Multidimensional Sensitivity Analysis of Large-Scale Mathematical Models

  • Ivan DimovEmail author
  • Rayna Georgieva
Conference paper
Part of the Springer Proceedings in Mathematics & Statistics book series (PROMS, volume 45)


Sensitivity analysis (SA) is a procedure for studying how sensitive are the output results of large-scale mathematical models to some uncertainties of the input data. The models are described as a system of partial differential equations. Often such systems contain a large number of input parameters. Obviously, it is important to know how sensitive is the solution to some uncontrolled variations or uncertainties in the input parameters of the model. Algorithms based on analysis of variances technique for calculating numerical indicators of sensitivity and computationally efficient Monte Carlo integration techniques have recently been developed by the authors. They have been successfully applied to sensitivity studies of air pollution levels calculated by the Unified Danish Eulerian Model with respect to several important input parameters. In this paper a comprehensive theoretical and experimental study of the Monte Carlo algorithm based on symmetrised shaking of Sobol sequences has been done. It has been proven that this algorithm has an optimal rate of convergence for functions with continuous and bounded second derivatives in terms of probability and mean square error. Extensive numerical experiments with Monte Carlo, quasi-Monte Carlo (QMC) and scrambled QMC algorithms based on Sobol sequences are performed to support the theoretical studies and to analyze applicability of the algorithms to various classes of problems. The numerical tests show that the Monte Carlo algorithm based on symmetrised shaking of Sobol sequences gives reliable results for multidimensional integration problems under consideration.


Global sensitivity analysis Analysis for independent inputs Monte Carlo and quasi-Monte Carlo algorithms Optimal Monte Carlo methods 



The research reported in this paper is partly supported by the Bulgarian NSF Grants DTK 02/44/2009 and DMU 03/61/2011.


  1. 1.
    Antonov, I., Saleev, V.: An economic method of computing L P τ-sequences. USSR Comput. Math. Math. Phys. 19, 252–256 (1979)MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    Bradley, P., Fox, B.: Algorithm 659: implementing Sobol’s quasi random sequence generator. ACM Trans. Math. Software 14(1), 88–100 (1988)CrossRefGoogle Scholar
  3. 3.
    Dimov, I.T.: Monte Carlo Methods for Applied Scientists. World Scientific, London (2008)zbMATHGoogle Scholar
  4. 4.
    Dimov, I.T., Farago, I., Havasi, A., Zlatev, Z.: Operator splitting and commutativity analysis in the Danish Eulerian Model. Math. Comput. Simulat. 67, 217–233 (2004)MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Dimov, I.T., Ostromsky, Tz., Zlatev, Z.: Challenges in using splitting techniques for large-scale environmental modeling. In: Farago, I., Georgiev, K., Havasi, A. (eds.) Advances in Air Pollution Modeling for Environmental Security. NATO Science Series 54, pp. 115–132. Springer, Dordrecht (2005)CrossRefGoogle Scholar
  6. 6.
    Dimov, I.T., Georgieva, R.: Monte Carlo method for numerical integration based on Sobol’s sequences. In: Dimov, I., Dimova, S., Kolkovska, N. (eds.) Numerical Methods and Applications. Lecture Notes in Computer Science 6046, pp. 50–59. Springer, Berlin (2011)Google Scholar
  7. 7.
    Dimov, I.T., Georgieva, R., Ostromsky, Tz., Zlatev, Z.: Advanced algorithms for multidimensional sensitivity studies of large-scale air pollution models based on Sobol sequences. Comput. Math. Appl. 65(3), 338–351 (2013). doi: 10.1016/j.camwa.2012.07.005Google Scholar
  8. 8.
    Faure, H., Tezuka, S.: Another random scrambling of digital (t, s)-sequences. In: (Fang, K., Hickernell, F., Niederreiter, H. (eds.) Monte Carlo and Quasi-Monte Carlo Methods. Springer, Berlin, pp. 242–256 (2000)Google Scholar
  9. 9.
    Homma, T., Saltelli, A.: Importance measures in global sensitivity analysis of nonlinear models. Reliab. Eng. Syst. Saf. 52, 1–17 (1996)CrossRefGoogle Scholar
  10. 10.
    Hong, H., Hickernell, F.: Algorithm 823: implementing scrambled digital sequences. ACM Trans. Math. Software 29(2), 95–109 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  11. 11.
    Joe, S., Kuo, F.: Constructing Sobol’ sequences with better two-dimensional projections. SIAM J. Sci. Comput. 30, 2635–2654 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  12. 12.
    Kucherenko, S., Feil, B., Shah, N., Mauntz, W.: The identification of model effective dimensions using global sensitivity analysis. Reliab. Eng. Syst. Saf. 96, 440–449 (2011)CrossRefGoogle Scholar
  13. 13.
    L’Ecuyer, P., Lecot, C., Tuffin, B.: A randomized quasi-Monte Carlo simulation method for Markov chains. Oper. Res. 56(4), 958–975 (2008)zbMATHCrossRefGoogle Scholar
  14. 14.
    L’Ecuyer, P., Lemieux, C.: Recent advances in randomized quasi-Monte Carlo methods. In: Dror, M., L’Ecuyer, P., Szidarovszki, F. (eds.) Modeling Uncertainty: An Examination of Stochastic Theory, Methods, and Applications, pp. 419–474. Kluwer, Boston (2002)Google Scholar
  15. 15.
    Levitan, Y., Markovich, N., Rozin, S., Sobol, I.: On quasi-random sequences for numerical computations. USSR Comput. Math. Math. Phys. 28(5), 755–759 (1988)MathSciNetzbMATHGoogle Scholar
  16. 16.
    Marchuk, G.I.: Mathematical Modeling for the Problem of the Environment, Studies in Mathematics and Applications, No. 16. North-Holland, Amsterdam (1985)Google Scholar
  17. 17.
    Matousek, J.: On the L 2-discrepancy for anchored boxes. J. Complex. 14, 527–556 (1998)MathSciNetzbMATHCrossRefGoogle Scholar
  18. 18.
    Niederreiter, H.: Low-discrepancy and low-dispersion sequences. J. Number Theor. 30, 51–70 (1988)MathSciNetzbMATHCrossRefGoogle Scholar
  19. 19.
    Owen, A.: Randomly permuted (t, m, s)-nets and (t, s)-sequences. In: Niederreiter, H., Shiue, P.J.-S. (eds.) Monte Carlo and Quasi-Monte Carlo Methods in Scientific Computing. Lecture Notes in Statistics, vol. 106, pp. 299–317. Springer, New York (1995)CrossRefGoogle Scholar
  20. 20.
    Owen, A.: Variance and discrepancy with alternative scramblings. ACM Trans. Comput. Logic. V, 1–16 (2002)Google Scholar
  21. 21.
    Saito, M., Matsumoto, M.: SIMD-oriented Fast Mersenne Twister: a 128-bit pseudorandom number generator. In: Keller, A., Heinrich, S., Niederreiter, H. (eds.) Monte Carlo and Quasi-Monte Carlo Methods 2006, pp. 607–622. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  22. 22.
    Saltelli, A., Tarantola, S., Campolongo, F., Ratto, M.: Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models. Halsted Press, New York (2004)Google Scholar
  23. 23.
    Sobol, I.M.: Monte Carlo Numerical Methods. Nauka, Moscow (1973) (in Russian)zbMATHGoogle Scholar
  24. 24.
    Sobol, I.M.: On the systematic search in a hypercube. SIAM J. Numer. Anal. 16, 790–793 (1979)MathSciNetzbMATHCrossRefGoogle Scholar
  25. 25.
    Sobol, I.M.: On quadratic formulas for functions of several variables satisfying a general Lipschitz condition. USSR Comput. Math. Math. Phys. 29(6), 936–941 (1989)MathSciNetGoogle Scholar
  26. 26.
    Sobol, I.M.: Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates. Math. Comput. Simulat. 55(1–3), 271–280 (2001)MathSciNetzbMATHCrossRefGoogle Scholar
  27. 27.
    Sobol, I., Asotsky, D., Kreinin, A., Kucherenko, S.: Construction and comparison of high-dimensional Sobol’ generators. Wilmott J. 2011, 67–79 (2011)Google Scholar
  28. 28.
    Sobol, I., Myshetskaya, E.: Monte Carlo estimators for small sensitivity indices. Monte Carlo Meth. Appl. 13(5–6), 455–465 (2007)MathSciNetzbMATHGoogle Scholar
  29. 29.
    Tezuka, S.: Uniform Random Numbers, Theory and Practice. Kluwer Academic Publishers, Boston; IBM Japan, Tokyo (1995)Google Scholar
  30. 30.
    Weyl, H.: Ueber die Gleichverteilung von Zahlen mod Eins. Math. Ann. 77(3), 313–352 (1916)MathSciNetzbMATHCrossRefGoogle Scholar
  31. 31.
  32. 32.
    SIMD-oriented Fast Mersenne Twister (SFMT) ( ~m-mat/MT/SFMT/).
  33. 33.
    Zlatev, Z., Dimov, I.T.: Computational and Numerical Challenges in Environmental Modelling. Elsevier, Amsterdam (2006)zbMATHGoogle Scholar
  34. 34.
    Zlatev, Z., Dimov, I.T., Georgiev, K.: Three-dimensional version of the Danish Eulerian model. Z. Angew. Math. Mech. 76(S4), 473–476 (1996)zbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Department of Parallel AlgorithmsIICT, Bulgarian Academy of SciencesSofiaBulgaria

Personalised recommendations