Skip navigation
Skip navigation

Machine learning for the identification of scaling laws and dynamical systems directly from data in fusion

Murari, A; Vega, J; Mazon, D; Patane, D.; Vagliasindi, G; Arena, P.; Martin, Nigel; Martin, N.F.; Ratta, G.; Caloone, V.; JET-EFDA, .

Description

Original methods to extract equations directly from experimental signals are presented. These techniques have been applied first to the determination of scaling laws for the threshold between the L and H mode of confinement in Tokamaks. The required equations can be extracted from the weights of neural networks and the separating hyperplane of Support Vector Machines. More powerful tools are required for the identification of differential equations directly from the time series of the signals....[Show more]

dc.contributor.authorMurari, A
dc.contributor.authorVega, J
dc.contributor.authorMazon, D
dc.contributor.authorPatane, D.
dc.contributor.authorVagliasindi, G
dc.contributor.authorArena, P.
dc.contributor.authorMartin, Nigel
dc.contributor.authorMartin, N.F.
dc.contributor.authorRatta, G.
dc.contributor.authorCaloone, V.
dc.contributor.authorJET-EFDA, .
dc.date.accessioned2015-12-13T22:44:52Z
dc.identifier.issn0168-9002
dc.identifier.urihttp://hdl.handle.net/1885/79506
dc.description.abstractOriginal methods to extract equations directly from experimental signals are presented. These techniques have been applied first to the determination of scaling laws for the threshold between the L and H mode of confinement in Tokamaks. The required equations can be extracted from the weights of neural networks and the separating hyperplane of Support Vector Machines. More powerful tools are required for the identification of differential equations directly from the time series of the signals. To this end, recurrent neural networks have proved to be very effective to properly identify ordinary differential equations and have been applied to the coupling between sawteeth and ELMs.
dc.publisherElsevier
dc.sourceNuclear Instruments and Methods in Physics Research: Section A
dc.subjectKeywords: L-H transition; Machine-learning; Regression; Sawteeth; Separating hyperplane; SVM; Couplings; Dynamical systems; Fusion reactors; Ordinary differential equations; Scaling laws; Support vector machines; Time series; Recurrent neural networks L-H transition; Recurrent neural networks; Regression; Scaling laws; SVM
dc.titleMachine learning for the identification of scaling laws and dynamical systems directly from data in fusion
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume623
dc.date.issued2010
local.identifier.absfor150310 - Organisation and Management Theory
local.identifier.ariespublicationf5625xPUB7933
local.type.statusPublished Version
local.contributor.affiliationMurari, A, Consorzio RFX
local.contributor.affiliationVega, J, CIEMAT:Research Centre for Energy, Environment & Technology
local.contributor.affiliationMazon, D, Association Eurotom-Cea
local.contributor.affiliationPatane, D., Universita a degli Studi di Catania
local.contributor.affiliationVagliasindi, G, Dipartimento di Ingegneria Elettrica Elettronica e dei Sistemi
local.contributor.affiliationArena, P., Universita a degli Studi di Catania
local.contributor.affiliationMartin, Nigel, College of Business and Economics, ANU
local.contributor.affiliationMartin, N.F., Arts et Metiers Paris Tech Engineering Colleg
local.contributor.affiliationRatta, G., CIEMAT:Research Centre for Energy, Environment & Technology
local.contributor.affiliationCaloone, V., Arts et Metiers Paris Tech Engineering Colleg
local.contributor.affiliationJET-EFDA, ., Culham Science Centre
local.description.embargo2037-12-31
local.bibliographicCitation.issue2
local.bibliographicCitation.startpage850
local.bibliographicCitation.lastpage854
local.identifier.doi10.1016/j.nima.2010.02.080
dc.date.updated2016-02-24T09:38:14Z
local.identifier.scopusID2-s2.0-77957941121
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Murari_Machine_learning_for_the_2010.pdf396.33 kBAdobe PDF    Request a copy


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

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator