Machine learning-driven image synthesis and analysis applications for inertial confinement fusion (invited)

Recent fusion breakeven [Abu-Shawareb et al., Phys. Rev. Lett. 132, 065102 (2024)] in the National Ignition Facility (NIF) motivates an integrated approach to data analysis from multiple diagnostics. Deep neural networks provide a seamless framework for multi-modal data fusion, automated data analys...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Review of scientific instruments 2024-12, Vol.95 (12)
Hauptverfasser: Wolfe, Bradley T., Chu, Pinghan, Nguyen-Fotiadis, Nga T. T., Zhang, Xinhua, Alvarado Alvarez, Mariana, Wang, Zhehui
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 12
container_start_page
container_title Review of scientific instruments
container_volume 95
creator Wolfe, Bradley T.
Chu, Pinghan
Nguyen-Fotiadis, Nga T. T.
Zhang, Xinhua
Alvarado Alvarez, Mariana
Wang, Zhehui
description Recent fusion breakeven [Abu-Shawareb et al., Phys. Rev. Lett. 132, 065102 (2024)] in the National Ignition Facility (NIF) motivates an integrated approach to data analysis from multiple diagnostics. Deep neural networks provide a seamless framework for multi-modal data fusion, automated data analysis, optimization, and uncertainty quantification [Wang et al., arXiv:2401.08390 (2024)]. Here, we summarize different neural network methods for x-ray and neutron imaging data from NIF. To compensate for the small experimental datasets, both model based physics-informed synthetic data generation and deep neural network methods, such as generative adversarial networks, have been successfully implemented to allow a variety of automated workflows in x-ray and neutron image processing. We highlight results in noise emulation, contour analysis for low-mode analysis and asymmetry, denoising, and super-resolution. Further advances in the integrated multi-modal imaging, in sync with experimental validation and uncertainty quantification, will help with the ongoing experimental optimization in NIF, as well as the maturation of alternate inertial confinement fusion (ICF) platforms such as double-shells.
doi_str_mv 10.1063/5.0219412
format Article
fullrecord <record><control><sourceid>proquest_scita</sourceid><recordid>TN_cdi_scitation_primary_10_1063_5_0219412</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3146925412</sourcerecordid><originalsourceid>FETCH-LOGICAL-c238t-3db65e0b26cd4a48b65e72fb9797a80b90e8a819a465ca1c3745d164766187373</originalsourceid><addsrcrecordid>eNp90U1LwzAYB_Agis7pwS8gAS9TqCbN-1GGb6B40XNJ03TLbNOZtIN9e-M2PXgwEMIDP_6Q_wPAGUbXGHFyw65RjhXF-R4YYSRVJnhO9sEIIUIzLqg8AscxLlA6DONDcEQUl5JSNQIfL9rMnbewsTp452dZFdzKeuhaPbMwrn0_t9FFqH2Vrm7Wm2G5bJzRvet8hHUXYEoIvdMNNJ2v09Ba38N6iAnAifMr19vq8gQc1LqJ9nT3jsH7_d3b9DF7fn14mt4-ZyYnss9IVXJmUZlzU1FN5fck8rpUQgktUamQlVpipSlnRmNDBGUV5lRwjqUggozBZJu7DN3nYGNftC4a2zTa226IBcGUq5ylvhK9-EMX3RDSNzeKSU4UQ0ldbpUJXYzB1sUypH7CusCo-N5AwYrdBpI93yUOZWurX_lTeQJXWxCN6zcV_pP2BYcPjYE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3145863950</pqid></control><display><type>article</type><title>Machine learning-driven image synthesis and analysis applications for inertial confinement fusion (invited)</title><source>AIP Journals Complete</source><creator>Wolfe, Bradley T. ; Chu, Pinghan ; Nguyen-Fotiadis, Nga T. T. ; Zhang, Xinhua ; Alvarado Alvarez, Mariana ; Wang, Zhehui</creator><creatorcontrib>Wolfe, Bradley T. ; Chu, Pinghan ; Nguyen-Fotiadis, Nga T. T. ; Zhang, Xinhua ; Alvarado Alvarez, Mariana ; Wang, Zhehui</creatorcontrib><description>Recent fusion breakeven [Abu-Shawareb et al., Phys. Rev. Lett. 132, 065102 (2024)] in the National Ignition Facility (NIF) motivates an integrated approach to data analysis from multiple diagnostics. Deep neural networks provide a seamless framework for multi-modal data fusion, automated data analysis, optimization, and uncertainty quantification [Wang et al., arXiv:2401.08390 (2024)]. Here, we summarize different neural network methods for x-ray and neutron imaging data from NIF. To compensate for the small experimental datasets, both model based physics-informed synthetic data generation and deep neural network methods, such as generative adversarial networks, have been successfully implemented to allow a variety of automated workflows in x-ray and neutron image processing. We highlight results in noise emulation, contour analysis for low-mode analysis and asymmetry, denoising, and super-resolution. Further advances in the integrated multi-modal imaging, in sync with experimental validation and uncertainty quantification, will help with the ongoing experimental optimization in NIF, as well as the maturation of alternate inertial confinement fusion (ICF) platforms such as double-shells.</description><identifier>ISSN: 0034-6748</identifier><identifier>ISSN: 1089-7623</identifier><identifier>EISSN: 1089-7623</identifier><identifier>DOI: 10.1063/5.0219412</identifier><identifier>PMID: 39688449</identifier><identifier>CODEN: RSINAK</identifier><language>eng</language><publisher>United States: American Institute of Physics</publisher><subject>Artificial neural networks ; Automation ; Data analysis ; Data integration ; Generative adversarial networks ; Image processing ; Image resolution ; Inertial confinement fusion ; Integrated approach ; Machine learning ; Modal data ; Neural networks ; Optimization ; Synthetic data ; Uncertainty ; X ray imagery</subject><ispartof>Review of scientific instruments, 2024-12, Vol.95 (12)</ispartof><rights>Author(s)</rights><rights>2024 Author(s). Published under an exclusive license by AIP Publishing.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c238t-3db65e0b26cd4a48b65e72fb9797a80b90e8a819a465ca1c3745d164766187373</cites><orcidid>0000-0003-1372-2910 ; 0000-0003-0473-6843 ; 0009-0007-8358-6711 ; 0000-0002-6830-1614 ; 0000-0003-3672-6666 ; 0000-0001-7826-4063</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubs.aip.org/rsi/article-lookup/doi/10.1063/5.0219412$$EHTML$$P50$$Gscitation$$H</linktohtml><link.rule.ids>314,776,780,790,4498,27901,27902,76127</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39688449$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Wolfe, Bradley T.</creatorcontrib><creatorcontrib>Chu, Pinghan</creatorcontrib><creatorcontrib>Nguyen-Fotiadis, Nga T. T.</creatorcontrib><creatorcontrib>Zhang, Xinhua</creatorcontrib><creatorcontrib>Alvarado Alvarez, Mariana</creatorcontrib><creatorcontrib>Wang, Zhehui</creatorcontrib><title>Machine learning-driven image synthesis and analysis applications for inertial confinement fusion (invited)</title><title>Review of scientific instruments</title><addtitle>Rev Sci Instrum</addtitle><description>Recent fusion breakeven [Abu-Shawareb et al., Phys. Rev. Lett. 132, 065102 (2024)] in the National Ignition Facility (NIF) motivates an integrated approach to data analysis from multiple diagnostics. Deep neural networks provide a seamless framework for multi-modal data fusion, automated data analysis, optimization, and uncertainty quantification [Wang et al., arXiv:2401.08390 (2024)]. Here, we summarize different neural network methods for x-ray and neutron imaging data from NIF. To compensate for the small experimental datasets, both model based physics-informed synthetic data generation and deep neural network methods, such as generative adversarial networks, have been successfully implemented to allow a variety of automated workflows in x-ray and neutron image processing. We highlight results in noise emulation, contour analysis for low-mode analysis and asymmetry, denoising, and super-resolution. Further advances in the integrated multi-modal imaging, in sync with experimental validation and uncertainty quantification, will help with the ongoing experimental optimization in NIF, as well as the maturation of alternate inertial confinement fusion (ICF) platforms such as double-shells.</description><subject>Artificial neural networks</subject><subject>Automation</subject><subject>Data analysis</subject><subject>Data integration</subject><subject>Generative adversarial networks</subject><subject>Image processing</subject><subject>Image resolution</subject><subject>Inertial confinement fusion</subject><subject>Integrated approach</subject><subject>Machine learning</subject><subject>Modal data</subject><subject>Neural networks</subject><subject>Optimization</subject><subject>Synthetic data</subject><subject>Uncertainty</subject><subject>X ray imagery</subject><issn>0034-6748</issn><issn>1089-7623</issn><issn>1089-7623</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp90U1LwzAYB_Agis7pwS8gAS9TqCbN-1GGb6B40XNJ03TLbNOZtIN9e-M2PXgwEMIDP_6Q_wPAGUbXGHFyw65RjhXF-R4YYSRVJnhO9sEIIUIzLqg8AscxLlA6DONDcEQUl5JSNQIfL9rMnbewsTp452dZFdzKeuhaPbMwrn0_t9FFqH2Vrm7Wm2G5bJzRvet8hHUXYEoIvdMNNJ2v09Ba38N6iAnAifMr19vq8gQc1LqJ9nT3jsH7_d3b9DF7fn14mt4-ZyYnss9IVXJmUZlzU1FN5fck8rpUQgktUamQlVpipSlnRmNDBGUV5lRwjqUggozBZJu7DN3nYGNftC4a2zTa226IBcGUq5ylvhK9-EMX3RDSNzeKSU4UQ0ldbpUJXYzB1sUypH7CusCo-N5AwYrdBpI93yUOZWurX_lTeQJXWxCN6zcV_pP2BYcPjYE</recordid><startdate>20241201</startdate><enddate>20241201</enddate><creator>Wolfe, Bradley T.</creator><creator>Chu, Pinghan</creator><creator>Nguyen-Fotiadis, Nga T. T.</creator><creator>Zhang, Xinhua</creator><creator>Alvarado Alvarez, Mariana</creator><creator>Wang, Zhehui</creator><general>American Institute of Physics</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0003-1372-2910</orcidid><orcidid>https://orcid.org/0000-0003-0473-6843</orcidid><orcidid>https://orcid.org/0009-0007-8358-6711</orcidid><orcidid>https://orcid.org/0000-0002-6830-1614</orcidid><orcidid>https://orcid.org/0000-0003-3672-6666</orcidid><orcidid>https://orcid.org/0000-0001-7826-4063</orcidid></search><sort><creationdate>20241201</creationdate><title>Machine learning-driven image synthesis and analysis applications for inertial confinement fusion (invited)</title><author>Wolfe, Bradley T. ; Chu, Pinghan ; Nguyen-Fotiadis, Nga T. T. ; Zhang, Xinhua ; Alvarado Alvarez, Mariana ; Wang, Zhehui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c238t-3db65e0b26cd4a48b65e72fb9797a80b90e8a819a465ca1c3745d164766187373</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial neural networks</topic><topic>Automation</topic><topic>Data analysis</topic><topic>Data integration</topic><topic>Generative adversarial networks</topic><topic>Image processing</topic><topic>Image resolution</topic><topic>Inertial confinement fusion</topic><topic>Integrated approach</topic><topic>Machine learning</topic><topic>Modal data</topic><topic>Neural networks</topic><topic>Optimization</topic><topic>Synthetic data</topic><topic>Uncertainty</topic><topic>X ray imagery</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wolfe, Bradley T.</creatorcontrib><creatorcontrib>Chu, Pinghan</creatorcontrib><creatorcontrib>Nguyen-Fotiadis, Nga T. T.</creatorcontrib><creatorcontrib>Zhang, Xinhua</creatorcontrib><creatorcontrib>Alvarado Alvarez, Mariana</creatorcontrib><creatorcontrib>Wang, Zhehui</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>MEDLINE - Academic</collection><jtitle>Review of scientific instruments</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wolfe, Bradley T.</au><au>Chu, Pinghan</au><au>Nguyen-Fotiadis, Nga T. T.</au><au>Zhang, Xinhua</au><au>Alvarado Alvarez, Mariana</au><au>Wang, Zhehui</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine learning-driven image synthesis and analysis applications for inertial confinement fusion (invited)</atitle><jtitle>Review of scientific instruments</jtitle><addtitle>Rev Sci Instrum</addtitle><date>2024-12-01</date><risdate>2024</risdate><volume>95</volume><issue>12</issue><issn>0034-6748</issn><issn>1089-7623</issn><eissn>1089-7623</eissn><coden>RSINAK</coden><abstract>Recent fusion breakeven [Abu-Shawareb et al., Phys. Rev. Lett. 132, 065102 (2024)] in the National Ignition Facility (NIF) motivates an integrated approach to data analysis from multiple diagnostics. Deep neural networks provide a seamless framework for multi-modal data fusion, automated data analysis, optimization, and uncertainty quantification [Wang et al., arXiv:2401.08390 (2024)]. Here, we summarize different neural network methods for x-ray and neutron imaging data from NIF. To compensate for the small experimental datasets, both model based physics-informed synthetic data generation and deep neural network methods, such as generative adversarial networks, have been successfully implemented to allow a variety of automated workflows in x-ray and neutron image processing. We highlight results in noise emulation, contour analysis for low-mode analysis and asymmetry, denoising, and super-resolution. Further advances in the integrated multi-modal imaging, in sync with experimental validation and uncertainty quantification, will help with the ongoing experimental optimization in NIF, as well as the maturation of alternate inertial confinement fusion (ICF) platforms such as double-shells.</abstract><cop>United States</cop><pub>American Institute of Physics</pub><pmid>39688449</pmid><doi>10.1063/5.0219412</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0003-1372-2910</orcidid><orcidid>https://orcid.org/0000-0003-0473-6843</orcidid><orcidid>https://orcid.org/0009-0007-8358-6711</orcidid><orcidid>https://orcid.org/0000-0002-6830-1614</orcidid><orcidid>https://orcid.org/0000-0003-3672-6666</orcidid><orcidid>https://orcid.org/0000-0001-7826-4063</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0034-6748
ispartof Review of scientific instruments, 2024-12, Vol.95 (12)
issn 0034-6748
1089-7623
1089-7623
language eng
recordid cdi_scitation_primary_10_1063_5_0219412
source AIP Journals Complete
subjects Artificial neural networks
Automation
Data analysis
Data integration
Generative adversarial networks
Image processing
Image resolution
Inertial confinement fusion
Integrated approach
Machine learning
Modal data
Neural networks
Optimization
Synthetic data
Uncertainty
X ray imagery
title Machine learning-driven image synthesis and analysis applications for inertial confinement fusion (invited)
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T04%3A15%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_scita&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20learning-driven%20image%20synthesis%20and%20analysis%20applications%20for%20inertial%20confinement%20fusion%20(invited)&rft.jtitle=Review%20of%20scientific%20instruments&rft.au=Wolfe,%20Bradley%20T.&rft.date=2024-12-01&rft.volume=95&rft.issue=12&rft.issn=0034-6748&rft.eissn=1089-7623&rft.coden=RSINAK&rft_id=info:doi/10.1063/5.0219412&rft_dat=%3Cproquest_scita%3E3146925412%3C/proquest_scita%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3145863950&rft_id=info:pmid/39688449&rfr_iscdi=true