Numerical Study of the Metamodel Validation Process

Complex computer codes are often too time expensive to be directly used to perform uncertainty, sensitivity, optimization and robustness analyses. A widely accepted method to circumvent this problem consists in replacing cpu time expensive computer models by cpu inexpensive mathematical functions, called metamodels. In this paper, we focus on the essential step of the metamodel validation phase which consists in evaluating the metamodel predictivity.It allows to allocate some confidence degrees to the results obtained by using the metamodel instead of the initial numerical model. We propose and test an algorithm which optimizes the distance between the validation points and the metamodel training points in order to estimate the true metamodel predictivity with a minimum number of additional calculations. Comparisons are made with classical validation algorithms and application to a nuclear safety computer code is shown.These tests show the relevance of this new validation design called the Feuillard design.