QUASAR CLASSIFICATION WITH NARROW-BAND SURVEYS

Authors

  • Natália V.N. Rodrigues Instituto de Física - USP
  • L. Raul Abramo Instituto de Física - USP

Keywords:

quasars, photometric surveys, machine learning

Abstract

The next generation of astrophysical surveys will rely on a large amount of data. This scenario encourages the investigation of automated techniques, such as machine learning, to identify objects from millions of sources. Despite being powerful tools, machine learning models still have some limitations in scientific applications. In particular, the uncertainties associated with the measurements are often discarded in the implementations of these models. In this work, we study how to incorporate uncertainties with machine learning in the context of astrophysical source classification. In particular, we apply convolutional neural networks to the low-resolution spectra of narrow-band surveys. Our goal is to identify quasars among other point-like sources, since these are promising tracers to study Large Scale Structure.

Downloads

Published

2022-12-10

How to Cite

Rodrigues, N. V., & Abramo, L. R. (2022). QUASAR CLASSIFICATION WITH NARROW-BAND SURVEYS. Journal of Production and Automation (JPAUT) ISSN 2595-9573, 5(2), 21–26. Retrieved from https://jpaut.com.br/index.php/jpaut/article/view/6