Toward machine-learning-assisted PW-class high-repetition-rate experiments with solid targets

Author:

Mariscal D. A.1ORCID,Djordjevic B. Z.1ORCID,Anirudh R.1ORCID,Jayaraman-Thiagarajan J.1ORCID,Grace E. S.1ORCID,Simpson R. A.1ORCID,Swanson K. K.1ORCID,Galvin T. C.1ORCID,Mittelberger D.1ORCID,Heebner J. E.1ORCID,Muir R.1ORCID,Folsom E.1ORCID,Hill M. P.1ORCID,Feister S.2ORCID,Ito E.2ORCID,Valdez-Sereno K.2ORCID,Rocca J. J.3,Park J.13ORCID,Wang S.3,Hollinger R.3ORCID,Nedbailo R.34ORCID,Sullivan B.3ORCID,Zeraouli G.13ORCID,Shukla A.5ORCID,Turaga P.5ORCID,Sarkar A.1ORCID,Van Essen B.1ORCID,Liu S.1ORCID,Spears B.1,Bremer P.-T.1ORCID,Ma T.1ORCID

Affiliation:

1. Lawrence Livermore National Laboratory 1 , Livermore, California 94550, USA

2. Department of Computer Science, California State University Channel Islands 2 , Camarillo, California 93012, USA

3. Colorado State University 3 , Fort Collins, Colorado 80523, USA

4. University of Texas 4 , Austin, Texas 78712, USA

5. Arizona State University 5 , Tempe, Arizona 85287, USA

Abstract

We present progress in utilizing a machine learning (ML) assisted optimization framework to study the trends in a parameter space defined by spectrally shaped, high-intensity, petawatt-class (8 J, 45 fs) laser pulses interacting with solid targets and give the first simulation-based overview of predicted trends. A neural network (NN) incorporating uncertainty quantification is trained to predict the number of hot electrons generated by the laser–target interaction as a function of pulse shaping parameters. The predictions of this NN serve as the basis function for a Bayesian optimization framework to navigate this space. For post-experimental evaluation, we compare two separate neural network (NN) models. One is based solely on data from experiments, and the other is trained only on ensemble particle-in-cell simulations. Reviewing the predicted and observed trends across the experiment-capable laser parameter search space, we find that both ML models predict a maximal increase in hot electron generation at a level of approximately 12%–18%; however, no statistically significant enhancement was observed in experiments. On direct comparison of the NN models, the average discrepancy is 8.5%, with a maximum of 30%. Since shot-to-shot fluctuations in experiments affect the observations, we evaluate the behavior of our optimization framework by performing virtual experiments that vary the number of repeated observations and the noise levels. Here, we discuss the implications of such a framework for future autonomous exploration platforms in high-repetition-rate experiments.

Funder

Lawrence Livermore National Laboratory

U.S. Department of Energy

Fusion Energy Sciences

Publisher

AIP Publishing

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3