A machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas

Abstract Experimental observations assisted by 2-D imaging diagnostics on the KSTAR tokamak show that a solitary perturbation (SP) emerges prior to a boundary burst of magnetized toroidal plasmas, which puts forward SP as a potential candidate for the burst trigger. We have constructed a machine lea...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: J. E. Lee, P. H. Seo, J. G. Bak, G. S. Yun
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/95ab80ccca8441a49a1bf962fef640bd
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:95ab80ccca8441a49a1bf962fef640bd
record_format dspace
spelling oai:doaj.org-article:95ab80ccca8441a49a1bf962fef640bd2021-12-02T14:11:32ZA machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas10.1038/s41598-021-83192-22045-2322https://doaj.org/article/95ab80ccca8441a49a1bf962fef640bd2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83192-2https://doaj.org/toc/2045-2322Abstract Experimental observations assisted by 2-D imaging diagnostics on the KSTAR tokamak show that a solitary perturbation (SP) emerges prior to a boundary burst of magnetized toroidal plasmas, which puts forward SP as a potential candidate for the burst trigger. We have constructed a machine learning (ML) model based on a convolutional deep neural network architecture for a statistical study to identify the SP as a boundary burst trigger. The ML model takes sequential signals detected from 19 toroidal Mirnov coils as input and predicts whether each temporal frame corresponds to an SP. We trained the network in a supervised manner on a training set consisting of real signals with manually annotated SP locations and synthetic burst signals. The trained model achieves high performances in various metrics on a test data set. We also demonstrated the reliability of the model by visualizing the discriminative parts of the input signals that the model recognizes. Finally, we applied the trained model to new data from KSTAR experiments, which were never seen during training, and confirmed that the large burst at the plasma boundary that can fatally damage the fusion device always involves the emergence of SP. This result suggests that the SP is a key to understanding and controlling of the boundary burst in magnetized toroidal plasmas.J. E. LeeP. H. SeoJ. G. BakG. S. YunNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
J. E. Lee
P. H. Seo
J. G. Bak
G. S. Yun
A machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas
description Abstract Experimental observations assisted by 2-D imaging diagnostics on the KSTAR tokamak show that a solitary perturbation (SP) emerges prior to a boundary burst of magnetized toroidal plasmas, which puts forward SP as a potential candidate for the burst trigger. We have constructed a machine learning (ML) model based on a convolutional deep neural network architecture for a statistical study to identify the SP as a boundary burst trigger. The ML model takes sequential signals detected from 19 toroidal Mirnov coils as input and predicts whether each temporal frame corresponds to an SP. We trained the network in a supervised manner on a training set consisting of real signals with manually annotated SP locations and synthetic burst signals. The trained model achieves high performances in various metrics on a test data set. We also demonstrated the reliability of the model by visualizing the discriminative parts of the input signals that the model recognizes. Finally, we applied the trained model to new data from KSTAR experiments, which were never seen during training, and confirmed that the large burst at the plasma boundary that can fatally damage the fusion device always involves the emergence of SP. This result suggests that the SP is a key to understanding and controlling of the boundary burst in magnetized toroidal plasmas.
format article
author J. E. Lee
P. H. Seo
J. G. Bak
G. S. Yun
author_facet J. E. Lee
P. H. Seo
J. G. Bak
G. S. Yun
author_sort J. E. Lee
title A machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas
title_short A machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas
title_full A machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas
title_fullStr A machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas
title_full_unstemmed A machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas
title_sort machine learning approach to identify the universality of solitary perturbations accompanying boundary bursts in magnetized toroidal plasmas
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/95ab80ccca8441a49a1bf962fef640bd
work_keys_str_mv AT jelee amachinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
AT phseo amachinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
AT jgbak amachinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
AT gsyun amachinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
AT jelee machinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
AT phseo machinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
AT jgbak machinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
AT gsyun machinelearningapproachtoidentifytheuniversalityofsolitaryperturbationsaccompanyingboundaryburstsinmagnetizedtoroidalplasmas
_version_ 1718391858303860736