Artificial intelligence-based predictive modeling for imaging neutral particle analyzers on the DIII-D tokamak

Garcia, Alvin; Liu, Sydney; Du, Xiaodi; Curie, Max; Jalalvand, Azarakhsh; Steiner, Peter; Kolemen, Egemen

doi:10.1088/1741-4326/adc58b

Artificial intelligence-based predictive modeling for imaging neutral particle analyzers on the DIII-D tokamak

Journal Article · Wed Apr 09 00:00:00 EDT 2025 · Nuclear Fusion

DOI:https://doi.org/10.1088/1741-4326/adc58b· OSTI ID:2553087

^[1]; Liu, Sydney ^[2]; ^[3]; Curie, Max ^[4]; ^[4]; ^[4]; ^[5]

Oak Ridge Institute for Science and Education, Oak Ridge, TN (United States); Princeton University, NJ (United States)
University of Illinois at Urbana-Champaign, IL (United States)
General Atomics, San Diego, CA (United States)
Princeton University, NJ (United States)
Princeton University, NJ (United States); Princeton Plasma Physics Laboratory (PPPL), Princeton, NJ (United States)

The Imaging Neutral Particle Analyzer (INPA) at DIII-D is a diagnostic system used to accurately resolve the energy and spatial distributions of fast ions in fusion plasmas. A novel artificial intelligence (AI) technique named INPA-net is based on Reservoir Computing Networks and developed here to predict active and passive signals produced by charge-exchange reactions from injected and edge-cold neutrals, respectively, in magnetically confined fusion plasmas. This model is trained using a set of 21 time domain signals between 0 s to 3.35 s that includes injected beam and thermal plasma information, and 6444 real 2D experimental images of the INPA in 12 plasma discharges at DIII-D. The trained neural network is able to forecast experimental images in real-time. The model achieves an R-squared value of 0.91, which is higher than the 0.83 value achieved by a simple linear regression model. This improvement highlights the model's enhanced predictive accuracy for measured images from the validation set. This AI approach is valuable due to its rapid response times and potential for integration into real-time plasma control systems. A version of this model capable of generating syntehic images would be useful for the real-time monitoring of fast-ion transport. A comprehensive sensitivity study reveals that INPA-net maintains high performance even with variations in the input parameters, indicating the model's robustness and reliability. While developed for the INPA, the underlying architecture is adaptable and may be applied to various 2D imaging diagnostics in fusion research.

View Accepted Manuscript (DOE)

Research Organization:: General Atomics, San Diego, CA (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF); USDOE Office of Science (SC), Fusion Energy Sciences (FES)

Grant/Contract Number:: AC02-09CH11466; FC02-04ER54698; SC0014664; SC0024527

OSTI ID:: 2553087

Alternate ID(s):: OSTI ID: 2539968

Journal Information:: Nuclear Fusion, Journal Name: Nuclear Fusion Journal Issue: 5 Vol. 65; ISSN 0029-5515

Publisher:: IOP ScienceCopyright Statement

Country of Publication:: United States

Language:: English

References (50)

Advancing Fusion with Machine Learning Research Needs Workshop Report Humphreys, David; Kupresanin, A.; Boyer, M. D. Journal of Fusion Energy, Vol. 39, Issue 4 https://doi.org/10.1007/s10894-020-00258-1	journal	August 2020
Introduction to the interaction between energetic particles and Alfven eigenmodes in toroidal plasmas Todo, Y. Reviews of Modern Plasma Physics, Vol. 3, Issue 1 https://doi.org/10.1007/s41614-018-0022-9	journal	December 2018
Clustering of periodic multichannel timeseries data with application to plasma fluctuations Haskey, S. R.; Blackwell, B. D.; Pretty, D. G. Computer Physics Communications, Vol. 185, Issue 6 https://doi.org/10.1016/j.cpc.2014.03.008	journal	June 2014
PyRCN: A toolbox for exploration and application of Reservoir Computing Networks Steiner, Peter; Jalalvand, Azarakhsh; Stone, Simon Engineering Applications of Artificial Intelligence, Vol. 113 https://doi.org/10.1016/j.engappai.2022.104964	journal	August 2022
Physics of the conceptual design of the ITER plasma control system Snipes, J. A.; Bremond, S.; Campbell, D. J. Fusion Engineering and Design, Vol. 89, Issue 5 https://doi.org/10.1016/j.fusengdes.2014.01.063	journal	May 2014
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
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
Basic physics of Alfvén instabilities driven by energetic particles in toroidally confined plasmas Heidbrink, W. W. Physics of Plasmas, Vol. 15, Issue 5 https://doi.org/10.1063/1.2838239	journal	May 2008
Extended fast-ion D-alpha diagnostic on DIII-D Muscatello, C. M.; Heidbrink, W. W.; Taussig, D. Review of Scientific Instruments, Vol. 81, Issue 10 https://doi.org/10.1063/1.3475367	journal	October 2010
Scintillator-based diagnostic for fast ion loss measurements on DIII-D Fisher, R. K.; Pace, D. C.; García-Muñoz, M. Review of Scientific Instruments, Vol. 81, Issue 10 https://doi.org/10.1063/1.3490020	journal	October 2010
Machine learning control for disruption and tearing mode avoidance Fu, Yichen; Eldon, David; Erickson, Keith Physics of Plasmas, Vol. 27, Issue 2 https://doi.org/10.1063/1.5125581	journal	February 2020
Toroidal Alfvén eigenmode‐induced ripple trapping White, R. B.; Fredrickson, E.; Darrow, D. Physics of Plasmas, Vol. 2, Issue 8 https://doi.org/10.1063/1.871452	journal	August 1995
Exploratory Machine Learning Studies for Disruption Prediction Using Large Databases on DIII-D Rea, Cristina; Granetz, Robert S. Fusion Science and Technology, Vol. 74, Issue 1-2 https://doi.org/10.1080/15361055.2017.1407206	journal	February 2018
Fast-wave heating of a two-component plasma Stix, T. H. Nuclear Fusion, Vol. 15, Issue 5 https://doi.org/10.1088/0029-5515/15/5/003	journal	October 1975
Loss of energetic beam ions during TAE instabilities Duong, H. H.; Heidbrink, W. W.; Strait, E. J. Nuclear Fusion, Vol. 33, Issue 5 https://doi.org/10.1088/0029-5515/33/5/I06	journal	May 1993
ASCOT simulations of fast ion power loads to the plasma-facing components in ITER Kurki-Suonio, T.; Asunta, O.; Hellsten, T. Nuclear Fusion, Vol. 49, Issue 9 https://doi.org/10.1088/0029-5515/49/9/095001	journal	August 2009
Control of power, torque, and instability drive using in-shot variable neutral beam energy in tokamaks Pace, D. C.; Collins, C. S.; Crowley, B. Nuclear Fusion, Vol. 57, Issue 1 https://doi.org/10.1088/0029-5515/57/1/014001	journal	September 2016
Principles of Plasma Diagnostics: Second Edition Hutchinson, I. H. Plasma Physics and Controlled Fusion, Vol. 44, Issue 12 https://doi.org/10.1088/0741-3335/44/12/701	journal	November 2002
The role of energetic particles in fusion plasmas Pinches, S. D.; Berk, H. L.; Borba, D. N. Plasma Physics and Controlled Fusion, Vol. 46, Issue 12B https://doi.org/10.1088/0741-3335/46/12B/017	journal	November 2004
Automatic disruption classification in JET with the ITER-like wall Cannas, B.; de Vries, P. C.; Fanni, A. Plasma Physics and Controlled Fusion, Vol. 57, Issue 12 https://doi.org/10.1088/0741-3335/57/12/125003	journal	October 2015
Experiment-theory comparison for low frequency BAE modes in the strongly shaped H-1NF stellarator Haskey, S. R.; Blackwell, B. D.; Nührenberg, C. Plasma Physics and Controlled Fusion, Vol. 57, Issue 9 https://doi.org/10.1088/0741-3335/57/9/095011	journal	August 2015
Measurement of the passive fast-ion D-alpha emission on the NSTX-U tokamak Hao, G. Z.; Heidbrink, W. W.; Liu, D. Plasma Physics and Controlled Fusion, Vol. 60, Issue 2 https://doi.org/10.1088/1361-6587/aa9fde	journal	January 2018
Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod Rea, C.; Granetz, R. S.; Montes, K. Plasma Physics and Controlled Fusion, Vol. 60, Issue 8 https://doi.org/10.1088/1361-6587/aac7fe	journal	June 2018
Active control of Alfvén eigenmodes in magnetically confined toroidal plasmas Garcia-Munoz, M.; Sharapov, S. E.; Van Zeeland, M. A. Plasma Physics and Controlled Fusion, Vol. 61, Issue 5 https://doi.org/10.1088/1361-6587/aaef08	journal	March 2019
Automatic identification of MHD modes in magnetic fluctuation spectrograms using deep learning techniques Bustos, A.; Ascasíbar, E.; Cappa, A. Plasma Physics and Controlled Fusion, Vol. 63, Issue 9 https://doi.org/10.1088/1361-6587/ac08f7	journal	July 2021
Commissioning of the imaging neutral particle analyser for the ASDEX Upgrade tokamak Rueda-Rueda, J.; Garcia-Munoz, M.; Viezzer, E. Plasma Physics and Controlled Fusion, Vol. 66, Issue 3 https://doi.org/10.1088/1361-6587/ad1ec1	journal	February 2024
Adaptive predictors based on probabilistic SVM for real time disruption mitigation on JET Murari, A.; Lungaroni, M.; Peluso, E. Nuclear Fusion, Vol. 58, Issue 5 https://doi.org/10.1088/1741-4326/aaaf9c	journal	March 2018
Development and verification of a novel scintillator-based, imaging neutral particle analyzer in DIII-D tokamak Du, X. D.; Van Zeeland, M. A.; Heidbrink, W. W. Nuclear Fusion, Vol. 58, Issue 8 https://doi.org/10.1088/1741-4326/aac3a2	journal	June 2018
Active real-time control of Alfvén eigenmodes by neutral beam and electron cyclotron heating in the DIII-D tokamak Hu, Wenhui; Olofsson, K. E. J.; Welander, A. S. Nuclear Fusion, Vol. 58, Issue 12 https://doi.org/10.1088/1741-4326/aaddaf	journal	September 2018
Machine learning for disruption warnings on Alcator C-Mod, DIII-D, and EAST Montes, K. J.; Rea, C.; Granetz, R. S. Nuclear Fusion, Vol. 59, Issue 9 https://doi.org/10.1088/1741-4326/ab1df4	journal	July 2019
Validation of the imaging neutral particle analyzer in nearly MHD quiescent plasmas using injected beam ions on DIII-D Lin, D. J.; Du, X. D.; Heidbrink, W. W. Nuclear Fusion, Vol. 60, Issue 11 https://doi.org/10.1088/1741-4326/ab8e10	journal	August 2020
‘BAAE’ instabilities observed without fast ion drive Heidbrink, W. W.; Van Zeeland, M. A.; Austin, M. E. Nuclear Fusion, Vol. 61, Issue 1 https://doi.org/10.1088/1741-4326/abc4c3	journal	December 2020
Stability of beta-induced Alfvén eigenmodes (BAE) in DIII-D Heidbrink, W. W.; Van Zeeland, M. A.; Austin, M. E. Nuclear Fusion, Vol. 61, Issue 6 https://doi.org/10.1088/1741-4326/abf953	journal	May 2021
Alfvén eigenmode classification based on ECE diagnostics at DIII-D using deep recurrent neural networks Jalalvand, Azarakhsh; Kaptanoglu, Alan A.; Garcia, Alvin V. Nuclear Fusion, Vol. 62, Issue 2 https://doi.org/10.1088/1741-4326/ac3be7	journal	December 2021
The radial phase variation of reversed-shear and toroidicity-induced Alfvén eigenmodes in DIII-D Heidbrink, W. W.; Hansen, E. C.; Austin, M. E. Nuclear Fusion, Vol. 62, Issue 6 https://doi.org/10.1088/1741-4326/ac5109	journal	April 2022
Disruption prediction at JET through deep convolutional neural networks using spatiotemporal information from plasma profiles Aymerich, E.; Sias, G.; Pisano, F. Nuclear Fusion, Vol. 62, Issue 6 https://doi.org/10.1088/1741-4326/ac525e	journal	April 2022
Modelling the Alfvén eigenmode induced fast-ion flow measured by an imaging neutral particle analyzer Gonzalez-Martin, J.; Du, X. D.; Heidbrink, W. W. Nuclear Fusion, Vol. 62, Issue 11 https://doi.org/10.1088/1741-4326/ac7406	journal	September 2022
Exploring data-driven models for spatiotemporally local classification of Alfvén eigenmodes Kaptanoglu, Alan A.; Jalalvand, Azarakhsh; Garcia, Alvin V. Nuclear Fusion, Vol. 62, Issue 10 https://doi.org/10.1088/1741-4326/ac8a03	journal	August 2022
Comparison of machine learning systems trained to detect Alfvén eigenmodes using the CO₂ interferometer on DIII-D Garcia, Alvin V.; Jalalvand, Azarakhsh; Steiner, Peter Nuclear Fusion, Vol. 63, Issue 12 https://doi.org/10.1088/1741-4326/acfe8b	journal	October 2023
Visualization of phase-space orbit topological boundary using imaging neutral particle analyzer Du, X. D.; Gonzalez-Martin, J.; Liu, D. Nuclear Fusion, Vol. 63, Issue 12 https://doi.org/10.1088/1741-4326/ad01ca	journal	October 2023
Initial testing of Alfvén eigenmode feedback control with machine-learning observers on DIII-D Rothstein, Andrew; Jalalvand, Azarakhsh; Abbate, Joseph Nuclear Fusion, Vol. 64, Issue 9 https://doi.org/10.1088/1741-4326/ad64e6	journal	July 2024
Neural networks for reconstruction and uncertainty quantification of fast-ion phase-space distributions using FILD and INPA measurements Schmidt, B. S.; Rueda-Rueda, J.; Galdon-Quíroga, J. Nuclear Fusion, Vol. 65, Issue 1 https://doi.org/10.1088/1741-4326/ad93e6	journal	November 2024
Imaging Neutral Particle Analyzer (INPA) measurements of confined fast ions in DIII-D Van Zeeland, M. A.; Du, X. D.; Heidbrink, W. W. Journal of Instrumentation, Vol. 14, Issue 09 https://doi.org/10.1088/1748-0221/14/09/C09027	journal	September 2019
Visualization of Fast Ion Phase-Space Flow Driven by Alfvén Instabilities Du, X. D.; Van Zeeland, M. A.; Heidbrink, W. W. Physical Review Letters, Vol. 127, Issue 23 https://doi.org/10.1103/PhysRevLett.127.235002	journal	December 2021
Physics of Alfvén waves and energetic particles in burning plasmas Chen, Liu; Zonca, Fulvio Reviews of Modern Physics, Vol. 88, Issue 1 https://doi.org/10.1103/RevModPhys.88.015008	journal	March 2016
Alfvén eigenmode detection using Long-Short Term Memory Networks and CO₂ Interferometer data on the DIII-D National Fusion Facility Garcia, Alvin V.; Jalalvand, Azarakhsh; Steiner, Peter 2023 International Joint Conference on Neural Networks (IJCNN) https://doi.org/10.1109/IJCNN54540.2023.10191760	conference	June 2023
Machine Learning Characterization of Alfvénic and Sub-Alfvénic Chirping and Correlation With Fast-Ion Loss at NSTX Woods, Benjamin J. Q.; Duarte, Vinicius N.; Fredrickson, Eric D. IEEE Transactions on Plasma Science, Vol. 48, Issue 1 https://doi.org/10.1109/TPS.2019.2960206	journal	January 2020
MHD and Plasma Control in ITER Snipes, J. A.; Campbell, D. J.; Casper, T. Fusion Science and Technology, Vol. 59, Issue 3 https://doi.org/10.13182/FST11-A11688	journal	April 2011
Contemporary Instrumentation and Application of Charge Exchange Neutral Particle Diagnostics in Magnetic Fusion Experiments Medley, S. S.; Donne, A. J. H.; Kaita, R. https://doi.org/10.2172/962733	report	July 2007
Multipitch tracking in music signals using Echo State Networks Steiner, Peter; Stone, Simon; Birkholz, Peter 2020 28th European Signal Processing Conference (EUSIPCO) https://doi.org/10.23919/Eusipco47968.2020.9287638	conference	January 2021

Similar Records

Validation of the imaging neutral particle analyzer in nearly MHD quiescent plasmas using injected beam ions on DIII-D

Journal Article · Mon Aug 24 20:00:00 EDT 2020 · Nuclear Fusion · OSTI ID:1740006

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
DIII-D
artificial intelligence
energetic particles
neutral particle analyzer

Artificial intelligence-based predictive modeling for imaging neutral particle analyzers on the DIII-D tokamak

Citation Formats

References (50)

Similar Records

Related Subjects