Efficient response surface methods based on generic surrogate models

TL;DR

This paper introduces a novel approach to surrogate modeling that leverages structural similarities among related problems using statistical shape models, resulting in more efficient and accurate approximations for computationally expensive simulations.

Contribution

The paper presents a generic surrogate modeling framework that combines structural similarity detection with variable fidelity data to improve approximation efficiency and accuracy.

Findings

Significant improvement in approximation quality demonstrated on an aerodynamic test case.

Reduction in sample evaluations needed for accurate modeling.

Effective use of statistical shape models to identify shared structures.

Abstract

Surrogate models are used for global approximation of responses generated by expensive computer experiments like CFD applications. In this paper, we make use of structural similarities which are shared by a class of related problems. We identify these structures by applying statistical shape models. They are used to build a generic surrogate model approximation to sample data of a new problem of the same class. In a variable fidelity framework the generic surrogate model is combined with the sample data to generate an efficient and globally accurate interpolation model, which requires less costly sample evaluations than ordinary response surface methods. We demonstrate our method with an aerodynamic test case and show that it significantly improves the approximation quality.