Efficient method for variance-based sensitivity analysis
Introduction
In the context of Uncertainty Quantification and Management (UQ&M), sensitivity analysis is used to identify the contribution of different uncertainty sources on the total variance of system/model outputs [1]. This is particularly useful for large scale simulation or design problems, where it is normally impractical to consider all the factors, especially at the outset. Various techniques have been developed for sensitivity analysis. Systematic reviews can be found in [1], [2], [3], [4] . Among these techniques, the variance-based method, also referred to as the Sobol’ Indices, is widely used. It has the benefits of being ‘global’ and ‘model-independent’ [1]; where ‘global’ refers to analysing all the factors simultaneously over the entire region of interest, while ‘model-independent’ means that the approach is sufficiently general to handle different problems, without the need of knowing the inner structure of the models (i.e. models are treated as ‘’black-boxes”).
The development of variance-based sensitivity analysis dates back to 1970s, when Cukier et al [5], [6], [7], Schaibly and Shuler [8], proposed the method of Fourier Amplitude Sensitivity Test (FAST), in which the Fourier Transformation and searching curves were used to decompose the output variances. Similar problems were also referred to as ‘Importance Measure’ by Hora and Iman [9], [10], Ishigami and Homma [11], and Saltelli et al [12], [13]; or ‘Top/Bottom Marginal Variance’ by Jansen [14]. In parallel, Sobol’ adopted the so-called ANOVA (Analysis of Variance)-representation to decompose a function, so that the portions of total variance caused by different factors can be formulated separately [15], [16], [17], [18], [19]. The numerical implementation is based on Monte Carlo Simulation along with multiple sampling sets (also referred as pick-freeze scheme [20]). It was later pointed out by Saltelli that all these methods calculate an equivalent statistical quantity [21], and that with this regard, the Sobol's approach is the most general one [22].
Further research has been focusing on the computational efficiency, which includes: improved sampling strategies (Sobol’ sequences [23], Latin Hyper Cube [24], and Random Balance Design (RBD) [25], [26], [27]); improved formulation of estimators (Jansen [28], Saltelli [29], Sobol’ et al [30]); approximation techniques (quadrature plus Latin Hyper Cube [31], grid quadrature [32]); Bayesian approach based on Gaussian processes (Oakley and O'hagan [33]); and Polynomial Chaos Expansion (PCE) [34], [35], [36], [37], [38], [39], [40] (where the polynomial coefficients are used to obtain the Sobol’ indices), etc.
In general, for most of the aforementioned techniques (except [26], [27]), the computational cost is related to the number of uncertainty sources, and becomes very expensive for high dimensional problems. Thus improving efficiency (i.e. the calculation speed), is still an area requiring further research, especially for early stage computational design, where the problem scale is large, and fast assessments are required.
In this research, a general approach is proposed to approximate the sensitivity indices based on the formulation from Saltelli [1], [2], [29]. In particular, we propose one implementation of the proposed approach, using the Univariate Reduced Quadrature (URQ) method [41], which was originally developed for uncertainty propagation.
The remaining part of the paper is structured as follows. Section 2 contains a background on variance-based sensitivity analysis and a brief description of the URQ method. In Section 3, the general approach for approximation is presented, followed by the detailed formulations incorporated with URQ, which include: the first order, second order, and total effect indices. The method is evaluated in Section 4, using a number of test-cases and is compared to the traditional (benchmark) MCS approach. Finally conclusions and future work are presented in Section 5.
Section snippets
Background
The rationale and the derivation of the variance-based sensitivity analysis method is given by Saltelli in [1], [2], [29]. In this section, only a brief overview is presented, along with a short description of the URQ technique, which forms a part of the method proposed in Section 3.
General approach
The formulations reviewed in Section 2.1 are summarized in Table 2, where the equations are categorised into four options. In the traditional Monte Carlo Simulation (MCS) approach [11], [16], only option 4 is adopted, because the other three options (1, 2, and 3) are computationally too expensive for MCS, due to the nested integrals in the formulations. The rationale of the proposed approach is that, since the nature of these integrals is to solve nested expectations/variances, the calculation
Evaluation
The proposed method is applied on a number of test-cases, and the results are compared with theoretical values (where available) or with estimations from the traditional (benchmark) MCS approach. These include 18 analytical test examples and one practical design case study. The analytical examples are based on single line algebraic equations so that representative mathematical properties can be explored explicitly. By contrast, the practical design case study is based on a complex engineering
Conclusions
Presented in this paper is a method for efficient variance-based sensitivity analysis. The main contribution can be seen in two aspects. The first aspect includes specific formulations allowing to integrate URQ with variance-based sensitivity analysis, which provides an alternative way of calculating Sobol’ indices, with considerable efficiency and effectiveness. The second aspect is regarding the general approach to transforming a sensitivity analysis problem into an uncertainty propagation
References (71)
- et al.
Survey of sampling-based methods for uncertainty and sensitivity analysis
Reliab Eng Syst Saf
(October 2006) - et al.
Nonlinear sensitivity analysis of multiparameter model systems
J Comput Phys
(January 1978) - et al.
Sensitivity analysis for model output
Comput Stat Data Anal
(January 1992) - et al.
Sensitivity analysis of model output: an investigation of new techniques
Comput Stat Data Anal
(1993) - et al.
On the use of variance reducing multipliers in Monte Carlo computations of a global sensitivity index
Comput Phys Commun
(March 1999) Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates
Math Comput Simul
(February 2001)Theorems and examples on high dimensional model representation
Reliab Eng Syst Saf
(2003)- et al.
Importance measures in global sensitivity analysis of nonlinear models
Reliab Eng Syst Saf
(April 1996) - et al.
Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index
Comput Phys Commun
(February 2010) - et al.
Latin hypercube sampling and the propagation of uncertainty in analyses of complex systems
Reliab Eng Syst Saf
(July 2003)