Enabling Dark Energy Science with Deep Generative Models of Galaxy Images

By Siamak Ravanbakhsh, François Lanusse, Rachel Mandelbaum, Jeff Schneider, Barnab'as P'oczos. 2016

68 citations recorded by the source corpus.

Understanding the nature of dark energy, the mysterious force driving the accelerated expansion of the Universe, is a major challenge of modern cosmology. The next generation of cosmological surveys, specifically designed to address this issue, rely on accurate measurements of the apparent shapes of distant galaxies. However, shape measurement methods suffer from various unavoidable biases and therefore will rely on a precise calibration to meet the accuracy requirements of the science analysis. This calibration process remains an open challenge as it requires large sets of high quality galaxy images. To this end, we study the application of deep conditional generative models in generating realistic galaxy images. In particular we consider variations on conditional variational autoencoder and introduce a new adversarial objective for training of conditional generative networks. Our results suggest a reliable alternative to the acquisition of expensive high quality observations for generating the calibration data needed by the next generation of cosmological surveys.

Subfields: Biophysics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

Nils Thürey

In Computer Vision and Pattern Recognition

Citations in the corpus

Generative Multi-Adversarial Networks (2016, methodology): “As training progresses and the discriminators improve, we can increase λ to become more critical of the generator for more reﬁned training.”
Deciphering protein evolution and fitness landscapes with latent space models (2019, background): “Latent space models learned with VAEs have been widely used in several machine learning problems, such as image and natural language processing, and produce state-of-the-art results 34,45,46 .”
Deep Fluids: A Generative Network for Parameterized Fluid Simulations (2018, methodology): “GANs have also been employed to generate [RLM ∗ 17] and deconvolve [SZZ ∗ 17] galaxy images, and reconstruct three-dimensional porous media [MDB17].”
CosmoFlow: Using Deep Learning to Learn the Universe at Scale (2018, methodology): “In recent years deep learning methods have started to be used in astronomy, including for the prediction of galaxy morphology [6] and generating models for galaxies images [7].”
An Introduction to Variational Autoencoders (2019, unknown): “In (Ravanbakhsh et al., 2017), VAEs are applied to simulate observations of distant galaxies.”
A high-bias, low-variance introduction to Machine Learning for physicists (2018, unknown): “…GANs are 100 already starting to make their way into physics (Heimel et al., 2018; Liu et al., 2017; Rocchetto et al., 2018; Wetzel, 2017) and astronomy (Ravanbakhsh et al., 2017), and methods from physics may prove useful for furthering our understanding of these methods (Alemi and Abbara, 2017).”