English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The accuracy of galaxy photometric redshift (photo-$z$) can significantlyaffect the analysis of weak gravitational lensing measurements, especially forfuture high-precision surveys. In this work, we try to extract photo-$z$information from both galaxy flux and image data expected to be obtained byChina Space Station Telescope (CSST) using neural networks. We generate mockgalaxy images based on the observational images from the Advanced Camera forSurveys of Hubble Space Telescope (HST-ACS) and COSMOS catalogs, consideringthe CSST instrumental effects. Galaxy flux data are then measured directly fromthese images by aperture photometry. The Multi-Layer Perceptron (MLP) andConvolutional Neural Network (CNN) are constructed to predict photo-$z$ fromfluxes and images, respectively. We also propose to use an efficient hybridnetwork, which combines MLP and CNN, by employing transfer learning techniquesto investigate the improvement of the result with both flux and image dataincluded. We find that the photo-$z$ accuracy and outlier fraction can achieve$\sigma_{\rm NMAD} = 0.023$ and $\eta = 1.43\%$ for the MLP using flux dataonly, and $\sigma_{\rm NMAD} = 0.025$ and $\eta = 1.21\%$ for the CNN usingimage data only. The result can be further improved in high efficiency as$\sigma_{\rm NMAD} = 0.020$ and $\eta = 0.90\%$ for the hybrid transfernetwork. These approaches result in similar galaxy median and mean redshifts~0.8 and 0.9, respectively, for the redshift range from 0 to 4. This indicatesthat our networks can effectively and properly extract photo-$z$ informationfrom the CSST galaxy flux and image data.

Extracting Photometric Redshift from Galaxy Flux and Image Data using Neural Networks in the CSST Survey