A software framework for probabilistic sensitivity analysis for computationally expensive models

N. Vu-Bac; T. Lahmer; X. Zhuang; T. Nguyen-Thoi; T. Rabczuk

doi:10.1016/j.advengsoft.2016.06.005

A software framework for probabilistic sensitivity analysis for computationally expensive models

N. Vu-Bac, T. Lahmer, X. Zhuang, T. Nguyen-Thoi, T. Rabczuk

College of Engineering

Research output: Contribution to journal › Article › peer-review

438 Citations (Scopus)

Abstract

We provide a sensitivity analysis toolbox consisting of a set of Matlab functions that offer utilities for quantifying the influence of uncertain input parameters on uncertain model outputs. It allows the determination of the key input parameters of an output of interest. The results are based on a probability density function (PDF) provided for the input parameters. The toolbox for uncertainty and sensitivity analysis methods consists of three ingredients: (1) sampling method, (2) surrogate models, (3) sensitivity analysis (SA) method. Numerical studies based on analytical functions associated with noise and industrial data are performed to prove the usefulness and effectiveness of this study.

Original language	English
Pages (from-to)	19-31
Number of pages	13
Journal	Advances in Engineering Software
Volume	100
DOIs	https://doi.org/10.1016/j.advengsoft.2016.06.005
Publication status	Published - 2016 Oct 1

Keywords

Matlab toolbox
Penalized spline regression
Random sampling
Sensitivity analysis
Uncertainty quantification

ASJC Scopus subject areas

Software
Engineering(all)

Access to Document

10.1016/j.advengsoft.2016.06.005

Cite this

@article{83f8dbd608e84a0280be61b9c908b37c,

title = "A software framework for probabilistic sensitivity analysis for computationally expensive models",

abstract = "We provide a sensitivity analysis toolbox consisting of a set of Matlab functions that offer utilities for quantifying the influence of uncertain input parameters on uncertain model outputs. It allows the determination of the key input parameters of an output of interest. The results are based on a probability density function (PDF) provided for the input parameters. The toolbox for uncertainty and sensitivity analysis methods consists of three ingredients: (1) sampling method, (2) surrogate models, (3) sensitivity analysis (SA) method. Numerical studies based on analytical functions associated with noise and industrial data are performed to prove the usefulness and effectiveness of this study.",

keywords = "Matlab toolbox, Penalized spline regression, Random sampling, Sensitivity analysis, Uncertainty quantification",

author = "N. Vu-Bac and T. Lahmer and X. Zhuang and T. Nguyen-Thoi and T. Rabczuk",

note = "Funding Information: We gratefully acknowledge the support from National Basic Research Program of China (973 Program: 2011CB013800), NSFC (41130751), the Ministry of Science and Technology of China (SLDRCE14-B-31), Science and Technology Commission of Shanghai Municipality (16QA1404000), IRSES-MULTIFRAC. The support from the Alexander von Humboldt Foundation in the framework of the Sofja Kovalevskaja Award endowed by the Federal Ministry of Education and Research is acknowledged by X. Zhuang. Publisher Copyright: {\textcopyright} 2016 Elsevier Ltd",

year = "2016",

month = oct,

day = "1",

doi = "10.1016/j.advengsoft.2016.06.005",

language = "English",

volume = "100",

pages = "19--31",

journal = "Advances in Engineering Software",

issn = "0965-9978",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A software framework for probabilistic sensitivity analysis for computationally expensive models

AU - Vu-Bac, N.

AU - Lahmer, T.

AU - Zhuang, X.

AU - Nguyen-Thoi, T.

AU - Rabczuk, T.

N1 - Funding Information: We gratefully acknowledge the support from National Basic Research Program of China (973 Program: 2011CB013800), NSFC (41130751), the Ministry of Science and Technology of China (SLDRCE14-B-31), Science and Technology Commission of Shanghai Municipality (16QA1404000), IRSES-MULTIFRAC. The support from the Alexander von Humboldt Foundation in the framework of the Sofja Kovalevskaja Award endowed by the Federal Ministry of Education and Research is acknowledged by X. Zhuang. Publisher Copyright: © 2016 Elsevier Ltd

PY - 2016/10/1

Y1 - 2016/10/1

N2 - We provide a sensitivity analysis toolbox consisting of a set of Matlab functions that offer utilities for quantifying the influence of uncertain input parameters on uncertain model outputs. It allows the determination of the key input parameters of an output of interest. The results are based on a probability density function (PDF) provided for the input parameters. The toolbox for uncertainty and sensitivity analysis methods consists of three ingredients: (1) sampling method, (2) surrogate models, (3) sensitivity analysis (SA) method. Numerical studies based on analytical functions associated with noise and industrial data are performed to prove the usefulness and effectiveness of this study.

AB - We provide a sensitivity analysis toolbox consisting of a set of Matlab functions that offer utilities for quantifying the influence of uncertain input parameters on uncertain model outputs. It allows the determination of the key input parameters of an output of interest. The results are based on a probability density function (PDF) provided for the input parameters. The toolbox for uncertainty and sensitivity analysis methods consists of three ingredients: (1) sampling method, (2) surrogate models, (3) sensitivity analysis (SA) method. Numerical studies based on analytical functions associated with noise and industrial data are performed to prove the usefulness and effectiveness of this study.

KW - Matlab toolbox

KW - Penalized spline regression

KW - Random sampling

KW - Sensitivity analysis

KW - Uncertainty quantification

UR - http://www.scopus.com/inward/record.url?scp=84975855891&partnerID=8YFLogxK

U2 - 10.1016/j.advengsoft.2016.06.005

DO - 10.1016/j.advengsoft.2016.06.005

M3 - Article

AN - SCOPUS:84975855891

VL - 100

SP - 19

EP - 31

JO - Advances in Engineering Software

JF - Advances in Engineering Software

SN - 0965-9978

ER -

A software framework for probabilistic sensitivity analysis for computationally expensive models

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this