A Clustered Gaussian Process Model for Computer Experiments

A Gaussian process has been one of the important approaches for emulating computer simulations. However, stationarity assumption a and intractability large-scale dataset limit its availability in practice. In this article, we propose clustered model which segments input data into multiple clusters, each is performed. The stochastic expectation-maximization employed to efficiently fit model. our simulations as well real application solar irradiance emulation, proposed method had smaller mean square errors than main competitors, with competitive computation time, provides valuable insights from by discovering clusters. An R package methodology provided an open repository.