Suscripción a Biblioteca: Guest
Portal Digitalde Biblioteca Digital eLibros Revistas Referencias y Libros de Ponencias Colecciones
International Journal for Uncertainty Quantification
Factor de Impacto: 3.259 Factor de Impacto de 5 años: 2.547 SJR: 0.531 SNIP: 0.8 CiteScore™: 1.52

ISSN Imprimir: 2152-5080
ISSN En Línea: 2152-5099

Acceso abierto

International Journal for Uncertainty Quantification

DOI: 10.1615/Int.J.UncertaintyQuantification.2014008084
pages 243-271

QUANTIFICATION OF UNCERTAINTY FROM HIGH-DIMENSIONAL SCATTERED DATA VIA POLYNOMIAL APPROXIMATION

Lionel Mathelin
LIMSI-CNRS, BP 133, 91403 Orsay, France; Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, USA

SINOPSIS

This paper discusses a methodology for determining a functional representation of a random process from a collection of scattered pointwise samples. The present work specifically focuses onto random quantities lying in a high-dimensional stochastic space in the context of limited amount of information. The proposed approach involves a procedure for the selection of an approximation basis and the evaluation of the associated coefficients. The selection of the approximation basis relies on the a priori choice of the high-dimensional model representation format combined with a modified least angle regression technique. The resulting basis then provides the structure for the actual approximation basis, possibly using different functions, more parsimonious and nonlinear in its coefficients. To evaluate the coefficients, both an alternate least squares and an alternate weighted total least squares methods are employed. Examples are provided for the approximation of a random variable in a high-dimensional space as well as the estimation of a random field. Stochastic dimensions up to 100 are considered, with an amount of information as low as about 3 samples per dimension, and robustness of the approximation is demonstrated with respect to noise in the dataset. The computational cost of the solution method is shown to scale only linearly with the cardinality of the a priori basis and exhibits a (Nq)s, 2 ≤ s ≤ 3, dependence with the number Nq of samples in the dataset. The provided numerical experiments illustrate the ability of the present approach to derive an accurate approximation from scarce scattered data even in the presence of noise.


Articles with similar content:

UTILIZING ADJOINT-BASED ERROR ESTIMATES FOR SURROGATE MODELS TO ACCURATELY PREDICT PROBABILITIES OF EVENTS
International Journal for Uncertainty Quantification, Vol.8, 2018, issue 2
Timothy Wildey, Troy Butler
HIGH DIMENSIONAL SENSITIVITY ANALYSIS USING SURROGATE MODELING AND HIGH DIMENSIONAL MODEL REPRESENTATION
International Journal for Uncertainty Quantification, Vol.5, 2015, issue 5
Edmondo Minisci, Marco Cisternino, Martin Kubicek
Nonlinear Parametric Identification Based on the Generalized Probabilistic Criteria
Journal of Automation and Information Sciences, Vol.40, 2008, issue 5
Sergey V. Sokolov, Pavel A. Kucherenko
A MULTILEVEL APPROACH FOR SEQUENTIAL INFERENCE ON PARTIALLY OBSERVED DETERMINISTIC SYSTEMS
International Journal for Uncertainty Quantification, Vol.9, 2019, issue 4
Ajay Jasra, Yi Xu, Kody J.H. Law
Estimation by Information Criteria
Journal of Automation and Information Sciences, Vol.37, 2005, issue 9
Oleg L. Levoshych