Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
Authors:
- Levi FussellLFLevi Fussell
- Ben MoewsBMBen Moews
Preprint
Abstract
Astronomy of the 21st century increasingly finds itself with extreme quantities of data. This growth in data is ripe for modern technologies such as deep image processing, which has the potential to allow astronomers to automatically identify, classify, segment and deblend various astronomical objects. In this paper, we explore the use of chained generative adversarial networks (GANs), a class of generative models that learn mappings from latent spaces to data distributions by modelling the joint distribution of the data, to produce physically realistic galaxy images as one use case of such models. In cosmology, such datasets can aid in the calibration of shape measurements for weak lensing by augmenting data with synthetic images. By measuring the distributions of multiple physical properties, we show that images generated with our approach closely follow the distributions of real galaxies, further establishing state-of-the-art GAN architectures as a valuable tool for modern-day astronomy.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Improving galaxy morphologies for SDSS with Deep LearningMonthly Notices of the Royal Astronomical Society, 2018
- Generative adversarial networks recover features in astrophysical images of galaxies beyond the deconvolution limitMonthly Notices of the Royal Astronomical Society: Letters, 2017
- THE THIRD GRAVITATIONAL LENSING ACCURACY TESTING (GREAT3) CHALLENGE HANDBOOKThe Astrophysical Journal Supplement Series, 2014
- Astropy: A community Python package for astronomyAstronomy & Astrophysics, 2013
- Galaxy Zoo 2: detailed morphological classifications for 304 122 galaxies from the Sloan Digital Sky SurveyMonthly Notices of the Royal Astronomical Society, 2013
- The EFIGI catalogue of 4458 nearby galaxies with detailed morphologyAstronomy & Astrophysics, 2011
- Galaxy Zoo 1: data release of morphological classifications for nearly 900 000 galaxies★Monthly Notices of the Royal Astronomical Society, 2010
- Galaxy Zoo: reproducing galaxy morphologies via machine learning★Monthly Notices of the Royal Astronomical Society, 2010
- CCD surface photometry of elliptical galaxies - I. Observations, reduction and resultsMonthly Notices of the Royal Astronomical Society, 1987