Painting with baryons: augmenting <i>N</i>-body simulations with gas using deep generative models

Tröster, Tilman; Ferguson, Cameron; Harnois-Déraps, Joachim; McCarthy, Ian G.

doi:10.1093/mnrasl/slz075

Cited by 78 publications

(65 citation statements)

References 20 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we have demonstrated the ability of generative AI models to serve as emulators of cosmological mass maps for a given redshift distribution of source galaxies n(z). Generative models have also been shown to work directly on the full or sliced 3D matter density distributions (Nathanaël et al, 2019;Tröster et al, 2019;Villaescusa-Navarro et al, 2020). The three dimensional generation of cosmological fields proves to be particularly difficult.…”

Section: Resultsmentioning

confidence: 99%

“…With a similar goal, multiple contributions have leveraged the recent advances in the field of deep learning to aid the generation of cosmological simulations. In particular, recent works (Mustafa et al, 2017;Rodriguez et al, 2018;Nathanaël et al, 2019;Tröster et al, 2019) have demonstrated the potential of Generative Adversarial Networks (GAN) (Goodfellow et al, 2014) for production of N-body simulations. The work of (Mustafa et al, 2017;Rodriguez et al, 2018;Nathanaël et al, 2019;Tröster et al, 2019;Giusarma et al, 2019;He et al, 2019) has shown deep generative models that can accurately model dark matter distributions and other related cosmological signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Emulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks

Perraudin

Marcon

Lucchi

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

Weak gravitational lensing mass maps play a crucial role in understanding the evolution of structures in the Universe and our ability to constrain cosmological models. The prediction of these mass maps is based on expensive N-body simulations, which can create a computational bottleneck for cosmological analyses. Simulation-based emulators of map summary statistics, such as the matter power spectrum and its covariance, are starting to play increasingly important role, as the analytical predictions are expected to reach their precision limits for upcoming experiments. Creating an emulator of the cosmological mass maps themselves, rather than their summary statistics, is a more challenging task. Modern deep generative models, such as Generative Adversarial Networks (GAN), have demonstrated their potential to achieve this goal. Most existing GAN approaches produce simulations for a fixed value of the cosmological parameters, which limits their practical applicability. We propose a novel conditional GAN model that is able to generate mass maps for any pair of matter density Ωm and matter clustering strength σ8, parameters which have the largest impact on the evolution of structures in the Universe, for a given source galaxy redshift distribution n(z). Our results show that our conditional GAN can interpolate efficiently within the space of simulated cosmologies, and generate maps anywhere inside this space with good visual quality high statistical accuracy. We perform an extensive quantitative comparison of the N-body and GAN -generated maps using a range of metrics: the pixel histograms, peak counts, power spectra, bispectra, Minkowski functionals, correlation matrices of the power spectra, the Multi-Scale Structural Similarity Index (MS-SSIM) and our equivalent of the Fréchet Inception Distance. We find a very good agreement on these metrics, with typical differences are <5% at the center of the simulation grid, and slightly worse for cosmologies at the grid edges. The agreement for the bispectrum is slightly worse, on the <20% level. This contribution is a step toward building emulators of mass maps directly, capturing both the cosmological signal and its variability. We make the code1 and the data2 publicly available.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Emulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks

Perraudin

Marcon

Lucchi

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…This application of machine learning techniques to aid in the efficient modeling of large-scale structure has not gone uninvestigated, and there has recently been great interest in the use of machine learning across the field 1 [12]. Image-to-image mapping techniques that transform initial conditions to the final structures [13][14][15] or augment dark matter-only simulation results with various physical effects not present in the simulation [16][17][18][19][20][21] have shown promise. However, these still require the generation of initial conditions, or the full simulation output, respectively.…”

Section: Introductionmentioning

confidence: 99%

“…One promising method is [26], in which a super-resolution GAN and deep physical model are used to map low resolution, 3D N-body simulations to their high resolution counterparts. This is similar in concept to [19,20], which used GANs to map dark matter density fields to corresponding halo number count maps and hydrodynamical quantities, respectively. Reference [27] proposes a super-resolution scheme for generating large-scale realizations of the matter density field hierarchically, treating the scalability problem separately from sample accuracy.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear 3D cosmic web simulation with heavy-tailed generative adversarial networks

2020

View full text Add to dashboard Cite

Fast and accurate simulations of the nonlinear evolution of the cosmic density field are a major component of many cosmological analyses, but the computational time and storage required to run them can be exceedingly large. For this reason, we use generative adversarial networks (GANs) to learn a compressed representation of the 3D matter density field that is fast and easy to sample, and for the first time show that GANs are capable of generating samples at the level of accuracy of other conventional methods. Using subvolumes from a suite of GADGET-2 N-body simulations, we demonstrate that a deepconvolutional GAN can generate samples that capture both large-and small-scale features of the matter density field, as validated through a variety of n-point statistics. The use of a data scaling that preserves high-density features and a heavy-tailed latent space prior allow us to obtain state of the art results for fast 3D cosmic web generation. In particular, the mean power spectra from generated samples agree to within 5% up to k ¼ 3 and within 10% for k ≤ 5 when compared with N-body simulations, and similar accuracy is obtained for a variety of bispectra. By modeling the latent space with a heavy-tailed prior rather than a standard Gaussian, we better capture sample variance in the high-density voxel PDF and reduce errors in power spectrum and bispectrum covariance on all scales. Furthermore, we show that a conditional GAN can smoothly interpolate between samples conditioned on redshift. Deep generative models, such as the ones described in this work, provide great promise as fast, low-memory, high-fidelity forward models of large-scale structure.

show abstract

“…The ever larger quantities and quality of astronomical data call for systematic approaches to properly interpret and extract the information that can be based on machinelearning techniques such as in Villaescusa-Navarro et al (2020), Schawinski et al (2018), or Bonjean (2020). Machine learning can also be used to produce density maps from large N-body simulations of dark matter (DM) (Rodríguez et al 2018;Feder et al 2020) in a computationally cheaper manner, to predict the effects of DM annihilation feedback on gas densities (List et al 2019), or to infer a mapping between the N-body and the hydrodynamical simulations without resorting to full simulations (Tröster et al 2019;Zamudio-Fernandez et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Encoding large-scale cosmological structure with generative adversarial networks

Ullmo

Decelle

Aghanim

2021

A&A

View full text Add to dashboard Cite

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.

show abstract

Painting with baryons: augmenting N-body simulations with gas using deep generative models

Cited by 78 publications

References 20 publications

Emulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks

Emulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks

Nonlinear 3D cosmic web simulation with heavy-tailed generative adversarial networks

Encoding large-scale cosmological structure with generative adversarial networks

Contact Info

Product

Resources

About