Issue |
A&A
Volume 651, July 2021
|
|
---|---|---|
Article Number | A46 | |
Number of page(s) | 14 | |
Section | Numerical methods and codes | |
DOI | https://doi.org/10.1051/0004-6361/202039866 | |
Published online | 12 July 2021 |
Encoding large-scale cosmological structure with generative adversarial networks
1
Université Paris-Saclay, CNRS, Institut d’Astrophysique Spatiale, Bâtiment 121 Campus Paris-Sud, 91405 Orsay, France
e-mail: marion.ullmo@ias.u-psud.fr
2
Université Paris-Saclay, CNRS, TAU team INRIA Saclay, Laboratoire de recherche en informatique, 91190 Gif-sur-Yvette, France
3
Departamento de Física Téorica I, Universidad Complutense, 28040 Madrid, Spain
Received:
6
November
2020
Accepted:
24
April
2021
Recently, a type of neural networks called generative adversarial networks (GANs) has been proposed as a solution for the fast generation of simulation-like datasets in an attempt to avoid intensive computations and running cosmological simulations that are expensive in terms of time and computing power. We built and trained a GAN to determine the strengths and limitations of such an approach in more detail. We then show how we made use of the trained GAN to construct an autoencoder (AE) that can conserve the statistical properties of the data. The GAN and AE were trained on images and cubes issued from two types of N-body simulations, namely 2D and 3D simulations. We find that the GAN successfully generates new images and cubes that are statistically consistent with the data on which it was trained. We then show that the AE can efficiently extract information from simulation data and satisfactorily infers the latent encoding of the GAN to generate data with similar large-scale structures.
Key words: methods: data analysis / methods: numerical / methods: statistical
© M. Ullmo et al. 2021
Open Access article, published by EDP Sciences, under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.