Photometric redshift estimates using Bayesian neural networks in the CSST survey

Abstract

Galaxy photometric redshift (photo-$z$) is crucial in cosmological studies, such as weak gravitational lensing and galaxy angular clustering measurements. In this work, we try to extract photo-$z$ information and construct its probability distribution function (PDF) using the Bayesian neural networks (BNN) from both galaxy flux and image data expected to be obtained by the China Space Station Telescope (CSST). The mock galaxy images are generated from the Advanced Camera for Surveys of Hubble Space Telescope ($HST$-ACS) and COSMOS catalog, in which the CSST instrumental effects are carefully considered. And the galaxy flux data are measured from galaxy images using aperture photometry. We construct Bayesian multilayer perceptron (B-MLP) and Bayesian convolutional neural network (B-CNN) to predict photo-$z$ along with the PDFs from fluxes and images, respectively. We combine the B-MLP and B-CNN together, and construct a hybrid network and employ the transfer learning techniques to investigate the improvement of including both flux and image data. For galaxy samples with SNR$>$10 in $g$ or $i$ band, we find the accuracy and outlier fraction of photo-$z$ can achieve ${\sigma }_{\mathrm{NMAD}}=0.022$ and $\eta =2.35\%$ for the B-MLP using flux data only, and ${\sigma }_{\mathrm{NMAD}}=0.022$ and $\eta =1.32\%$ for the B-CNN using image data only. The Bayesian hybrid network can achieve ${\sigma }_{\mathrm{NMAD}}=0.021$ and $\eta =1.23\%$, and utilizing transfer learning technique can improve results to ${\sigma }_{\mathrm{NMAD}}=0.019$ and $\eta =1.17\%$, which can provide the most confident predictions with the lowest average uncertainty.

22 pages, 12 figures, 3 tables, accepted for publication in RAA

References in corpus (8)

• Weak Gravitational Lensing with COSMOS: Galaxy Selection and Shape Measurements
• The Dark Energy Survey Data Release 2
• 4MOST: Project overview and information for the First Call for Proposals
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Investigating Deep Learning Methods for Obtaining Photometric Redshift Estimations from Images
• Spectroscopic and Photometric Redshift Estimation by Neural Networks For the China Space Station Optical Survey (CSS-OS)
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• Extracting Photometric Redshift from Galaxy Flux and Image Data using Neural Networks in the CSST Survey

Cited by in corpus (8)

• Synergy between CSST galaxy survey and gravitational-wave observation: Inferring the Hubble constant from dark standard sirens
• Future Cosmology: New Physics and Opportunity from the China Space Station Telescope (CSST)
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• Estimating Photometric Redshifts for Galaxies from the DESI Legacy Imaging Surveys with Bayesian Neural Networks Trained by DESI EDR
• Forecasting Supernova Observations with the CSST: I. Photometric Samples
• Accurately Estimating Redshifts from CSST Slitless Spectroscopic Survey using Deep Learning
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• GalaxyGenius: Mock galaxy image generator for various telescopes from hydrodynamical simulations