Transfer learning driven design optimization for inertial confinement fusion
Transfer learning driven design optimization for inertial confinement fusion
复制标题
迁移学习驱动的惯性约束聚变设计优化
作者：
K. Humbird;J. Peterson
迁移学习是一种很有前途的方法，可以创建将模拟和实验数据整合到一个通用框架中的预测模型。在这种技术中，神经网络首先在大型模拟数据库上进行训练，然后在稀疏的实验数据集上进行部分重新训练，以调整预测，使其与现实更加一致。以前，该技术已被用于创建Omega的预测模型[Humbird等人，IEEE等离子体科学学报48，61-70（2019）]和NIF [Humbird等人，Phys. Plasmas 28，042709（2021）; Kustowski等人，马赫学习. 3，015035（2022）]惯性约束聚变（ICF）实验比单独的模拟更准确。在这项工作中，我们进行了一项迁移学习驱动的假设ICF活动，其目标是通过贝叶斯优化最大化实验中子产额。迁移学习模型在不到20个实验中，在中等大小的设计空间中实现了最大可实现产量的5%以内的产量。此外，我们证明了这种方法是更有效的优化设计比传统的模型校准技术通常采用ICF设计。这种ICF设计方法可以在不确定性下实现实验性能的稳健优化。
Transfer learning is a promising approach to create 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 and 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 [Humbird et al., IEEE Trans. Plasma Sci. 48, 61–70 (2019)] and NIF [Humbird et al., Phys. Plasmas 28, 042709 (2021); Kustowski et al., Mach. Learn. 3, 015035 (2022)] 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.