Transfer learning driven design optimization for inertial confinement fusion

TL;DR

This paper demonstrates how transfer learning can efficiently optimize inertial confinement fusion experiments, achieving near-optimal neutron yields with fewer experiments than traditional methods.

Contribution

It introduces a transfer learning-based approach for ICF design optimization, combining simulation and experimental data for improved efficiency and accuracy.

Findings

Achieved neutron yields within 5% of maximum in fewer than 20 experiments.

Outperformed traditional model calibration techniques in design optimization.

Enabled robust optimization under uncertainty.

Abstract

Transfer learning is a promising approach to creating predictive models that incorporate simulation and experimental data into a common framework. In this technique, a neural network is first trained on a large database of simulations, then partially retrained on sparse sets of experimental data to adjust predictions to be more consistent with reality. Previously, this technique has been used to create predictive models of Omega and NIF inertial confinement fusion (ICF) experiments that are more accurate than simulations alone. In this work, we conduct a transfer learning driven hypothetical ICF campaign in which the goal is to maximize experimental neutron yield via Bayesian optimization. The transfer learning model achieves yields within 5% of the maximum achievable yield in a modest-sized design space in fewer than 20 experiments. Furthermore, we demonstrate that this method is more efficient at optimizing designs than traditional model calibration techniques commonly employed in ICF design. Such an approach to ICF design could enable robust optimization of experimental performance under uncertainty.