Predicting disruptive instabilities in controlled fusion plasmas through deep learning
Abstract
Nuclear fusion power via magnetic confinement tokamak reactors carries the promise of sustainable and clean energy production for the future [1]. The avoidance of large-scale plasma instabilities called disruptions [2, 3] is one of the most pressing challenges [4, 5] towards this goal. Disruptions are particularly deleterious for large reactors such as the multi-billion dollar international ITER project [6] currently under construction, whose reaction for the first time aims to produce more power from fusion than is injected to heat the plasma. Here, we present a new approach to forecast disruptions based on deep learning that for the first time overcomes the crucial limitations of past work, such as first-principles based [5] and classical machine learning approaches [7, 8, 9, 10, 11]. In particular, our method for the first time (i) delivers reliable predictions on machines other than the one it was trained on — a crucial requirement for large future reactors that cannot afford “training” disruptions; (ii) utilizes high-dimensional training data such as profiles to add new physics information and boost predictive performance; and (iii) engages supercomputing at the largest scale to deliver solutions with improved accuracy and speed. Trained on experimental data from the largest tokamaks in themore »
- Authors:
-
- Harvard Univ., Cambridge, MA (United States); Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)
- Princeton Univ., NJ (United States)
- Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Princeton Univ., NJ (United States)
- Publication Date:
- Research Org.:
- Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); General Atomics, San Diego, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Fusion Energy Sciences (FES)
- OSTI Identifier:
- 1507546
- Alternate Identifier(s):
- OSTI ID: 1566845
- Grant/Contract Number:
- FG02-97ER25308; FC02-04ER54698
- Resource Type:
- Journal Article: Accepted Manuscript
- Journal Name:
- Nature (London)
- Additional Journal Information:
- Journal Volume: 568; Journal Issue: 7753; Journal ID: ISSN 0028-0836
- Publisher:
- Nature Publishing Group
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 70 PLASMA PHYSICS AND FUSION TECHNOLOGY
Citation Formats
Kates-Harbeck, Julian, Svyatkovskiy, Alexey, and Tang, William. Predicting disruptive instabilities in controlled fusion plasmas through deep learning. United States: N. p., 2019.
Web. doi:10.1038/s41586-019-1116-4.
Kates-Harbeck, Julian, Svyatkovskiy, Alexey, & Tang, William. Predicting disruptive instabilities in controlled fusion plasmas through deep learning. United States. https://doi.org/10.1038/s41586-019-1116-4
Kates-Harbeck, Julian, Svyatkovskiy, Alexey, and Tang, William. 2019.
"Predicting disruptive instabilities in controlled fusion plasmas through deep learning". United States. https://doi.org/10.1038/s41586-019-1116-4. https://www.osti.gov/servlets/purl/1507546.
@article{osti_1507546,
title = {Predicting disruptive instabilities in controlled fusion plasmas through deep learning},
author = {Kates-Harbeck, Julian and Svyatkovskiy, Alexey and Tang, William},
abstractNote = {Nuclear fusion power via magnetic confinement tokamak reactors carries the promise of sustainable and clean energy production for the future [1]. The avoidance of large-scale plasma instabilities called disruptions [2, 3] is one of the most pressing challenges [4, 5] towards this goal. Disruptions are particularly deleterious for large reactors such as the multi-billion dollar international ITER project [6] currently under construction, whose reaction for the first time aims to produce more power from fusion than is injected to heat the plasma. Here, we present a new approach to forecast disruptions based on deep learning that for the first time overcomes the crucial limitations of past work, such as first-principles based [5] and classical machine learning approaches [7, 8, 9, 10, 11]. In particular, our method for the first time (i) delivers reliable predictions on machines other than the one it was trained on — a crucial requirement for large future reactors that cannot afford “training” disruptions; (ii) utilizes high-dimensional training data such as profiles to add new physics information and boost predictive performance; and (iii) engages supercomputing at the largest scale to deliver solutions with improved accuracy and speed. Trained on experimental data from the largest tokamaks in the US (DIII-D [12]) and the world (JET [13]), our method moreover can be tuned for physics-specific tasks such as prediction with long warning times, and opens up possible avenues for moving forward the goal from passive disruption prediction to active reactor control and optimization. These results illustrate the potential for deep learning to accelerate progress in fusion energy science and in the understanding and prediction of complex systems in the physical sciences in general.},
doi = {10.1038/s41586-019-1116-4},
url = {https://www.osti.gov/biblio/1507546},
journal = {Nature (London)},
issn = {0028-0836},
number = 7753,
volume = 568,
place = {United States},
year = {2019},
month = {4}
}
Web of Science
Works referenced in this record:
Commissioning of electron cyclotron emission imaging instrument on the DIII-D tokamak and first data
journal, October 2010
- Tobias, B.; Domier, C. W.; Liang, T.
- Review of Scientific Instruments, Vol. 81, Issue 10
Statistical analysis of disruptions in JET
journal, April 2009
- de Vries, P. C.; Johnson, M. F.; Segui, I.
- Nuclear Fusion, Vol. 49, Issue 5
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Fast visible camera installation and operation in JET
conference, January 2008
- Alonso, J. A.; Andrew, P.; Neto, A.
- 2007, AIP Conference Proceedings
Advances and challenges in computational plasma science
journal, January 2005
- Tang, W. M.; Chan, V. S.
- Plasma Physics and Controlled Fusion, Vol. 47, Issue 2
Human-level control through deep reinforcement learning
journal, February 2015
- Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David
- Nature, Vol. 518, Issue 7540
Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization
conference, August 2016
- Khomenko, Viacheslav; Shyshkov, Oleg; Radyvonenko, Olga
- 2016 IEEE First International Conference on Data Stream Mining & Processing (DSMP)
Survey of disruption causes at JET
journal, April 2011
- de Vries, P. C.; Johnson, M. F.; Alper, B.
- Nuclear Fusion, Vol. 51, Issue 5
Cost-sensitive learning by cost-proportionate example weighting
conference, January 2003
- Zadrozny, B.; Langford, J.; Abe, N.
- Third IEEE International Conference on Data Mining
Simultaneous closed-loop control of the current profile and the electron temperature profile in the TCV tokamak
conference, July 2015
- Barton, Justin E.; Wehner, William P.; Schuster, Eugenio
- 2015 American Control Conference (ACC)
Disruption Prediction on JET during the ILW Experimental Campaigns
journal, April 2016
- Moreno, R.; Vega, J.; Dormido-Canto, S.
- Fusion Science and Technology, Vol. 69, Issue 2
Disruption mitigation studies in DIII-D
journal, May 1999
- Taylor, P. L.; Kellman, A. G.; Evans, T. E.
- Physics of Plasmas, Vol. 6, Issue 5
Real time equilibrium reconstruction for tokamak discharge control
journal, July 1998
- Ferron, J. R.; Walker, M. L.; Lao, L. L.
- Nuclear Fusion, Vol. 38, Issue 7
JET ITER-like wall—overview and experimental programme
journal, December 2011
- Matthews, G. F.; Beurskens, M.; Brezinsek, S.
- Physica Scripta, Vol. T145
Overview of the JET results in support to ITER
journal, June 2017
- Litaudon, X.; Abduallev, S.; Abhangi, M.
- Nuclear Fusion, Vol. 57, Issue 10
Prototype of an adaptive disruption predictor for JET based on fuzzy logic and regression trees
journal, February 2008
- Murari, A.; Vagliasindi, G.; Arena, P.
- Nuclear Fusion, Vol. 48, Issue 3
Training distributed deep recurrent neural networks with mixed precision on GPU clusters
conference, January 2017
- Svyatkovskiy, Alexey; Kates-Harbeck, Julian; Tang, William
- Proceedings of the Machine Learning on HPC Environments - MLHPC'17
Disruption forecasting at JET using neural networks
journal, December 2003
- Cannas, B.; Fanni, A.; Marongiu, E.
- Nuclear Fusion, Vol. 44, Issue 1
Improved feature selection based on genetic algorithms for real time disruption prediction on JET
journal, September 2012
- Rattá, G. A.; Vega, J.; Murari, A.
- Fusion Engineering and Design, Vol. 87, Issue 9
A design retrospective of the DIII-D tokamak
journal, May 2002
- Luxon, J. L.
- Nuclear Fusion, Vol. 42, Issue 5
ImageNet: A large-scale hierarchical image database
conference, June 2009
- Deng, Jia; Dong, Wei; Socher, Richard
- 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2009 IEEE Conference on Computer Vision and Pattern Recognition
The use of the area under the ROC curve in the evaluation of machine learning algorithms
journal, July 1997
- Bradley, Andrew P.
- Pattern Recognition, Vol. 30, Issue 7, p. 1145-1159
Disruptions in tokamaks
journal, November 1995
- Schuller, F. C.
- Plasma Physics and Controlled Fusion, Vol. 37, Issue 11A
The ITER design
journal, April 2002
- Aymar, R.; Barabaschi, P.; Shimomura, Y.
- Plasma Physics and Controlled Fusion, Vol. 44, Issue 5
XGBoost: A Scalable Tree Boosting System
conference, January 2016
- Chen, Tianqi; Guestrin, Carlos
- Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16
Cyclical Learning Rates for Training Neural Networks
conference, March 2017
- Smith, Leslie N.
- 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
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
Disruptions in ITER and strategies for their control and mitigation
journal, August 2015
- Lehnen, M.; Aleynikova, K.; Aleynikov, P. B.
- Journal of Nuclear Materials, Vol. 463
Requirements for Triggering the ITER Disruption Mitigation System
journal, April 2016
- de Vries, P. C.; Pautasso, G.; Humphreys, D.
- Fusion Science and Technology, Vol. 69, Issue 2
Tokamak disruption alarm based on a neural network model of the high- beta limit
journal, June 1997
- Wroblewski, D.; Jahns, G. L.; Leuer, J. A.
- Nuclear Fusion, Vol. 37, Issue 6
Feature extraction for improved disruption prediction analysis at JET
journal, October 2008
- Rattá, G. A.; Vega, J.; Murari, A.
- Review of Scientific Instruments, Vol. 79, Issue 10
The Power of an Idea: The International Impacts of the Grand Challenges for Engineering
journal, March 2016
- Mote, C. D.; Dowling, Dame Ann; Zhou, Ji
- Engineering, Vol. 2, Issue 1
Solving the quantum many-body problem with artificial neural networks
journal, February 2017
- Carleo, Giuseppe; Troyer, Matthias
- Science, Vol. 355, Issue 6325
Machine learning phases of matter
journal, February 2017
- Carrasquilla, Juan; Melko, Roger G.
- Nature Physics, Vol. 13, Issue 5
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
Random forest-based prediction of stroke outcome
journal, May 2021
- Fernandez-Lozano, Carlos; Hervella, Pablo; Mato-Abad, Virginia
- Scientific Reports, Vol. 11, Issue 1
Plasma Physics and Fusion Energy
journal, November 2008
- Dolan, Thomas J.
- Fusion Science and Technology, Vol. 54, Issue 4
Plasma Physics and Fusion Energy
journal, November 2008
- Dolan, Thomas J.
- Fusion Science and Technology, Vol. 54, Issue 4
Works referencing / citing this record:
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
Progress in disruption prevention for ITER
journal, June 2019
- Strait, E. J.; Barr, J. L.; Baruzzo, M.
- 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
Disruptive plasma simulations in EAST including 3D effects
journal, September 2019
- Chen, S. L.; Villone, F.; Sun, Y. W.
- Nuclear Fusion, Vol. 59, Issue 10
Deep neural network Grad–Shafranov solver constrained with measured magnetic signals
journal, December 2019
- Joung, Semin; Kim, Jaewook; Kwak, Sehyun
- Nuclear Fusion, Vol. 60, Issue 1
A linear equation based on signal increments to predict disruptive behaviours and the time to disruption on JET
journal, December 2019
- Vega, J.; Murari, A.; Dormido-Canto, S.
- Nuclear Fusion, Vol. 60, Issue 2
Machine learning and big scientific data
journal, January 2020
- Hey, Tony; Butler, Keith; Jackson, Sam
- Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 378, Issue 2166
“Zhores” — Petaflops supercomputer for data-driven modeling, machine learning and artificial intelligence installed in Skolkovo Institute of Science and Technology
journal, October 2019
- Zacharov, Igor; Arslanov, Rinat; Gunin, Maksim
- Open Engineering, Vol. 9, Issue 1