Exclusive Content & Downloads from ASQ

Gaussian Surrogates for Computer Models With Time-Varying Inputs and Outputs

Summary: While time-indexed outputs of computer models are often reduced via principal components, time-indexed inputs often lack the characteristic shapes that make it possible to simplify the outputs. This article describes Gaussian process surrogates that can be used in place of principal component reduction to simplify models with inputs and outputs that are both time-dependent. The article focuses on constructing a covariance structure for the surrogates, but it also addresses experimental issues and demonstrates the use of Gaussian surrogates on a marrow cell model.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

  • Topics: Software and Technology (for statistics, measurement, analysis)
  • Keywords: Computer models, Covariance, Principal components, Computer experiment, Dynamic model, Gaussian stochastic process, Maximin distance design, Meta-model
  • Author: Morris, Max D.
  • Journal: Technometrics