Sensitivity analysis via Karhunen-Loève expansion of a random field model: Estimation of Sobol' indices and experimental design

We use the Karhunen-Loeve expansion of a random-field model to construct a tensorised Bayesian linear model from which Sobol' sensitivity indices can be estimated straightforwardly. The method combines the advantages of models built from families of orthonormal functions, which facilitate computations, and Gaussian-process models, which offer a lot of flexibility. The posterior distribution of the indices can be derived, and its normal approximation can be used to design experiments especially adapted to their estimation. Implementation details are provided, and values of tuning parameters are indicated that yield precise estimation from a small number of function evaluations. Several illustrative examples are included that show the good performance of the method, in particular in comparison with estimation based on polynomial chaos expansion.

[1]  W. J. Studden,et al.  Theory Of Optimal Experiments , 1972 .

[2]  Toby J. Mitchell,et al.  An Algorithm for the Construction of “D-Optimal” Experimental Designs , 2000, Technometrics.

[3]  Thierry Alex Mara,et al.  Comparison of some efficient methods to evaluate the main effect of computer model factors , 2008 .

[4]  Adrian E. Raftery,et al.  Bayesian Model Averaging: A Tutorial , 2016 .

[5]  K. Shuler,et al.  A STUDY OF THE SENSITIVITY OF COUPLED REACTION SYSTEMS TO UNCERTAINTIES IN RATE COEFFICIENTS . II , 2014 .

[6]  Olivier Dubrule,et al.  Cross validation of kriging in a unique neighborhood , 1983 .

[7]  Ilya M. Sobol,et al.  Sensitivity Estimates for Nonlinear Mathematical Models , 1993 .

[8]  Agnès Lagnoux,et al.  Estimation of the Sobol indices in a linear functional multidimensional model , 2013 .

[9]  Bruno Sudret,et al.  Efficient computation of global sensitivity indices using sparse polynomial chaos expansions , 2010, Reliab. Eng. Syst. Saf..

[10]  Clémentine Prieur,et al.  A randomized orthogonal array-based procedure for the estimation of first- and second-order Sobol' indices , 2015 .

[11]  J. Imhof.  Computing the distribution of quadratic forms in normal variables , 1961 .

[12]  A. O'Hagan,et al.  Probabilistic sensitivity analysis of complex models: a Bayesian approach , 2004 .

[13]  Marc S. Paolella,et al.  Evaluating the density of ratios of noncentral quadratic forms in normal variables , 2009, Comput. Stat. Data Anal..

[14]  Elise Arnaud,et al.  Recursive estimation procedure of Sobol' indices based on replicated designs , 2016 .

[15]  C. Fortuin,et al.  Study of the sensitivity of coupled reaction systems to uncertainties in rate coefficients. I Theory , 1973 .

[16]  Olivier Roustant,et al.  Calculations of Sobol indices for the Gaussian process metamodel , 2008, Reliab. Eng. Syst. Saf..

[17]  Stefano Tarantola,et al.  Variance-Based Sensitivity Analysis: Theory and Estimation Algorithms , 2015 .

[18]  Lluís Antoni Jiménez Rugama,et al.  Iterative construction of replicated designs based on Sobol' sequences , 2017 .

[19]  Anthony C. Atkinson,et al.  Optimum Experimental Designs, with SAS , 2007 .

[20]  Valerii Fedorov,et al.  16 Design of spatial experiments: Model fitting and prediction , 1996 .

[21]  B. Torsney,et al.  MV-Optimization in Weighted Linear Regression , 1998 .

[22]  Bruno Sudret,et al.  Effective Design for Sobol Indices Estimation Based on Polynomial Chaos Expansions , 2016, COPA.

[23]  K. Shuler,et al.  Study of the sensitivity of coupled reaction systems to uncertainties in rate coefficients. II Applications , 1973 .

[24]  A. Saltelli,et al.  Making best use of model evaluations to compute sensitivity indices , 2002 .

[25]  L. Pronzato.  Minimax and maximin space-filling designs: some properties and methods for construction , 2017 .

[26]  B. Efron,et al.  The Jackknife Estimate of Variance , 1981 .

[27]  Roger Woodard,et al.  Interpolation of Spatial Data: Some Theory for Kriging , 1999, Technometrics.

[28]  Bruno Sudret,et al.  Global sensitivity analysis using polynomial chaos expansions , 2008, Reliab. Eng. Syst. Saf..

[29]  David Ginsbourger,et al.  On ANOVA Decompositions of Kernels and Gaussian Random Field Paths , 2014, MCQMC.

[30]  Claire Cannamela,et al.  A Bayesian Approach for Global Sensitivity Analysis of (Multifidelity) Computer Codes , 2013, SIAM/ASA J. Uncertain. Quantification.

[31]  Adrian E. Raftery,et al.  Bayesian model averaging: a tutorial (with comments by M. Clyde, David Draper and E. I. George, and a rejoinder by the authors , 1999 .

[32]  Alen Alexanderian.  On spectral methods for variance based sensitivity analysis , 2013 .

[33]  Stefano Tarantola,et al.  A Quantitative Model-Independent Method for Global Sensitivity Analysis of Model Output , 1999, Technometrics.

[34]  K. Shuler,et al.  Study of the sensitivity of coupled reaction systems to uncertainties in rate coefficients. III. Analysis of the approximations , 1975 .

[35]  David Ginsbourger,et al.  ANOVA kernels and RKHS of zero mean functions for model-based sensitivity analysis , 2011, J. Multivar. Anal..

[36]  Luc Pronzato,et al.  Convex relaxation for IMSE optimal design in random-field models , 2017, Comput. Stat. Data Anal..

[37]  Luc Pronzato,et al.  Bayesian Local Kriging , 2014, Technometrics.