Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit

Abstract

Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data. Conventional deconvolution techniques are limited in their ability to recover features in imaging data by the Shannon-Nyquist sampling theorem. Here we train a generative adversarial network (GAN) on a sample of $4,550$ images of nearby galaxies at $0.01<z<0.02$ from the Sloan Digital Sky Survey and conduct $10\times$ cross validation to evaluate the results. We present a method using a GAN trained on galaxy images that can recover features from artificially degraded images with worse seeing and higher noise than the original with a performance which far exceeds simple deconvolution. The ability to better recover detailed features such as galaxy morphology from low-signal-to-noise and low angular resolution imaging data significantly increases our ability to study existing data sets of astrophysical objects as well as future observations with observatories such as the Large Synoptic Sky Telescope (LSST) and the Hubble and James Webb space telescopes.

Accepted for publication in MNRAS, for the full code and a virtual machine set up to run it, see http://space.ml/proj/GalaxyGAN.html

References in corpus (2)

• On-axis spectroscopy of the host galaxies of 20 optically luminous quasars at z~0.3
• A deconvolution-based algorithm for crowded field photometry with unknown Point Spread Function

Cited by in corpus (100)

• Machine learning and the physical sciences
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Probabilistic Random Forest: A machine learning algorithm for noisy datasets
• Quantum Machine Learning for Chemistry and Physics
• StressGAN: A Generative Deep Learning Model for 2D Stress Distribution Prediction
• Finding strong lenses in CFHTLS using convolutional neural networks
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Regressive and generative neural networks for scalar field theory
• Scalable Population Synthesis with Deep Generative Modeling
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• AI-assisted super-resolution cosmological simulations
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Fast cosmic web simulations with generative adversarial networks
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• ExoGAN: Retrieving Exoplanetary Atmospheres Using Deep Convolutional Generative Adversarial Networks
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Enhancing SDO/HMI images using deep learning
• Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
• Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
• Learning to Denoise Astronomical Images with U-nets
• Photometry of high-redshift blended galaxies using deep learning
• Real-time multiframe blind deconvolution of solar images
• Deep Generative Models for Galaxy Image Simulations
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• Realistic galaxy image simulation via score-based generative models
• Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
• A Data Quality-Driven View of MLOps
• Detecting outliers and learning complex structures with large spectroscopic surveys - a case study with APOGEE stars
• Divergence of predictive model output as indication of phase transitions
• Supervised detection of exoplanets in high-contrast imaging sequences
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Accelerating lattice quantum Monte Carlo simulation using artificial neural networks: an application to the Holstein model
• Pulsar Candidate Identification Using Semi-Supervised Generative Adversarial Networks
• Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
• A single $T$-gate makes distribution learning hard
• Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques
• Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
• Efficient End-to-End AutoML via Scalable Search Space Decomposition
• 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
• PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light
• A Machine-Learning-Based Direction-of-Origin Filter for the Identification of Radio Frequency Interference in the Search for Technosignatures
• Solar Image Restoration with the Cycle-GAN Based on Multi-Fractal Properties of Texture Features
• Generating transient noise artifacts in gravitational-wave detector data with generative adversarial networks
• 21st Century Statistical and Computational Challenges in Astrophysics
• Beyond the Local Volume. I. Surface Densities of Ultracool Dwarfs in Deep HST/WFC3 Parallel Fields
• VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition
• Machine learner optimization of optical nanofiber-based dipole traps for cold ${}^{87}$Rb atoms
• Eigengalaxies: describing galaxy morphology using principal components in image space
• A Two-Stage Deep Learning Detection Classifier for the ATLAS Asteroid Survey
• Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection
• Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads
• 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
• Point Spread Function Estimation for Wide Field Small Aperture Telescopes with Deep Neural Networks and Calibration Data
• Improved detection of farside solar active regions using deep learning
• Deblending Galaxies with Generative Adversarial Networks
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• RadioGAN - Translations between different radio surveys with generative adversarial networks
• Deep Forest: Neural Network reconstruction of the Lyman-alpha forest
• Pulsar Candidate Identification with Artificial Intelligence Techniques
• De-noising of galaxy optical spectra with autoencoders
• Improving galaxy morphology with machine learning
• A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time
• Astronomical image denoising by self-supervised deep learning and restoration processes
• Instrument-To-Instrument translation: Instrumental advances drive restoration of solar observation series via deep learning
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Using a Conditional Generative Adversarial Network to Control the Statistical Characteristics of Generated Images for IACT Data Analysis
• Stellar Cluster Detection using GMM with Deep Variational Autoencoder
• Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks
• Quantitative Overfitting Management for Human-in-the-loop ML Application Development with ease.ml/meter
• Probing Neural Networks for the Gamma/Hadron Separation of the Cherenkov Telescope Array
• Galaxy Imaging with Generative Models: Insights from a Two-Models Framework
• How the spectral energy distribution and galaxy morphology constrain each other, with application to morphological selection using galaxy colours
• Searching for Sub-Second Stellar Variability with Wide-Field Star Trails and Deep Learning
• Classifying CMB time-ordered data through deep neural networks
• Generative adversarial network for stellar core-collapse gravitational waves
• A study of Neural networks point source extraction on simulated Fermi/LAT Telescope images
• Multiqubit state learning with entangling quantum generative adversarial networks
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• Time delay estimation in unresolved lensed quasars
• Deblurring galaxy images with Tikhonov regularization on magnitude domain
• Reconstructing the mid-infrared spectra of galaxies using ultraviolet to submillimeter photometry and Deep Generative Networks
• Investigation on deep learning-based galaxy image translation models
• Machine learning and serving of discrete field theories -- when artificial intelligence meets the discrete universe
• A machine learning approach to assessing the presence of substructure in quasar host galaxies using the Hyper Suprime-Cam Subaru Strategic Program
• Radio Halo Detection in MWA Data using Deep Neural Networks and Generative Data Augmentation
• Pushing the Technical Frontier: From Overwhelmingly Large Data Sets to Machine Learning
• Detecting and analysing the topology of the cosmic web with spatial clustering algorithms I: Methods
• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift
• Fast Generation of Large-scale Structure Density Maps via Generative Adversarial Networks
• A CNN--Transformer Denoiser for low-$S/N$ Galaxy Spectra: Stellar Population Recovery in Synthetic Tests
• Generative Adversarial Networks for Astronomical Images Generation