机器学习辅助贝叶斯推断 NIF 内爆的混合和热点条件。

IF 1.6 3区物理与天体物理 Q3 PHYSICS, FLUIDS & PLASMAS

High Energy Density Physics Pub Date : 2024-01-22 DOI:10.1016/j.hedp.2024.101077

B.A. Hammel, B.D. Hammel, H.A. Scott, J. Luc Peterson

{"title":"机器学习辅助贝叶斯推断 NIF 内爆的混合和热点条件。","authors":"B.A. Hammel, B.D. Hammel, H.A. Scott, J. Luc Peterson","doi":"10.1016/j.hedp.2024.101077","DOIUrl":null,"url":null,"abstract":"<div><p>Experiments on the National Ignition Facility (NIF) have provided clear evidence of ablator material mixing into the Hot-Spot, leading to degraded performance. However, inferring the amount of mix and Hot-Spot conditions from typical experimental observations (e.g. x-ray spectra and images) is highly challenging. We have developed an analysis method that utilizes machine learning assisted Bayesian inference to find the probability distributions of the Hot-Spot and mix conditions. This approach uses a neural network, trained on an idealized 2-dimensional representation of the Hot-Spot and mix distribution, and Bayesian inference to find the statistical distributions of Hot-Spot conditions that provide a match with observations. We have tested this method with synthetic data from simulations.</p></div>","PeriodicalId":49267,"journal":{"name":"High Energy Density Physics","volume":"50 ","pages":"Article 101077"},"PeriodicalIF":1.6000,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning assisted bayesian inference of mix and hot-spot conditions in NIF implosions\",\"authors\":\"B.A. Hammel, B.D. Hammel, H.A. Scott, J. Luc Peterson\",\"doi\":\"10.1016/j.hedp.2024.101077\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Experiments on the National Ignition Facility (NIF) have provided clear evidence of ablator material mixing into the Hot-Spot, leading to degraded performance. However, inferring the amount of mix and Hot-Spot conditions from typical experimental observations (e.g. x-ray spectra and images) is highly challenging. We have developed an analysis method that utilizes machine learning assisted Bayesian inference to find the probability distributions of the Hot-Spot and mix conditions. This approach uses a neural network, trained on an idealized 2-dimensional representation of the Hot-Spot and mix distribution, and Bayesian inference to find the statistical distributions of Hot-Spot conditions that provide a match with observations. We have tested this method with synthetic data from simulations.</p></div>\",\"PeriodicalId\":49267,\"journal\":{\"name\":\"High Energy Density Physics\",\"volume\":\"50 \",\"pages\":\"Article 101077\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2024-01-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"High Energy Density Physics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1574181824000028\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"PHYSICS, FLUIDS & PLASMAS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"High Energy Density Physics","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1574181824000028","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PHYSICS, FLUIDS & PLASMAS","Score":null,"Total":0}

引用次数: 0

摘要

在国家点火装置（NIF）上进行的实验提供了烧蚀器材料混入热点导致性能下降的明显证据。然而，从典型的实验观察结果（如 X 射线光谱和图像）中推断混合量和热斑条件极具挑战性。我们开发了一种分析方法，利用机器学习辅助贝叶斯推理，找到热斑和混合情况的概率分布。这种方法使用一个神经网络，在理想化的热斑和混合分布的二维表示上进行训练，并利用贝叶斯推理找到与观测结果相匹配的热斑条件的统计分布。我们用模拟的合成数据对这种方法进行了测试。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Machine learning assisted bayesian inference of mix and hot-spot conditions in NIF implosions

Experiments on the National Ignition Facility (NIF) have provided clear evidence of ablator material mixing into the Hot-Spot, leading to degraded performance. However, inferring the amount of mix and Hot-Spot conditions from typical experimental observations (e.g. x-ray spectra and images) is highly challenging. We have developed an analysis method that utilizes machine learning assisted Bayesian inference to find the probability distributions of the Hot-Spot and mix conditions. This approach uses a neural network, trained on an idealized 2-dimensional representation of the Hot-Spot and mix distribution, and Bayesian inference to find the statistical distributions of Hot-Spot conditions that provide a match with observations. We have tested this method with synthetic data from simulations.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

High Energy Density Physics PHYSICS, FLUIDS & PLASMAS-

CiteScore

4.20

自引率

6.20%

发文量

审稿时长

6-12 weeks

期刊介绍： High Energy Density Physics is an international journal covering original experimental and related theoretical work studying the physics of matter and radiation under extreme conditions. ''High energy density'' is understood to be an energy density exceeding about 1011 J/m3. The editors and the publisher are committed to provide this fast-growing community with a dedicated high quality channel to distribute their original findings. Papers suitable for publication in this journal cover topics in both the warm and hot dense matter regimes, such as laboratory studies relevant to non-LTE kinetics at extreme conditions, planetary interiors, astrophysical phenomena, inertial fusion and includes studies of, for example, material properties and both stable and unstable hydrodynamics. Developments in associated theoretical areas, for example the modelling of strongly coupled, partially degenerate and relativistic plasmas, are also covered.