The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys

Abstract

The amount and complexity of data delivered by modern galaxy surveys has been steadily increasing over the past years. Extracting coherent scientific information from these large and multi-modal data sets remains an open issue and data driven approaches such as deep learning have rapidly emerged as a potentially powerful solution to some long lasting challenges. This enthusiasm is reflected in an unprecedented exponential growth of publications using neural networks. Half a decade after the first published work in astronomy mentioning deep learning, we believe it is timely to review what has been the real impact of this new technology in the field and its potential to solve key challenges raised by the size and complexity of the new datasets. In this review we first aim at summarizing the main applications of deep learning for galaxy surveys that have emerged so far. We then extract the major achievements and lessons learned and highlight key open questions and limitations. Overall, state-of-the art deep learning methods are rapidly adopted by the astronomical community, reflecting a democratization of these methods. We show that the majority of works using deep learning up to date are oriented to computer vision tasks. This is also the domain of application where deep learning has brought the most important breakthroughs so far. We report that the applications are becoming more diverse and deep learning is used for estimating galaxy properties, identifying outliers or constraining the cosmological model. Most of these works remain at the exploratory level. Some common challenges will most likely need to be addressed before moving to the next phase of deployment of deep learning in the processing of future surveys; e.g. uncertainty quantification, interpretability, data labeling and domain shift issues from training with simulations, which constitutes a common practice in astronomy.

Invited DAWES review. Accepted for publication in PASA

References in corpus (67)

• Simba: Cosmological Simulations with Black Hole Growth and Feedback
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Galaxy Merger Morphologies and Time-Scales from Simulations of Equal-Mass Gas-Rich Disc Mergers
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Photometric redshift estimation via deep learning
• Classifying Radio Galaxies with Convolutional Neural Network
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• A robust morphological classification of high-redshift galaxies using support vector machines on seeing limited images. I Method description
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Nuisance hardened data compression for fast likelihood-free inference
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Early formation of massive, compact, spheroidal galaxies with classical profiles by violent disc instability or mergers
• Robust Machine Learning Applied to Astronomical Datasets I: Star-Galaxy Classification of the SDSS DR3 Using Decision Trees
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Galaxy Merger Rates up to z $\sim$ 3 using a Bayesian Deep Learning Model $-$ A Major-Merger classifier using IllustrisTNG Simulation data
• Identifying Galaxy Mergers in Observations and Simulations with Deep Learning
• Deep learning for galaxy surface brightness profile fitting
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• Convolutional neural network identification of galaxy post-mergers in UNIONS using IllustrisTNG
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• The quenching of galaxies, bulges, and disks since cosmic noon: A machine learning approach for identifying causality in astronomical data
• A comparative study of host galaxy properties between Fast Radio Bursts and stellar transients
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• Learning to Denoise Astronomical Images with U-nets
• Using Convolutional Neural Networks to identify Gravitational Lenses in Astronomical images
• Anomaly detection in the Zwicky Transient Facility DR3
• Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• Stellar Masses of Giant Clumps in CANDELS and Simulated Galaxies Using Machine Learning
• Cataloging the radio-sky with unsupervised machine learning: a new approach for the SKA era
• Galaxy Evolution in all Five CANDELS Fields and IllustrisTNG: Morphological, Structural, and the Major Merger Evolution to $z\sim 3$
• CNN Architecture Comparison for Radio Galaxy Classification
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• Mining the SDSS archive. I. Photometric redshifts in the nearby universe
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domains
• The use of convolutional neural networks for modelling large optically-selected strong galaxy-lens samples
• Realistic galaxy image simulation via score-based generative models
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Galaxy cluster mass estimation with deep learning and hydrodynamical simulations
• ERGO-ML I: Inferring the assembly histories of IllustrisTNG galaxies from integral observable properties via invertible neural networks
• ParSNIP: Generative Models of Transient Light Curves with Physics-Enabled Deep Learning
• Probabilistic Mass Mapping with Neural Score Estimation
• Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
• Predicting star formation properties of galaxies using deep learning
• Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques
• Spin Parity of Spiral Galaxies II: A catalogue of 80k spiral galaxies using big data from the Subaru Hyper Suprime-Cam Survey and deep learning
• Explaining deep learning of galaxy morphology with saliency mapping
• GAlaxy Light profile convolutional neural NETworks (GaLNets). I. fast and accurate structural parameters for billion galaxy samples
• Deep Learning Assisted Data Inspection for Radio Astronomy
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning
• Preparing to discover the unknown with Rubin LSST -- I: Time domain
• Auto-identification of unphysical source reconstructions in strong gravitational lens modelling
• The PAU survey: Estimating galaxy photometry with deep learning
• deepSIP: Linking Type Ia Supernova Spectra to Photometric Quantities with Deep Learning
• Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets
• Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks
• Toward a Full MHD Jet Model of Spinning Black Holes--II: Kinematics and Application to the M87 Jet
• Classifying the formation processes of S0 galaxies using Convolutional Neural Networks
• A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification
• Automatic identification of outliers in Hubble Space Telescope galaxy images
• Predicting bulge to total luminosity ratio of galaxies using deep learning

Cited by in corpus (47)

• Euclid. I. Overview of the Euclid mission
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• AstroCLIP: A Cross-Modal Foundation Model for Galaxies
• COSMOS2025: The COSMOS-Web galaxy catalog of photometry, morphology, redshifts, and physical parameters from JWST, HST, and ground-based imaging
• Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data
• Effective cosmic density field reconstruction with convolutional neural network
• YOLO-CL: Galaxy cluster detection in the SDSS with deep machine learning
• Galaxy merger challenge: A comparison study between machine learning-based detection methods
• YOLO-CIANNA: Galaxy detection with deep learning in radio data. I. A new YOLO-inspired source detection method applied to the SKAO SDC1
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Learning the Universe: Cosmological and Astrophysical Parameter Inference with Galaxy Luminosity Functions and Colours
• Ask The Machine: Systematic detection of wind-type outflows in low-mass X-ray binaries
• Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
• Beyond Traditional Diagnostics: Identifying Active Galactic Nuclei with Spectral Energy Distribution Fitting in DESI Data
• A post-merger enhancement only in star-forming Type 2 Seyfert galaxies: the deep learning view
• A morphological segmentation approach to determining bar lengths
• Predictive uncertainty on improved astrophysics recovery from multifield cosmology
• Generative modelling for mass-mapping with fast uncertainty quantification
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
• Discovery of the Polar Ring Galaxies with deep learning
• Applying machine learning to Galactic Archaeology: how well can we recover the origin of stars in Milky Way-like galaxies?
• YOLO-CL cluster detection in the Rubin/LSST DC2 simulation
• From VIPERS to SDSS: Unveiling galaxy spectra evolution over 9 Gyr through unsupervised machine-learning
• Bayesian and Convolutional Networks for Hierarchical Morphological Classification of Galaxies
• AGN -- host galaxy photometric decomposition using a fast, accurate and precise deep learning approach
• Uncertainty Quantification of the Virial Black Hole Mass with Conformal Prediction
• Exploring Galaxy Properties of eCALIFA with Contrastive Learning
• Classifying merger stages with adaptive deep learning and cosmological hydrodynamical simulations
• Insights on Galaxy Evolution from Interpretable Sparse Feature Networks
• Datacube segmentation via Deep Spectral Clustering
• Deciphering galaxy images using machine vision -- Combining variational autoencoder and principal component analysis for feature extraction
• J-PAS: A Neural Network Approach to Single Stellar Population Characterization
• Generating Galaxy Clusters Mass Density Maps from Mock Multiview Images via Deep Learning
• Direct reconstruction of the Reionization history from 21cm 2D Power Spectra
• Identifying Anomalous DESI Galaxy Spectra with a Variational Autoencoder
• Very-Long Baseline Interferometry Imaging with Closure Invariants using Conditional Image Diffusion
• Bar Properties and Star-by-Star Bar Membership via Action Conservation
• Measuring the Dark Matter Self-Interaction Cross-Section with Deep Compact Clustering for Robust Machine Learning Inference
• Photometric Redshift Estimation Using Scaled Ensemble Learning
• A gradient boosting and broadband approach to finding Lyman-α emitting galaxies beyond narrowband surveys
• Searching for a signature of turnaround in galaxy clusters with convolutional neural networks
• Neural network emulator to constrain the high-$z$ IGM thermal state from Lyman-$\alpha$ forest flux auto-correlation function
• Fast Sampling of Cosmological Initial Conditions with Gaussian Neural Posterior Estimation