Learning and Optimization with Bayesian Hybrid Models
This addresses the challenge of data-informed decision-making under uncertainty for applications like ballistic systems, though it appears incremental as it builds on existing hybrid modeling concepts.
The paper tackled the problem of systematic bias in models by comparing Bayesian hybrid models, which combine physics-based insights with machine learning, against pure physics-based and machine learning approaches in a ballistic firing case study, showing that hybrid models overcome bias with less data than pure machine learning.
Bayesian hybrid models fuse physics-based insights with machine learning constructs to correct for systematic bias. In this paper, we compare Bayesian hybrid models against physics-based glass-box and Gaussian process black-box surrogate models. We consider ballistic firing as an illustrative case study for a Bayesian decision-making workflow. First, Bayesian calibration is performed to estimate model parameters. We then use the posterior distribution from Bayesian analysis to compute optimal firing conditions to hit a target via a single-stage stochastic program. The case study demonstrates the ability of Bayesian hybrid models to overcome systematic bias from missing physics with less data than the pure machine learning approach. Ultimately, we argue Bayesian hybrid models are an emerging paradigm for data-informed decision-making under parametric and epistemic uncertainty.