Machine learning applications in astrophysics: Photometric redshift estimation

Abstract

Machine learning has rose to become an important research tool in the past decade, its application has been expanded to almost if not all disciplines known to mankind. Particularly, the use of machine learning in astrophysics research had a humble beginning in the early 1980s, it has rose and become widely used in many sub-fields today, driven by the vast availability of free astronomical data online. In this short review, we narrow our discussion to a single topic in astrophysics - the estimation of photometric redshifts of galaxies and quasars, where we discuss its background, significance, and how machine learning has been used to improve its estimation methods in the past 20 years. We also show examples of some recent machine learning photometric redshift work done in Malaysia, affirming that machine learning is a viable and easy way a developing nation can contribute towards general research in astronomy and astrophysics.

8 pages, 5 figures, published in the proceedings of the First International Conference on Computational Science and Data Analytics (COMDATA), 21-24 November 2021, Kuala Lumpur, Malaysia

References in corpus (14)

• Photometric redshift estimation via deep learning
• MegaZ-LRG: A photometric redshift catalogue of one million SDSS Luminous Red Galaxies
• Evaluation of probabilistic photometric redshift estimation approaches for The Rubin Observatory Legacy Survey of Space and Time (LSST)
• Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning
• Bright galaxy sample in the Kilo-Degree Survey Data Release 4: selection, photometric redshifts, and physical properties
• The PAU Survey: Photometric redshifts using transfer learning from simulations
• The Physics of the Accelerating Universe Camera
• Data-driven, interpretable photometric redshifts trained on heterogeneous and unrepresentative data
• Improving the reliability of photometric redshift with machine learning
• The PAU Survey: narrowband photometric redshifts using Gaussian processes
• QSO photometric redshifts using machine learning and neural networks
• Classification of 4XMM-DR9 Sources by Machine Learning
• 21st Century Statistical and Computational Challenges in Astrophysics
• Z-Sequence: Photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours