Transfer learning to model inertial confinement fusion experiments

TL;DR

This paper introduces a hierarchical transfer learning approach using neural networks to calibrate low fidelity simulations to high fidelity simulations and experimental data in inertial confinement fusion, improving predictive accuracy and enabling efficient design optimization.

Contribution

The paper presents a novel hierarchical transfer learning method that calibrates simulations to experiments in ICF, reducing computational costs and enhancing predictive capabilities.

Findings

Models calibrated with transfer learning outperform pure simulations in predicting Omega experiments.

Calibrated models accurately forecast future experiments, aiding in optimal implosion design.

Hierarchical transfer learning accelerates the calibration process and improves model fidelity.

Abstract

Inertial confinement fusion (ICF) experiments are designed using computer simulations that are approximations of reality, and therefore must be calibrated to accurately predict experimental observations. In this work, we propose a novel nonlinear technique for calibrating from simulations to experiments, or from low fidelity simulations to high fidelity simulations, via "transfer learning". Transfer learning is a commonly used technique in the machine learning community, in which models trained on one task are partially retrained to solve a separate, but related task, for which there is a limited quantity of data. We introduce the idea of hierarchical transfer learning, in which neural networks trained on low fidelity models are calibrated to high fidelity models, then to experimental data. This technique essentially bootstraps the calibration process, enabling the creation of models which predict high fidelity simulations or experiments with minimal computational cost. We apply this technique to a database of ICF simulations and experiments carried out at the Omega laser facility. Transfer learning with deep neural networks enables the creation of models that are more predictive of Omega experiments than simulations alone. The calibrated models accurately predict future Omega experiments, and are used to search for new, optimal implosion designs.