A Framework for Strategic Discovery of Credible Neural Network Surrogate Models under Uncertainty
This work addresses the need for reliable surrogate models in high-stakes decision-making for physical simulations, representing an incremental improvement through a systematic framework.
The study tackled the problem of developing credible neural network surrogate models for complex physical systems under uncertainty by introducing the OPAL-surrogate framework, which systematically balances model complexity, accuracy, and prediction uncertainty, demonstrating effectiveness in applications like porous material deformation and turbulent combustion flow.
The widespread integration of deep neural networks in developing data-driven surrogate models for high-fidelity simulations of complex physical systems highlights the critical necessity for robust uncertainty quantification techniques and credibility assessment methodologies, ensuring the reliable deployment of surrogate models in consequential decision-making. This study presents the Occam Plausibility Algorithm for surrogate models (OPAL-surrogate), providing a systematic framework to uncover predictive neural network-based surrogate models within the large space of potential models, including various neural network classes and choices of architecture and hyperparameters. The framework is grounded in hierarchical Bayesian inferences and employs model validation tests to evaluate the credibility and prediction reliability of the surrogate models under uncertainty. Leveraging these principles, OPAL-surrogate introduces a systematic and efficient strategy for balancing the trade-off between model complexity, accuracy, and prediction uncertainty. The effectiveness of OPAL-surrogate is demonstrated through two modeling problems, including the deformation of porous materials for building insulation and turbulent combustion flow for the ablation of solid fuels within hybrid rocket motors.