Paper abstract bibtex

We have updated and applied a convolutional neural network (CNN) machine learning model to discover and characterize damped Ly\${\textbackslash}alpha\$ 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\${\textbackslash}%\$ for spectra which have signal-to-noise (S/N) above 5 per pixel. Classification accuracy is the rate of correct classifications. This accuracy remains above 97\${\textbackslash}%\$ for lower signal-to-noise (S/N) \${\textbackslash}approx1\$ spectra. This CNN model provides estimations for redshift and HI column density with standard deviations of 0.002 and 0.17 dex for spectra with S/N above 3 per pixel. 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 Oscillation (BAO) is investigated. The cosmological fitting parameter result for BAO has less than \$0.61{\textbackslash}%\$ 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{\textbackslash}%\$. We also compared the performance of CNN and Gaussian Process (GP) model. Our improved CNN model has moderately 14\${\textbackslash}%\$ higher purity and 7\${\textbackslash}%\$ higher completeness than an older version of GP code, for S/N \${\textgreater}\$ 3. Both codes provide good DLA redshift estimates, but the GP produces a better column density estimate by \$24{\textbackslash}%\$ less standard deviation. A credible DLA catalog for DESI main survey can be provided by combining these two algorithms.

@article{wang_deep_2022, title = {Deep {Learning} of {DESI} {Mock} {Spectra} to {Find} {Damped} {Ly}\{{\textbackslash}alpha\} {Systems}}, url = {http://arxiv.org/abs/2201.00827}, abstract = {We have updated and applied a convolutional neural network (CNN) machine learning model to discover and characterize damped Ly\${\textbackslash}alpha\$ 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\${\textbackslash}\%\$ for spectra which have signal-to-noise (S/N) above 5 per pixel. Classification accuracy is the rate of correct classifications. This accuracy remains above 97\${\textbackslash}\%\$ for lower signal-to-noise (S/N) \${\textbackslash}approx1\$ spectra. This CNN model provides estimations for redshift and HI column density with standard deviations of 0.002 and 0.17 dex for spectra with S/N above 3 per pixel. 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 Oscillation (BAO) is investigated. The cosmological fitting parameter result for BAO has less than \$0.61{\textbackslash}\%\$ 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{\textbackslash}\%\$. We also compared the performance of CNN and Gaussian Process (GP) model. Our improved CNN model has moderately 14\${\textbackslash}\%\$ higher purity and 7\${\textbackslash}\%\$ higher completeness than an older version of GP code, for S/N \${\textgreater}\$ 3. Both codes provide good DLA redshift estimates, but the GP produces a better column density estimate by \$24{\textbackslash}\%\$ less standard deviation. A credible DLA catalog for DESI main survey can be provided by combining these two algorithms.}, urldate = {2022-01-05}, journal = {arXiv:2201.00827 [astro-ph]}, author = {Wang, Ben and Zou, Jiaqi and Cai, Zheng and Prochaska, J. Xavier and Sun, Zechang and Ding, Jiani and Font-Ribera, Andreu and Gonzalez, Alma and Herrera-Alcantar, Hiram K. and Irsic, Vid and Lin, Xiaojing and Brooks, David and Chabanier, Solène and de Belsunce, Roger and Palanque-Delabrouille, Nathalie and Tarle, Gregory and Zhou, Zhimin}, month = jan, year = {2022}, note = {arXiv: 2201.00827}, keywords = {Astrophysics - Astrophysics of Galaxies, Astrophysics - Cosmology and Nongalactic Astrophysics}, }

Downloads: 0