Weak lensing cosmology with convolutional neural networks on noisy data

Abstract

Weak gravitational lensing is one of the most promising cosmological probes of the late universe. Several large ongoing (DES, KiDS, HSC) and planned (LSST, EUCLID, WFIRST) astronomical surveys attempt to collect even deeper and larger scale data on weak lensing. Due to gravitational collapse, the distribution of dark matter is non-Gaussian on small scales. However, observations are typically evaluated through the two-point correlation function of galaxy shear, which does not capture non-Gaussian features of the lensing maps. Previous studies attempted to extract non-Gaussian information from weak lensing observations through several higher-order statistics such as the three-point correlation function, peak counts or Minkowski-functionals. Deep convolutional neural networks (CNN) emerged in the field of computer vision with tremendous success, and they offer a new and very promising framework to extract information from 2 or 3-dimensional astronomical data sets, confirmed by recent studies on weak lensing. We show that a CNN is able to yield significantly stricter constraints of (${\sigma }_8,{\Omega }_m$) cosmological parameters than the power spectrum using convergence maps generated by full N-body simulations and ray-tracing, at angular scales and shape noise levels relevant for future observations. In a scenario mimicking LSST or Euclid, the CNN yields 2.4-2.8 times smaller credible contours than the power spectrum, and 3.5-4.2 times smaller at noise levels corresponding to a deep space survey such as WFIRST. We also show that at shape noise levels achievable in future space surveys the CNN yields 1.4-2.1 times smaller contours than peak counts, a higher-order statistic capable of extracting non-Gaussian information from weak lensing maps.

References in corpus (46)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Planck 2015 results. XIII. Cosmological parameters
• A Universal Density Profile from Hierarchical Clustering
• Simulating Galaxy Formation with the IllustrisTNG Model
• Understanding deep learning requires rethinking generalization
• Cosmology with cosmic shear observations: a review
• A new measure for cosmic shear
• Detection of (dark) matter concentrations via weak gravitational lensing
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• How Does Batch Normalization Help Optimization?
• Cosmology with the shear-peak statistics
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• CFHTLenS: Cosmological constraints from a combination of cosmic shear two-point and three-point correlations
• Cosmology Constraints from the Weak Lensing Peak Counts and the Power Spectrum in CFHTLenS
• Three-Point Correlations in Weak Lensing Surveys: Model Predictions and Applications
• Cosmology constraints from shear peak statistics in Dark Energy Survey Science Verification data
• Probing Cosmology with Weak Lensing Peak Counts
• Non-Gaussian information from weak lensing data via deep learning
• Probing Cosmology with Weak Lensing Minkowski Functionals
• Simulating weak lensing by large scale structure
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Cosmological Information in Weak Lensing Peaks
• Fast cosmic web simulations with generative adversarial networks
• The three-point correlation function of cosmic shear: I. The natural components
• Cosmological constraints from noisy convergence maps through deep learning
• Breaking degeneracies in modified gravity with higher (than 2nd) order weak-lensing statistics
• The cosmology dependence of weak lensing cluster counts
• Distinguishing standard and modified gravity cosmologies with machine learning
• On the validity of the Born approximation for beyond-Gaussian weak lensing observables
• Statistical and Systematic Errors in Measurement of Weak-Lensing Minkowski Functionals: Application to Canada-France-Hawaii Lensing Survey
• The Kurtosis of the Cosmic Shear Field
• Mocking the Weak Lensing universe: the LensTools python computing package
• Weak lensing mass map and peak statistics in Canada-France-Hawaii Telescope Stripe 82 survey
• Sample variance in weak lensing: how many simulations are required?
• On the dissection of degenerate cosmologies with machine learning
• Higher-order moments of the lensing shear and other spin two fields
• Denoising Weak Lensing Mass Maps with Deep Learning
• Implication of Omega_m through the Morphological Analysis of Weak Lensing Fields
• Detecting gravitational lensing cosmic shear from samples of several galaxies using two-dimensional spectral imaging
• Do dark matter halos explain lensing peaks?
• A Technique for Weak Lensing with Velocity Maps: Eliminating Ellipticity Noise in HI Radio Observations
• Cosmology with photometric weak lensing surveys: constraints with redshift tomography of convergence peaks and moments
• Cosmological model discrimination with Deep Learning
• Cosmic shear without shape noise
• Cosmological model differentiation through weak gravitational lensing

Cited by in corpus (66)

• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• A new approach to observational cosmology using the scattering transform
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Reconstructing Functions and Estimating Parameters with Artificial Neural Networks: A Test with the Hubble Parameter and SNe Ia
• Gravitational wave signal recognition of O1 data by deep learning
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• Lifting weak lensing degeneracies with a field-based likelihood
• Learning cosmology and clustering with cosmic graphs
• A Full $w$CDM Analysis of KiDS-1000 Weak Lensing Maps using Deep Learning
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• Field Level Neural Network Emulator for Cosmological N-body Simulations
• Interpreting deep learning models for weak lensing
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Cosmology with one galaxy?
• $\kappa$TNG: Effect of Baryonic Processes on Weak Lensing with IllustrisTNG Simulations
• Revisiting the cosmic distance duality relation with machine learning reconstruction methods: the combination of HII galaxies and ultra-compact radio quasars
• The DES view of the Eridanus supervoid and the CMB Cold Spot
• CosmoGridV1: a simulated $w$CDM theory prediction for map-level cosmological inference
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Machine Learning for Observational Cosmology
• Cosmological constraints from HSC survey first-year data using deep learning
• Simultaneously constraining cosmology and baryonic physics via deep learning from weak lensing
• Neural Network Reconstruction of $H^{\prime }(z)$ and its application in Teleparallel Gravity
• Recovering the CMB Signal with Machine Learning
• Starlet l1-norm for weak lensing cosmology
• Effective cosmic density field reconstruction with convolutional neural network
• KaRMMa -- Kappa Reconstruction for Mass Mapping
• Likelihood-free Inference with Mixture Density Network
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• Multifield Cosmology with Artificial Intelligence
• A comparative study of cosmological constraints from weak lensing using Convolutional Neural Networks
• A simulation-based inference pipeline for cosmic shear with the Kilo-Degree Survey
• Deep-CEE I: Fishing for Galaxy Clusters with Deep Neural Nets
• Cosmological constraints from weak lensing scattering transform using HSC Y1 data
• Machine Learning and Cosmology
• Cosmological Parameter Estimation and Inference using Deep Summaries
• Comparing weak lensing peak counts in baryonic correction models to hydrodynamical simulations
• Deep Forest: Neural Network reconstruction of the Lyman-alpha forest
• Simulation-Based Inference Benchmark for Weak Lensing Cosmology
• Transformation Importance with Applications to Cosmology
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Cosmological constraints from low redshift 21 cm intensity mapping with machine learning
• Ly$\alpha$NNA: A Deep Learning Field-level Inference Machine for the Lyman-$\alpha$ Forest
• Inpainting hydrodynamical maps with deep learning
• Cosmic topology. Part IVa. Classification of manifolds using machine learning: a case study with small toroidal universes
• Inferring Cosmological Parameters on SDSS via Domain-Generalized Neural Networks and Lightcone Simulations
• Massive $\nu$s through the CNN lens: interpreting the field-level neutrino mass information in weak lensing
• Accurate Kappa Reconstruction Algorithm for masked shear catalog (AKRA)
• Adaptive wavelet distillation from neural networks through interpretations
• AKRA 2.0: Accurate Kappa Reconstruction Algorithm for masked shear catalog
• Hybrid summary statistics: neural weak lensing inference beyond the power spectrum
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• Differentiating Warm Dark Matter Models through 21cm Line Intensity Mapping: A Convolutional Neural Network Approach
• Numerical investigation of non-Gaussianities in the phase and modulus of density Fourier modes
• Clusternets: A deep learning approach to probe clustering dark energy
• Neural style transfer of weak lensing mass maps
• Weak lensing peak statistics -- steepness versus height
• Galaxies OBserved as Low-luminosity Identified Nebulae (GOBLIN): a catalog of 43,000 high-probability dwarf galaxy candidates in the UNIONS survey
• Distribution-free uncertainty quantification for inverse problems: application to weak lensing mass mapping
• Deconfusing intensity maps with neural networks
• Impact of astrophysical effects on the dark matter mass constraint with 21cm intensity mapping
• Replicating weak-lensing summary-statistic covariances with normalizing flows
• Generative modeling of convergence maps based on predicted one-point statistics
• D${}_4$CNN$\times$AnaCal: Physics-Informed Machine Learning for Accurate and Precise Weak Lensing Shear Estimation