Exploratory Machine Learning Studies for Disruption Prediction Using Large Databases on DIII-D
- 1 January 2018
- journal article
- conference paper
- Published by Informa UK Limited in Fusion Science and Technology
- Vol. 74 (1-2), 89-100
- https://doi.org/10.1080/15361055.2017.1407206
Abstract
Using data-driven methodology, we exploit the time series of relevant plasma parameters for a large set of disrupted and non-disrupted discharges from the DIII-D tokamak with the objective of developing a disruption classification algorithm. We focus on a subset of disruption predictors, most of which are dimensionless and/or machine-independent parameters such as the plasma internal inductance l(i) and the Greenwald density fraction n/n(G), coming from both plasma diagnostics and equilibrium reconstructions. The utilization of dimensionless indicators will facilitate a more direct comparison between different tokamak devices. In order to eventually develop a robust disruption warning algorithm, we leverage Machine Learning techniques, and in particular, we choose the Random Forests algorithm to explore the DIII-D database. We show the results coming from both binary (disrupted/non-disrupted) and multiclass classification problems. In the latter, the time dependency is introduced through the definition of class labels on the basis of the elapsed time before the disruption (i.e., 'far from a disruption', 'within 350 ms of disruption', etc.). Depending on the formulation of the problem, overall disruption prediction accuracy up to 90% is demonstrated, approaching 97% when identifying a stable and a disruptive phase for disrupted discharges. The performances of the different Random Forest classifiers are discussed in terms of accuracy, by showing the percentages of successfully detected samples, together with the false positive and false negative rates.Keywords
Funding Information
- U.S. Department of Energy (DE-FC02-04ER54698 and DE-SC0014264)
This publication has 21 references indexed in Scilit:
- Unbiased and non-supervised learning methods for disruption prediction at JETNuclear Fusion, 2009
- Statistical analysis of disruptions in JETNuclear Fusion, 2009
- SmcHD1, containing a structural-maintenance-of-chromosomes hinge domain, has a critical role in X inactivationNature Genetics, 2008
- Prototype of an adaptive disruption predictor for JET based on fuzzy logic and regression treesNuclear Fusion, 2008
- Disruption forecasting at JET using neural networksNuclear Fusion, 2003
- Real time equilibrium reconstruction for tokamak discharge controlNuclear Fusion, 1998
- Selecting and interpreting measures of thematic classification accuracyRemote Sensing of Environment, 1997
- Tokamak disruption alarm based on a neural network model of the high- beta limitNuclear Fusion, 1997
- MDSplus data acquisition systemReview of Scientific Instruments, 1997
- Reconstruction of current profile parameters and plasma shapes in tokamaksNuclear Fusion, 1985