Baryon acoustic oscillations reconstruction using convolutional neural networks

Abstract

We propose a new scheme to reconstruct the baryon acoustic oscillations (BAO) signal, which contains key cosmological information, based on deep convolutional neural networks (CNN). Trained with almost no fine-tuning, the network can recover large-scale modes accurately in the test set: the correlation coefficient between the true and reconstructed initial conditions reaches $90\%$ at $k\le 0.2h{\mathrm{Mpc}}^{-1}$, which can lead to significant improvements of the BAO signal-to-noise ratio down to $k\simeq 0.4h{\mathrm{Mpc}}^{-1}$. Since this new scheme is based on the configuration-space density field in sub-boxes, it is local and less affected by survey boundaries than the standard reconstruction method, as our tests confirm. We find that the network trained in one cosmology is able to reconstruct BAO peaks in the others, i.e. recovering information lost to non-linearity independent of cosmology. The accuracy of recovered BAO peak positions is far less than that caused by the difference in the cosmology models for training and testing, suggesting that different models can be distinguished efficiently in our scheme. It is very promising that Our scheme provides a different new way to extract the cosmological information from the ongoing and future large galaxy surveys.

arXiv commentAccepted for publication in MNRAS

References in corpus (95)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Planck 2015 results. XIII. Cosmological parameters
• Seven-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Interpretation
• The cosmological simulation code GADGET-2
• Simulating the joint evolution of quasars, galaxies and their large-scale distribution
• Deep Residual Learning for Image Recognition
• The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: cosmological analysis of the DR12 galaxy sample
• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Final Maps and Results
• The clustering of galaxies in the SDSS-III Baryon Oscillation Spectroscopic Survey: Baryon Acoustic Oscillations in the Data Release 10 and 11 galaxy samples
• The Clustering of the SDSS DR7 Main Galaxy Sample I: A 4 per cent Distance Measure at z=0.15
• Five-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Data Processing, Sky Maps, and Basic Results
• Observational Probes of Cosmic Acceleration
• The DESI Experiment Part I: Science,Targeting, and Survey Design
• The 6dF Galaxy Survey: Final Redshift Release (DR3) and Southern Large-Scale Structures
• The Dark Energy Survey: more than dark energy - an overview
• Euclid Definition Study Report
• A 2% Distance to z=0.35 by Reconstructing Baryon Acoustic Oscillations - I : Methods and Application to the Sloan Digital Sky Survey
• Extragalactic Science, Cosmology and Galactic Archaeology with the Subaru Prime Focus Spectrograph (PFS)
• Don't Decay the Learning Rate, Increase the Batch Size
• Improving Cosmological Distance Measurements by Reconstruction of the Baryon Acoustic Peak
• On the Robustness of the Acoustic Scale in the Low-Redshift Clustering of Matter
• The WiggleZ Dark Energy Survey: Improved Distance Measurements to z = 1 with Reconstruction of the Baryonic Acoustic Feature
• Bayesian physical reconstruction of initial conditions from large scale structure surveys
• Memory of Initial Conditions in Gravitational Clustering
• The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: Baryon Acoustic Oscillations in Fourier-space
• nbodykit: an open-source, massively parallel toolkit for large-scale structure
• Baryonic Signatures in Large-Scale Structure
• Canadian Hydrogen Intensity Mapping Experiment (CHIME) Pathfinder
• Learning to Predict the Cosmological Structure Formation
• Measuring D_A and H at z=0.35 from the SDSS DR7 LRGs using baryon acoustic oscillations
• Baryonic acoustic oscillations in simulated galaxy redshift surveys
• 4MOST - 4-metre Multi-Object Spectroscopic Telescope
• Perturbation Theory Reloaded: Analytical Calculation of Non-linearity in Baryonic Oscillations in the Real Space Matter Power Spectrum
• The detectability of baryonic acoustic oscillations in future galaxy surveys
• A Lagrangian effective field theory
• Non-linear structure formation and the acoustic scale
• Reconstructing Baryon Oscillations: A Lagrangian Theory Perspective
• The Shift of the Baryon Acoustic Oscillation Scale: A Simple Physical Picture
• High-precision predictions for the acoustic scale in the non-linear regime
• Non-Gaussian information from weak lensing data via deep learning
• Calibrating the Baryon Oscillation Ruler for Matter and Halos
• Reconstructing baryon oscillations
• The Initial Conditions of the Universe from Constrained Simulations
• Towards optimal extraction of cosmological information from nonlinear data
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Iterative initial condition reconstruction
• Reconstruction within the Zeldovich approximation
• Fast cosmic web simulations with generative adversarial networks
• Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks
• Eulerian BAO Reconstructions and N-Point Statistics
• Forecasts on the Dark Energy and Primordial Non-Gaussianity Observations with the Tianlai Cylinder Array
• Reconstructing the Initial Density Field of the Local Universe: Method and Test with Mock Catalogs
• Reconstructing the cosmic density field with the distribution of dark matter halos
• Simulations of Baryon Oscillations
• Reconstruction in Fourier space
• Galaxy Bias and its Effects on the Baryon Acoustic Oscillations Measurements
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• The BOSS-WiggleZ overlap region I: Baryon Acoustic Oscillations
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• Machine learning cosmological structure formation
• Constraints on the dark energy equation of state from the imprint of baryons on the power spectrum of clusters
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• An iterative reconstruction of cosmological initial density fields
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• COSMIC BIRTH: Efficient Bayesian Inference of the Evolving Cosmic Web from Galaxy Surveys
• An interpretable machine learning framework for dark matter halo formation
• Nonlinear reconstruction
• Measuring the 2D Baryon Acoustic Oscillation signal of galaxies in WiggleZ: Cosmological constraints
• New method for initial density reconstruction
• Isobaric Reconstruction of the Baryonic Acoustic Oscillation
• Very High Angular Resolution Science with the Square Kilometre Array
• Weak-lensing shear measurement with machine learning: teaching artificial neural networks about feature noise
• Update on the BINGO 21cm intensity mapping experiment
• Halo nonlinear reconstruction
• BAO reconstruction: a swift numerical action method for massive spectroscopic surveys
• Exploring the posterior surface of the large scale structure reconstruction
• Nonlinear reconstruction of redshift space distortions
• Baryon Acoustic Oscillations reconstruction with pixels
• CosmoFlow: Using Deep Learning to Learn the Universe at Scale
• Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
• Cosmological model discrimination with Deep Learning
• Reconstructing the baryon acoustic oscillations using biased tracers
• Predicting the Neutral Hydrogen Content of Galaxies From Optical Data Using Machine Learning
• Bayesian cosmic density field inference from redshift space dark matter maps
• Primordial power spectrum and cosmology from black-box galaxy surveys
• Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
• Increasing Fisher Information by Moving-Mesh Reconstruction
• Application of the iterative reconstruction to simulated galaxy fields
• Iterative removal of redshift space distortions from galaxy clustering
• Weak lensing shear estimation beyond the shape-noise limit: a machine learning approach
• Understanding the Reconstruction of the Biased Tracer
• Reconstruction with velocities
• Primordial density and BAO reconstruction

Cited by in corpus (19)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Reconstructing Cosmological Initial Conditions from Late-Time Structure with Convolutional Neural Networks
• Euclid: The search for primordial features
• Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net
• Effective cosmic density field reconstruction with convolutional neural network
• Cosmic Velocity Field Reconstruction Using AI
• (DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence
• Nonlinear reconstruction of features in the primordial power spectrum from large-scale structure
• Fast generation of mock galaxy catalogues with COLA
• A Machine Learning Approach to Correct for Mass Resolution Effects in Simulated Halo Clustering Statistics
• DarkAI: Reconstructing the density, velocity and tidal field of dark matter from a DESI-like bright galaxy sample
• Extended Fast Action Minimisation method: application to SDSS-DR12 Combined Sample
• Lagrangian displacement field estimators in cosmology
• Baryon Acoustic Oscillations analyses with Density-Split Statistics
• Interpreting Cosmological Information from Neural Networks in the Hydrodynamic Universe
• Prediction of Individual Halo Concentrations Across Cosmic Time Using Neural Networks
• Cosmological constraints from the density gradient weighted correlation function
• Searching optimal scales for reconstructing cosmological initial conditions using convolutional neural networks