Advanced stochastic approaches for Sobol’ sensitivity indices evaluation

Sensitivity analysis is a modern promising technique for studying large systems such as ecological systems. The main idea of sensitivity analysis is to evaluate and predict (through computer simulations on large mathematical models) the measure of the sensitivity of the model’s output to the perturbations of some input parameters, and it is a technique for refining the mathematical model. The main problem in the sensitivity analysis is the evaluation of total sensitivity indices. The mathematical formulation of this problem is represented by a set of multidimensional integrals. In this work, some new stochastic approaches for evaluating Sobol’ sensitivity indices of the unified Danish Eulerian model have been presented. For the first time, a special type of digital nets and lattice rules are applied for multidimensional sensitivity analysis and their advantages are discussed. A comparison of accuracy of eight stochastic approaches for evaluating Sobol’ sensitivity indices is performed. The obtained results will be important and useful for the surveyed scientists (physicists, chemicals, meteorologists) to make a comparative classification of the input parameters with respect to their influence on the concentration of the pollutants of interest.

[1]  I. Sloan.  Lattice Methods for Multiple Integration , 1994 .

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

[3]  Michael D. McKay,et al.  Evaluating Prediction Uncertainty , 1995 .

[4]  I. Sobol,et al.  Sensitivity Measures, ANOVA-like Techniques and the Use of Bootstrap , 1997 .

[5]  Zahari Zlatev,et al.  Computer Treatment of Large Air Pollution Models , 1995 .

[6]  Ivan Tomov Dimov,et al.  Exact Error Estimates and Optimal Randomized Algorithms for Integration , 2006, Numerical Methods and Applications.

[7]  Zahari Zlatev,et al.  Challenges in Using Splitting Techniques for Large-Scale Environmental Modeling , 2005 .

[8]  A. Stroud.  Approximate calculation of multiple integrals , 1973 .

[9]  Zahari Zlatev,et al.  Testing the Sensitivity of Air Pollution Levels to Variations of Some Chemical Rate Constants , 1997, LSSC.

[10]  I. Georgiev,et al.  An Immersed Interface FEM for Elliptic Problems with Local Own Sources , 2009 .

[11]  Zahari Zlatev,et al.  Air pollution modelling, sensitivity analysis and parallel implementation , 2011 .

[12]  Takashi Goda,et al.  Digital nets with infinite digit expansions and construction of folded digital nets for quasi-Monte Carlo integration , 2014, J. Complex..

[13]  Ilya M. Sobol,et al.  Theorems and examples on high dimensional model representation , 2003, Reliab. Eng. Syst. Saf..

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

[15]  Y. Wang,et al.  An Historical Overview of Lattice Point Sets , 2002 .

[16]  Z. Zlatev,et al.  Sensitivity studies of pollutant concentrations calculated by the UNI-DEM with respect to the input emissions , 2013 .

[17]  A. Saltelli,et al.  A quantitative model-independent method for global sensitivity analysis of model output , 1999 .

[18]  Stefano Tarantola,et al.  Trends in sensitivity analysis practice in the last decade. , 2016, The Science of the total environment.

[19]  F. Pillichshammer,et al.  Digital Nets and Sequences: Discrepancy Theory and Quasi-Monte Carlo Integration , 2010 .

[20]  Frances Y. Kuo,et al.  Remark on algorithm 659: Implementing Sobol's quasirandom sequence generator , 2003, TOMS.

[21]  Paul Bratley,et al.  Algorithm 659: Implementing Sobol's quasirandom sequence generator , 1988, TOMS.

[22]  R. Caflisch.  Monte Carlo and quasi-Monte Carlo methods , 1998, Acta Numerica.

[23]  Terje O. Espelid,et al.  An adaptive algorithm for the approximate calculation of multiple integrals , 1991, TOMS.

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

[25]  A. Saltelli,et al.  Importance measures in global sensitivity analysis of nonlinear models , 1996 .

[26]  H. Faure.  Discrépance de suites associées à un système de numération (en dimension s) , 1982 .

[27]  Ivan Ganchev,et al.  Conceptual and Analytical Models for Predicting the Quality of Service of Overall Telecommunication Systems , 2018, Autonomous Control for a Reliable Internet of Services.

[28]  Bennett L. Fox,et al.  Algorithm 647: Implementation and Relative Efficiency of Quasirandom Sequence Generators , 1986, TOMS.

[29]  Stefano Tarantola,et al.  Estimating the approximation error when fixing unessential factors in global sensitivity analysis , 2007, Reliab. Eng. Syst. Saf..

[30]  Sean McKee,et al.  Monte Carlo Methods for Applied Scientists , 2005 .

[31]  I. Dimov,et al.  Error analysis of an adaptive Monte Carlo method for numerical integration , 1998 .

[32]  M. C. Dodge,et al.  A photochemical kinetics mechanism for urban and regional scale computer modeling , 1989 .

[33]  Ostwald's Klassiker der Exacten Wissenschaften , Nature.

[34]  I. F. Sharygin,et al.  A lower estimate for the error of quadrature formulae for certain classes of functions , 1963 .

[35]  Zahari Zlatev,et al.  Three-Dimensional Version of the Danish Eulerian Model , 1995, PARA.

[36]  A. Owen.  Randomly Permuted (t,m,s)-Nets and (t, s)-Sequences , 1995 .

[37]  R. Wasserstein.  Monte Carlo Methods, Volume 1: Basics , 1989 .

[38]  H. Niederreiter,et al.  Monte Carlo and quasi-Monte Carlo methods 2000 : proceedings of a conference held at the Hong Kong Baptist University, Hong Kong SAR, China, November 27-December 1, 2000 , 2002 .

[39]  Z. Zlatev,et al.  Modeling the long-range transport of air pollutants , 1994, IEEE Computational Science and Engineering.

[40]  Judit Bartholy,et al.  Splitting method and its application in air pollution modeling , 2001 .

[41]  S. Haber.  Parameters for integrating periodic functions of several variables , 1983 .

[42]  H. Niederreiter.  Existence of good lattice points in the sense of Hlawka , 1978 .

[43]  Zahari Zlatev,et al.  Variance-Based Sensitivity Analysis of the Unified Danish Eulerian Model According to Variations of Chemical Rates , 2012, NAA.

[44]  T. Hesterberg,et al.  Weighted Average Importance Sampling and Defensive Mixture Distributions , 1995 .

[45]  Carlo Jacoboni,et al.  Convergency of the Monte Carlo algorithm for the solution of the Wigner quantum-transport equation , 1996 .

[46]  Zahari Zlatev,et al.  Computational and Numerical Challenges in Environmental Modelling , 2006 .

[47]  Zahari Zlatev,et al.  Flexible Two-Level Parallel Implementations of a Large Air Pollution Model , 2002, Numerical Methods and Application.

[48]  Miglena N. Koleva,et al.  A Second-Order Cartesian Grid Finite Volume Technique for Elliptic Interface Problems , 2007, LSSC.

[49]  Stefano Tarantola,et al.  Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models , 2004 .

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

[51]  Rayna Georgieva,et al.  Monte Carlo algorithms for evaluating Sobol' sensitivity indices , 2010, Math. Comput. Simul..

[52]  Frances Y. Kuo,et al.  Application of Quasi-Monte Carlo Methods to Elliptic PDEs with Random Diffusion Coefficients: A Survey of Analysis and Implementation , 2016, Foundations of Computational Mathematics.

[53]  Charles Pezerat,et al.  Sensitivity analysis and propagation of uncertainty for the simulation of vehicle pass-by noise , 2019 .

[54]  Leonidas J. Guibas,et al.  Optimally combining sampling techniques for Monte Carlo rendering , 1995, SIGGRAPH.

[55]  I. A. Antonov,et al.  An economic method of computing LPτ-sequences , 1979 .

[56]  Emanouil I. Atanassov,et al.  Generating and Testing the Modified Halton Sequences , 2002, Numerical Methods and Application.

[57]  H. Keng,et al.  Applications of number theory to numerical analysis , 1981 .

[58]  Zahari Zlatev,et al.  Advanced Sensitivity Analysis of the Danish Eulerian Model in Parallel and Grid Environment , 2011 .

[59]  Karl Karlovich Sabelʹfelʹd.  Monte Carlo methods in boundary value problems , 1991 .

[60]  Paula A. Whitlock,et al.  An efficient backward Monte Carlo estimator for solving of a quantum-kinetic equation with memory kernel , 2002, Math. Comput. Simul..

[61]  H. Niederreiter,et al.  Monte Carlo and Quasi-Monte Carlo Methods in Scientific Computing , 1995 .

[62]  Krassimir T. Atanassov,et al.  Generalized Nets as a Tool for Modelling of the Urban Bus Transport , 2017, FQAS.

[63]  Stefka Fidanova.  Convergence Proof for a Monte Carlo Method for Combinatorial Optimization Problems , 2004, International Conference on Computational Science.

[64]  I. Sobola,et al.  Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates , 2001 .

[65]  Harald Niederreiter,et al.  Random number generation and Quasi-Monte Carlo methods , 1992, CBMS-NSF regional conference series in applied mathematics.

[66]  James A. Nichols,et al.  Quasi-Monte Carlo finite element methods for elliptic PDEs with lognormal random coefficients , 2015, Numerische Mathematik.

[67]  Zahari Zlatev,et al.  Advanced algorithms for multidimensional sensitivity studies of large-scale air pollution models based on Sobol sequences , 2013, Comput. Math. Appl..

[68]  I. Faragó,et al.  Weighted sequential splittings and their analysis , 2005 .

[69]  Zahari Zlatev,et al.  Parallel Computation of Sensitivity Analysis Data for the Danish Eulerian Model , 2011, LSSC.

[70]  Dirk Nuyens.  Fast construction of good lattice rules , 2007 .

[71]  Ian H. Sloan,et al.  Component-by-component construction of good lattice rules , 2002, Math. Comput..

[72]  I. Sloan,et al.  Lattice methods for multiple integration: theory, error analysis and examples , 1987 .

[73]  J. Halton.  On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals , 1960 .

[74]  Spassimir H. Paskov.  Computing High Dimensional Integrals with Applications to Finance , 1994 .