Sequential Bayesian experimental design for calibration of expensive simulation models

TL;DR

This paper introduces a sequential Bayesian experimental design method that adaptively selects parameters for building emulators, significantly improving calibration efficiency for expensive simulation models.

Contribution

It proposes a novel criterion for parameter selection that balances exploration and exploitation to efficiently learn the posterior density of model parameters.

Findings

Improved calibration efficiency demonstrated on simulation experiments.

Effective balancing of exploration and exploitation in parameter selection.

Enhanced accuracy in posterior density estimation.

Abstract

Simulation models of critical systems often have parameters that need to be calibrated using observed data. For expensive simulation models, calibration is done using an emulator of the simulation model built on simulation output at different parameter settings. Using intelligent and adaptive selection of parameters to build the emulator can drastically improve the efficiency of the calibration process. The article proposes a sequential framework with a novel criterion for parameter selection that targets learning the posterior density of the parameters. The emergent behavior from this criterion is that exploration happens by selecting parameters in uncertain posterior regions while simultaneously exploitation happens by selecting parameters in regions of high posterior density. The advantages of the proposed method are illustrated using several simulation experiments and a nuclear physics reaction model.