Title: Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod

Abstract

Using data-driven methodology, we exploit the time series of relevant plasma parameters for a large set of disrupted and non-disrupted discharges to develop a classification algorithm for detecting disruptive phases in shots that eventually disrupt. Comparing the same methodology on different devices is crucial in order to have information on the portability of the developed algorithm and the possible extrapolation to ITER. Therefore, we use data from two very different tokamaks, DIII-D and Alcator C-Mod. We then focus on a subset of disruption predictors, most of which are dimensionless and/or machine-independent parameters, coming from both plasma diagnostics and equilibrium reconstructions, such as the normalized plasma internal inductance ℓ and the n = 1 mode amplitude normalized to the toroidal magnetic field. Using such dimensionless indicators facilitates a more direct comparison between DIII-D and C-Mod. We then choose a shallow Machine Learning technique, called Random Forests, to explore the databases available for the two devices. We show results from the classification task, where we introduce a time dependency through the definition of class labels on the basis of the elapsed time before the disruption (i.e. ‘far from a disruption’ and ‘close to a disruption’). The performances of the different Random Forestmore » classifiers are discussed in terms of several metrics, by showing the number of successfully detected samples, as well as the misclassifications. The overall model accuracies are above 97% when identifying a ‘far from disruption’ and a ‘disruptive’ phase for disrupted discharges. Nevertheless, the Forests are intrinsically different in their capability of predicting a disruptive behavior, with C-Mod predictions comparable to random guesses. Indeed, we show that C-Mod recall index, i.e. the sensitivity to a disruptive behavior, is as low as 0.47, while DIII-D recall is ~0.72. The portability of the developed algorithm is also tested across the two devices, by using DIII-D data for training the forests and C-Mod for testing and vice versa.« less

Authors:

Rea, C.  ^[1];

• Search DOE PAGES for author "Rea, C."
• Search DOE PAGES for ORCID "0000-0002-9948-2649"

Granetz, R. S.  ^[1];

• Search DOE PAGES for author "Granetz, R. S."
• Search DOE PAGES for ORCID "0000-0002-6560-1881"

Montes, K.  ^[1];

• Search DOE PAGES for author "Montes, K."
• Search DOE PAGES for ORCID "0000-0002-0762-3708"

Tinguely, R. A.  ^[1];

• Search DOE PAGES for author "Tinguely, R. A."
• Search DOE PAGES for ORCID "0000-0002-3711-1834"

Eidietis, N.  ^[2];

• Search DOE PAGES for author "Eidietis, N."
• Search DOE PAGES for ORCID "0000-0003-0167-5053"

Hanson, J. M. ^[3]; Sammuli, B. ^[2]

---

+ Show Author Affiliations

1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Plasma Science and Fusion Center (PSFC)
2. General Atomics, San Diego, CA (United States)
3. Columbia Univ., New York, NY (United States)

Publication Date:

Mon Jun 18 00:00:00 EDT 2018

Research Org.:

Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)

Sponsoring Org.:

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

OSTI Identifier:

1454268

Grant/Contract Number:  

FC02-04ER54698; SC0014264; FG02-04ER54761

Resource Type:

Accepted Manuscript

Journal Name:

Plasma Physics and Controlled Fusion

Additional Journal Information:

Journal Volume: 60; Journal Issue: 8; Journal ID: ISSN 0741-3335

Publisher:

IOP Science

Country of Publication:

United States

Language:

English

Subject:

70 PLASMA PHYSICS AND FUSION TECHNOLOGY; 43 PARTICLE ACCELERATORS; cross-device study; machine learning; disruptions