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

  title={Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit},
  author={Kevin Schawinski and Ce Zhang and Hantian Zhang and Lucas Fowler and Gokula Krishnan Santhanam},
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… Expand
Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
This work proposes a two-way image translation model using GANs that exploits both paired and unpaired images in a semi-supervised manner, and introduces a noise emulating module that is able to learn and reconstruct noise characterized by high-frequency features. Expand
Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
Generative adversarial networks (GANs) are a class of artificial neural network that can produce realistic, but artificial, images that resemble those in a training set. In typical GANExpand
Learning to denoise astronomical images with U-nets
Astronomical images are essential for exploring and understanding the universe. Optical telescopes capable of deep observations, such as the Hubble Space Telescope, are heavily oversubscribed in theExpand
Photometry of high-redshift blended galaxies using deep learning
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, oneExpand
Deep generative models for galaxy image simulations
This work proposes a methodology based on Deep Generative Models to create complex models of galaxy morphologies that may meet the image simulation needs of upcoming surveys, and introduces GalSim-Hub, a community-driven repository of generative models, and a framework for incorporatingGenerative models within the GalSim image simulation software. Expand
Fast cosmic web simulations with generative adversarial networks
This paper demonstrates the application of a machine learning technique called Generative Adversarial Networks (GAN) to learn models that can efficiently generate new, physically realistic realizations of the cosmic web, and finds a good match for the correlation matrix of full Pk$P_{k}$ range for 100 Mpc data and of small scales for 500 Mpc, with ∼20% disagreement for large scales. Expand
Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
Galaxy morphology is a fundamental quantity, which is essential not only for the full spectrum of galaxy-evolution studies, but also for a plethora of science in observational cosmology (e.g. as aExpand
AI-assisted superresolution cosmological simulations
A deep neural network is built to enhance low-resolution dark-matter simulations, generating superresolution realizations that agree remarkably well with authentic high-resolution counterparts on their statistical properties and are orders-of-magnitude faster. Expand
Data-driven Image Restoration with Option-driven Learning for Big and Small Astronomical Image Datasets
This paper proposes a new data--driven image restoration method based on generative adversarial networks with option--driven learning that can obtain very stable image restoration results, regardless of the number of reference images. Expand
Finding strong lenses in CFHTLS using convolutional neural networks
We train and apply convolutional neural networks, a machine learning technique developed to learn from and classify image data, to Canada-France-Hawaii Telescope Legacy Survey (CFHTLS) imaging forExpand


Deconvolution with Correct Sampling
A new method for improving the resolution of astronomical images is presented. It is based on the principle that sampled data cannot be fully deconvolved without violating the sampling theorem. Thus,Expand
Generative Adversarial Text to Image Synthesis
A novel deep architecture and GAN formulation is developed to effectively bridge advances in text and image modeling, translating visual concepts from characters to pixels. Expand
On-axis spectroscopy of the host galaxies of 20 optically luminous quasars at z ~ 0.3
We present the analysis of a sample of 20 bright low-redshift quasars (M B < - 23 and z < 0.35) observed spectroscopically with the Very Large Telescope (VLT). The Focal Reducer/low dispersionExpand
LSST Science Book, Version 2.0
A survey that can cover the sky in optical bands over wide fields to faint magnitudes with a fast cadence will enable many of the exciting science opportunities of the next decade. The Large SynopticExpand
Euclid Definition Study Report
Euclid is a space-based survey mission from the European Space Agency designed to understand the origin of the Universe's accelerating expansion. It will use cosmological probes to investigate theExpand
Importance of input data normalization for the application of neural networks to complex industrial problems
Recent advances in artificial intelligence have allowed the application of such technologies in real industrial problems. We have studied the application of backpropagation neural networks to severalExpand
Bayesian-Based Iterative Method of Image Restoration
An iterative method of restoring degraded images was developed by treating images, point spread functions, and degraded images as probability-frequency functions and by applying Bayes’s theorem. TheExpand
Chaotic communications in the presence of noise
By modulating data on the chaotic signal used to synchronize two nonlinear systems, this work has created a Low Probability of Intercept (LPI) communications system and derived the equations which govern the system. Expand
Mem. Soc. Astron. Italiana
  • Mem. Soc. Astron. Italiana
  • 2008
LSST Science Collaboration et al
  • LSST Science Collaboration et al