Deep Learning of Dark Energy Spectroscopic Instrument Mock Spectra to Find Damped Lyα Systems
[1];
[1];
[2];
[3];
[1];
[4];
[6];
[7];
[1];
[8];
[9];
[10];
[11];
- Tsinghua Univ., Beijing (China)
- Tsinghua Univ., Beijing (China); Peng Cheng Laboratory (China)
- Univ. of California, Santa Cruz, CA (United States); Univ. of Tokyo (Japan)
- Univ. of California, Santa Cruz, CA (United States)
- Barcelona Institute of Science and Technology (BIST) (Spain)
- Consejo Nacional de Ciencia y Tecnologia (CONACYT), Mexico City (Mexico); Univ. of Guanajuato (Mexico)
- Univ. of Cambridge (United Kingdom)
- Univ. College London (United Kingdom)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Univ. Paris-Saclay, Gif-sur-Yvette (France)
- Univ. of Michigan, Ann Arbor, MI (United States)
- Chinese Academy of Sciences (CAS), Beijing (China)
We have updated and applied a convolutional neural network (CNN) machine-learning model to discover and characterize damped Lyα 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 i column density with standard deviations of 0.002 and 0.17 dex for spectra with S/N above 3 pixel-1. 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.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), High Energy Physics (HEP); National Science Foundation (NSF); National Key Research and Development Program of China; National Science Foundation of China; Spanish Ministry of Science and Innovation
- Grant/Contract Number:
- AC02-05CH11231
- OSTI ID:
- 1891305
- Journal Information:
- The Astrophysical Journal. Supplement Series, Journal Name: The Astrophysical Journal. Supplement Series Journal Issue: 1 Vol. 259; ISSN 0067-0049
- Publisher:
- IOP PublishingCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Efficient construction of mock catalogs for baryon acoustic oscillation surveys
Mock data sets for the Eboss and DESI Lyman-α forest surveys