onr:"swepub:oai:DiVA.org:kth-328777"
Search: onr:"swepub:oai:DiVA.org:kth-328777" > Developing deep lea...
- 1 of 1
- Previous record
- Next record
- To hitlist
Developing deep learning algorithms for inferring upstream separatrix density at JET
-
- Kit, A. (author)
- Univ Helsinki, FI-00014 Helsinki, Finland.
-
- Jarvinen, A. E. (author)
- Univ Helsinki, FI-00014 Helsinki, Finland.;VTT Tech Res Ctr Finland, FI-02044 Espoo, Finland.
-
- Wiesen, S. (author)
- Forschungszentrum Julich, Inst Energie & Klimaforsch Plasmaphys, DE-52425 Julich, Germany.
- show more...
- show less...
- Univ Helsinki, FI-00014 Helsinki, Finland Univ Helsinki, FI-00014 Helsinki, Finland.;VTT Tech Res Ctr Finland, FI-02044 Espoo, Finland. (creator_code:org_t)
- Elsevier BV, 2023
- 2023
- English.
- In: Nuclear Materials and Energy. - : Elsevier BV. - 2352-1791. ; 34
- Journal article (peer-reviewed)
Abstract
Subject headings
Close
- Predictive and real-time inference capability for the upstream separatrix electron density, ne, sep, is essential for design and control of core-edge integrated plasma scenarios. In this study, both supervised and semi -supervised machine learning algorithms are explored to establish direct mapping as well as indirect compressed representation of the pedestal profiles for predictions and inference of ne, sep. Based on the EUROfusion pedestal database for JET (Frassinetti et al., 2021), a tabular dataset was created, consisting of machine parameters, fraction of ELM cycle, high resolution Thomson scattering profiles of electron density and temperature, and ne, sep for 608 JET shots. Using the tabular dataset, the direct mapping approach provides a mapping of machine parameters and ELM percentage to ne, sep. Through representation learning, a compressed representation of the experimental pedestal electron density and temperature profiles is established. By conditioning the representation with machine control parameters, a probabilistic generative predictive model is established. For prediction, the machine parameters can be used to establish a conditional distribution of the compressed pedestal profiles, and the decoder that is trained as part of the algorithm can be used to decode the compressed representation back to full pedestal profiles. Although, in this work, a proof-of-principle for predicting and inferring ne, sep is given, such a representation learning can be used also for many other applications as the full pedestal profile is predicted. An implementation of this work can be found at https://github.com/ fusionby2030/psi_2022.
Subject headings
- NATURVETENSKAP -- Fysik -- Fusion, plasma och rymdfysik (hsv//swe)
- NATURAL SCIENCES -- Physical Sciences -- Fusion, Plasma and Space Physics (hsv//eng)
Keyword
- Separatrix
- Machine learning
- JET
- Representation learning
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
- Nuclear Materials and Energy (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Kit, A.
- Jarvinen, A. E.
- Wiesen, S.
- Poels, Y.
- Frassinetti, Lor ...
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Physical Science ...
- and Fusion Plasma an ...
- Articles in the publication
- Nuclear Material ...
- By the university
- Royal Institute of Technology
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
