학술논문
Machine Learning for Stellar Magnetic Field Determination
Document Type
article
Source
International Journal of Computational Intelligence Systems, Vol 11, Iss 1 (2018)
Subject
Language
English
ISSN
1875-6883
Abstract
Abstract In this work we present the results for the automatic determination of the mean longitudinal magnetic field in polarized stellar spectra through the analysis of spectropolarimetric observations. In order to determine this important parameter, we first developed a synthetic database encompassing a set of different stellar spectra, each one defined by a set of free parameters. Then, we used supervised learning for artificial neural networks, a machine learning approach, to achieve our goal.