RECORD
Estimation of line-of-sight velocities of individual galaxies using neural networks I. Modelling redshift-space distortions at large scales
Cosmology and Nongalactic Astrophysics · Submitted 6 Dec 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Our scheme provides a novel way to predict the peculiar velocity of individual galaxies, to eliminate the RSD effect directly in future large galaxy surveys, and to reconstruct the 3-D cosmic velocity field accurately.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
We present a scheme based on artificial neural networks (ANN) to estimate the line-of-sight velocities of individual galaxies from an observed redshift-space galaxy distribution. We find an estimate of the peculiar velocity at a galaxy based on galaxy counts and barycenters in shells around it. By training the network with environmental characteristics, such as the total mass and mass center within each shell surrounding every galaxy in redshift space, our ANN model can accurately predict the line-of-sight velocity of each individual galaxy. When this velocity is used to eliminate the RSD effect, the two-point correlation function (TPCF) in real space can be recovered with an accuracy better than 1% at $s$ > 8 $h^{-1}\mathrm{Mpc}$, and 4% on all scales compared to ground truth. The real-space power spectrum can be recovered within 3% on $k$< 0.5 $\mathrm{Mpc}^{-1}h$, and less than 5% for all $k$ modes. The quadrupole moment of the TPCF or power spectrum is almost zero down to $s$ = 10 $h^{-1}\mathrm{Mpc}$ or all $k$ modes, indicating an effective correction of the spatial anisotropy caused by the RSD effect. We demonstrate that on large scales, without additional training with new data, our network is adaptable to different galaxy formation models, different cosmological models, and mock galaxy samples at high redshifts and high biases, achieving less than 10% error for scales greater than 15 $h^{-1}\mathrm{Mpc}$. As it is sensitive to large-scale densities, it does not manage to remove Fingers of God in large clusters, but works remarkably well at recovering real-space galaxy positions elsewhere. Our scheme provides a novel way to predict the peculiar velocity of individual galaxies, to eliminate the RSD effect directly in future large galaxy surveys, and to reconstruct the 3-D cosmic velocity field accurately.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We present a scheme based on artificial neural networks (ANN) to estimate the line-of-sight velocities of individual galaxies from an observed redshift-space galaxy distribution. | contribution 0.95 | 0.94 | 0.09 | asserted 0.99 |
| s1 | We find an estimate of the peculiar velocity at a galaxy based on galaxy counts and barycenters in shells around it. | method 0.93 | 0.93 | 0.06 | asserted 1.00 |
| s2 | By training the network with environmental characteristics, such as the total mass and mass center within each shell surrounding every galaxy in redshift space, our ANN model can accurately predict the line-of-sight velocity of each individual galaxy. | method 0.99 | 0.88 | 0.14 | asserted 0.90 |
| s3 | When this velocity is used to eliminate the RSD effect, the two-point correlation function (TPCF) in real space can be recovered with an accuracy better than 1% at $s$ > 8 $h^{-1}\mathrm{Mpc}$, and 4% on all scales compared to ground truth. | result 1.00 | 0.94 | 0.25 | asserted 1.00 |
| s4 | The real-space power spectrum can be recovered within 3% on $k$< 0.5 $\mathrm{Mpc}^{-1}h$, and less than 5% for all $k$ modes. | result 1.00 | 0.94 | 0.11 | asserted 1.00 |
| s5 | The quadrupole moment of the TPCF or power spectrum is almost zero down to $s$ = 10 $h^{-1}\mathrm{Mpc}$ or all $k$ modes, indicating an effective correction of the spatial anisotropy caused by the RSD effect. | result 0.82 | 0.94 | 0.13 | asserted 0.67 |
| s6 | We demonstrate that on large scales, without additional training with new data, our network is adaptable to different galaxy formation models, different cosmological models, and mock galaxy samples at high redshifts and high biases, achieving less than 10% error for scales greater than 15 $h^{-1}\mathrm{Mpc}$. | result 0.98 | 0.95 | 0.19 | asserted 1.00 |
| s7 | As it is sensitive to large-scale densities, it does not manage to remove Fingers of God in large clusters, but works remarkably well at recovering real-space galaxy positions elsewhere. | limitation 1.00 | 0.91 | 0.10 | asserted 1.00 |
| s8 | Our scheme provides a novel way to predict the peculiar velocity of individual galaxies, to eliminate the RSD effect directly in future large galaxy surveys, and to reconstruct the 3-D cosmic velocity field accurately. | contribution 0.49 | 0.73 | 0.72 | asserted 0.96 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
We present a scheme based on artificial neural networks (ANN) to estimate the line-of-sight velocities of individual galaxies from an observed redshift-space galaxy distribution. We find an estimate of the peculiar velocity at a galaxy based on galaxy counts and barycenters in shells around it. By training the network with environmental characteristics, such as the total mass and mass center within each shell surrounding every galaxy in redshift space, our ANN model can accurately predict the line-of-sight velocity of each individual galaxy. When this velocity is used to eliminate the RSD effect, the two-point correlation function (TPCF) in real space can be recovered with an accuracy better than 1% at $s$ > 8 $h^{-1}\mathrm{Mpc}$, and 4% on all scales compared to ground truth. The real-space power spectrum can be recovered within 3% on $k$< 0.5 $\mathrm{Mpc}^{-1}h$, and less than 5% for all $k$ modes. The quadrupole moment of the TPCF or power spectrum is almost zero down to $s$ = 10 $h^{-1}\mathrm{Mpc}$ or all $k$ modes, indicating an effective correction of the spatial anisotropy caused by the RSD effect. We demonstrate that on large scales, without additional training with new data, our network is adaptable to different galaxy formation models, different cosmological models, and mock galaxy samples at high redshifts and high biases, achieving less than 10% error for scales greater than 15 $h^{-1}\mathrm{Mpc}$. As it is sensitive to large-scale densities, it does not manage to remove Fingers of God in large clusters, but works remarkably well at recovering real-space galaxy positions elsewhere. Our scheme provides a novel way to predict the peculiar velocity of individual galaxies, to eliminate the RSD effect directly in future large galaxy surveys, and to reconstruct the 3-D cosmic velocity field accurately.
Human review
References
How the literature uses it
3 arXiv papers cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Cites it as background 1 paper
-
These progresses have been achieved through the application of higher-order perturbation theory and the halo model [ref] , iterative methods [ref] , and artificial neural networks [ref] .
The Poisson noise in modeling the redshift-space distortion at large scales · Introduction · 0.91
What it cites · 6 sentences without a confident label
Uses the method or tool of 1 paper
-
We choose xavier_Initialization [ref] to initialize the trainable parameters, the Adam optimizer [ref] and L2 regularization [ref] .
Adam: A Method for Stochastic Optimization · Artificial neural network · 0.99
Cites as background 1 paper
-
The RSD effect can approximately be decomposed into the Kaiser effect [ref] and the Finger-of-God effect (FoG) [ref] .
Linear Redshift Distortions: A Review · Introduction · 0.96
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.