Non-Gaussian information from weak lensing data via deep learning

Abstract

Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a 2D convolutional neural network to simulated noiseless lensing maps covering 96 different cosmological models over a range of {${\Omega }_m,{\sigma }_8$}. Using the area of the confidence contour in the {${\Omega }_m,{\sigma }_8$} plane as a figure-of-merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields $\approx 5\times$ tighter constraints than the power spectrum, and $\approx 4\times$ tighter than the lensing peaks. Such gains illustrate the extent to which weak lensing data encode cosmological information not accessible to the power spectrum or even other, non-Gaussian statistics such as lensing peaks.

15 pages, 13 figures, accepted to PRD

References in corpus (11)

• Why your model parameter confidences might be too optimistic -- unbiased estimation of the inverse covariance matrix
• KiDS-450: Cosmological Constraints from Weak Lensing Peak Statistics - II: Inference from Shear Peaks using N-body Simulations
• Emulating the CFHTLenS Weak Lensing data: Cosmological Constraints from moments and Minkowski functionals
• A new model to predict weak-lensing peak counts I. Comparison with $N$-body Simulations
• Impact of Baryonic Processes on Weak Lensing Cosmology: Power Spectrum, Non-Local Statistics, and Parameter Bias
• Re-capturing cosmic information
• Precise Estimation of Cosmological Parameters Using a More Accurate Likelihood Function
• Do dark matter halos explain lensing peaks?
• Constraining Dark Energy by Combining Cluster Counts and Shear-Shear Correlations in a Weak Lensing Survey
• Statistical connection of peak counts to power spectrum and moments in weak lensing field
• Dark energy constraints and correlations with systematics from CFHTLS weak lensing, SNLS supernovae Ia and WMAP5

Cited by in corpus (92)

• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Fast likelihood-free cosmology with neural density estimators and active learning
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• Large-scale dark matter simulations
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• A new approach to observational cosmology using the scattering transform
• Nuisance hardened data compression for fast likelihood-free inference
• Towards an Optimal Estimation of Cosmological Parameters with the Wavelet Scattering Transform
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Weak lensing cosmology with convolutional neural networks on noisy data
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Fast cosmic web simulations with generative adversarial networks
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Gravitational wave signal recognition of O1 data by deep learning
• Cosmological constraints from noisy convergence maps through deep learning
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• Distinguishing standard and modified gravity cosmologies with machine learning
• Going Beyond the Galaxy Power Spectrum: an Analysis of BOSS Data with Wavelet Scattering Transforms
• Identifying Reionization Sources from 21cm Maps using Convolutional Neural Networks
• 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 volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Interpreting deep learning models for weak lensing
• On the dissection of degenerate cosmologies with machine learning
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Cosmology with one galaxy?
• Bayesian forward modelling of cosmic shear data
• $\kappa$TNG: Effect of Baryonic Processes on Weak Lensing with IllustrisTNG Simulations
• Denoising Weak Lensing Mass Maps with Deep Learning
• Noise reduction for weak lensing mass mapping: An application of generative adversarial networks to Subaru Hyper Suprime-Cam first-year data
• Cosmic Shear: Inference from Forward Models
• Machine Learning Applied to the Reionization History of the Universe in the 21 cm Signal
• CosmoGridV1: a simulated $w$CDM theory prediction for map-level cosmological inference
• Machine Learning for Observational Cosmology
• Precise Cosmological Constraints from BOSS Galaxy Clustering with a Simulation-Based Emulator of the Wavelet Scattering Transform
• Cosmological constraints from HSC survey first-year data using deep learning
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Simultaneously constraining cosmology and baryonic physics via deep learning from weak lensing
• Starlet l1-norm for weak lensing cosmology
• Wavelet Moments for Cosmological Parameter Estimation
• Effective cosmic density field reconstruction with convolutional neural network
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• KaRMMa -- Kappa Reconstruction for Mass Mapping
• Cosmic Velocity Field Reconstruction Using AI
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Multifield Cosmology with Artificial Intelligence
• Higher order statistics of shear field: a machine learning approach
• A simulation-based inference pipeline for cosmic shear with the Kilo-Degree Survey
• Foreground model recognition through Neural Networks for CMB B-mode observations
• Towards a full $w$CDM map-based analysis for weak lensing surveys
• A comparative study of cosmological constraints from weak lensing using Convolutional Neural Networks
• The self similarity of weak lensing peaks
• Machine Learning and Cosmology
• Scattering Spectra Models for Physics
• Cosmological constraints using Minkowski functionals from the first year data of the Hyper Suprime-Cam
• Comparing weak lensing peak counts in baryonic correction models to hydrodynamical simulations
• Flow-Based Likelihoods for Non-Gaussian Inference
• Cosmological Constraints from Weak Lensing Peaks: Can Halo Models Accurately Predict Peak Counts?
• Towards unveiling the large-scale nature of gravity with the wavelet scattering transform
• Simulation-Based Inference Benchmark for Weak Lensing Cosmology
• Wavelet Conditional Renormalization Group
• A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks
• Cosmological constraints from low redshift 21 cm intensity mapping with machine learning
• Inpainting hydrodynamical maps with deep learning
• The Impact of Photometric Redshift Errors on Lensing Statistics in Ray-Tracing Simulations
• A Machine Learning Approach to Correct for Mass Resolution Effects in Simulated Halo Clustering Statistics
• Accurately Estimating Redshifts from CSST Slitless Spectroscopic Survey using Deep Learning
• Ly$\alpha$NNA: A Deep Learning Field-level Inference Machine for the Lyman-$\alpha$ Forest
• Massive $\nu$s through the CNN lens: interpreting the field-level neutrino mass information in weak lensing
• Inferring Cosmological Parameters on SDSS via Domain-Generalized Neural Networks and Lightcone Simulations
• Predictive uncertainty on improved astrophysics recovery from multifield cosmology
• Accurate Kappa Reconstruction Algorithm for masked shear catalog (AKRA)
• Constraining cosmology with thermal Sunyaev-Zel'dovich maps: Minkowski functionals, peaks, minima, and moments
• AKRA 2.0: Accurate Kappa Reconstruction Algorithm for masked shear catalog
• Weak lensing peak statistics -- steepness versus height
• A simple equivariant machine learning method for dynamics based on scalars
• Numerical investigation of non-Gaussianities in the phase and modulus of density Fourier modes
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• A new way to constrain the densities of intra-group medium in groups of galaxies with convolutional neural networks
• Machine learning uncovers new cosmological information
• CMB delensing with deep learning
• Detecting Modeling Bias with Continuous Time Flow Models on Weak Lensing Maps
• An improved cosmological parameter inference scheme motivated by deep learning
• Parameter estimation from Ly$\alpha$ forest in Fourier space using Information Maximising Neural Network
• Success of Machine Learning algorithms in Dynamical Mass Measurements of Galaxy Clusters
• Towards an optimal extraction of cosmological parameters from galaxy cluster surveys using convolutional neural networks
• Conditionally Strongly Log-Concave Generative Models
• Dark Energy Survey Year 3 results: Cosmology with peaks using an emulator approach
• Replicating weak-lensing summary-statistic covariances with normalizing flows
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations