Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Deep learning for plasma tomography using the bolometer system at JET
Univ Lisbon, Inst Super Tecn, P-1699 Lisbon, Portugal..
KTH, School of Electrical Engineering (EES), Fusion Plasma Physics.ORCID iD: 0000-0001-7741-3370
KTH, School of Electrical Engineering (EES), Fusion Plasma Physics.
KTH, School of Electrical Engineering (EES), Fusion Plasma Physics.
Show others and affiliations
Number of Authors: 11082017 (English)In: Fusion engineering and design, ISSN 0920-3796, E-ISSN 1873-7196, Vol. 114, p. 18-25Article in journal (Refereed) Published
Abstract [en]

Deep learning is having a profound impact in many fields, especially those that involve some form of image processing. Deep neural networks excel in turning an input image into a set of high-level features. On the other hand, tomography deals with the inverse problem of recreating an image from a number of projections. In plasma diagnostics, tomography aims at reconstructing the cross-section of the plasma from radiation measurements. This reconstruction can be computed with neural networks. However, previous attempts have focused on learning a parametric model of the plasma profile. In this work, we use a deep neural network to produce a full, pixel-by-pixel reconstruction of the plasma profile. For this purpose, we use the overview bolometer system at JET, and we introduce an up-convolutional network that has been trained and tested on a large set of sample tomograms. We show that this network is able to reproduce existing reconstructions with a high level of accuracy, as measured by several metrics.

Place, publisher, year, edition, pages
ELSEVIER SCIENCE SA , 2017. Vol. 114, p. 18-25
Keywords [en]
Plasma diagnostics, Computed tomography, Neural networks, Deep learning
Identifiers
URN: urn:nbn:se:kth:diva-272153DOI: 10.1016/j.fusengdes.2016.11.006ISI: 000393004700004Scopus ID: 2-s2.0-85007427960OAI: oai:DiVA.org:kth-272153DiVA, id: diva2:1425324
Note

QC 20200420

Available from: 2020-04-20 Created: 2020-04-20 Last updated: 2020-04-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Bergsåker, HenricBykov, IgorElevant, ThomasFrassinetti, LorenzoGarcia Carrasco, AlvaroHellsten, TorbjörnIvanova, DaryaJonsson, ThomasMenmuir, SheenaPetersson, PerRachlew, ElisabethRubel, MarekStröm, PetterTholerus, SimonWeckmann, Armin
By organisation
Fusion Plasma PhysicsAtomic and Molecular Physics
In the same journal
Fusion engineering and design

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf