Peculiar Velocity Reconstruction From Simulations and Observations Using Deep Learning Algorithms
arXiv:2406.14101 · doi:10.3847/1538-4357/ad4d84
Abstract
In this paper, we introduce a Unet model of deep learning algorithms for reconstructions of the 3D peculiar velocity field, which simplifies the reconstruction process with enhanced precision. We test the adaptability of the Unet model with simulation data under more realistic conditions, including the redshift space distortion (RSD) effect and halo mass threshold. Our results show that the Unet model outperforms the analytical method that runs under ideal conditions, with a 16% improvement in precision, 13% in residuals, 18% in correlation coefficient and 27% in average coherence. The deep learning algorithm exhibits exceptional capacities to capture velocity features in non-linear regions and substantially improve reconstruction precision in boundary regions. We then apply the Unet model trained under SDSS observational conditions to the SDSS DR7 data for observational 3D peculiar velocity reconstructions.
References in corpus (11)
- Galaxy Groups in the SDSS DR4: I. The Catalogue and Basic Properties
- The 6dF Galaxy Survey: Peculiar Velocity Field and Cosmography
- An Unbiased Estimator of Peculiar Velocity with Gaussian Distributed Errors for Precision Cosmology
- An estimation of the Local growth rate from Cosmicflows-3 peculiar velocities
- A local measurement of the growth rate from peculiar velocities and galaxy clustering correlations in the 6dF Galaxy Survey
- Not a Copernican observer: biased peculiar velocity statistics in the local Universe
- Cosmic Velocity Field Reconstruction Using AI
- Assessing the accuracy of cosmological parameters estimated from velocity -- density comparisons via simulations
- DESI Legacy Imaging Surveys Data Release 9: Cosmological Constraints from Galaxy Clustering and Weak Lensing using the Minimal Bias Model
- Improving estimates of the growth rate using galaxy-velocity correlations: a simulation study
- Galaxy Morphology Classification Using Multi-Scale Convolution Capsule Network