Application of machine learning for optical emission spectroscopy data in NAGDIS-II

Kajita, Shin; Sakakibara, Takehiro; Kaizawa, Hideki; Natsume, Hiroki; Tanaka, Hirohiko; Fujii, Keisuke; Ohno, Noriyasu

doi:10.1016/j.fusengdes.2023.114012

Application of machine learning for optical emission spectroscopy data in NAGDIS-II

Journal Article · Sat Sep 30 00:00:00 EDT 2023 · Fusion Engineering and Design

DOI:https://doi.org/10.1016/j.fusengdes.2023.114012· OSTI ID:2076177

^[1]; Sakakibara, Takehiro ^[2]; Kaizawa, Hideki ^[2]; ^[2]; Tanaka, Hirohiko ^[2]; ^[3]; Ohno, Noriyasu ^[2]

University of Tokyo, Chiba (Japan)
Nagoya University (Japan)
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

In this study, we applied machine learning to optical emission spectroscopy (OES) data and device parameters from the linear plasma device NAGDIS-II to explore the potential application of machine learning for predicting electron density, $$n$$_e, and temperature, $$T$$_e. The covered ranges of $$n$$_e and $$T$$_e, which were measured by an electrostatic probe, are 3.6 × 10¹⁷–2.4 × 10¹⁹ m^-3 and 0.3–7.1 eV, respectively. A three hidden layer neural network (NN) is introduced to model the relationship between $$n$$_e/$$T$$_e and the combination of line intensities, radial position, and device parameters. It is shown that the errors in $$n$$_e and $$T$$_e become 18.0 and 18.8%, respectively, which were almost the same level for the electrostatic probe, using all available data. Lasso regression and greedy algorithm are used to select the necessary line emissions. In conclusion, it is shown that four- or five-line intensities are sufficient to obtain almost the same quality as the one with all the other lines.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2076177

Journal Information:: Fusion Engineering and Design, Journal Name: Fusion Engineering and Design Vol. 196; ISSN 0920-3796

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (23)

Fluctuating Helium Emission in Optically Thick Divertor Plasmas Rosmej, F. B.; Ohno, N.; Takamura, S. Contributions to Plasma Physics, Vol. 48, Issue 1-3 https://doi.org/10.1002/ctpp.200810042	journal	March 2008
2D Measurement of Edge Plasma Dynamics by Using High-Speed Camera Based on HeI Line Intensity Ratio Method Ohno, N.; Miyamoto, K.; Kodama, K. Contributions to Plasma Physics, Vol. 50, Issue 10 https://doi.org/10.1002/ctpp.201000030	journal	November 2010
Current Research into Applications of Tomography for Fusion Diagnostics Mlynar, Jan; Craciunescu, Teddy Journal of Fusion Energy, Vol. 38, Issue 3-4 https://doi.org/10.1007/s10894-018-0178-x	journal	August 2018
Collisional-radiative model for neutral helium in plasma revisited Goto, M. Journal of Quantitative Spectroscopy and Radiative Transfer, Vol. 76, Issue 3-4 https://doi.org/10.1016/S0022-4073(02)00060-2	journal	February 2003
A framework for the greedy algorithm Vince, A. Discrete Applied Mathematics, Vol. 121, Issue 1-3 https://doi.org/10.1016/S0166-218X(01)00362-6	journal	September 2002
High-fluence and high-flux performance characteristics of the superconducting Magnum-PSI linear plasma facility van Eck, H. J. N.; Akkermans, G. R. A.; Alonso van der Westen, S. Fusion Engineering and Design, Vol. 142 https://doi.org/10.1016/j.fusengdes.2019.04.020	journal	May 2019
On the application of He I collisional-radiative model to the He–H2 mixture plasmas in MAP-II divertor simulator Iida, Y.; Kado, S.; Tanaka, S. Journal of Nuclear Materials, Vol. 438 https://doi.org/10.1016/j.jnucmat.2013.01.274	journal	July 2013
Predicting disruptive instabilities in controlled fusion plasmas through deep learning Kates-Harbeck, Julian; Svyatkovskiy, Alexey; Tang, William Nature, Vol. 568, Issue 7753 https://doi.org/10.1038/s41586-019-1116-4	journal	April 2019
Tracking blobs in the turbulent edge plasma of a tokamak fusion device Han, Woonghee; Pietersen, Randall A.; Villamor-Lora, Rafael Scientific Reports, Vol. 12, Issue 1 https://doi.org/10.1038/s41598-022-21671-w	journal	October 2022
Helium I line intensity ratios in a plasma for the diagnostics of fusion edge plasmas Sasaki, Satoshi; Takamura, Shuichi; Watanabe, Shinichi Review of Scientific Instruments, Vol. 67, Issue 10 https://doi.org/10.1063/1.1147060	journal	October 1996
Comparison of He I line intensity ratio method and electrostatic probe for electron density and temperature measurements in NAGDIS-II Kajita, Shin; Ohno, Noriyasu; Takamura, Shuichi Physics of Plasmas, Vol. 13, Issue 1 https://doi.org/10.1063/1.2164461	journal	January 2006
Practical selection of emission lines of He I to determine the photon absorption rate Kajita, Shin; Ohno, Noriyasu Review of Scientific Instruments, Vol. 82, Issue 2 https://doi.org/10.1063/1.3548923	journal	February 2011
Helium line emission spectroscopy in recombining detached plasmas Kajita, Shin; Suzuki, Kensuke; Tanaka, Hirohiko Physics of Plasmas, Vol. 25, Issue 6 https://doi.org/10.1063/1.5029414	journal	June 2018
Emission spectroscopy of He lines in high-density plasmas in Magnum-PSI Kajita, Shin; Akkermans, Gijs; Fujii, Keisuke AIP Advances, Vol. 10, Issue 2 https://doi.org/10.1063/1.5143481	journal	February 2020
Development and characterization of thermal helium beam diagnostic with four helium lines for RFX-mod2 experiment Agostini, M.; Scarin, P.; Milazzo, R. Review of Scientific Instruments, Vol. 91, Issue 11 https://doi.org/10.1063/5.0023310	journal	November 2020
Machine learning prediction of electron density and temperature from He I line ratios Nishijima, D.; Kajita, S.; Tynan, G. R. Review of Scientific Instruments, Vol. 92, Issue 2 https://doi.org/10.1063/5.0028000	journal	February 2021
Measuring the electron temperature and identifying plasma detachment using machine learning and spectroscopy Samuell, C. M.; Mclean, A. G.; Johnson, C. A. Review of Scientific Instruments, Vol. 92, Issue 4 https://doi.org/10.1063/5.0034552	journal	April 2021
Machine learning-aided line intensity ratio technique applied to deuterium plasmas Nishijima, D.; Baldwin, M. J.; Chang, F. AIP Advances, Vol. 13, Issue 5 https://doi.org/10.1063/5.0147463	journal	May 2023
Application of passive spectroscopy to the He I line intensity ratio technique: a new tool for electron temperature and density measurement in fusion boundary plasmas Cal, E. de la Plasma Physics and Controlled Fusion, Vol. 43, Issue 6 https://doi.org/10.1088/0741-3335/43/6/306	journal	May 2001
Determination of the optical escape factor in the He I line intensity ratio technique applied for weakly ionized plasmas Nishijima, D.; Hollmann, E. M. Plasma Physics and Controlled Fusion, Vol. 49, Issue 6 https://doi.org/10.1088/0741-3335/49/6/007	journal	April 2007
Influence of stray light on visible spectroscopy for the scrape-off layer in ITER Kajita, Shin; Veshchev, Evgeny; Lisgo, Steve Plasma Physics and Controlled Fusion, Vol. 55, Issue 8 https://doi.org/10.1088/0741-3335/55/8/085020	journal	June 2013
Application of multiple regression for sensitivity analysis of helium line emissions to the electron density and temperature in Magnum-PSI Kajita, Shin; Nishijima, Daisuke; Fujii, Keisuke Plasma Physics and Controlled Fusion, Vol. 63, Issue 5 https://doi.org/10.1088/1361-6587/abf36e	journal	April 2021
Deep Learning for Plasma Tomography and Disruption Prediction From Bolometer Data Ferreira, Diogo R.; Carvalho, Pedro J.; Fernandes, Horacio IEEE Transactions on Plasma Science, Vol. 48, Issue 1 https://doi.org/10.1109/TPS.2019.2947304	journal	January 2020

Similar Records

Machine learning-aided line intensity ratio technique applied to deuterium plasmas

Journal Article · Mon May 01 20:00:00 EDT 2023 · AIP Advances · OSTI ID:1972220

Helium I line intensity ratios in a plasma for the diagnostics of fusion edge plasmas

Journal Article · Tue Oct 01 00:00:00 EDT 1996 · Review of Scientific Instruments · OSTI ID:385888

Machine learning prediction of electron density and temperature from He I line ratios

Journal Article · Mon Feb 15 19:00:00 EST 2021 · Review of Scientific Instruments · OSTI ID:1849823

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
Diagnostics
Machine learning
Optical emission spectroscopy
Plasma

Application of machine learning for optical emission spectroscopy data in NAGDIS-II

Citation Formats

References (23)

Similar Records

Related Subjects