A semi-supervised machine learning detector for physics events in tokamak discharges
Abstract
Databases of physics events have been used in various fusion research applications, including the development of scaling laws and disruption avoidance algorithms, yet they can be time-consuming and tedious to construct. This paper presents a novel application of the label spreading semi-supervised learning algorithm to accelerate this process by detecting distinct events in a large dataset of discharges, given few manually labeled examples. A high detection accuracy (> 85%) for H-L back transitions and initially rotating locked modes is demonstrated on a dataset of hundreds of discharges from DIII-D with manually identified events for which only 3 discharges are initially labeled by the user. Lower yet reasonable performance (~75%) is also demonstrated for the core radiative collapse, an event with a much lower prevalence in the dataset. Additionally, analysis of the performance sensitivity indicates that the same set of algorithmic parameters is optimal for each event. Furthermore, this suggests that the method can be applied to detect a variety of other events not included in this paper, given that the event is well described by a set of 0D signals robustly available on many discharges. Procedures for analysis of new events are demonstrated, showing automatic event detection with increasing fidelitymore »
- Authors:
-
- Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
- Publication Date:
- Research Org.:
- General Atomics, San Diego, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Fusion Energy Sciences (FES)
- OSTI Identifier:
- 1735519
- Grant/Contract Number:
- FC02-04ER54698; SC0010492
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Nuclear Fusion
- Additional Journal Information:
- Journal Volume: 61; Journal Issue: 2; Journal ID: ISSN 0029-5515
- Publisher:
- IOP Science
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 70 PLASMA PHYSICS AND FUSION TECHNOLOGY; Disruption; event; detection; semi-supervised; machine-learning
Citation Formats
Montes, Kevin Joseph, Rea, Cristina, Tinguely, Roy Alexander, Sweeney, Ryan, Zhu, Jinxiang, and Granetz, Robert. A semi-supervised machine learning detector for physics events in tokamak discharges. United States: N. p., 2020.
Web. doi:10.1088/1741-4326/abcdb9.
Montes, Kevin Joseph, Rea, Cristina, Tinguely, Roy Alexander, Sweeney, Ryan, Zhu, Jinxiang, & Granetz, Robert. A semi-supervised machine learning detector for physics events in tokamak discharges. United States. https://doi.org/10.1088/1741-4326/abcdb9
Montes, Kevin Joseph, Rea, Cristina, Tinguely, Roy Alexander, Sweeney, Ryan, Zhu, Jinxiang, and Granetz, Robert. Wed .
"A semi-supervised machine learning detector for physics events in tokamak discharges". United States. https://doi.org/10.1088/1741-4326/abcdb9. https://www.osti.gov/servlets/purl/1735519.
@article{osti_1735519,
title = {A semi-supervised machine learning detector for physics events in tokamak discharges},
author = {Montes, Kevin Joseph and Rea, Cristina and Tinguely, Roy Alexander and Sweeney, Ryan and Zhu, Jinxiang and Granetz, Robert},
abstractNote = {Databases of physics events have been used in various fusion research applications, including the development of scaling laws and disruption avoidance algorithms, yet they can be time-consuming and tedious to construct. This paper presents a novel application of the label spreading semi-supervised learning algorithm to accelerate this process by detecting distinct events in a large dataset of discharges, given few manually labeled examples. A high detection accuracy (> 85%) for H-L back transitions and initially rotating locked modes is demonstrated on a dataset of hundreds of discharges from DIII-D with manually identified events for which only 3 discharges are initially labeled by the user. Lower yet reasonable performance (~75%) is also demonstrated for the core radiative collapse, an event with a much lower prevalence in the dataset. Additionally, analysis of the performance sensitivity indicates that the same set of algorithmic parameters is optimal for each event. Furthermore, this suggests that the method can be applied to detect a variety of other events not included in this paper, given that the event is well described by a set of 0D signals robustly available on many discharges. Procedures for analysis of new events are demonstrated, showing automatic event detection with increasing fidelity as the user strategically adds manually labeled examples. Detections on Alcator C-Mod and EAST are also shown, demonstrating the potential for this to be used on a multi-tokamak dataset.},
doi = {10.1088/1741-4326/abcdb9},
journal = {Nuclear Fusion},
number = 2,
volume = 61,
place = {United States},
year = {Wed Nov 25 00:00:00 EST 2020},
month = {Wed Nov 25 00:00:00 EST 2020}
}
Works referenced in this record:
Integrated modeling applications for tokamak experiments with OMFIT
journal, July 2015
- Meneghini, O.; Smith, S. P.; Lao, L. L.
- Nuclear Fusion, Vol. 55, Issue 8
Impact of ELM control techniques on tungsten sputtering in the DIII-D divertor and extrapolations to ITER
journal, June 2019
- Abrams, T.; Unterberg, E. A.; Rudakov, D. L.
- Physics of Plasmas, Vol. 26, Issue 6
Survey of disruption causes at JET
journal, April 2011
- de Vries, P. C.; Johnson, M. F.; Alper, B.
- Nuclear Fusion, Vol. 51, Issue 5
Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas
journal, March 2020
- Piccione, A.; Berkery, J. W.; Sabbagh, S. A.
- Nuclear Fusion, Vol. 60, Issue 4
Adaptive mapping of the plasma operational space of ASDEX Upgrade for disruption prediction
journal, September 2012
- Aledda, Raffaele; Cannas, Barbara; Fanni, Alessandra
- International Journal of Applied Electromagnetics and Mechanics, Vol. 39, Issue 1-4
A reduced resistive wall mode kinetic stability model for disruption forecasting
journal, May 2017
- Berkery, J. W.; Sabbagh, S. A.; Bell, R. E.
- Physics of Plasmas, Vol. 24, Issue 5
Advances in the steady-state hybrid regime in DIII-D—a fully non-inductive, ELM-suppressed scenario for ITER
journal, August 2017
- Petty, C. C.; Nazikian, R.; Park, J. M.
- Nuclear Fusion, Vol. 57, Issue 11
Hybrid deep-learning architecture for general disruption prediction across multiple tokamaks
journal, December 2020
- Zhu, J. X.; Rea, C.; Montes, K.
- Nuclear Fusion, Vol. 61, Issue 2
Comparison of heat flux measurement techniques during the DIII-D metal ring campaign
journal, September 2017
- Barton, J. L.; Nygren, R. E.; Unterberg, E. A.
- Physica Scripta, Vol. T170
Machine learning control for disruption and tearing mode avoidance
journal, February 2020
- Fu, Yichen; Eldon, David; Erickson, Keith
- Physics of Plasmas, Vol. 27, Issue 2
MDSplus yesterday, today and tomorrow
journal, February 2018
- Fredian, T.; Stillerman, J.; Manduchi, G.
- Fusion Engineering and Design, Vol. 127
Unbiased and non-supervised learning methods for disruption prediction at JET
journal, April 2009
- Murari, A.; Vega, J.; Rattá, G. A.
- Nuclear Fusion, Vol. 49, Issue 5
Graph-Based Label Propagation in Digital Media: A Review
journal, April 2015
- Zoidi, Olga; Fotiadou, Eftychia; Nikolaidis, Nikos
- ACM Computing Surveys, Vol. 47, Issue 3
Improved confinement in highly powered high performance scenarios on DIII-D
journal, June 2017
- Petrie, T. W.; Osborne, T.; Fenstermacher, M. E.
- Nuclear Fusion, Vol. 57, Issue 8
Validation of a tearing mode locking model using a database of disruptive plasmas at ASDEX Upgrade
journal, December 2019
- Klevarová, V.; Zohm, H.; Pautasso, G.
- Plasma Physics and Controlled Fusion, Vol. 62, Issue 2
Results of the JET real-time disruption predictor in the ITER-like wall campaigns
journal, October 2013
- Vega, Jesús; Dormido-Canto, Sebastián; López, Juan M.
- Fusion Engineering and Design, Vol. 88, Issue 6-8
Predicting disruptive instabilities in controlled fusion plasmas through deep learning
journal, April 2019
- Kates-Harbeck, Julian; Svyatkovskiy, Alexey; Tang, William
- Nature, Vol. 568, Issue 7753
Progress Toward Interpretable Machine Learning–Based Disruption Predictors Across Tokamaks
journal, September 2020
- Rea, C.; Montes, K. J.; Pau, A.
- Fusion Science and Technology, Vol. 76, Issue 8
Tungsten erosion by unipolar arcing in DIII-D
journal, October 2017
- Bykov, I.; Chrobak, C. P.; Abrams, T.
- Physica Scripta, Vol. T170
Viability Assessment of a Cross-Tokamak AUG-JET Disruption Predictor
journal, February 2018
- Rattá, G. A.; Vega, J.; Murari, A.
- Fusion Science and Technology, Vol. 74, Issue 1-2
Machine learning for disruption warnings on Alcator C-Mod, DIII-D, and EAST
journal, July 2019
- Montes, K. J.; Rea, C.; Granetz, R. S.
- Nuclear Fusion, Vol. 59, Issue 9
Safety factor and turbulence dynamics dependence of the L-H power threshold on DIII-D
journal, June 2019
- Yan, Z.; Mckee, G. R.; Gohil, P.
- Physics of Plasmas, Vol. 26, Issue 6
Power requirement for accessing the H-mode in ITER
journal, July 2008
- Martin, Y. R.; Takizuka, T.; Group, the ITPA CDBM H-mode Threshold Data
- Journal of Physics: Conference Series, Vol. 123
Progress in disruption prevention for ITER
journal, June 2019
- Strait, E. J.; Barr, J. L.; Baruzzo, M.
- Nuclear Fusion, Vol. 59, Issue 11
A cross-tokamak neural network disruption predictor for the JET and ASDEX Upgrade tokamaks
journal, April 2005
- Windsor, C. G.; Pautasso, G.; Tichmann, C.
- Nuclear Fusion, Vol. 45, Issue 5
NSTX/NSTX-U theory, modeling and analysis results
journal, June 2019
- Kaye, S. M.; Battaglia, D. J.; Baver, D.
- Nuclear Fusion, Vol. 59, Issue 11
A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET
journal, August 2019
- Pau, A.; Fanni, A.; Carcangiu, S.
- Nuclear Fusion, Vol. 59, Issue 10
A real-time machine learning-based disruption predictor in DIII-D
journal, July 2019
- Rea, C.; Montes, K. J.; Erickson, K. G.
- Nuclear Fusion, Vol. 59, Issue 9
Hybrid neural network for density limit disruption prediction and avoidance on J-TEXT tokamak
journal, March 2018
- Zheng, W.; Hu, F. R.; Zhang, M.
- Nuclear Fusion, Vol. 58, Issue 5