摘要
Galaxy photometric redshift(photoz)is crucial in cosmological studies,such as weak gravitational lensing and galaxy angular clustering measurements.In this work,we try to extract photoz information and construct its probability distribution function(PDF)using the Bayesian neural networks 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 Hubble Space Telescope-Advanced Camera for Surveys(HST-ACS)and COSMOS catalogs,in which the CSST instrumental effects are carefully considered.In addition,the galaxy flux data are measured from galaxy images using aperture photometry.We construct a Bayesian multilayer perceptron(B-MLP)and Bayesian convolutional neural network(B-CNN)to predict photoz 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 signal-to-noise ratio(SNR)>10 in g or i band,we find the accuracy and outlier fraction of photoz can achieve σ_(NMAD)=0.022 and η=2.35% for the B-MLP using flux data only,and σ_(NMAD)=0.022 and η=1.32% for the B-CNN using image data only.The Bayesian hybrid network can achieve σ_(NMAD)=0.021 and η=1.23%,and utilizing transfer learning technique can improve results to σ_(NMAD)=0.019 and η=1.17%,which can provide the most confident predictions with the lowest average uncertainty.
基金
the support of MOST-2018YFE0120800
2020SKA0110402
NSFC-11822305
NSFC-11773031
NSFC-11633004
CAS Interdisciplinary Innovation Team
support from the National Natural Science Foundation of China(NSFC,Grant Nos.11473044 and 11973047)
the Chinese Academy of Science grants QYZDJ-SSW-SLH017,XDB 23040100 and XDA15020200
support from NSFC grant 11933002
the Dawn Program 19SG41
the Innovation Program 2019-0107-00-02-E00032 of SMEC
supported by the science research grants from the China Manned Space Project with No.CMS-CSST-2021-B01 and CMS-CSST-2021-A01
funded by the National Natural Science Foundation of China(NSFC,Grant No.11080922)。