Deep Learning of Dark Energy Spectroscopic Instrument Mock Spectra to Find Damped Ly α Systems
Authors
Font-Ribera, A
Gonzalez, A
Belsunce, RD
Zhou, Z
Publication Date
2022Journal Title
Astrophysical Journal, Supplement Series
ISSN
0067-0049
Publisher
American Astronomical Society
Volume
259
Issue
1
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Wang, B., Zou, J., Cai, Z., Prochaska, J., Sun, Z., Ding, J., Font-Ribera, A., et al. (2022). Deep Learning of Dark Energy Spectroscopic Instrument Mock Spectra to Find Damped Ly α Systems. Astrophysical Journal, Supplement Series, 259 (1) https://doi.org/10.3847/1538-4365/ac4504
Abstract
<jats:title>Abstract</jats:title>
<jats:p>We have updated and applied a convolutional neural network (CNN) machine-learning model to discover and characterize damped Ly<jats:italic>α</jats:italic> systems (DLAs) based on Dark Energy Spectroscopic Instrument (DESI) mock spectra. We have optimized the training process and constructed a CNN model that yields a DLA classification accuracy above 99% for spectra that have signal-to-noise ratios (S/N) above 5 per pixel. The classification accuracy is the rate of correct classifications. This accuracy remains above 97% for lower S/N ≈1 spectra. This CNN model provides estimations for redshift and H <jats:sc>i</jats:sc> column density with standard deviations of 0.002 and 0.17 dex for spectra with S/N above 3 pixel<jats:sup>−1</jats:sup>. Also, this DLA finder is able to identify overlapping DLAs and sub-DLAs. Further, the impact of different DLA catalogs on the measurement of baryon acoustic oscillations (BAO) is investigated. The cosmological fitting parameter result for BAO has less than 0.61% difference compared to analysis of the mock results with perfect knowledge of DLAs. This difference is lower than the statistical error for the first year estimated from the mock spectra: above 1.7%. We also compared the performances of the CNN and Gaussian Process (GP) models. Our improved CNN model has moderately 14% higher purity and 7% higher completeness than an older version of the GP code, for S/N > 3. Both codes provide good DLA redshift estimates, but the GP produces a better column density estimate by 24% less standard deviation. A credible DLA catalog for the DESI main survey can be provided by combining these two algorithms.</jats:p>
Keywords
310, Galaxies and Cosmology
Sponsorship
the Direc, Office of Science, Office of High Energy Physics of the U.S Department of Energy (DE-AC02-05CH11231)
U.S National Science Foundation, Division of Astronomical Sciences (AST-0950945)
National Key R&D Program of China (2018YFA0404503)
National Science Foundation of China (12073014)
Program Ranmon y Cajal of the Spanish Ministry of Science and Innovation (RYC-2018-025210)
Identifiers
apjsac4504, ac4504, aas35212
External DOI: https://doi.org/10.3847/1538-4365/ac4504
This record's URL: https://www.repository.cam.ac.uk/handle/1810/334835
Rights
Licence:
http://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.