Neural networks for estimation of divertor conditions in DIII-D using C III imaging

Boyer, M. D.; Scotti, F.; Gajaraj, V.

doi:10.1088/1741-4326/ad724d

Title: Neural networks for estimation of divertor conditions in DIII-D using C III imaging

Journal Article · 11 September 2024 · Nuclear Fusion

DOI: https://doi.org/10.1088/1741-4326/ad724d · OSTI ID:2440449

; Scotti, F.; Gajaraj, V.

Abstract Deep learning approaches have been applied to images of C III emission in the lower divertor of DIII-D to develop models for estimating the level of detachment and magnetic configuration (X-point location and strike point radial location). The poloidal distance from the target to the C III emission front is used to represent the level of detachment. The models perform well on a test dataset not used in training, achieving F ₁ scores as high as 0.99 for detachment state classification and root mean squared error (RMSE) as low as 2 cm for front location regression. Predictions for shots with intermittent reattachment are studied, with class activation mapping used to aid in interpretation of the model predictions. Based on the success of these models, a third model was trained to predict the X-point location and strike point radial position from C III images. Though the dataset covers only a small range of possible magnetic configurations, the model shows promising results, achieving RMSE around 1 cm for the test data.

View Journal Article

Cite

Export

Save

Sponsoring Organization:: USDOE Office of Science (SC), Fusion Energy Sciences (FES)

Grant/Contract Number:: AC02-09CH11466

OSTI ID:: 2440449

Journal Information:: Nuclear Fusion, Journal Name: Nuclear Fusion Journal Issue: 10 Vol. 64; ISSN 0029-5515

Publisher:: IOP PublishingCopyright Statement

Country of Publication:: IAEA

Language:: English

References (31)

Accelerated version of NUBEAM capabilities in DIII-D using neural networks Morosohk, Shira M.; Boyer, Mark D.; Schuster, Eugenio Fusion Engineering and Design, Vol. 163 https://doi.org/10.1016/j.fusengdes.2020.112125	journal	February 2021
Heat flux management via advanced magnetic divertor configurations and divertor detachment Kolemen, E.; Allen, S. L.; Bray, B. D. Journal of Nuclear Materials, Vol. 463 https://doi.org/10.1016/j.jnucmat.2014.11.099	journal	August 2015
Electron pressure balance in the SOL through the transition to detachment McLean, A. G.; Leonard, A. W.; Makowski, M. A. Journal of Nuclear Materials, Vol. 463 https://doi.org/10.1016/j.jnucmat.2015.01.066	journal	August 2015
Advances in radiated power control at DIII-D Eldon, D.; Kolemen, E.; Humphreys, D. A. Nuclear Materials and Energy, Vol. 18 https://doi.org/10.1016/j.nme.2019.01.010	journal	January 2019
Physics basis for the first ITER tungsten divertor Pitts, R. A.; Bonnin, X.; Escourbiac, F. Nuclear Materials and Energy, Vol. 20 https://doi.org/10.1016/j.nme.2019.100696	journal	August 2019
Real-time feedback control of the impurity emission front in tokamak divertor plasmas Ravensbergen, T.; van Berkel, M.; Perek, A. Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-21268-3	journal	February 2021
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
A tangentially viewing visible TV system for the DIII-D divertor Fenstermacher, M. E.; Meyer, W. H.; Wood, R. D. Review of Scientific Instruments, Vol. 68, Issue 1 https://doi.org/10.1063/1.1147729	journal	January 1997
Optical boundary reconstruction of tokamak plasmas for feedback control of plasma position and shape Hommen, G.; de Baar, M.; Nuij, P. Review of Scientific Instruments, Vol. 81, Issue 11 https://doi.org/10.1063/1.3499219	journal	November 2010
Feedback system for divertor impurity seeding based on real-time measurements of surface heat flux in the Alcator C-Mod tokamak Brunner, D.; Burke, W.; Kuang, A. Q. Review of Scientific Instruments, Vol. 87, Issue 2 https://doi.org/10.1063/1.4941047	journal	February 2016
A low energy ion beam facility for mass spectrometer calibration: First results Meyer, Stefan; Tulej, Marek; Wurz, Peter Review of Scientific Instruments, Vol. 89, Issue 1 https://doi.org/10.1063/1.5006528	journal	January 2018
MANTIS: A real-time quantitative multispectral imaging system for fusion plasmas Perek, A.; Vijvers, W. A. J.; Andrebe, Y. Review of Scientific Instruments, Vol. 90, Issue 12 https://doi.org/10.1063/1.5115569	journal	December 2019
Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data Churchill, R. M.; Tobias, B.; Zhu, Y. Physics of Plasmas, Vol. 27, Issue 6 https://doi.org/10.1063/1.5144458	journal	June 2020
Progress Toward Interpretable Machine Learning–Based Disruption Predictors Across Tokamaks Rea, C.; Montes, K. J.; Pau, A. Fusion Science and Technology, Vol. 76, Issue 8 https://doi.org/10.1080/15361055.2020.1798589	journal	September 2020
On the physics guidelines for a tokamak DEMO Zohm, H.; Angioni, C.; Fable, E. Nuclear Fusion, Vol. 53, Issue 7 https://doi.org/10.1088/0029-5515/53/7/073019	journal	June 2013
Real-time optical plasma boundary reconstruction for plasma position control at the TCV Tokamak Hommen, G.; Baar, M. de; Duval, B. P. Nuclear Fusion, Vol. 54, Issue 7 https://doi.org/10.1088/0029-5515/54/7/073018	journal	May 2014
Partial detachment of high power discharges in ASDEX Upgrade Kallenbach, A.; Bernert, M.; Beurskens, M. Nuclear Fusion, Vol. 55, Issue 5 https://doi.org/10.1088/0029-5515/55/5/053026	journal	April 2015
Real-time capable first principle based modelling of tokamak turbulent transport Citrin, J.; Breton, S.; Felici, F. Nuclear Fusion, Vol. 55, Issue 9 https://doi.org/10.1088/0029-5515/55/9/092001	journal	July 2015
Transient heat loads in current fusion experiments, extrapolation to ITER and consequences for its operation Loarte, A.; Saibene, G.; Sartori, R. Physica Scripta, Vol. T128 https://doi.org/10.1088/0031-8949/2007/T128/043	journal	March 2007
Real-time control of divertor detachment in H-mode with impurity seeding using Langmuir probe feedback in JET-ITER-like wall Guillemaut, C.; Lennholm, M.; Harrison, J. Plasma Physics and Controlled Fusion, Vol. 59, Issue 4 https://doi.org/10.1088/1361-6587/aa5951	journal	February 2017
Plasma detachment in divertor tokamaks Leonard, A. W. Plasma Physics and Controlled Fusion, Vol. 60, Issue 4 https://doi.org/10.1088/1361-6587/aaa7a9	journal	February 2018
High-energy ballistic electrons in low-pressure radio-frequency plasmas Fu, Yangyang; Zheng, Bocong; Wen, De-Qi Plasma Sources Science and Technology, Vol. 29, Issue 9 https://doi.org/10.1088/1361-6595/abb21b	journal	September 2020
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
Development of a real-time algorithm for detection of the divertor detachment radiation front using multi-spectral imaging Ravensbergen, T.; van Berkel, M.; Silburn, S. A. Nuclear Fusion, Vol. 60, Issue 6 https://doi.org/10.1088/1741-4326/ab8183	journal	May 2020
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
X-point radiation, its control and an ELM suppressed radiating regime at the ASDEX Upgrade tokamak Bernert, M.; Janky, F.; Sieglin, B. Nuclear Fusion, Vol. 61, Issue 2 https://doi.org/10.1088/1741-4326/abc936	journal	December 2020
Prediction of electron density and pressure profile shapes on NSTX-U using neural networks Boyer, M. D.; Chadwick, J. Nuclear Fusion, Vol. 61, Issue 4 https://doi.org/10.1088/1741-4326/abe08b	journal	March 2021
Data-driven profile prediction for DIII-D Abbate, J.; Conlin, R.; Kolemen, E. Nuclear Fusion, Vol. 61, Issue 4 https://doi.org/10.1088/1741-4326/abe08d	journal	March 2021
DIII-D research advancing the physics basis for optimizing the tokamak approach to fusion energy Fenstermacher, Max E.; Abrams, Tyler; Barada, Kshitish Nuclear Fusion https://doi.org/10.1088/1741-4326/ac2ff2	journal	October 2021
Physics design of new lower tungsten divertor for long-pulse high-power operations in EAST Xu, G. S.; Wang, L.; Yao, D. M. Nuclear Fusion, Vol. 61, Issue 12 https://doi.org/10.1088/1741-4326/ac3297	journal	November 2021
Detecting Plasma Detachment in the Wendelstein 7-X Stellarator Using Machine Learning Szűcs, Máté; Szepesi, Tamás; Biedermann, Christoph Applied Sciences, Vol. 12, Issue 1 https://doi.org/10.3390/app12010269	journal	December 2021

Similar Records

Identifying divertor detachment using a machine learning model trained on divertor camera images from DIII-D

Journal Article · 2024 · Review of Scientific Instruments · OSTI ID:2439941

Victor, B. S.; Scotti, F.

Optimizing detachment control using the magnetic configuration of divertors

Journal Article · 2022 · Nuclear Fusion · OSTI ID:1874826

Cowley, C.; Lipschultz, B.; Moulton, D.; +1 more

Enhanced particle flux due to localized divertor MHD instability in DIII-D tokamak

Journal Article · 2020 · Physics of Plasmas · OSTI ID:1608578

Wang, H. Q.; Watkins, J. G.; Guo, H. Y.; +4 more

Title: Neural networks for estimation of divertor conditions in DIII-D using C III imaging

Citation Formats

References (31)

Similar Records

Related Subjects