Selection of surrogate modeling techniques for surface approximation and surrogate-based optimization

Abstract

Surrogate models are used to map input data to output data when the actual relationship between the two is unknown or computationally expensive to evaluate for several applications, including surface approximation and surrogate-based optimization. This work evaluates the performance of eight surrogate modeling techniques for those two applications over a set of generated datasets with known characteristics. With this work, we aim to provide general rules for selecting an appropriate surrogate model form based solely on the characteristics of the data being modeled. The computational experiments revealed that there is a dependence of the surrogate modeling performance on the data characteristics. However, in general, multivariate adaptive regression spline models and Gaussian process regression yielded the most accurate predictions for approximating a surface. Random forests, support vector machine regression, and Gaussian process regression models most reliably identified the optimum locations and values when used for surrogate-based optimization.