Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloAn alternative approach to the determination of scaling law expressions for the L-H transition in Tokamaks utilizing classification tools instead of regression
Anno di pubblicazione2014
  • Elettronico
  • Cartaceo
Autore/iGaudio P.; Murari A.; Gelfusa M.; Lupelli I.; Vega J.
Affiliazioni autori1,3,4 : Associazione EURATOM-ENEA-University of Rome 'Tor Vergata', Department of Industrial Engineering, Roma, 00133, Italy; / 2 : Consorzio RFX Associazione-EURATOM-ENEA per la Fusione, Padova, 4-35127, Italy (Consorzio RFX - CNR, ENEA, INFN, Università di Padova, Acciaierie Venete SpA -, Corso Stati Uniti 4 - 35127 Padova (Italy); / 5 : Asociación EURATOM/CIEMAT Para Fusión, Avda. Complutense 22, Madrid, 28040, Spain.
Autori CNR e affiliazioni
  • inglese
AbstractA new approach to determine the power law expressions for the threshold between the H and L mode of confinement is presented. The method is based on two powerful machine learning tools for classification: neural networks and support vector machines. Using as inputs clear examples of the systems on either side of the transition, the machine learning tools learn the input-output mapping corresponding to the equations of the boundary separating the confinement regimes. Systematic tests with synthetic data show that the machine learning tools provide results competitive with traditional statistical regression and more robust against random noise and systematic errors. The developed tools have then been applied to the multi-machine International Tokamak Physics Activity International Global Threshold Database of validated ITER-like Tokamak discharges. The machine learning tools converge on the same scaling law parameters obtained with non-linear regression. On the other hand, the developed tools allow a reduction of 50% of the uncertainty in the extrapolations to ITER. Therefore the proposed approach can effectively complement traditional regression since its application poses much less stringent requirements on the experimental data, to be used to determine the scaling laws, because they do not require examples exactly at the moment of the transition.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali12
RivistaPlasma physics and controlled fusion (Print)
Attiva dal 1984
Editore: Institute of Physics, - Bristol
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 0741-3335
Titolo chiave: Plasma physics and controlled fusion (Print)
Titolo proprio: Plasma physics and controlled fusion. (Print)
Titolo abbreviato: Plasma phys. control. fusion (Print)
Numero volume della rivista56
Fascicolo della rivista11
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-84908032814)
  • ISI Web of Science (WOS) (Codice:000344009000003)
Parole chiaveL-H threshold, neural networks, power law, support vector machines
Link (URL, URI)
Titolo parallelo-
Scadenza embargo-
Data di accettazione10/07/2014
Note/Altre informazioniArticle Number 114002; Plasma Physics and Controlled Fusion (online) e-ISSN: 1361-6587;; /
Strutture CNR
  • IGI — Istituto gas ionizzati
Moduli/Attività/Sottoprogetti CNR
  • ET.P05.003.001 : Esperimento RFX ed attività collegate
Progetti Europei
An alternative approach to the determination of scaling law expressions for the L-H transition (documento privato )
Descrizione: L'allegato contiene l'articolo così come pubblicato. / The Annex contains the article as published.
Tipo documento: application/pdf

Dati associati a vecchie tipologie
I dati associati a vecchie tipologie non sono modificabili, derivano dal cambiamento della tipologia di prodotto e hanno solo valore storico.
Citazione bibliograficaGaudio, P., Murari, A., Gelfusa, M., Lupelli, I., & Vega, J. (2014). An alternative approach to the determination of scaling law expressions for the L-H transition in Tokamaks utilizing classification tools instead of regression. Plasma Physics and Controlled Fusion, 56(11), 114002.