Cosmology with One Galaxy?

Villaescusa-Navarro, Francisco; Ding, Jupiter; Genel, Shy; Tonnesen, Stephanie; Torre, Valentina La; Spergel, David N.; Teyssier, Romain; Li, Yin; Heneka, Caroline; Lemos, Pablo; Anglés-Alcázar, Daniel; Nagai, Daisuke; Vogelsberger, Mark

doi:10.3847/1538-4357/ac5d3f

Cited by 25 publications

(31 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To illustrate the potential information that galaxy properties may encode, we show in Figure 1 correlations among different galaxy features, color coded by Ω m , for galaxies in the z = 0 catalogs. As can be seen, and already noted in Villaescusa-Navarro et al (2022c), there are some noticeable correlations between galaxy properties and Ω m . Thus, our model may learn to extract cosmological information based on galaxy properties, on top of galaxy clustering.…”

Section: Datasupporting

confidence: 74%

See 1 more Smart Citation

Learning Cosmology and Clustering with Cosmic Graphs

Villanueva-Domingo

Villaescusa-Navarro

2022

ApJ

Self Cite

View full text Add to dashboard Cite

We train deep-learning models on thousands of galaxy catalogs from the state-of-the-art hydrodynamic simulations of the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project to perform regression and inference. We employ Graph Neural Networks (GNNs), architectures designed to work with irregular and sparse data, like the distribution of galaxies in the universe. We first show that GNNs can learn to compute the power spectrum of galaxy catalogs with a few percent accuracy. We then train GNNs to perform likelihood-free inference at the galaxy-field level. Our models are able to infer the value of Ωm with a ∼12%–13% accuracy just from the positions of ∼1000 galaxies in a volume of ( 25 h − 1 Mpc ) 3 at z = 0 while accounting for astrophysical uncertainties as modeled in CAMELS. Incorporating information from galaxy properties, such as the stellar mass, stellar metallicity, and stellar radius, increases the accuracy to 4%–8%. Our models are built to be translation and rotation invariant, and they can extract information from any scale larger than the minimum distance between two galaxies. However, our models are not completely robust: testing on simulations run with a different subgrid physics than the ones used for training does not yield accurate results.

show abstract

Section: Datasupporting

confidence: 74%

“…3. In Villaescusa-Navarro et al (2022c), Ω m was inferred from the properties of individual galaxies. The accuracy of their results is quantified with the rms error,…”

Section: From Galaxy Positions and Intrinsic Features To ω Mmentioning

confidence: 99%

Learning Cosmology and Clustering with Cosmic Graphs

Villanueva-Domingo

Villaescusa-Navarro

2022

ApJ

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this work we have used galaxy catalogues from simulations of the CAMELS project (Villaescusa-Navarro et al 2020b;Villaescusa-Navarro et al 2022a). Each galaxy catalogue is obtained from a snapshot of a stateof-the-art hydrodynamic simulation that follows the evolution of 256 3 dark matter particles and 256 3 fluid elements from z = 127 down to z = 0.…”

Section: Datamentioning

confidence: 99%

“…First, we use a deep learning architecture based on GNNs that we believe is more appropriate to deal with the sparse and irregular data associated to galaxies. Second, our galaxy catalogues come from stateof-the-art hydrodynamic simulations of the CAMELS project (Villaescusa-Navarro et al 2020b) that model galaxy positions and properties more accurately than other methods. Third, we use GNNs to extract information not only from galaxy clustering, but also from galaxy properties such as stellar mass, stellar metallicity, and stellar radius.…”

Section: Introductionmentioning

confidence: 99%

Learning cosmology and clustering with cosmic graphs

Villanueva-Domingo,

Villaescusa-Navarro

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We train deep learning models on thousands of galaxy catalogues from the state-of-the-art hydrodynamic simulations of the CAMELS project to perform regression and inference. We employ Graph Neural Networks (GNNs), architectures designed to work with irregular and sparse data, like the distribution of galaxies in the Universe. We first show that GNNs can learn to compute the power spectrum of galaxy catalogues with a few percent accuracy. We then train GNNs to perform likelihood-free inference at the galaxy-field level. Our models are able to infer the value of Ω m with a ∼ 12% − 13% accuracy just from the positions of ∼ 1000 galaxies in a volume of (25 h −1 Mpc) 3 at z = 0 while accounting for astrophysical uncertainties as modelled in CAMELS. Incorporating information from galaxy properties, such as stellar mass, stellar metallicity, and stellar radius, increases the accuracy to 4% − 8%. Our models are built to be translational and rotational invariant, and they can extract information from any scale larger than the minimum distance between two galaxies. However, our models are not completely robust: testing on simulations run with a different subgrid physics than the ones used for training does not yield as accurate results.

show abstract

“…In particular, in Ref. [42] it was shown how neural networks can be used to derive a number of parameters from the physical properties of a single galaxy.…”

mentioning

confidence: 99%

Improving cosmological covariance matrices with machine learning

de Santi,

Abramo

2022

Preprint

View full text Add to dashboard Cite

Cosmological covariance matrices are fundamental for parameter inference, since they are responsible for propagating uncertainties from the data down to the model parameters. However, when data vectors are large, in order to estimate accurate and precise matrices we need huge numbers of observations, or rather costly simulations -neither of which may be viable. In this work we propose a machine learning approach to alleviate this problem in the context of the matrices used in the study of large-scale structure. With only a small amount of data (matrices built with samples of 50-200 halo power spectra) we are able to provide significantly improved matrices, which are almost indistinguishable from the ones built from much larger samples (thousands of spectra). In order to perform this task we trained convolutional neural networks to denoise the matrices, using in the training process a data set made up entirely of spectra extracted from simple, inexpensive halo simulations (mocks). We then show that the method not only removes the noise in the matrices of the cheap simulation, but it is also able to successfully denoise the matrices of halo power spectra from N-body simulations. We compare the denoised to the other matrices using several metrics, and in all of them they score better, without any signs of spurious artifacts. With the help of the Wishart distribution we derive an analytical extrapolation for the effective sample augmentation allowed by the denoiser. Finally, we show that, by using the denoised matrices, the cosmological parameters can be recovered with nearly the same accuracy as when using matrices built with a sample of 30,000 spectra in the case of the cheap simulations, and with 15,000 spectra in the case of the N-body simulations. Of particular interest is the bias in the Hubble parameter H 0 , which was significantly reduced after applying the denoiser.

show abstract

Cosmology with One Galaxy?

Cited by 25 publications

References 70 publications

Learning Cosmology and Clustering with Cosmic Graphs

Learning Cosmology and Clustering with Cosmic Graphs

Learning cosmology and clustering with cosmic graphs

Improving cosmological covariance matrices with machine learning

Contact Info

Product

Resources

About