“…Metamodels are typically constructed by examining the response of the simulator to a limited number of intelligently chosen parameter sets. Examples of metamodeling techniques include: kriging [ Sacks et al , 1989; Sakata et al , 2003; Simpson and Mistree , 2001], neural networks [ Behzadian et al , 2009; Papadrakakis et al , 1998], radial basis functions [ Hussain et al , 2002; Mugunthan et al , 2005; Mullur and Messac , 2006; Nakayama et al , 2002], multivariate adaptive regression splines [ Friedman , 1991; Jin et al , 2001], high‐dimensional model representation [ Rabitz et al , 1999; Sobol , 2003], treed Gaussian processes [ Gramacy and Lee , 2008], Gaussian emulator machines [ Shahsavani and Grimall , 2009], proper orthogonal decomposition [ Audouze et al , 2009], and others [ Myers and Montgomery , 2002; Wang , 2003].…”