Extracting cosmological parameters from N-body simulations using machine learning techniques

Lazanu, Andrei

doi:10.1088/1475-7516/2021/09/039

Cited by 18 publications

(13 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventionally, summary statistics of lensing shear and convergence fields are used to characterize the matter distribution and to infer cosmological parameters such as matter density Ω m and the density fluctuation amplitude σ 8 (see Section 5 in this review). There have been several proposals to use reconstructed two-dimensional [147] or three-dimensional density fields [148] to study baryonic effects as well as to determine cosmological parameters from density distribution features that are not well captured by conventional summary statistics [149].…”

Section: Dark Matter Distribution Probed With Gravitational Lensingmentioning

confidence: 99%

Machine Learning for Observational Cosmology

Moriwaki¹,

Nishimichi²,

Yoshida³

2023

Preprint

View full text Add to dashboard Cite

An array of large observational programs using ground-based and spaceborne telescopes is planned in the next decade. The forthcoming wide-field sky surveys are expected to deliver a sheer volume of data exceeding an exabyte. Processing the large amount of multiplex astronomical data is technically challenging, and fully automated technologies based on machine learning and artificial intelligence are urgently needed. Maximizing scientific returns from the big data requires communitywide efforts. We summarize recent progress in machine learning applications in observational cosmology. We also address crucial issues in high-performance computing that are needed for the data processing and statistical analysis.

show abstract

Section: Dark Matter Distribution Probed With Gravitational Lensingmentioning

confidence: 99%

Machine Learning for Observational Cosmology

Moriwaki¹,

Nishimichi²,

Yoshida³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recent tremendous advances in machine learning algorithms, especially those based on deep neural networks, provide us with a great opportunity to extract useful information from complex data. In more recent years, deep learning-based techniques have been applied to almost all areas of cosmology and astrophysics (Mehta et al 2019;Jennings et al 2019;Carleo et al 2019;Ntampaka et al 2019), such as weak gravitational lensing (Schmelzle et al 2017;Gupta et al 2018;Springer et al 2018;Fluri et al 2019;Jeffrey et al 2019;Merten et al 2019;Peel et al 2019;Tewes et al 2019), the Cosmic Microwave Background (Caldeira et al 2018;Rodriguez et al 2018;Perraudin et al 2019;Münchmeyer & Smith 2019;Mishra et al 2019), the LSS including estimating cosmological parameters from the distribution of matter (Ravanbakhsh et al 2017a;Lucie-Smith et al 2018;Pan et al 2020;Lazanu 2021), identifying dark matter halos and reconstruct the initial conditions of the universe using machine learning (Modi et al 2018;Berger & Stein 2019;Lucie-Smith et al 2019;Ramanah et al 2019c), mapping rough cosmology to fine one (He et al 2019;Li et al 2021), extracting line intensity maps (Pfeffer et al 2019), foreground removal in 21cm intensity mapping (Makinen et al 2021), augmenting N-body simulations with gas (Tröster et al 2019), a mapping between the 3D galaxy distribution in hydrodynamic simulations and its underlying dark matter distribution (Zhang et al 2019a), modelling small-scale galaxy formation physics in large cosmological volumes (Ni et al 2021), reconstructing the baryon acoustic oscillations…”

Section: Introductionmentioning

confidence: 99%

AI-assisted reconstruction of cosmic velocity field from redshift-space spatial distribution of halos

Wu¹,

Liang²,

Xu³

et al. 2023

Preprint

View full text Add to dashboard Cite

The peculiar velocities of dark matter halos are crucial to study many issues in cosmology and galaxy evolution. In this study, by using the state-of-the-art deep learning technique, a UNet-based neural network, we propose to reconstruct the peculiar velocity field from the redshift-space distribution of dark matter halos. Through a point-to-point comparison and examination of various statistical properties, we demonstrate that, the reconstructed velocity field is in good agreement with the ground truth. The power spectra of various velocity field components, including velocity magnitude, divergence and vorticity, can be successfully recovered when 𝑘 1.1 ℎ/Mpc (the Nyquist frequency of the simulations) at about 80% accuracy. This approach is very promising and presents an alternative method to correct the redshift-space distortions using the measured 3D spatial information of halos. Additionally, for the reconstruction of the momentum field of halos, UNet achieves similar good results. Hence the applications in various aspects of cosmology are very broad, such as correcting redshift errors and improving measurements in the structure of the cosmic web, the kinetic Sunyaev-Zel'dovich effect, BAO reconstruction, etc.

show abstract

“…Alternatively, machine-learning (ML) methods can be used to optimally extract information from the field itself without using summary statistics. This task has been carried out, typically using convolutional neural networks (CNNs), for density fields (Ravanbakhsh et al 2017;Hortua 2021;Lazanu 2021;Makinen et al 2021;Villaescusa-Navarro et al 2021b, 2021c, weak lensing maps (Schmelzle et al 2017;Gupta et al 2018;Fluri et al 2019;Ribli et al 2019;Zorrilla Matilla et al 2020;Jeffrey et al 2020;Lu et al 2022), cosmic microwave background maps (He et al 2018), and 21 cm maps (Gillet et al 2019;Hassan et al 2020; among others.…”

Section: Introductionmentioning

confidence: 99%

Learning Cosmology and Clustering with Cosmic Graphs

Villanueva-Domingo

Villaescusa-Navarro

2022

ApJ

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

Extracting cosmological parameters from N-body simulations using machine learning techniques

Cited by 18 publications

References 44 publications

Machine Learning for Observational Cosmology

Machine Learning for Observational Cosmology

AI-assisted reconstruction of cosmic velocity field from redshift-space spatial distribution of halos

Learning Cosmology and Clustering with Cosmic Graphs

Contact Info

Product

Resources

About