Please use this identifier to cite or link to this item: https://physrep.ff.bg.ac.rs/handle/123456789/320
DC FieldValueLanguage
dc.contributor.authorTapalaga, Irinelen
dc.contributor.authorTraparić, Ivanen
dc.contributor.authorTrklja Boca, Noraen
dc.contributor.authorPurić, Jagošen
dc.contributor.authorDojčinović, Ivanen
dc.date.accessioned2022-07-12T15:09:06Z-
dc.date.available2022-07-12T15:09:06Z-
dc.date.issued2022-04-01en
dc.identifier.issn0941-0643en
dc.identifier.urihttps://physrep.ff.bg.ac.rs/handle/123456789/320-
dc.description.abstractVarious types of electric fields contained in the laboratory and astrophysical plasma cause a Stark broadening of spectral lines in plasma. Therefore, a large number of spectroscopic diagnostics of laboratory and astrophysical plasma are based on experimental and theoretical studies of Stark broadening of spectral lines in plasma. The topic of the present investigation is the Stark broadening caused by free electrons in plasma and its dependence on certain atomic parameters using a new method based on the machine learning (ML) approach. Analysis of empirical data on atomic parameters was done by ML algorithms with more success that it was previously done by classical methods of data analysis. The correlation parameter obtained by artificial intelligence (AI) is slightly better than the one obtained by classical methods, but the scope of application is much wider. AI conclusions are applicable to any physical system while conclusions made by classical analysis are applicable only to a small portion of these systems. ML algorithms successfully identified quantum nature by analyzing atomic parameters. The biggest issue of classical analysis, which is infinite spectral line broadening for high ionization stages, was resolved by AI with a saturation tendency.en
dc.relation.ispartofNeural Computing and Applicationsen
dc.subjectAtomic dataen
dc.subjectMachine learningen
dc.subjectPlasma physicsen
dc.subjectStark broadeningen
dc.titleStark spectral line broadening modeling by machine learning algorithmsen
dc.typeArticleen
dc.identifier.doi10.1007/s00521-021-06763-4en
dc.identifier.scopus2-s2.0-85123089681en
dc.identifier.urlhttps://api.elsevier.com/content/abstract/scopus_id/85123089681en
dc.relation.issue8en
dc.relation.volume34en
dc.relation.firstpage6349en
dc.relation.lastpage6358en
item.grantfulltextnone-
item.openairetypeArticle-
item.cerifentitytypePublications-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextNo Fulltext-
Appears in Collections:Journal Article
Show simple item record

SCOPUSTM   
Citations

1
checked on Nov 1, 2024

Page view(s)

18
checked on Nov 6, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.