Photometry of high-redshift blended galaxies using deep learning

Abstract

The new generation of deep photometric surveys requires unprecedentedly precise shape and photometry measurements of billions of galaxies to achieve their main science goals. At such depths, one major limiting factor is the blending of galaxies due to line-of-sight projection, with an expected fraction of blended galaxies of up to 50%. Current deblending approaches are in most cases either too slow or not accurate enough to reach the level of requirements. This work explores the use of deep neural networks to estimate the photometry of blended pairs of galaxies in monochrome space images, similar to the ones that will be delivered by the Euclid space telescope. Using a clean sample of isolated galaxies from the CANDELS survey, we artificially blend them and train two different network models to recover the photometry of the two galaxies. We show that our approach can recover the original photometry of the galaxies before being blended with $\sim$7% accuracy without any human intervention and without any assumption on the galaxy shape. This represents an improvement of at least a factor of 4 compared to the classical SExtractor approach. We also show that forcing the network to simultaneously estimate a binary segmentation map results in a slightly improved photometry. All data products and codes will be made public to ease the comparison with other approaches on a common data set.

16 pages, 12 figures, submitted to MNRAS, comments welcome

References in corpus (27)

• Deep Learning in Neural Networks: An Overview
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• GEMS: Galaxy Evolution from Morphologies and SEDs
• Improving galaxy morphologies for SDSS with Deep Learning
• CANDELS Multiwavelength catalogs: Source Identification and Photometry in the CANDELS UKIDSS Ultra-Deep Survey Field
• GEMS: Galaxy fitting catalogues and testing parametric galaxy fitting codes
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Practical recommendations for gradient-based training of deep architectures
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Precision calculations of the cosmic shear power spectrum projection
• SCARLET: Source separation in multi-band images by Constrained Matrix Factorization
• Deep Learning Identifies High-z Galaxies in a Central Blue Nugget Phase in a Characteristic Mass Range
• The Limits of Cosmic Shear
• A catalog of polychromatic bulge-disk decompositions of ~ 17.600 galaxies in CANDELS
• On the realistic validation of photometric redshifts, or why Teddy will never be Happy
• The Ellipticity Distribution of Ambiguously Blended Objects
• Deblending galaxy superpositions with branched generative adversarial networks
• Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
• The Overlooked Potential of Generalized Linear Models in Astronomy-II: Gamma regression and photometric redshifts
• Multi-band morpho-Spectral Component Analysis Deblending Tool (MuSCADeT): Deblending colourful objects
• The first analytical expression to estimate photometric redshifts suggested by a machine
• Bayesian photometric redshifts of blended sources
• ASTErIsM - Application of topometric clustering algorithms in automatic galaxy detection and classification
• De-Confusing blended field images using graphs and bayesian priors
• PyGFit: A Tool for Extracting PSF Matched Photometry
• Everything we'd like to do with LSST data, but we don't know (yet) how

Cited by in corpus (37)

• Painting a portrait of the Galactic disc with its stellar clusters
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning
• Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
• Detecting outliers in astronomical images with deep generative networks
• Stellar Masses of Giant Clumps in CANDELS and Simulated Galaxies Using Machine Learning
• Deblending galaxies with Variational Autoencoders: a joint multi-band, multi-instrument approach
• Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
• Optimising and comparing source extraction tools using objective segmentation quality criteria
• Quantifying Non-parametric Structure of High-redshift Galaxies with Deep Learning
• Machine Learning for Observational Cosmology
• Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data
• GAlaxy Light profile convolutional neural NETworks (GaLNets). I. fast and accurate structural parameters for billion galaxy samples
• 21st Century Statistical and Computational Challenges in Astrophysics
• Quantitative inference of the $H_2$ column densities from 3 mm molecular emission: A case study towards Orion B
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• The PAU survey: Estimating galaxy photometry with deep learning
• Machines Learn to Infer Stellar Parameters Just by Looking at a Large Number of Spectra
• The nature of giant clumps in high-z discs: a deep-learning comparison of simulations and observations
• Quantifying the fine structures of disk galaxies with deep learning:Segmentation of spiral arms in different Hubble types
• From Images to Features: Unbiased Morphology Classification via Variational Auto-Encoders and Domain Adaptation
• Deblending Galaxies with Generative Adversarial Networks
• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• Galaxy Deblending using Residual Dense Neural networks
• Galaxy Spectra Networks (GaSNet). III. Generative pre-trained network for spectrum reconstruction, redshift estimate and anomaly detection
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• SKATR: A Self-Supervised Summary Transformer for SKA
• Score-matching neural networks for improved multi-band source separation
• A morphological segmentation approach to determining bar lengths
• Deblending Overlapping Galaxies in DECaLS Using Transformer-Based Algorithm: A Method Combining Multiple Bands and Data Types
• Investigation on deep learning-based galaxy image translation models
• Automated galaxy sizes in Euclid images using the Segment Anything Model
• Identifying Radio Active Galactic Nuclei with Machine Learning and Large-Area Surveys
• Efficient neutral-IGM inference from noisy 21-cm forest spectra with latent-space U-Net encoding and XGBoost
• Identification of gravitational lenses obscured by foreground light in the KiDS dataset using U-Nets and ResNets
• Solving Inverse Problems for Spectral Energy Distributions with Deep Generative Networks