Investigation on deep learning-based galaxy image translation models

Abstract

Galaxy image translation is an important application in galaxy physics and cosmology. With deep learning-based generative models, image translation has been performed for image generation, data quality enhancement, information extraction, and generalized for other tasks such as deblending and anomaly detection. However, most endeavors on image translation primarily focus on the pixel-level and morphology-level statistics of galaxy images. There is a lack of discussion on the preservation of complex high-order galaxy physical information, which would be more challenging but crucial for studies that rely on high-fidelity image translation. Therefore, we investigated the effectiveness of generative models in preserving high-order physical information (represented by spectroscopic redshift) along with pixel-level and morphology-level information. We tested four representative models, i.e. a Swin Transformer, an SRGAN, a capsule network, and a diffusion model, using the SDSS and CFHTLS galaxy images. We found that these models show different levels of incapabilities in retaining redshift information, even if the global structures of galaxies and morphology-level statistics can be roughly reproduced. In particular, the cross-band peak fluxes of galaxies were found to contain meaningful redshift information, whereas they are subject to noticeable uncertainties in the translation of images, which may substantially be due to the nature of many-to-many mapping. Nonetheless, imperfect translated images may still contain a considerable amount of information and thus hold promise for downstream applications for which high image fidelity is not strongly required. Our work can facilitate further research on how complex physical information is manifested on galaxy images, and it provides implications on the development of image translation models for scientific use.

Accepted at A&A; 18+6 pages; 12+6 figures

References in corpus (29)

• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Eleventh and Twelfth Data Releases of the Sloan Digital Sky Survey: Final Data from SDSS-III
• Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
• The Atlas3D project - XX. Mass-size and mass-sigma distributions of early-type galaxies: bulge fraction drives kinematics, mass-to-light ratio, molecular gas fraction and stellar initial mass function
• Preparing Red-Green-Blue (RGB) Images from CCD Data
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• The CFHT Legacy Survey: stacked images and catalogs
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• The relationship between fine galaxy stellar morphology and star formation activity in cosmological simulations: a deep learning view
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• Photometry of high-redshift blended galaxies using deep learning
• Deblending galaxy superpositions with branched generative adversarial networks
• Deep Generative Models for Galaxy Image Simulations
• Deblending galaxies with Variational Autoencoders: a joint multi-band, multi-instrument approach
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
• Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
• Photometric Redshifts from SDSS Images with an Interpretable Deep Capsule Network
• Automatic Classification of Galaxy Morphology: a rotationally invariant supervised machine learning method based on the UML-dataset
• Deep Learning-based galaxy image deconvolution
• Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• Galaxy Deblending using Residual Dense Neural networks
• Anomaly detection in Astrophysics: a comparison between unsupervised Deep and Machine Learning on KiDS data
• Ground-based image deconvolution with Swin Transformer UNet
• Deblending Overlapping Galaxies in DECaLS Using Transformer-Based Algorithm: A Method Combining Multiple Bands and Data Types
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• Galaxy Image Deconvolution for Weak Gravitational Lensing with Unrolled Plug-and-Play ADMM