An application of survival analysis to disruption prediction via Random Forests

Tinguely, R. A.; Montes, K. J.; Rea, C.; Sweeney, R.; Granetz, R. S.

doi:10.1088/1361-6587/ab32fc

An application of survival analysis to disruption prediction via Random Forests

Journal Article · Wed Aug 07 00:00:00 EDT 2019 · Plasma Physics and Controlled Fusion

DOI:https://doi.org/10.1088/1361-6587/ab32fc· OSTI ID:1609307

^[1]; ^[2]; ^[2]; Sweeney, R. ^[2]; Granetz, R. S. ^[2]

Massachusetts Institute of Technology (MIT), Cambridge, MA (United States). Plasma Science and Fusion Center; OSTI
Massachusetts Institute of Technology (MIT), Cambridge, MA (United States). Plasma Science and Fusion Center

We report one of the most pressing challenges facing the fusion community is adequately mitigating or, even better, avoiding disruptions of tokamak plasmas. However, before this can be done, disruptions must first be predicted with sufficient warning time to actuate a response. The established field of survival analysis provides a convenient statistical framework for time-to-event (i.e. time-to-disruption) studies. This paper demonstrates the integration of an existing disruption prediction machine learning algorithm with the Kaplan–Meier estimator of survival probability. Specifically discussed are the implied warning times from binary classification of disruption databases and the interpretation of output signals from Random Forest algorithms trained and tested on these databases. This survival analysis approach is applied to both smooth and noisy test data to highlight important features of the survival and hazard functions. In addition, this method is applied to three Alcator C-Mod plasma discharges and compared to a threshold-based scheme for triggering alarms. In one case, both techniques successfully predict the disruption; although, in another, neither warns of the impending disruption with enough time to mitigate. For the final discharge, the survival analysis approach could avoid the false alarm triggered by the threshold method. Limitations of this analysis and opportunities for future work are also presented.

View Accepted Manuscript (DOE)

Research Organization:: Massachusetts Institute of Technology (MIT), Cambridge, MA (United States); Oak Ridge Institute for Science and Education (ORISE), Oak Ridge, TN (United States)

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

Grant/Contract Number:: FC02-99ER54512; SC0014664

OSTI ID:: 1609307

Alternate ID(s):: OSTI ID: 23004087

Report Number(s):: PPCF-102353

Journal Information:: Plasma Physics and Controlled Fusion, Journal Name: Plasma Physics and Controlled Fusion Journal Issue: 9 Vol. 61; ISSN 0741-3335

Publisher:: IOP ScienceCopyright Statement

Country of Publication:: United States

Language:: English

References (32)

Improvements in disruption prediction at ASDEX Upgrade Aledda, R.; Cannas, B.; Fanni, A. Fusion Engineering and Design, Vol. 96-97 https://doi.org/10.1016/j.fusengdes.2015.03.045	journal	October 2015
Disruptions in ITER and strategies for their control and mitigation Lehnen, M.; Aleynikova, K.; Aleynikov, P. B. Journal of Nuclear Materials, Vol. 463 https://doi.org/10.1016/j.jnucmat.2014.10.075	journal	August 2015
On-line prediction and mitigation of disruptions in ASDEX Upgrade Pautasso, G.; Tichmann, C.; Egorov, S. Nuclear Fusion, Vol. 42, Issue 1 https://doi.org/10.1088/0029-5515/42/1/314	journal	January 2002
Overview of manifold learning techniques for the investigation of disruptions on JET Cannas, B.; Fanni, A.; Murari, A. Plasma Physics and Controlled Fusion, Vol. 56, Issue 11 https://doi.org/10.1088/0741-3335/56/11/114005	journal	October 2014
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
Wear of the high-density polyethylene socket in total hip arthroplasty and its role in endosteal cavitation Wroblewski, B. M. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, Vol. 211, Issue 1 https://doi.org/10.1243/0954411971534737	journal	January 1997
The High-Field Path to Practical Fusion Energy M. Greenwald, D. Whyte Harvard Dataverse https://doi.org/10.7910/dvn/oyybnu	dataset	January 2018
Support vector machines for disruption prediction and novelty detection at JET Cannas, B.; Delogu, R. S.; Fanni, A. Fusion Engineering and Design, Vol. 82, Issue 5-14 https://doi.org/10.1016/j.fusengdes.2007.07.004	journal	October 2007
Results of the JET real-time disruption predictor in the ITER-like wall campaigns Vega, Jesús; Dormido-Canto, Sebastián; López, Juan M. Fusion Engineering and Design, Vol. 88, Issue 6-8 https://doi.org/10.1016/j.fusengdes.2013.03.003	journal	October 2013
Hazard function exploration of tokamak tearing mode stability boundaries Olofsson, K. E. J.; Sammuli, B. S.; Humphreys, D. A. Fusion Engineering and Design, Vol. 146 https://doi.org/10.1016/j.fusengdes.2019.02.109	journal	September 2019
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Nonparametric Estimation from Incomplete Observations Kaplan, E. L.; Meier, Paul Journal of the American Statistical Association, Vol. 53, Issue 282 https://doi.org/10.1080/01621459.1958.10501452	journal	June 1958
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
Tokamak disruption alarm based on a neural network model of the high- beta limit Wroblewski, D.; Jahns, G. L.; Leuer, J. A. Nuclear Fusion, Vol. 37, Issue 6 https://doi.org/10.1088/0029-5515/37/6/I02	journal	June 1997
Forecasting disruptions in the ADITYA tokamak using neural networks Sengupta, A.; Ranjan, P. Nuclear Fusion, Vol. 40, Issue 12 https://doi.org/10.1088/0029-5515/40/12/304	journal	December 2000
Prediction of density limit disruption boundaries from diagnostic signals using neural networks Sengupta, A.; Ranjan, P. Nuclear Fusion, Vol. 41, Issue 5 https://doi.org/10.1088/0029-5515/41/5/302	journal	May 2001
Neural-net disruption predictor in JT-60U Yoshino, R. Nuclear Fusion, Vol. 43, Issue 12 https://doi.org/10.1088/0029-5515/43/12/021	journal	December 2003
Disruption forecasting at JET using neural networks Cannas, B.; Fanni, A.; Marongiu, E. Nuclear Fusion, Vol. 44, Issue 1 https://doi.org/10.1088/0029-5515/44/1/008	journal	December 2003
Neural-net predictor for beta limit disruptions in JT-60U Yoshino, R. Nuclear Fusion, Vol. 45, Issue 11 https://doi.org/10.1088/0029-5515/45/11/003	journal	October 2005
A cross-tokamak neural network disruption predictor for the JET and ASDEX Upgrade tokamaks Windsor, C. G.; Pautasso, G.; Tichmann, C. Nuclear Fusion, Vol. 45, Issue 5 https://doi.org/10.1088/0029-5515/45/5/004	journal	April 2005
Prototype of an adaptive disruption predictor for JET based on fuzzy logic and regression trees Murari, A.; Vagliasindi, G.; Arena, P. Nuclear Fusion, Vol. 48, Issue 3 https://doi.org/10.1088/0029-5515/48/3/035010	journal	February 2008
Overview of the Alcator C-Mod Research Program Marmar, E.; Bader, A.; Bakhtiari, M. Nuclear Fusion, Vol. 49, Issue 10 https://doi.org/10.1088/0029-5515/49/10/104014	journal	September 2009
Unbiased and non-supervised learning methods for disruption prediction at JET Murari, A.; Vega, J.; Rattá, G. A. Nuclear Fusion, Vol. 49, Issue 5 https://doi.org/10.1088/0029-5515/49/5/055028	journal	April 2009
An advanced disruption predictor for JET tested in a simulated real-time environment Rattá, G. A.; Vega, J.; Murari, A. Nuclear Fusion, Vol. 50, Issue 2 https://doi.org/10.1088/0029-5515/50/2/025005	journal	January 2010
Survey of disruption causes at JET de Vries, P. C.; Johnson, M. F.; Alper, B. Nuclear Fusion, Vol. 51, Issue 5 https://doi.org/10.1088/0029-5515/51/5/053018	journal	April 2011
Simulation and real-time replacement of missing plasma signals for disruption prediction: an implementation with APODIS Rattá, G. A.; Vega, J.; Murari, A. Plasma Physics and Controlled Fusion, Vol. 56, Issue 11 https://doi.org/10.1088/0741-3335/56/11/114004	journal	October 2014
Interpretation of machine-learning-based disruption models for plasma control Parsons, Matthew S. Plasma Physics and Controlled Fusion, Vol. 59, Issue 8 https://doi.org/10.1088/1361-6587/aa72a3	journal	June 2017
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
A First Analysis of JET Plasma Profile-Based Indicators for Disruption Prediction and Avoidance Pau, A.; Fanni, A.; Cannas, B. IEEE Transactions on Plasma Science, Vol. 46, Issue 7 https://doi.org/10.1109/TPS.2018.2841394	journal	July 2018
Regression Models and Life-Tables Cox, D. R. Journal of the Royal Statistical Society: Series B (Methodological), Vol. 34, Issue 2 https://doi.org/10.1111/j.2517-6161.1972.tb00899.x	journal	January 1972
Predicting good probabilities with supervised learning Niculescu-Mizil, Alexandru; Caruana, Rich Proceedings of the 22nd international conference on Machine learning - ICML '05 https://doi.org/10.1145/1102351.1102430	conference	January 2005
The High-Field Path to Practical Fusion Energy M. Greenwald, D. Whyte Harvard Dataverse https://doi.org/10.7910/DVN/OYYBNU	dataset	January 2018

Similar Records

An application of survival analysis to disruption prediction via Random Forests

Dataset · Mon Nov 18 23:00:00 EST 2019 · OSTI ID:1881445

Risk-Aware Framework Development for Disruption Prediction: Alcator C-Mod and DIII-D Survival Analysis

Journal Article · Mon Jun 10 00:00:00 EDT 2024 · Journal of Fusion Energy (Online) · OSTI ID:2377869

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
binary classification
disruption prediction
machine learning
random forest
survival analysis
tokamak plasma

An application of survival analysis to disruption prediction via Random Forests

Citation Formats

References (32)

Similar Records

Related Subjects