Polynomial Chaos Expansions (PCE) represent a class of methods which employ orthonormal polynomials to construct approximate response surfaces (metamodels or surrogate models) to identify a mapping between inputs and outputs of a numerical model PCE1
. .PolynomialChaosExpansion
methods can be directly used for moment estimation and sensitivity analysis (Sobol indices). A PCE object can be instantiated from the class .PolynomialChaosExpansion
. The method can be used for models of both one-dimensional and multi-dimensional outputs.
Let us consider a computational model Y = ℳ(x), with Y ∈ ℝ and a random vector with independent components X ∈ ℝM described by the joint probability density function fX. The polynomial chaos expansion of ℳ(x) is
Y = ℳ(x) = ∑α ∈ ℕMyαΨα(X)
where the Ψα(X) are multivariate polynomials orthonormal with respect to fX and yα ∈ ℝ are the corresponding coefficients.
Practically, the above sum needs to be truncated to a finite sum so that α ∈ A where A ⊂ ℕM. The polynomial basis Ψα(X) is built from a set of univariate orthonormal polynomials ϕji(xi) which satisfy the following relation
<ϕji(xi), ϕki(xi)> = ∫DXiϕji(xi), ϕki(xi)fXi(xi)dxi = δjk
The multivariate polynomials Ψα(X) are assembled as the tensor product of their univariate counterparts as follows
which are also orthonormal.
Polynomial Bases <pce/polynomial_bases> Polynomials <pce/polynomials> Regressions <pce/regressions> Polynomial Chaos Expansion <pce/pce> Physics-informed Polynomial Chaos Expansion <pce/physics_informed>