{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:59:29Z","timestamp":1740182369956,"version":"3.37.3"},"reference-count":56,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"US DoE Office of Fusion Energy Sciences","award":["DeepFusion pilot project in scientific machine lea"],"award-info":[{"award-number":["DeepFusion pilot project in scientific machine lea"]}]},{"name":"US DoE Office of Fusion Energy Sciences, Office of Advanced Scientific Computing Research, SciDAC","award":["89233218CNA000001"],"award-info":[{"award-number":["89233218CNA000001"]}]},{"name":"US DoE Office of Science, Office of Advanced Scientific Computing Research","award":["AC02\u201306CH11357"],"award-info":[{"award-number":["AC02\u201306CH11357"]}]},{"DOI":"10.13039\/100007000","name":"Laboratory Directed Research and Development","doi-asserted-by":"crossref","award":["20200356ER"],"award-info":[{"award-number":["20200356ER"]}],"id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Argonne Leadership Computing Facility","award":["DE-AC02\u201306CH11357"],"award-info":[{"award-number":["DE-AC02\u201306CH11357"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Effective plasma transport modeling of magnetically confined fusion devices relies on having an accurate understanding of the ion composition and radiative power losses of the plasma. Generally, these quantities can be obtained from solutions of a collisional-radiative (CR) model at each time step within a plasma transport simulation. However, even compact, approximate CR models can be computationally onerous to evaluate, and in-situ evaluation of these models within a larger plasma transport code can lead to a rigid bottleneck. As a way to bypass this bottleneck, we propose deploying artificial neural network (ANN) surrogates to allow rapid evaluation of the necessary plasma quantities. However, one issue with training an accurate ANN surrogate is the reliance on a sufficiently large and representative training and validation data set, which can be time-consuming to generate. In this work we explore a data-driven active learning and training routine to allow autonomous adaptive sampling of the problem parameter space to ensure a sufficiently large and meaningful set of training data is assembled for the network training. As a result, we can demonstrate approximately order-of-magnitude savings in required training data samples to produce an accurate surrogate.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac93e7","type":"journal-article","created":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T22:44:20Z","timestamp":1663800260000},"page":"045003","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0343-0199","authenticated-orcid":true,"given":"Nathan A","family":"Garland","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9731-8936","authenticated-orcid":true,"given":"Romit","family":"Maulik","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9614-1075","authenticated-orcid":true,"given":"Qi","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Xian-Zhu","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Prasanna","family":"Balaprakash","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"mlstac93e7bib1","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1088\/0029-5515\/39\/12\/301","article-title":"Chapter 1: overview and summary","volume":"39","author":"","year":"1999","journal-title":"Nucl. Fusion"},{"key":"mlstac93e7bib2","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1088\/0029-5515\/47\/6\/S01","article-title":"Chapter 1: overview and summary","volume":"47","author":"Shimada","year":"2007","journal-title":"Nucl. Fusion"},{"key":"mlstac93e7bib3","doi-asserted-by":"publisher","DOI":"10.1088\/1741-4326\/aae990","article-title":"3D two-temperature magnetohydrodynamic modeling of fast thermal quenches due to injected impurities in tokamaks","volume":"59","author":"Ferraro","year":"2018","journal-title":"Nucl. Fusion"},{"key":"mlstac93e7bib4","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6587\/aa5952","article-title":"Phase-space dynamics of runaway electrons in magnetic fields","volume":"59","author":"Guo","year":"2017","journal-title":"Plasma Phys. Control. Fusion"},{"key":"mlstac93e7bib5","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6587\/ab0d6d","article-title":"Avalanche mechanism for runaway electron amplification in a tokamak plasma","volume":"61","author":"McDevitt","year":"2019","journal-title":"Plasma Phys. Control. Fusion"},{"key":"mlstac93e7bib6","doi-asserted-by":"publisher","DOI":"10.1063\/5.0003299","article-title":"Study of argon expulsion from the post-disruption runaway electron plateau following low-Z massive gas injection in DIII-D","volume":"27","author":"Hollmann","year":"2020","journal-title":"Phys. Plasmas"},{"key":"mlstac93e7bib7","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1016\/S0022-3115(02)01525-8","article-title":"Disruption mitigation with high-pressure noble gas injection","volume":"313\u2013316","author":"Whyte","year":"2003","journal-title":"J. Nucl. Mater."},{"key":"mlstac93e7bib8","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0375-9601(96)00629-9","article-title":"Application of the collisional-radiative, atomic-molecular model to the recombining divertor plasma","volume":"222","author":"Yu","year":"1996","journal-title":"Phys. Lett. A"},{"key":"mlstac93e7bib9","doi-asserted-by":"publisher","DOI":"10.1063\/5.0003638","article-title":"Impact of a minority relativistic electron tail interacting with a thermal plasma containing high-atomic-number impurities","volume":"27","author":"Garland","year":"2020","journal-title":"Phys. Plasmas"},{"key":"mlstac93e7bib10","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1088\/0029-5515\/40\/4\/309","article-title":"Calculation of the radiative cooling coefficient for krypton in a low density plasma","volume":"40","author":"Fournier","year":"2000","journal-title":"Nucl. Fusion"},{"year":"2016","author":"Ralchenko","key":"mlstac93e7bib11"},{"key":"mlstac93e7bib12","doi-asserted-by":"publisher","DOI":"10.1088\/0031-8949\/T167\/1\/014070","article-title":"Melt damage to the JET ITER-like Wall and divertor","volume":"T167","author":"Matthews","year":"2016","journal-title":"Phys. Scr."},{"key":"mlstac93e7bib13","doi-asserted-by":"publisher","DOI":"10.1088\/0741-3335\/55\/12\/124041","article-title":"Impurity seeding for tokamak power exhaust: from present devices via ITER to DEMO","volume":"55","author":"Kallenbach","year":"2013","journal-title":"Plasma Phys. Control. Fusion"},{"key":"mlstac93e7bib14","doi-asserted-by":"publisher","DOI":"10.1063\/5.0015647","article-title":"Effects of nitrogen seeding in a tokamak plasma","volume":"27","author":"Shrish Raj","year":"2020","journal-title":"Phys. Plasmas"},{"key":"mlstac93e7bib15","doi-asserted-by":"publisher","DOI":"10.1088\/1741-4326\/ab15de","article-title":"Progress in disruption prevention for ITER","volume":"59","author":"Strait","year":"2019","journal-title":"Nucl. Fusion"},{"key":"mlstac93e7bib16","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.jnucmat.2014.10.075","article-title":"Disruptions in ITER and strategies for their control and mitigation","volume":"463","author":"Lehnen","year":"2015","journal-title":"J. Nucl. Mater."},{"article-title":"Executive report of the disruption mitigation workshop","year":"2018","author":"Lehnen","key":"mlstac93e7bib17"},{"key":"mlstac93e7bib18","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.hedp.2005.07.001","article-title":"FLYCHK: Generalized population kinetics and spectral model for rapid spectroscopic analysis for all elements","volume":"1","author":"Chung","year":"2005","journal-title":"High Energy Density Phys."},{"key":"mlstac93e7bib19","doi-asserted-by":"publisher","DOI":"10.1088\/0953-4075\/48\/14\/144014","article-title":"The Los Alamos suite of relativistic atomic physics codes","volume":"48","author":"Fontes","year":"2015","journal-title":"J. Phys. B: At. Mol. Opt. Phys."},{"year":"2015","author":"Bauche","key":"mlstac93e7bib20"},{"key":"mlstac93e7bib21","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1063\/1.3585817","article-title":"Atomic data and modelling for fusion: the ADAS project","volume":"1344","author":"Summers","year":"2011","journal-title":"AIP Conf. Proc."},{"key":"mlstac93e7bib22","first-page":"p 1137","volume":"vol 21A","author":"Whyte","year":"1997"},{"key":"mlstac93e7bib23","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.1103\/PhysRevLett.75.3594","article-title":"Neural network differential equation and plasma equilibrium solver","volume":"75","author":"van Milligen","year":"1995","journal-title":"Phys. Rev. Lett."},{"key":"mlstac93e7bib24","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1016\/S0022-3115(06)80146-7","article-title":"A design study for an advanced divertor for DIII-D and ITER: the radiative slot divertor","volume":"196\u2013198","author":"Allen","year":"1992","journal-title":"J. Nucl. Mater."},{"key":"mlstac93e7bib25","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/27.106821","article-title":"The feasibility of using neural networks to obtain cross sections from electron swarm data","volume":"19","author":"Morgan","year":"1991","journal-title":"IEEE Trans. Plasma Sci."},{"key":"mlstac93e7bib26","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1038\/s41586-019-1116-4","article-title":"Predicting disruptive instabilities in controlled fusion plasmas through deep learning","volume":"568","author":"Kates-Harbeck","year":"2019","journal-title":"Nature"},{"key":"mlstac93e7bib27","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1080\/15361055.2020.1798589","article-title":"Progress toward interpretable machine learning-based disruption predictors across tokamaks","volume":"76","author":"Rea","year":"2020","journal-title":"Fusion Sci. Technol."},{"key":"mlstac93e7bib28","first-page":"pp 1","article-title":"Recurrent neural network architecture search for geophysical emulation","author":"Maulik","year":"2020"},{"key":"mlstac93e7bib29","doi-asserted-by":"publisher","DOI":"10.1063\/5.0010917","article-title":"Deep learning surrogate model for kinetic Landau-fluid closure with collision","volume":"10","author":"Wang","year":"2020","journal-title":"AIP Adv."},{"key":"mlstac93e7bib30","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s10894-020-00258-1","article-title":"Advancing fusion with machine learning research needs workshop report","volume":"39","author":"Humphreys","year":"2020","journal-title":"J. Fusion Energy"},{"key":"mlstac93e7bib31","doi-asserted-by":"publisher","first-page":"4775","DOI":"10.1063\/1.1143558","article-title":"Artificial neural networks for plasma x-ray spectroscopic analysis","volume":"63","author":"Larsen","year":"1992","journal-title":"Rev. Sci. Instrum."},{"key":"mlstac93e7bib32","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0022-4073(94)90086-8","article-title":"The use of artificial neural networks in plasma spectroscopy","volume":"51","author":"Morgan","year":"1994","journal-title":"J. Quant. Spectrosc. Radiat. Transfer"},{"key":"mlstac93e7bib33","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1103\/PhysRevLett.73.1505","article-title":"Analysis of spectra from laser produced plasmas using a neural network","volume":"73","author":"Osterheld","year":"1994","journal-title":"Phys. Rev. Lett."},{"key":"mlstac93e7bib34","doi-asserted-by":"publisher","first-page":"26LT01","DOI":"10.1088\/1361-6463\/ac5d04","article-title":"A neural network model relating extraction current characteristics with optical emission spectra for the purpose of a digital twin of miniaturized ion thrusters","volume":"55","author":"Zhang","year":"2022","journal-title":"J. Appl. Phys."},{"key":"mlstac93e7bib35","doi-asserted-by":"publisher","DOI":"10.1002\/advs.201801367","article-title":"Deep learning spectroscopy: neural networks for molecular excitation spectra","volume":"6","author":"Ghosh","year":"2019","journal-title":"Adv. Sci."},{"key":"mlstac93e7bib36","doi-asserted-by":"publisher","DOI":"10.1063\/5.0006784","article-title":"Deep learning for NLTE spectral opacities","volume":"27","author":"Kluth","year":"2020","journal-title":"Phys. Plasmas"},{"key":"mlstac93e7bib37","doi-asserted-by":"publisher","first-page":"4590","DOI":"10.1063\/1.1312816","article-title":"Runaway electron production in DIII-D killer pellet experiments, calculated with the CQL3D\/KPRAD model","volume":"7","author":"Harvey","year":"2000","journal-title":"Phys. Plasmas"},{"key":"mlstac93e7bib38","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1098\/rspa.1962.0209","article-title":"Recombination between electrons and atomic ions, II. Optically thick plasmas","volume":"270","author":"David Robert","year":"1962","journal-title":"Proc. R. Soc. A"},{"key":"mlstac93e7bib39","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1088\/0370-1328\/82\/5\/301","article-title":"A calculation of the instantaneous population densities of the excited levels of hydrogen-like ions in a plasma","volume":"82","author":"McWhirter","year":"1963","journal-title":"Proc. Phys. Soc."},{"year":"2018","author":"Tallents","key":"mlstac93e7bib40"},{"key":"mlstac93e7bib41","doi-asserted-by":"publisher","DOI":"10.1017\/S0022377818001113","article-title":"Generalized collision operator for fast electrons interacting with partially ionized impurities","volume":"84","author":"Hesslow","year":"2018","journal-title":"J. Plasma Phys."},{"key":"mlstac93e7bib42","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"mlstac93e7bib43","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/BF02985802","article-title":"The elements of statistical learning: data mining, inference and prediction","volume":"27","author":"Hastie","year":"2005","journal-title":"Math. Intell."},{"article-title":"Latin hypercube sampling (program user\u2019s guide) [lhc, in fortran]","year":"1980","author":"Iman","key":"mlstac93e7bib44"},{"key":"mlstac93e7bib45","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":"mlstac93e7bib46","first-page":"pp 65","article-title":"Theory of the backpropagation neural network","author":"Hecht-Nielsen","year":"1992"},{"key":"mlstac93e7bib47","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":"mlstac93e7bib48","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/18.256500","article-title":"Universal approximation bounds for superpositions of a sigmoidal function","volume":"39","author":"Barron","year":"1993","journal-title":"IEEE Trans. Inf. Theory"},{"article-title":"Deep-ensemble-based uncertainty quantification in spatiotemporal graph neural networks for traffic forecasting","year":"2022","author":"Mallick","key":"mlstac93e7bib49"},{"key":"mlstac93e7bib50","first-page":"pp 42","article-title":"Deephyper: asynchronous hyperparameter search for deep neural networks","author":"Balaprakash","year":"2018"},{"article-title":"Adam: a method for stochastic optimization","year":"2017","author":"Kingma","key":"mlstac93e7bib51"},{"article-title":"Progress towards high fidelity collisional-radiative model surrogates for rapid in-situ evaluation","year":"2020","author":"Garland","key":"mlstac93e7bib52"},{"article-title":"Searching for activation functions","year":"2017","author":"Ramachandran","key":"mlstac93e7bib53"},{"key":"mlstac93e7bib54","first-page":"pp 1","article-title":"P-swish: activation function with learnable parameters based on swish activation function in deep learning","author":"Mercioni","year":"2020"},{"article-title":"Notes on Kullback\u2013Leibler divergence and likelihood","year":"2014","author":"Shlens","key":"mlstac93e7bib55"},{"year":"2006","author":"Cover","key":"mlstac93e7bib56"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T11:53:58Z","timestamp":1665402838000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac93e7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":56,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,10,10]]},"published-print":{"date-parts":[[2022,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac93e7","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling","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 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-12-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-09-21","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-10-10","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}