激光尾流场加速器的变分神经网络建模

IF 5.2 1区 物理与天体物理 Q1 OPTICS High Power Laser Science and Engineering Pub Date : 2023-01-06 DOI:10.1017/hpl.2022.47
M. Streeter, C. Colgan, C. Cobo, C. Arran, E. Los, R. Watt, N. Bourgeois, L. Calvin, J. Carderelli, N. Cavanagh, S. Dann, R. Fitzgarrald, E. Gerstmayr, A. Joglekar, B. Kettle, P. McKenna, C. Murphy, Z. Najmudin, P. Parsons, Q. Qian, P. Rajeev, C. Ridgers, D. Symes, A. Thomas, G. Sarri, S. Mangles
{"title":"激光尾流场加速器的变分神经网络建模","authors":"M. Streeter, C. Colgan, C. Cobo, C. Arran, E. Los, R. Watt, N. Bourgeois, L. Calvin, J. Carderelli, N. Cavanagh, S. Dann, R. Fitzgarrald, E. Gerstmayr, A. Joglekar, B. Kettle, P. McKenna, C. Murphy, Z. Najmudin, P. Parsons, Q. Qian, P. Rajeev, C. Ridgers, D. Symes, A. Thomas, G. Sarri, S. Mangles","doi":"10.1017/hpl.2022.47","DOIUrl":null,"url":null,"abstract":"Abstract A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.","PeriodicalId":54285,"journal":{"name":"High Power Laser Science and Engineering","volume":"200 1","pages":""},"PeriodicalIF":5.2000,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Laser wakefield accelerator modelling with variational neural networks\",\"authors\":\"M. Streeter, C. Colgan, C. Cobo, C. Arran, E. Los, R. Watt, N. Bourgeois, L. Calvin, J. Carderelli, N. Cavanagh, S. Dann, R. Fitzgarrald, E. Gerstmayr, A. Joglekar, B. Kettle, P. McKenna, C. Murphy, Z. Najmudin, P. Parsons, Q. Qian, P. Rajeev, C. Ridgers, D. Symes, A. Thomas, G. Sarri, S. Mangles\",\"doi\":\"10.1017/hpl.2022.47\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.\",\"PeriodicalId\":54285,\"journal\":{\"name\":\"High Power Laser Science and Engineering\",\"volume\":\"200 1\",\"pages\":\"\"},\"PeriodicalIF\":5.2000,\"publicationDate\":\"2023-01-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"High Power Laser Science and Engineering\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1017/hpl.2022.47\",\"RegionNum\":1,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"OPTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"High Power Laser Science and Engineering","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1017/hpl.2022.47","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 4

摘要

摘要为预测gev级激光尾流场加速器产生的电子能谱,建立了机器学习模型。该模型由变分卷积神经网络构建,将二次激光和等离子体诊断结果映射到生成的电子谱。用一个训练好的网络集合来预测电子能谱,并对预测的不确定性进行估计。预计这种方法将有助于在进行任何可以改变或破坏光束的过程之前推断电子能谱。此外,该模型还提供了由于激光能量和等离子体电子密度的随机波动而导致的电子束特性的缩放的见解。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Laser wakefield accelerator modelling with variational neural networks
Abstract A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.
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 Power Laser Science and Engineering
High Power Laser Science and Engineering Physics and Astronomy-Nuclear and High Energy Physics
CiteScore
7.10
自引率
4.20%
发文量
401
审稿时长
21 weeks
期刊介绍: High Power Laser Science and Engineering (HPLaser) is an international, peer-reviewed open access journal which focuses on all aspects of high power laser science and engineering. HPLaser publishes research that seeks to uncover the underlying science and engineering in the fields of high energy density physics, high power lasers, advanced laser technology and applications and laser components. Topics covered include laser-plasma interaction, ultra-intense ultra-short pulse laser interaction with matter, attosecond physics, laser design, modelling and optimization, laser amplifiers, nonlinear optics, laser engineering, optical materials, optical devices, fiber lasers, diode-pumped solid state lasers and excimer lasers.
期刊最新文献
Efficient dual-stage all-solid-state post-compression for 100 W level ultrafast lasers Compression and acceleration processes of spherical shells in gold cones Design and optimization methods towards a 10 kW high beam quality fiber laser based on the counter tandem pumping scheme Precise mode control of mid-infrared high-power laser diodes using on-chip advanced sawtooth waveguide designs New grating compressor designs for XCELS and SEL-100 PW projects
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1