Deblending Galaxies with Generative Adversarial Networks

Abstract

Deep generative models including generative adversarial networks (GANs) are powerful unsupervised tools in learning the distributions of data sets. Building a simple GAN architecture in PyTorch and training on the CANDELS data set, we generate galaxy images with the Hubble Space Telescope resolution starting from a noise vector. We proceed by modifying the GAN architecture to improve the Subaru Hyper Suprime-Cam ground-based images by increasing their resolution to the HST resolution. We use the super resolution GAN on a large sample of blended galaxies which we create using CANDELS cutouts. In our simulated blend sample, $\sim 20\%$ would unrecognizably be blended even in the HST resolution cutouts. In the HSC-like cutouts this fraction rises to $\sim 90\%$. With our modified GAN we can lower this value to $\sim 50\%$. We quantify the blending fraction in the high, low and GAN resolutions over the whole manifold of angular separation, flux ratios, sizes and redshift difference between the two blended objects. The two peaks found by the GAN deblender result in ten times improvement in the photometry measurement of the blended objects. Modifying the architecture of the GAN, we also train a Multi-wavelength GAN with seven band optical+NIR HST cutouts. This multi-wavelength GAN improves the fraction of detected blends by another $\sim 10\%$ compared to the single-band GAN. This is most beneficial to the current and future precision cosmology experiments (e.g., LSST, SPHEREx, Euclid, Roman), specifically those relying on weak gravitational lensing, where blending is a major source of systematic error.

12 pages, 9 figures, accepted for publication in the Astrophysical Journal

References in corpus (5)

• The James Webb Space Telescope
• Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
• From GAN to WGAN
• Improving the Speed and Quality of GAN by Adversarial Training
• Joint Survey Processing of Euclid, Rubin and Roman: Final Report

Cited by in corpus (11)

• Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data
• Denoising Diffusion Probabilistic Models to Predict the Density of Molecular Clouds
• Score-matching neural networks for improved multi-band source separation
• Accurately Estimating Redshifts from CSST Slitless Spectroscopic Survey using Deep Learning
• Galaxy Imaging with Generative Models: Insights from a Two-Models Framework
• Denoising Diffusion Probabilistic Model for realistic and fast generated \textit{Euclid}-like data for weak lensing analysis
• GalaxyGenius: Mock galaxy image generator for various telescopes from hydrodynamical simulations
• A machine learning approach to assessing the presence of substructure in quasar host galaxies using the Hyper Suprime-Cam Subaru Strategic Program
• Blending effects on shear measurement synergy between Euclid-like and LSST-like surveys
• Diffusion-based Galaxy Simulations for the Roman High Latitude Survey
• On the detection of stellar wakes in the Milky Way: a deep learning approach