New paper published in International Journal for Uncertainty Quantification

The paper entitled Stochastic polynomial chaos expansions to emulate stochastic simulators proposes a novel surrogate model called stochastic polynomial chaos expansion (SPCE) to represent stochastic simulators. This stochastic emulator introduces a latent variable and an additional noise variable, on top of the well-defined input variables, to mimic the intrinsic randomness of stochastic models. An adaptive method is developed to build such a surrogate model nonintrusively without the need for replications. The results of various examples show that SPCE is able to well approximate the response distributions, whether unimodal or not, with a reasonable number of model runs.

For more information, please follow external page this link for the publication and this link for the associated report on our internal archive.