Advanced search
1 file | 923.67 KB Add to list

Modeling fusion data in probabilistic metric spaces: applications to the identification of confinement regimes and plasma disruptions

(2012) FUSION SCIENCE AND TECHNOLOGY. 62(2). p.356-365
Author
Organization
Abstract
Pattern recognition is becoming an increasingly important tool for making inferences from the massive amounts of data produced in fusion experiments. In this work, we present an integrated framework for (real-time) pattern recognition for fusion data. The main starting point is the inherent probabilistic nature of measurements of plasma quantities. Since pattern recognition is essentially based on geometric concepts such as the notion of distance, this necessitates a geometric formalism for probability distributions. To this end, we apply information geometry for calculating geodesic distances on probabilistic manifolds. This provides a natural and theoretically motivated similarity measure between data points for use in pattern recognition techniques. We apply this formalism to classification for the automated identification of plasma confinement regimes in an international database and the prediction of plasma disruptions at JET. We show the distinct advantage in terms of classification performance that is obtained by considering the measurement uncertainty and its geometry. We hence advocate the essential role played by measurement uncertainty for data interpretation in fusion experiments. Finally, we discuss future applications such as the establishment of scaling laws.
Keywords
disruption prediction, confinement regime identification, ELLIPTIC DISTRIBUTIONS, probabilistic pattern recognition, JET

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 923.67 KB

Citation

Please use this url to cite or link to this publication:

MLA
Verdoolaege, Geert, Giorgos Karagounis, Andrea Murari, et al. “Modeling Fusion Data in Probabilistic Metric Spaces: Applications to the Identification of Confinement Regimes and Plasma Disruptions.” FUSION SCIENCE AND TECHNOLOGY 62.2 (2012): 356–365. Print.
APA
Verdoolaege, Geert, Karagounis, G., Murari, A., Vega, J., & Van Oost, G. (2012). Modeling fusion data in probabilistic metric spaces: applications to the identification of confinement regimes and plasma disruptions. FUSION SCIENCE AND TECHNOLOGY, 62(2), 356–365.
Chicago author-date
Verdoolaege, Geert, Giorgos Karagounis, Andrea Murari, Jesus Vega, and Guido Van Oost. 2012. “Modeling Fusion Data in Probabilistic Metric Spaces: Applications to the Identification of Confinement Regimes and Plasma Disruptions.” Fusion Science and Technology 62 (2): 356–365.
Chicago author-date (all authors)
Verdoolaege, Geert, Giorgos Karagounis, Andrea Murari, Jesus Vega, and Guido Van Oost. 2012. “Modeling Fusion Data in Probabilistic Metric Spaces: Applications to the Identification of Confinement Regimes and Plasma Disruptions.” Fusion Science and Technology 62 (2): 356–365.
Vancouver
1.
Verdoolaege G, Karagounis G, Murari A, Vega J, Van Oost G. Modeling fusion data in probabilistic metric spaces: applications to the identification of confinement regimes and plasma disruptions. FUSION SCIENCE AND TECHNOLOGY. 2012;62(2):356–65.
IEEE
[1]
G. Verdoolaege, G. Karagounis, A. Murari, J. Vega, and G. Van Oost, “Modeling fusion data in probabilistic metric spaces: applications to the identification of confinement regimes and plasma disruptions,” FUSION SCIENCE AND TECHNOLOGY, vol. 62, no. 2, pp. 356–365, 2012.
@article{3103334,
  abstract     = {Pattern recognition is becoming an increasingly important tool for making inferences from the massive amounts of data produced in fusion experiments. In this work, we present an integrated framework for (real-time) pattern recognition for fusion data. The main starting point is the inherent probabilistic nature of measurements of plasma quantities. Since pattern recognition is essentially based on geometric concepts such as the notion of distance, this necessitates a geometric formalism for probability distributions. To this end, we apply information geometry for calculating geodesic distances on probabilistic manifolds. This provides a natural and theoretically motivated similarity measure between data points for use in pattern recognition techniques. We apply this formalism to classification for the automated identification of plasma confinement regimes in an international database and the prediction of plasma disruptions at JET. We show the distinct advantage in terms of classification performance that is obtained by considering the measurement uncertainty and its geometry. We hence advocate the essential role played by measurement uncertainty for data interpretation in fusion experiments. Finally, we discuss future applications such as the establishment of scaling laws.},
  author       = {Verdoolaege, Geert and Karagounis, Giorgos and Murari, Andrea and Vega, Jesus and Van Oost, Guido},
  issn         = {1536-1055},
  journal      = {FUSION SCIENCE AND TECHNOLOGY},
  keywords     = {disruption prediction,confinement regime identification,ELLIPTIC DISTRIBUTIONS,probabilistic pattern recognition,JET},
  language     = {eng},
  number       = {2},
  pages        = {356--365},
  title        = {Modeling fusion data in probabilistic metric spaces: applications to the identification of confinement regimes and plasma disruptions},
  url          = {http://www.new.ans.org/pubs/journals/fst/a_14627},
  volume       = {62},
  year         = {2012},
}

Web of Science
Times cited: