Scaled Gaussian Stochastic Process for Computer Model Calibration and Prediction

TL;DR

This paper introduces the scaled Gaussian stochastic process (S-GaSP), a new method for calibrating computer models that improves prediction accuracy by bridging existing calibration techniques and providing a Bayesian computational framework.

Contribution

The paper proposes the S-GaSP, a novel stochastic process that combines $L_2$ and GaSP calibration methods, enhancing model calibration and prediction accuracy.

Findings

S-GaSP outperforms traditional GaSP calibration in predictive accuracy.

The approach effectively handles calibration parameter unidentifiability.

Numerical experiments demonstrate improved calibration and prediction with S-GaSP.

Abstract

We consider the problem of calibrating an imperfect computer model using experimental data. To compensate the misspecification of the computer model and make more accurate predictions, a discrepancy function is often included and modeled via a Gaussian stochastic process (GaSP). The calibrated computer model alone, however, sometimes fits the experimental data poorly, as the calibration parameters become unidentifiable. In this work, we propose the scaled Gaussian stochastic process (S-GaSP), a novel stochastic process that bridges the gap between two predominant methods, namely the $L_2$ calibration and the GaSP calibration. It is shown that our approach performs well in both calibration and prediction. A computationally feasible approach is introduced for this new model under the Bayesian paradigm. Compared with the GaSP calibration, the S-GaSP calibration enables the calibrated computer model itself to predict the reality well, based on the posterior distribution of the calibration parameters. Numerical comparisons of the simulated and real data are provided to illustrate the connections and differences between the proposed S-GaSP and other alternative approaches.