A hybrid supervised/unsupervised machine learning approach to solar flare prediction

Federico Benvenuto; Michele Piana; Cristina Campi; Anna Maria Massone

doi:10.3847/1538-4357/aaa23c

A hybrid supervised/unsupervised machine learning approach to solar flare prediction

Solar and Stellar Astrophysics 2018-02-07 v1 Machine Learning

Authors: Federico Benvenuto , Michele Piana , Cristina Campi , Anna Maria Massone

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

We introduce a hybrid approach to solar flare prediction, whereby a supervised regularization method is used to realize feature importance and an unsupervised clustering method is used to realize the binary flare/no-flare decision. The approach is validated against NOAA SWPC data.

Cite

@article{arxiv.1706.07103,
  title  = {A hybrid supervised/unsupervised machine learning approach to solar flare prediction},
  author = {Federico Benvenuto and Michele Piana and Cristina Campi and Anna Maria Massone},
  journal= {arXiv preprint arXiv:1706.07103},
  year   = {2018}
}

Related papers

View all related →