Classifying Emission-Line Galaxies using a Dense Neural Network & Support Vector Machine

Date

2024

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

In this study we present an innovative approach to classifying emission-line galaxies, specifically categorizing them as Star-Forming, Seyfert, LINERs (Low Ionization Nuclear Emission Line Region), or Composites. Leveraging both a Dense Neural Network (DNN) and Support Vector Machine (SVM), we use key emission-line flux ratios as input features extracted from the Baryon Oscillation Spectroscopic Survey (BOSS) data within the Sloan Digital Sky Survey (SDSS). The high accuracy in classification for both Machine Learning models showcases their effectiveness and viability in accurately classifying emission-line galaxies with slightly different inputs and target classifications compared to past Machine Learning models.

Description

LCSH Subject Headings

Citation