Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra

Arellano, Fatima Jenina; Kusaba, Minoru; Wu, Stephen; Yoshida, Ryo; Donkó, Zoltán; Hartmann, Peter; Tsankov, Tsanko V.; Hamaguchi, Satoshi

doi:https://doi.org/10.1116/6.0003731

Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra

Arellano, Fatima Jenina; Kusaba, Minoru; Wu, Stephen et al.

Journal of Vacuum Science and Technology A, 2024, 42(5), 053001

Number of Access:278（2025-08-28 17:09 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/97738

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
JVacSciTechnolA_42_5_53001	pdf	None	2.94 MB	6	2025.07.11

Item Information

Output File Export EndNote Basic Export Mendeley

Title	Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra
Creator	CreatorName Arellano, Fatima Jenina
	NRID 1000050965803 1000050965803 CreatorName Kusaba, Minoru
	NRID 1000070804186 1000070804186 CreatorName Wu, Stephen
	NRID 1000070401263 1000070401263 CreatorName Yoshida, Ryo
	CreatorName Donkó, Zoltán
	CreatorName Hartmann, Peter
	CreatorName Tsankov, Tsanko V.
	NRID 1000060301826 1000060301826 ORCID 0000-0001-6580-8797 0000-0001-6580-8797 researchmap permalink satoshi_hamaguchi satoshi_hamaguchi Scopus Author ID 55220082400 55220082400 CreatorName Hamaguchi, Satoshi
Description	Arellano F.J., Kusaba M., Wu S., et al. Journal of Vacuum Science and Technology A 42, 053001 (2024) https://doi.org/10.1116/6.0003731.
Abstract	Optical emission spectroscopy (OES) is a highly valuable tool for plasma characterization due to its nonintrusive and versatile nature. The intensities of the emission lines contain information about the parameters of the underlying plasma-electron density n e and temperature or, more generally, the electron energy distribution function (EEDF). This study aims to obtain the EEDF and n e from the OES data of argon plasma with machine learning (ML) techniques. Two different models, i.e., the Kernel Regression for Functional Data (KRFD) and an artificial neural network (ANN), are used to predict the normalized EEDF and Random Forest (RF) regression is used to predict n e . The ML models are trained with computed plasma data obtained from Particle-in-Cell/Monte Carlo Collision simulations coupled with a collisional-radiative model. All three ML models developed in this study are found to predict with high accuracy what they are trained to predict when the simulated test OES data are used as the input data. When the experimentally measured OES data are used as the input data, the ANN-based model predicts the normalized EEDF with reasonable accuracy under the discharge conditions where the simulation data are known to agree well with the corresponding experimental data. However, the capabilities of the KRFD and RF models to predict the EEDF and n e from experimental OES data are found to be rather limited, reflecting the need for further improvement of the robustness of these models.
Publisher	AVS Science and Technology Society
Source Title	Journal of Vacuum Science and Technology A
Volume (Issue)	42(5)
Page	053001
Date of Issued	2024-07-11
Language	English
Handle URL	https://hdl.handle.net/11094/97738
PISSN	07342101
eISSN	15208559
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.1116/6.0003731
Access Rights	open access
CopyRight	This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Arellano F.J., Kusaba M., Wu S., et al. Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra. Journal of Vacuum Science and Technology A 42, 053001 (2024) and may be found at https://doi.org/10.1116/6.0003731.
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCTERMS.bibliographicCitation	Journal of Vacuum Science and Technology A. 2024, 42(5), p. 053001
DC.title	Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra
DC.creator	Arellano, Fatima Jenina
	Kusaba, Minoru
	Wu, Stephen
	Yoshida, Ryo
	Donkó, Zoltán
	Hartmann, Peter
	Tsankov, Tsanko V.
	Hamaguchi, Satoshi
DC.publisher	AVS Science and Technology Society
DC.language' scheme='DCTERMS.RFC1766	English
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2024-07-11
DC.identifier	https://doi.org/10.1116/6.0003731
DC.description	Arellano F.J., Kusaba M., Wu S., et al. Journal of Vacuum Science and Technology A 42, 053001 (2024) https://doi.org/10.1116/6.0003731.
DCTERMS.abstract	Optical emission spectroscopy (OES) is a highly valuable tool for plasma characterization due to its nonintrusive and versatile nature. The intensities of the emission lines contain information about the parameters of the underlying plasma-electron density n e and temperature or, more generally, the electron energy distribution function (EEDF). This study aims to obtain the EEDF and n e from the OES data of argon plasma with machine learning (ML) techniques. Two different models, i.e., the Kernel Regression for Functional Data (KRFD) and an artificial neural network (ANN), are used to predict the normalized EEDF and Random Forest (RF) regression is used to predict n e . The ML models are trained with computed plasma data obtained from Particle-in-Cell/Monte Carlo Collision simulations coupled with a collisional-radiative model. All three ML models developed in this study are found to predict with high accuracy what they are trained to predict when the simulated test OES data are used as the input data. When the experimentally measured OES data are used as the input data, the ANN-based model predicts the normalized EEDF with reasonable accuracy under the discharge conditions where the simulation data are known to agree well with the corresponding experimental data. However, the capabilities of the KRFD and RF models to predict the EEDF and n e from experimental OES data are found to be rather limited, reflecting the need for further improvement of the robustness of these models.
DC.rights	This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Arellano F.J., Kusaba M., Wu S., et al. Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra. Journal of Vacuum Science and Technology A 42, 053001 (2024) and may be found at https://doi.org/10.1116/6.0003731.
DC.format	97738
citation_title	Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra
citation_author	Arellano, Fatima Jenina
	Kusaba, Minoru
	Wu, Stephen
	Yoshida, Ryo
	Donkó, Zoltán
	Hartmann, Peter
	Tsankov, Tsanko V.
	Hamaguchi, Satoshi
citation_publisher	AVS Science and Technology Society
citation_language	English
citation_date	2024-07-11
citation_journal_title	Journal of Vacuum Science and Technology A
citation_volume	42
citation_issue	5
citation_firstpage	053001
citation_doi	https://doi.org/10.1116/6.0003731
citation_public_url	https://hdl.handle.net/11094/97738

Machine learning-based prediction of the electron energy distribution function and electron density of argon plasma from the optical emission spectra

Link to primary information

Item Information

Show details