions or basis partial derivatives, respectively, by sparse regression. We show on two numerical examples that the derivative-based expansions provide accurate estimates for Sobol' indices, even outperforming PCE in terms of bias and variance. In addition, we derive an analytical expression based on the PoinCE coefficients for a second popular sensitivity index, the derivative-based sensitivity measure (DGSM), and explore its performance as upper bound to the corresponding total Sobol' indices.

Zitieren

APA

Lüthen, N., Roustant, O., Gamboa, F., Iooss, B., Marelli, S., & Sudret, B. (2023). GLOBAL SENSITIVITY ANALYSIS USING DERIVATIVE-BASED SPARSE POINCARÉ CHAOS EXPANSIONS. International Journal for Uncertainty Quantification, 13(6), 57-82. https://doi.org/10.1615/int.j.uncertaintyquantification.2023043593

Vancouver

Lüthen N, Roustant O, Gamboa F, Iooss B, Marelli S, Sudret B. GLOBAL SENSITIVITY ANALYSIS USING DERIVATIVE-BASED SPARSE POINCARÉ CHAOS EXPANSIONS. International Journal for Uncertainty Quantification. 2023;13(6):57-82. doi:10.1615/int.j.uncertaintyquantification.2023043593

BibTeX
@article{Lthen2023,
  author = {Lüthen, Nora and Roustant, Olivier and Gamboa, Fabrice and Iooss, Bertrand and Marelli, Stefano and Sudret, Bruno},
  title = {GLOBAL SENSITIVITY ANALYSIS USING DERIVATIVE-BASED SPARSE POINCARÉ CHAOS EXPANSIONS},
  journal = {International Journal for Uncertainty Quantification},
  year = {2023},
  volume = {13},
  number = {6},
  pages = {57--82},
  doi = {10.1615/int.j.uncertaintyquantification.2023043593}
}
Kostenlos starten →