Data augmentation for disruption prediction via robust surrogate models

Journal of Plasma Physics, vol. 88

Abstract

The goal of this work is to generate large statistically representative data sets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student $t$ process regression. We apply Student $t$ process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via colouring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics and classic machine learning clustering algorithms.

Authors 8

1. Katharina Rath corresponding

   Max Planck Institute for Plasma Physics · Ludwig-Maximilians-Universität München

   Affiliation as printed

   Department of Statistics, Ludwig-Maximilians-Universität München, Germany

   Max-Planck-Institut für Plasmaphysik, Garching, Germany

2. David Rügamer Aachen Institute of Statistics

   Ludwig-Maximilians-Universität München · RWTH Aachen University

   Affiliation as printed

   Department of Statistics, Ludwig-Maximilians-Universität München, Germany

   Institute of Statistics, RWTH Aachen University, Germany

3. Bernd Bischl

   Ludwig-Maximilians-Universität München

   Affiliation as printed

   Department of Statistics, Ludwig-Maximilians-Universität München, Germany

4. U. von Toussaint

   Max Planck Institute for Plasma Physics

   Affiliation as printed

   Max-Planck-Institut für Plasmaphysik, Garching, Germany

5. Cristina Rea

   Massachusetts Institute of Technology

   Affiliation as printed

   Plasma Science and Fusion Center, Massachusetts Institute of Technology, Cambridge, MA, USA

6. Andrew Maris

   Massachusetts Institute of Technology

   Affiliation as printed

   Plasma Science and Fusion Center, Massachusetts Institute of Technology, Cambridge, MA, USA

7. R. Granetz

   Massachusetts Institute of Technology

   Affiliation as printed

   Plasma Science and Fusion Center, Massachusetts Institute of Technology, Cambridge, MA, USA

8. Christopher G. Albert

   Graz University of Technology

   Affiliation as printed

   Fusion@OEAW, Institute of Theoretical and Computational Physics, Graz University of Technology, Austria