Skip to main content

PREDISOL

Characterization of active region time evolution in view of solar flare prediction

BRAIN.be Pioneer Project, 2013-2015

Consortium

This project is a collaboration between Royal Observatory of Belgium/SIDC, Universite catholique de Louvain/ICTEAM, and University of Michigan/Electrical Engineering and Computer Science Department

Context

Solar flares are the most powerful examples of solar activity. When intense and directed towards the Earth, they may affect the ionosphere and radio communications. Providing a reliable prediction with confidence interval for their onset time is thus crucial for Space Weather applications. In particular it is important to predict as early as possible whether an active region will develop into a flare productive active region. About one out of ten active regions will produce one large flare or more (minority class), whereas nine out of ten will produce no or small flares (majority class), but a higher risk is associated to a wrong prediction of the minority class.

Objectives

The objective of PREDISOL is to characterize the evolution of active regions through quantities computed from magnetogram and continuum images, and to be able to link this evolution to the production of large solar flares. A first objective is to provide an optimal classification between flaring and non-flaring active regions that takes into account the specificities of the problem such as the imbalanced class distribution. The second objective is to model sequences of magnetogram and continuum images in order to: make inference about their correlation structure, derive a prediction model, and finally gain insight about the physical processes at work.

References

  • K. Moon, J. Li, V. Delouille, F. Watson, A.O. Hero III Image patch analysis and clustering of sunspots: a dimensionality reduction approach, Proceedings of IEEE International Conference on Image Processing, Paris, France, 2014.

  • De Visscher R, Delouille V, Dupont P, and Deledalle C-A. Supervised classification of solar features using prior information. Journal of Space Weather and Space Climate,5, A34, 2015, DOI: 10.1051/swsc/2015033.

  • K. Moon, V. Delouille, A.O. Hero III. Meta learning of bounds on the Bayes classifier error, Proceeding of IEEE Signal Processing and SP Education workshop, Snowbird UT, 2015.

  • K. Moon, J. Li, V. Delouille, R. De Visscher, F. Watson, A.O. Hero III. Image patch analysis of sunspots and active regions. I. Intrinsic dimension and correlation analysis. Journal of Space Weather and Space Climate, 6, A2, 2016, DOI: 10.1051/swsc/2015044

  • K. Moon, V. Delouille, J. Li, R. De Visscher, F. Watson, A.O. Hero III. Image patch analysis of sunspots and active regions. II. Clustering via dictionary learning Journal of Space Weather and Space Climate, 6, A3, 2016, DOI: 10.1051/swsc/2015043