A
Amandine Marrel
Researcher at Institut de Mathématiques de Toulouse
Publications - 54
Citations - 1810
Amandine Marrel is an academic researcher from Institut de Mathématiques de Toulouse. The author has contributed to research in topics: Gaussian process & Sobol sequence. The author has an hindex of 18, co-authored 51 publications receiving 1569 citations. Previous affiliations of Amandine Marrel include Commissariat à l'énergie atomique et aux énergies alternatives & French Institute of Petroleum.
Papers
More filters
Journal ArticleDOI
Calculations of sobol indices for the gaussian process metamodel
TL;DR: In this article, two approaches are studied to compute the Sobol indices: the first based on the predictor of the Gaussian process model and the second based on global stochastic process model.
Posted Content
Calculations of Sobol indices for the Gaussian process metamodel
TL;DR: In this paper, the Gaussian process model which gives analytical expressions of Sobol indices is discussed, and the techniques are finally applied to a real case of hydrogeological modeling.
Journal ArticleDOI
An efficient methodology for modeling complex computer codes with Gaussian processes
TL;DR: A specific estimation procedure is developed to adjust a Gaussian process model that is characterized by its mean and covariance functions in complex cases (non-linear relations, highly dispersed or discontinuous output, high-dimensional input, inadequate sampling designs, etc.).
Posted Content
An efficient methodology for modeling complex computer codes with Gaussian processes
TL;DR: In this article, a specific estimation procedure is developed to adjust a Gaussian process model in complex cases (non linear relations, highly dispersed or discontinuous output, high dimensional input, inadequate sampling designs,...).
Journal ArticleDOI
Global sensitivity analysis of stochastic computer models with joint metamodels
TL;DR: In this article, the authors proposed a global sensitivity analysis methodology for stochastic computer codes, for which the result of each code run is itself random and the framework of the joint modeling of the mean and dispersion of heteroscedastic data is used.