Euclid preparation – XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images

L. Bisigello*, C. J. Conselice, M. Baes, M. Bolzonella, M. Brescia, S. Cavuoti, O. Cucciati, A. Humphrey, L. K. Hunt, C. Maraston, L. Pozzetti, C. Tortora, S. E. van Mierlo, N. Aghanim, N. Auricchio, M. Baldi, R. Bender, C. Bodendorf, D. Bonino, E. BranchiniJ. Brinchmann, S. Camera, V. Capobianco, C. Carbone, J. Carretero, F. J. Castander, M. Castellano, A. Cimatti, G. Congedo, L. Conversi, Y. Copin, L. Corcione, F. Courbin, M. Cropper, A. Da Silva, H. Degaudenzi, M. Douspis, F. Dubath, C. A.J. Duncan, X. Dupac, S. Dusini, S. Farrens, S. Ferriol, M. Frailis, E. Franceschi, S. M. Niemi, P. Schneider, Y. Wang, G. Gozaliasl, A. G. Sánchez, Euclid Collaboration

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

14 Citations (Scopus)

Abstract

Next-generation telescopes, like Euclid, Rubin/LSST, and Roman, will open new windows on the Universe, allowing us to infer physical properties for tens of millions of galaxies. Machine-learning methods are increasingly becoming the most efficient tools to handle this enormous amount of data, because they are often faster and more accurate than traditional methods. We investigate how well redshifts, stellar masses, and star-formation rates (SFRs) can be measured with deep-learning algorithms for observed galaxies within data mimicking the Euclid and Rubin/LSST surveys. We find that deep-learning neural networks and convolutional neural networks (CNNs), which are dependent on the parameter space of the training sample, perform well in measuring the properties of these galaxies and have a better accuracy than methods based on spectral energy distribution fitting. CNNs allow the processing of multiband magnitudes together with HE-band images. We find that the estimates of stellar masses improve with the use of an image, but those of redshift and SFR do not. Our best results are deriving (i) the redshift within a normalized error of <0.15 for 99.9 per cent of the galaxies with signal-to-noise ratio >3 in the HE band; (ii) the stellar mass within a factor of two (∼0.3 dex) for 99.5 per cent of the considered galaxies; and (iii) the SFR within a factor of two (∼0.3 dex) for ∼70 per cent of the sample. We discuss the implications of our work for application to surveys as well as how measurements of these galaxy parameters can be improved with deep learning.

Original languageEnglish
Pages (from-to)3529-3548
Number of pages20
JournalMonthly Notices of the Royal Astronomical Society
Volume520
Issue number3
DOIs
Publication statusPublished - 1 Apr 2023
MoE publication typeA1 Journal article-refereed

Keywords

  • galaxies: evolution
  • galaxies: general
  • galaxies: photometry
  • galaxies: star formation

Fingerprint

Dive into the research topics of 'Euclid preparation – XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images'. Together they form a unique fingerprint.

Cite this