Accurately Estimating Redshifts from CSST Slitless Spectroscopic Survey using Deep Learning

Abstract

Chinese Space Station Telescope (CSST) has the capability to conduct slitless spectroscopic survey simultaneously with photometric survey. The spectroscopic survey will measure slitless spectra, potentially providing more accurate estimations of galaxy properties, particularly redshifts, compared to using broadband photometry. CSST relies on these accurate redshifts to perform baryon acoustic oscilliation (BAO) and other probes to constrain the cosmological parameters. However, due to low resolution and signal-to-noise ratio of slitless spectra, measurement of redshifts is significantly challenging.} In this study, we employ a Bayesian neural network (BNN) to assess the accuracy of redshift estimations from slitless spectra anticipated to be observed by CSST. The simulation of slitless spectra is based on real observational data from the early data release of the Dark Energy Spectroscopic Instrument (DESI-EDR) and the 16th data release of the Baryon Oscillation Spectroscopic Survey (BOSS-DR16), combined with the 9th data release of the DESI Legacy Survey (DESI LS DR9). The BNN is constructed employing transfer learning technique, by appending two Bayesian layers after a convolutional neural network (CNN), leveraging the features learned from the slitless spectra and corresponding redshifts. Our network can provide redshift estimates along with corresponding uncertainties, achieving an accuracy of ${\sigma }_{\mathrm{NMAD}}=0.00063$, outlier percentage $\eta =0.92\%$ and weighted mean uncertainty $\bar{E}=0.00228$. These results successfully fulfill the requirement of ${\sigma }_{\mathrm{NMAD}}<0.005$ for BAO and other studies employing CSST slitless spectroscopic surveys.

14 pages, 12 figures, accepted for publication in ApJ

References in corpus (34)

• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• Overview of the DESI Legacy Imaging Surveys
• Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
• The Sixteenth Data Release of the Sloan Digital Sky Surveys: First Release from the APOGEE-2 Southern Survey and Full Release of eBOSS Spectra
• zCOSMOS: A Large VLT/VIMOS redshift survey covering 0 < z < 3 in the COSMOS field
• ANNz: estimating photometric redshifts using artificial neural networks
• The VIMOS VLT Deep Survey final data release: a spectroscopic sample of 35016 galaxies and AGN out to z~6.7 selected with 17.5<=i_{AB}<=24.7
• The Early Data Release of the Dark Energy Spectroscopic Instrument
• Cosmology from the Chinese Space Station Optical Survey (CSS-OS)
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• Prime Focus Spectrograph (PFS) for the Subaru Telescope: Overview, recent progress, and future perspectives
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Non-Gaussian information from weak lensing data via deep learning
• Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning
• Identifying Galaxy Mergers in Observations and Simulations with Deep Learning
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• New high-quality strong lens candidates with deep learning in the Kilo Degree Survey
• Photometric Redshift Estimation with a Convolutional Neural Network: NetZ
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• A Full $w$CDM Analysis of KiDS-1000 Weak Lensing Maps using Deep Learning
• Deblending galaxies with Variational Autoencoders: a joint multi-band, multi-instrument approach
• Investigating Deep Learning Methods for Obtaining Photometric Redshift Estimations from Images
• Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
• Weak-lensing shear measurement with machine learning: teaching artificial neural networks about feature noise
• Spectroscopic and Photometric Redshift Estimation by Neural Networks For the China Space Station Optical Survey (CSS-OS)
• A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
• Extracting Photometric Redshift from Galaxy Flux and Image Data using Neural Networks in the CSST Survey
• Photometric redshift estimates using Bayesian neural networks in the CSST survey
• Deep Learning in Searching the Spectroscopic Redshift of Quasars
• Deblending Galaxies with Generative Adversarial Networks
• Forklens: Accurate weak-lensing shear measurement with deep learning
• Constraining cosmological parameters from N-body simulations with Variational Bayesian Neural Networks
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• Deep learning for cosmological parameter inference from a dark matter halo density field

Cited by in corpus (2)

• Future Cosmology: New Physics and Opportunity from the China Space Station Telescope (CSST)
• GalaxyGenius: Mock galaxy image generator for various telescopes from hydrodynamical simulations