Machine learning for observational cosmology

Kana Moriwaki; Takahiro Nishimichi; Naoki Yoshida

doi:10.1088/1361-6633/acd2ea

Machine learning for observational cosmology

Rep Prog Phys. 2023 May 26;86(7). doi: 10.1088/1361-6633/acd2ea.

Authors

Kana Moriwaki¹, Takahiro Nishimichi^{2

3}, Naoki Yoshida^{3

4}

Affiliations

¹ Research Center for the Early Universe, The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo 113-0033, Japan.
² Center for Gravitational Physics and Quantum Information, Yukawa Institute for Theoretical Physics, Kyoto University, Kitashirakawa Oiwakecho, Sakyo-ku, Kyoto 606-8502, Japan.
³ Kavli Institute for the Physics and Mathematics of the Universe (WPI), The University of Tokyo Institutes for Advanced Study (UTIAS), The University of Tokyo, Kashiwa, Chiba 277-8583, Japan.
⁴ Department of Physics, The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo 113-0033, Japan.

PMID: 37146601
DOI: 10.1088/1361-6633/acd2ea

Abstract

An array of large observational programs using ground-based and space-borne telescopes is planned in the next decade. The forthcoming wide-field sky surveys are expected to deliver a sheer volume of data exceeding an exabyte. Processing the large amount of multiplex astronomical data is technically challenging, and fully automated technologies based on machine learning (ML) and artificial intelligence are urgently needed. Maximizing scientific returns from the big data requires community-wide efforts. We summarize recent progress in ML applications in observational cosmology. We also address crucial issues in high-performance computing that are needed for the data processing and statistical analysis.

Keywords: artificial intelligence; cosmology; emulation; machine learning; sky survey.

Publication types

Review