{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T22:38:25Z","timestamp":1778798305691,"version":"3.51.4"},"reference-count":29,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T00:00:00Z","timestamp":1580774400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/"},{"start":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T00:00:00Z","timestamp":1580774400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2020,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>We propose a method for data-driven modelling of the temporal evolution of the plasma and neutral characteristics at the edge of a tokamak using neural networks. Our method proposes a novel fully convolutional network to serve as function approximators in modelling complex nonlinear phenomenon observed in the multi-physics representations of high energy physics. More specifically, we target the evolution of the temperatures, densities and parallel velocities of the electrons, ions and neutral particles at the edge. The central challenge in this context is in modelling together the different physics principles encapsulated in the evolution of plasma and the neutrals. We demonstrate that the inherent differences in nonlinear behaviour can be addressed by forking the network to process the plasma and neutral information individually before integrating as a holistic system. Our approach takes into account the spatial dependencies of the physics parameters across the grid while performing the temporal mappings, ensuring that the underlying physics is factored in and not lost to the black-box. Having used the conventional edge plasma-neutral solver code SOLPS to build the synthetic dataset, our method demonstrates a computational gain of over 5 orders of magnitude over it without a considerable compromise on accuracy.<\/jats:p>","DOI":"10.1088\/2632-2153\/ab5639","type":"journal-article","created":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T17:52:56Z","timestamp":1580838776000},"page":"015006","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Image mapping the temporal evolution of edge characteristics in tokamaks using neural networks"],"prefix":"10.1088","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0904-3448","authenticated-orcid":false,"given":"Vignesh","family":"Gopakumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D","family":"Samaddar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2020,2,4]]},"reference":[{"key":"mlstab5639bib1","doi-asserted-by":"publisher","first-page":"1638","DOI":"10.1063\/1.872268","article-title":"Plasma recombination and molecular effects in tokamak divertors and divertor simulators","volume":"4","author":"Krasheninnikov","year":"1997","journal-title":"Phys. Plasmas"},{"key":"mlstab5639bib2","first-page":"1-1","article-title":"Boltzmann and vlasov equations in plasma physics","volume":"vol 2053\u20132563","author":"Colonna","year":"2016"},{"key":"mlstab5639bib3","doi-asserted-by":"publisher","DOI":"10.1088\/0741-3335\/53\/12\/124010","article-title":"Advances on modelling of ITER scenarios: physics and computational challenges","volume":"53","author":"Giruzzi","year":"2011","journal-title":"Plasma Phys. Control. Fusion"},{"key":"mlstab5639bib4","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/j.jnucmat.2014.10.012","article-title":"The new solps-iter code package","volume":"463","author":"Wiesen","year":"2015","journal-title":"J. Nucl. Mater."},{"key":"mlstab5639bib5","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"mlstab5639bib6","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1016\/S0893-6080(97)00010-5","article-title":"Approximations of functions by a multilayer perceptron: a new approach","volume":"10","author":"Attali","year":"1997","journal-title":"Neural Netw."},{"key":"mlstab5639bib7","author":"Stanojevic","year":"2015"},{"key":"mlstab5639bib8","doi-asserted-by":"publisher","first-page":"2865","DOI":"10.1016\/j.fusengdes.2011.06.009","article-title":"Finalizing the iter divertor design: the key role of solps modeling","volume":"86","author":"Kukushkin","year":"2011","journal-title":"Fusion Eng. Des."},{"key":"mlstab5639bib9","doi-asserted-by":"publisher","first-page":"S545","DOI":"10.1016\/j.jnucmat.2010.12.223","article-title":"Detachment physics in solps simulations","volume":"415","author":"Coster","year":"2011","journal-title":"Proc. 19th Int. Conf. on Plasma-Surface Interactions in Controlled Fusion: J. Nucl. Mater."},{"key":"mlstab5639bib10","doi-asserted-by":"publisher","DOI":"10.1088\/0031-8949\/T167\/1\/014078","article-title":"Modelling of plasma-edge and plasma\u2013wall interaction physics at JET with the metallic first-wall","volume":"T167","author":"Wiesen","year":"2016","journal-title":"Phys. Scr."},{"key":"mlstab5639bib11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/ctpp.200610001","article-title":"Plasma edge physics with b2-eirene","volume":"46","author":"Schneider","journal-title":"Contrib. Plasma Phys."},{"key":"mlstab5639bib12","first-page":"205","article-title":"Transport processes in a plasma","volume":"1","author":"Braginskii","year":"1965","journal-title":"Rev. Plasma Phys."},{"key":"mlstab5639bib13","author":"Dekeyser","year":"2011"},{"key":"mlstab5639bib14","doi-asserted-by":"publisher","first-page":"02","DOI":"10.13182\/FST47-172","article-title":"The eirene and b2-eirene codes","volume":"47","author":"Reiter","year":"2005","journal-title":"Fusion Sci. Technol."},{"key":"mlstab5639bib15","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.cpc.2017.07.012","article-title":"Temporal parallelization of edge plasma simulations using the parareal algorithm and the solps code","volume":"221","author":"Samaddar","year":"2017","journal-title":"Comput. Phys. Commun."},{"key":"mlstab5639bib16","article-title":"Solps modelling: inputs and outputs, and the connection between","author":"Coster","year":"2005"},{"key":"mlstab5639bib17","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1140\/epjh\/e2017-70068-y","article-title":"The joint european torus (jet)","volume":"43","author":"Rebut","year":"2018","journal-title":"Eur. Phys. J. H"},{"key":"mlstab5639bib18","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1103\/PhysRevLett.53.1453","article-title":"Development of an edge transport barrier at the h-mode transition of asdex","volume":"53","author":"Wagner","year":"1984","journal-title":"Phys. Rev. Lett."},{"key":"mlstab5639bib19","first-page":"572","article-title":"Nonlinear dimensionality reduction as information retrieval","author":"Venna","year":"2007"},{"key":"mlstab5639bib20","author":"Vincent Dumoulin","year":"2018"},{"key":"mlstab5639bib21","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2015.7298594","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"mlstab5639bib22","author":"Chollet","year":"2015"},{"key":"mlstab5639bib23","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.fusengdes.2017.11.004","article-title":"Marconi-fusion: the new high performance computing facility for european nuclear fusion modelling","volume":"129","author":"Iannone","year":"2018","journal-title":"Fusion Eng. Des."},{"key":"mlstab5639bib24","first-page":"114","article-title":"Overfitting and neural networks: conjugate gradient and backpropagation","volume":"vol 1","author":"Lawrence","year":"2000"},{"key":"mlstab5639bib25","article-title":"ADADELTA: an adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"CoRR"},{"key":"mlstab5639bib26","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"CoRR"},{"key":"mlstab5639bib27","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoidal function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Math. Control Signals Syst."},{"key":"mlstab5639bib28","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"Zeiler","year":"2014"},{"key":"mlstab5639bib29","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: an overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,22]],"date-time":"2021-11-22T21:12:45Z","timestamp":1637615565000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab5639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,4]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,2,4]]},"published-print":{"date-parts":[[2020,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ab5639","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,4]]},"assertion":[{"value":"Image mapping the temporal evolution of edge characteristics in tokamaks using neural networks","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2020 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2019-09-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2019-11-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-02-04","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}