Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulations
This addresses the need for interpretable uncertainty in scientific comparisons between simulations and experiments, though it is incremental as it applies existing Bayesian methods to a specific domain.
The paper tackled the problem of deep neural network surrogates lacking uncertainty estimates for scientific simulations, and demonstrated a variational inference approach that provides calibrated Bayesian uncertainties for inertial confinement fusion simulations, preserving physics-correlations.
Large-scale numerical simulations are used across many scientific disciplines to facilitate experimental development and provide insights into underlying physical processes, but they come with a significant computational cost. Deep neural networks (DNNs) can serve as highly-accurate surrogate models, with the capacity to handle diverse datatypes, offering tremendous speed-ups for prediction and many other downstream tasks. An important use-case for these surrogates is the comparison between simulations and experiments; prediction uncertainty estimates are crucial for making such comparisons meaningful, yet standard DNNs do not provide them. In this work we define the fundamental requirements for a DNN to be useful for scientific applications, and demonstrate a general variational inference approach to equip predictions of scalar and image data from a DNN surrogate model trained on inertial confinement fusion simulations with calibrated Bayesian uncertainties. Critically, these uncertainties are interpretable, meaningful and preserve physics-correlations in the predicted quantities.