Identification of Confinement Regimes in Tokamak Plasmas by Conformal Prediction on a Probabilistic Manifold

  • Geert Verdoolaege
  • Jesús Vega
  • Andrea Murari
  • Guido Van Oost
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 382)


Pattern recognition is becoming an increasingly important tool for making inferences from the massive amounts of data produced in magnetic confinement fusion experiments. However, the measurements obtained from the various plasma diagnostics are typically affected by a considerable statistical uncertainty. In this work, we consider the inherent stochastic nature of the data by modeling the measurements by probability distributions in a metric space. Information geometry permits the calculation of the geodesic distances on such manifolds, which we apply to the important problem of the classification of plasma confinement regimes. We use a distance-based conformal predictor, which we first apply to a synthetic data set. Next, the method yields an excellent classification performance with measurements from an international database. The conformal predictor also returns confidence and credibility measures, which are particularly important for interpretation of pattern recognition results in stochastic fusion data.


Magnetic confinement fusion probabilistic manifold conformal predictor 


  1. 1.
    Amari, S., Nagaoka, H.: Methods of information geometry. Transactions of mathematical monographs, vol. 191. American Mathematical Society, New York (2000)MATHGoogle Scholar
  2. 2.
    Burbea, J., Rao, C.R.: Entropy differential metric, distance and divergence measures in probability spaces: a unified approach. J. Multivariate Anal. 12(4), 575–596 (1982)MathSciNetMATHCrossRefGoogle Scholar
  3. 3.
    Fischer, R., Dinklage, A., Pasch, E.: Bayesian modelling of fusion diagnostics. Plasma Phys. Control. Fusion 45(7), 1095–1111 (2003)CrossRefGoogle Scholar
  4. 4.
  5. 5.
    Lukianitsa, A., Zhdanov, F., Zaitsev, F.: Analyses of ITER operation mode using the support vector machine technique for plasma discharge classification. Plasma Phys. Control. Fusion 50(6, article no. 065013) (2008)Google Scholar
  6. 6.
    McDonald, D., et al.: Recent progress on the development and analysis of the ITPA global H-mode confinement database. Nucl. Fusion 47(3), 147–174 (2007)CrossRefGoogle Scholar
  7. 7.
    Meakins, A., McDonald, D., JET-EFDA Contributors: The application of classification methods in a data driven investigation of the JET L-H transition. Plasma Phys. Control. Fusion 52(7, article no. 075005) (2010)Google Scholar
  8. 8.
    Murari, A., Vagliasindi, G., Zedda, M., Felton, R., Sammon, C., Fortuna, L., Arena, P., JET-EFDA Contributors: Fuzzy logic and support vector machine approaches to regime identification in JET. IEEE Trans. Plasma Sci. 34(3), 1013–1020 (2006)Google Scholar
  9. 9.
    Murari, A., Vega, J., Mazon, D., Rattà, G.A., Svensson, J., Palazzo, S., Vagliasindi, G., Arena, P., Boulbé, C., Faugeras, B., Fortuna, L., Moreau, D., JET-EFDA Contributors: Innovative signal processing and data analysis methods on JET for control in the perspective of next-step devices. Nucl. Fusion 50(5, art. no. 055005) (2010)Google Scholar
  10. 10.
    Vega, J., Murari, A., Pereira, A., González, S., Pastor, I.: Accurate and reliable image classification by using conformal predictors in the TJ-II Thomson scattering. Rev. Sci. Instrum. 81(10, article no. 10E118) (2010)Google Scholar
  11. 11.
    Verdoolaege, G., Fischer, R., Van Oost, G., JET-EFDA Contributors: Potential of a Bayesian integrated determination of the ion effective charge via bremsstrahlung and charge exchange spectroscopy in tokamak plasmas. IEEE Trans. Plasma Sci. 38(11), 3168–3196 (2010)CrossRefGoogle Scholar
  12. 12.
    Verdoolaege, G., Scheunders, P.: Geodesics on the manifold of multivariate generalized Gaussian distributions with an application to multicomponent texture discrimination. Int. J. Comput. Vis. 95(3), 265–286 (2011)MATHCrossRefGoogle Scholar
  13. 13.
    Verdoolaege, G., Scheunders, P.: On the geometry of multivariate generalized Gaussian models. J. Math. Imaging Vis. 43(3), 180–193 (2011)CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2012

Authors and Affiliations

  • Geert Verdoolaege
    • 1
  • Jesús Vega
    • 2
  • Andrea Murari
    • 3
  • Guido Van Oost
    • 1
  1. 1.Department of Applied PhysicsGhent UniversityGhentBelgium
  2. 2.Laboratorio Nacional de FusionAsociacion EURATOM-CIEMATMadridSpain
  3. 3.Associazione EURATOM-ENEA sulla FusioneConsorzio RFXPadovaItaly

Personalised recommendations