Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloDeep neural networks for plasma tomography with applications to JET and COMPASS
Anno di pubblicazione2019
FormatoElettronico
Autore/iCarvalho D.D.; Ferreira D.R.; Carvalho P.J.; Imrisek M.; Mlynar J.; Fernandes H.; Jet Contributors
Affiliazioni autoriEUROfusion Consortium, Culham Science Centre, Abingdon, OX14 3DB, EUROfusion Consortium, JET, Culham Science Centre, Abingdon, OX14 3DB, United Kingdom; Instituto de Plasmas e Fusão Nuclear, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, 1049-001, Instituto de Plasmas e Fusão Nuclear, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisboa, Portugal; Instituto de Plasmas e Fusão Nuclear, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, 1049-001, Instituto de Plasmas e Fusão Nuclear, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisboa, Portugal; Institute of Plasma Physics AS CR, Prague, Institute of Plasma Physics AS CR, Prague, Czech Republic; et al.
Autori CNR e affiliazioni
  • DAVIDE RIGAMONTI
  • STEFAN SCHMUCK
  • DANIELE BRUNETTI
  • ALBERTO MARIANI
  • ANDREA MURARI
  • NICOLA POMARO
  • CARLO SOZZI
  • CESARE TALIERCIO
  • FRANCESCO MAURO GHEZZI
  • GABRIELE GERVASINI
  • PAOLO INNOCENTE
  • NICOLA VIANELLO
  • ITALO PREDEBON
  • DAVID TERRANOVA
  • PAOLO PIOVESAN
  • LORENZO FIGINI
  • DANIELE BONFIGLIO
  • MATTEO BROMBIN
  • ENZO LAZZARO
  • SILVANA NOWAK
  • LAURA LAGUARDIA
  • ENRICO PERELLI CIPPO
  • DARIA RICCI
  • EDOARDO ALESSI
  • LUCA CARLO GIACOMELLI
  • MARIA ESTER PUIATTI
  • ROBERTO PACCAGNELLA
  • FEDERICA CAUSA
  • MARICA REBAI
  • ANDREA MURARO
  • ANDREA UCCELLO
  • MARCO VALISA
  • CHIARA MARCHETTO
  • MARCO TARDOCCHI
  • LORELLA CARRARO
  • PAOLA MANTICA
  • GABRIELE MANDUCHI
  • ROBERTO PASQUALOTTO
Lingua/e
  • inglese
AbstractConvolutional neural networks (CNNs) have found applications in many image processing tasks, such as feature extraction, image classification, and object recognition. It has also been shown that the inverse of CNNs, so-called deconvolutional neural networks, can be used for inverse problems such as plasma tomography. In essence, plasma tomography consists in reconstructing the 2D plasma profile on a poloidal cross-section of a fusion device, based on line-integrated measurements from multiple radiation detectors. Since the reconstruction process is computationally intensive, a deconvolutional neural network trained to produce the same results will yield a significant computational speedup, at the expense of a small error which can be assessed using different metrics. In this work, we discuss the design principles behind such networks, including the use of multiple layers, how they can be stacked, and how their dimensions can be tuned according to the number of detectors and the desired tomographic resolution for a given fusion device. We describe the application of such networks at JET and COMPASS, where at JET we use the bolometer system, and at COMPASS we use the soft X-ray diagnostic based on photodiode arrays.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da1
Pagine a6
Pagine totali6
RivistaJournal of instrumentation
Attiva dal 2006
Editore: Institute of Physics Publishing - Bristol
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 1748-0221
Titolo chiave: Journal of instrumentation
Titolo proprio: Journal of instrumentation.
Numero volume della rivista14
Fascicolo della rivista9
DOI10.1088/1748-0221/14/09/C09011
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85074284403)
  • ISI Web of Science (WOS) (Codice:000486989800011)
Parole chiaveComputerized Tomography (CT) and Computed Radiography (CR), Plasma diagnostics - interferometry spectroscopy and imaging
Link (URL, URI)https://iopscience.iop.org/article/10.1088/1748-0221/14/09/C09011/meta
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione23/08/2019
Note/Altre informazioniL'elenco completo degli autori e delle rispettive affiliazioni è disponibile alla pagina Web of Science http://biblioproxy.cnr.it:2084/full_record.do?product=UA&search_mode=GeneralSearch&qid=9&SID=F5c9GA7T7xpIcdV9Wza&page=1&doc=1 // This work has been carried out within the framework of the EUROfusion Consortium and hasreceived funding from the Euratom research and training programme 2014-2018 and 2019-2020under grant agreement No 633053. / http://www.scopus.com/inward/record.url?eid=2-s2.0-85074284403&partnerID=q2rCbXpz
Strutture CNR
  • IFP — Istituto di fisica del plasma "Piero Caldirola"
  • IGI — Istituto gas ionizzati
  • ISC — Istituto dei sistemi complessi
  • ISTP — Istituto per la Scienza e Tecnologia dei Plasmi
Moduli/Attività/Sottoprogetti CNR
  • DIT.AD020.001.001 : EUROfusion
  • DIT.AD020.019.001 : attività di supporto a ITER e DEMO
Progetti Europei
Allegati
Deep neural networks for plasma tomography with applications to JETand COMPASS (documento privato )
Descrizione: L'allegato contiene l'articolo così come pubblicato. / The annex contains the article as published.
Tipo documento: application/pdf