Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

Zeger, Emi U.; Laggner, Florian M.; Bortolon, Alessandro; Rea, Cristina; Meneghini, Orso; Saarelma, Samuli; Sammuli, Brian S.; Smith, Sterling P.; Zhao, Jinjin

doi:10.1109/tps.2021.3114608

Title: Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

Journal Article · Wed Oct 06 00:00:00 EDT 2021 · IEEE Transactions on Plasma Science

DOI:https://doi.org/10.1109/tps.2021.3114608· OSTI ID:1846185

^[1];

^[2]; Bortolon, Alessandro ^[2];

^[3]; Meneghini, Orso ^[4]; Saarelma, Samuli ^[4]; Sammuli, Brian S. ^[4];

^[4]; Zhao, Jinjin ^[5]

Univ. of California, Los Angeles, CA (United States)
Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Plasma Science and Fusion Center
General Atomics, San Diego, CA (United States)
Univ. of Chicago, IL (United States)

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. Here, an experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (n_e) and electron temperature (T_e) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (I_p), toroidal magnetic field (B_Φ), neutral beam heating power (P_NBI) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

View Accepted Manuscript (DOE)

Cite

Export

Save

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

Sponsoring Organization:: USDOE Office of Science (SC), Fusion Energy Sciences (FES); USDOE Office of Science (SC), Workforce Development for Teachers and Scientists (WDTS)

Grant/Contract Number:: FC02-04ER54698; AC02-09CH11466; SC0014264

OSTI ID:: 1846185

Alternate ID(s):: OSTI ID: 1846619

Journal Information:: IEEE Transactions on Plasma Science, Vol. 49, Issue 10; ISSN 0093-3813

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (59)

Suppression of Edge Localized Modes in High-Confinement KSTAR Plasmas by Nonaxisymmetric Magnetic Perturbations Jeon, Y. M.; Park, J. -K.; Yoon, S. W. Physical Review Letters, Vol. 109, Issue 3 https://doi.org/10.1103/PhysRevLett.109.035004	journal	July 2012
Role of transport versus fueling upon pedestal density Mordijck, Saskia; Groebner, Rich; Hughes, Jerry https://doi.org/10.2172/1615234	report	October 2019
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
Reconstruction of current profile parameters and plasma shapes in tokamaks Lao, L. L.; St. John, H.; Stambaugh, R. D. Nuclear Fusion, Vol. 25, Issue 11 https://doi.org/10.1088/0029-5515/25/11/007	journal	November 1985
Initial results of the high resolution edge Thomson scattering upgrade at DIII-D Eldon, D.; Bray, B. D.; Deterly, T. M. Review of Scientific Instruments, Vol. 83, Issue 10 https://doi.org/10.1063/1.4738656	journal	October 2012
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
Improved edge charge exchange recombination spectroscopy in DIII-D Chrystal, C.; Burrell, K. H.; Grierson, B. A. Review of Scientific Instruments, Vol. 87, Issue 11 https://doi.org/10.1063/1.4958915	journal	August 2016
Classification of tokamak plasma confinement states with convolutional recurrent neural networks Matos, F.; Menkovski, V.; Felici, F. Nuclear Fusion, Vol. 60, Issue 3 https://doi.org/10.1088/1741-4326/ab6c7a	journal	February 2020
Controlling marginally detached divertor plasmas Eldon, D.; Kolemen, E.; Barton, J. L. Nuclear Fusion, Vol. 57, Issue 6 https://doi.org/10.1088/1741-4326/aa6b16	journal	May 2017
Multi-mode error field correction on the DIII-D tokamak Scoville, J. T.; Haye, R. J. La Nuclear Fusion, Vol. 43, Issue 4 https://doi.org/10.1088/0029-5515/43/4/305	journal	March 2003
Dependence of pedestal structure on collisionality at fixed beta in JT-60U Urano, H.; Aiba, N.; Kamiya, K. Nuclear Fusion, Vol. 56, Issue 1 https://doi.org/10.1088/0029-5515/56/1/016005	journal	November 2015
The spectral basis of optimal error field correction on DIII-D Paz-Soldan, C.; Buttery, R. J.; Garofalo, A. M. Nuclear Fusion, Vol. 54, Issue 7 https://doi.org/10.1088/0029-5515/54/7/073013	journal	April 2014
MHD Equilibrium Reconstruction in the DIII-D Tokamak Lao, L. L.; John, H. E. St.; Peng, Q. Fusion Science and Technology, Vol. 48, Issue 2 https://doi.org/10.13182/FST48-968	journal	October 2005
Self-consistent core-pedestal transport simulations with neural network accelerated models Meneghini, O.; Smith, S. P.; Snyder, P. B. Nuclear Fusion, Vol. 57, Issue 8 https://doi.org/10.1088/1741-4326/aa7776	journal	July 2017
Self-consistent pedestal prediction for JET-ILW in preparation of the DT campaign Saarelma, S.; Frassinetti, L.; Bilkova, P. Physics of Plasmas, Vol. 26, Issue 7 https://doi.org/10.1063/1.5096870	journal	July 2019
Comparison of H-mode barrier width with a model of neutral penetration length Groebner, R. J.; Mahdavi, M. A.; Leonard, A. W. Nuclear Fusion, Vol. 44, Issue 1 https://doi.org/10.1088/0029-5515/44/1/022	journal	December 2003
The Unreasonable Effectiveness of Data Halevy, Alon; Norvig, Peter; Pereira, Fernando IEEE Intelligent Systems, Vol. 24, Issue 2 https://doi.org/10.1109/MIS.2009.36	journal	March 2009
Pedestal confinement and stability in JET-ILW ELMy H-modes Maggi, C. F.; Saarelma, S.; Casson, F. J. Nuclear Fusion, Vol. 55, Issue 11 https://doi.org/10.1088/0029-5515/55/11/113031	journal	September 2015
Characterization of peeling–ballooning stability limits on the pedestal Snyder, P. B.; Wilson, H. R.; Osborne, T. H. Plasma Physics and Controlled Fusion, Vol. 46, Issue 5A https://doi.org/10.1088/0741-3335/46/5A/014	journal	April 2004
Bias in random forest variable importance measures: Illustrations, sources and a solution Strobl, Carolin; Boulesteix, Anne-Laure; Zeileis, Achim BMC Bioinformatics, Vol. 8, Issue 1 https://doi.org/10.1186/1471-2105-8-25	journal	January 2007
Probability distribution functions for ELM bursts in a series of JET tokamak discharges Greenhough, J.; Chapman, S. C.; Dendy, R. O. Plasma Physics and Controlled Fusion, Vol. 45, Issue 5 https://doi.org/10.1088/0741-3335/45/5/316	journal	April 2003
Development and validation of a predictive model for the pedestal height Snyder, P. B.; Groebner, R. J.; Leonard, A. W. Physics of Plasmas, Vol. 16, Issue 5 https://doi.org/10.1063/1.3122146	journal	May 2009
The H-mode pedestal structure and its role on confinement in JET with a carbon and metal wall Leyland, M. J.; Beurskens, M. N. A.; Frassinetti, L. Nuclear Fusion, Vol. 55, Issue 1 https://doi.org/10.1088/0029-5515/55/1/013019	journal	December 2014
High resolution main-ion charge exchange spectroscopy in the DIII-D H-mode pedestal Grierson, B. A.; Burrell, K. H.; Chrystal, C. Review of Scientific Instruments, Vol. 87, Issue 11 https://doi.org/10.1063/1.4960604	journal	September 2016
TokSearch: A search engine for fusion experimental data Sammuli, B. S.; Barr, J. L.; Eidietis, N. W. Fusion Engineering and Design, Vol. 129 https://doi.org/10.1016/j.fusengdes.2018.02.003	journal	April 2018
Inductive classification of low-mode and high-mode edge parameters Deranian, R. D.; Groebner, R. J.; Pham, D. T. Physics of Plasmas, Vol. 7, Issue 4 https://doi.org/10.1063/1.873934	journal	April 2000
Chapter 1: Overview and summary Shimada, M.; Campbell, D. J.; Mukhovatov, V. Nuclear Fusion, Vol. 47, Issue 6 https://doi.org/10.1088/0029-5515/47/6/S01	journal	June 2007
Scaling studies of the high mode pedestal Groebner, R. J.; Osborne, T. H. Physics of Plasmas, Vol. 5, Issue 5 https://doi.org/10.1063/1.872849	journal	May 1998
Integrated modeling applications for tokamak experiments with OMFIT Meneghini, O.; Smith, S. P.; Lao, L. L. Nuclear Fusion, Vol. 55, Issue 8 https://doi.org/10.1088/0029-5515/55/8/083008	journal	July 2015
Real-time pedestal optimization and ELM control with 3D fields and gas flows on DIII-D Laggner, F. M.; Eldon, D.; Nelson, A. O. Nuclear Fusion, Vol. 60, Issue 7 https://doi.org/10.1088/1741-4326/ab88e1	journal	June 2020
Improved understanding of physics processes in pedestal structure, leading to improved predictive capability for ITER Groebner, R. J.; Chang, C. S.; Hughes, J. W. Nuclear Fusion, Vol. 53, Issue 9 https://doi.org/10.1088/0029-5515/53/9/093024	journal	August 2013
Fueling with edge recycling to high-density in DIII-D Leonard, A. W.; Elder, J. D.; Canik, J. M. Journal of Nuclear Materials, Vol. 438 https://doi.org/10.1016/j.jnucmat.2013.01.037	journal	July 2013
Neural-network accelerated coupled core-pedestal simulations with self-consistent transport of impurities and compatible with ITER IMAS Meneghini, O.; Snoep, G.; Lyons, B. C. Nuclear Fusion, Vol. 61, Issue 2 https://doi.org/10.1088/1741-4326/abb918	journal	December 2020
Mutual Information between Discrete and Continuous Data Sets Ross, Brian C. PLoS ONE, Vol. 9, Issue 2 https://doi.org/10.1371/journal.pone.0087357	journal	February 2014
Thomson scattering diagnostic upgrade on DIII-D Ponce-Marquez, D. M.; Bray, B. D.; Deterly, T. M. Review of Scientific Instruments, Vol. 81, Issue 10 https://doi.org/10.1063/1.3495759	journal	October 2010
New capabilities and upgrade path for the DIII-D neutral beam heating system Scoville, J. T.; Boyer, M. D.; Crowley, B. J. Fusion Engineering and Design, Vol. 146 https://doi.org/10.1016/j.fusengdes.2018.10.015	journal	September 2019
Edge-localized-modes in tokamaks Leonard, A. W. Physics of Plasmas, Vol. 21, Issue 9 https://doi.org/10.1063/1.4894742	journal	September 2014
Pedestal structure in H-mode plasmas Urano, Hajime Nuclear Fusion, Vol. 54, Issue 11 https://doi.org/10.1088/0029-5515/54/11/116001	journal	November 2014
ELMs and constraints on the H-mode pedestal: peeling–ballooning stability calculation and comparison with experiment Snyder, P. B.; Wilson, H. R.; Ferron, J. R. Nuclear Fusion, Vol. 44, Issue 2 https://doi.org/10.1088/0029-5515/44/2/014	journal	January 2004
Neutral pressure and separatrix density related models for seed impurity divertor radiation in ASDEX Upgrade Kallenbach, A.; Bernert, M.; Dux, R. Nuclear Materials and Energy, Vol. 18 https://doi.org/10.1016/j.nme.2018.12.021	journal	January 2019
Estimating mutual information Kraskov, Alexander; Stögbauer, Harald; Grassberger, Peter Physical Review E, Vol. 69, Issue 6 https://doi.org/10.1103/PhysRevE.69.066138	journal	June 2004
Identifying the location of the OMP separatrix in DIII-D using power accounting Stangeby, P. C.; Canik, J. M.; Elder, J. D. Nuclear Fusion, Vol. 55, Issue 9 https://doi.org/10.1088/0029-5515/55/9/093014	journal	August 2015
Real-time capable modeling of neutral beam injection on NSTX-U using neural networks Boyer, M. D.; Kaye, S.; Erickson, K. Nuclear Fusion, Vol. 59, Issue 5 https://doi.org/10.1088/1741-4326/ab0762	journal	March 2019
Progress in quantifying the edge physics of the H mode regime in DIII-D Groebner, R. J.; Baker, D. R.; Burrell, K. H. Nuclear Fusion, Vol. 41, Issue 12 https://doi.org/10.1088/0029-5515/41/12/306	journal	December 2001
A quarter-century of H-mode studies Wagner, F. Plasma Physics and Controlled Fusion, Vol. 49, Issue 12B https://doi.org/10.1088/0741-3335/49/12B/S01	journal	November 2007
Statistical Characterization and Classification of Edge-Localized Plasma Instabilities Webster, A. J.; Dendy, R. O. Physical Review Letters, Vol. 110, Issue 15 https://doi.org/10.1103/PhysRevLett.110.155004	journal	April 2013
Correlation analysis for energy losses, waiting times and durations of type I edge-localized modes in the Joint European Torus Shabbir, A.; Verdoolaege, G.; Hornung, G. Nuclear Fusion, Vol. 57, Issue 3 https://doi.org/10.1088/1741-4326/aa5098	journal	January 2017
A design retrospective of the DIII-D tokamak Luxon, J. L. Nuclear Fusion, Vol. 42, Issue 5 https://doi.org/10.1088/0029-5515/42/5/313	journal	May 2002
ITER predictions using the GYRO verified and experimentally validated trapped gyro-Landau fluid transport model Kinsey, J. E.; Staebler, G. M.; Candy, J. Nuclear Fusion, Vol. 51, Issue 8 https://doi.org/10.1088/0029-5515/51/8/083001	journal	June 2011
Design and operation of the multipulse Thomson scattering diagnostic on DIII‐D (invited) Carlstrom, T. N.; Campbell, G. L.; DeBoo, J. C. Review of Scientific Instruments, Vol. 63, Issue 10 https://doi.org/10.1063/1.1143545	journal	October 1992
Use of a pattern recognition algorithm to obtain a parametrization of low-mode and high-mode plasma states Deranian, R. D.; Groebner, R. J.; Pham, D. T. Physics of Plasmas, Vol. 9, Issue 6 https://doi.org/10.1063/1.1476000	journal	June 2002
Physics of pedestal density profile formation and its impact on H-mode density limit in burning plasmas Mahdavi, M. A.; Maingi, R.; Groebner, R. J. Physics of Plasmas, Vol. 10, Issue 10 https://doi.org/10.1063/1.1605101	journal	October 2003
A classification scheme for edge-localized modes based on their probability distributions Shabbir, A.; Hornung, G.; Verdoolaege, G. Review of Scientific Instruments, Vol. 87, Issue 11 https://doi.org/10.1063/1.4955479	journal	July 2016
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
Edge-localized modes - physics and theory Connor, J. W. Plasma Physics and Controlled Fusion, Vol. 40, Issue 5 https://doi.org/10.1088/0741-3335/40/5/002	journal	May 1998
Global performance enhancements via pedestal optimisation on ASDEX Upgrade Dunne, M. G.; Frassinetti, L.; Beurskens, M. N. A. Plasma Physics and Controlled Fusion, Vol. 59, Issue 2 https://doi.org/10.1088/1361-6587/59/2/025010	journal	December 2016
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Suppression of Large Edge-Localized Modes in High-Confinement DIII-D Plasmas with a Stochastic Magnetic Boundary Evans, T. E.; Moyer, R. A.; Thomas, P. R. Physical Review Letters, Vol. 92, Issue 23 https://doi.org/10.1103/PhysRevLett.92.235003	journal	June 2004
Analysis of temperature and density pedestal gradients in AUG, DIII-D and JET Schneider, P. A.; Wolfrum, E.; Groebner, R. J. Nuclear Fusion, Vol. 53, Issue 7 https://doi.org/10.1088/0029-5515/53/7/073039	journal	June 2013

Similar Records

Prediction of DIII-D Pedestal Structure from Externally Controllable Parameters

Dataset · Mon Jun 06 00:00:00 EDT 2022 · OSTI ID:1846185

Zeger, Emi U.; Laggner, Florian M.; Bortolon, Alessandro; +6 more

Integrated modeling applications for tokamak experiments with OMFIT

Journal Article · Wed Jul 01 00:00:00 EDT 2015 · Nuclear Fusion · OSTI ID:1846185

Meneghini, O.; Smith, S. P.; Lao, L. L.; +21 more

Pedestal main ion particle transport inference through gas puff modulation with experimental source measurements

Journal Article · Wed Jan 24 00:00:00 EST 2024 · Nuclear Fusion · OSTI ID:1846185

Rosenthal, A. M.; Hughes, J. W.; Laggner, F. M.; +6 more

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
plasma
tokamak
pedestal
neural net
random forest
machine learning
TokSearch
OMFIT

Title: Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

Citation Formats

References (59)

Similar Records

Related Subjects