Distinguishing standard and modified gravity cosmologies with machine learning

Abstract

We present a convolutional neural network to classify distinct cosmological scenarios based on the statistically similar weak-lensing maps they generate. Modified gravity (MG) models that include massive neutrinos can mimic the standard concordance model ($\Lambda$CDM) in terms of Gaussian weak-lensing observables. An inability to distinguish viable models that are based on different physics potentially limits a deeper understanding of the fundamental nature of cosmic acceleration. For a fixed redshift of sources, we demonstrate that a machine learning network trained on simulated convergence maps can discriminate between such models better than conventional higher-order statistics. Results improve further when multiple source redshifts are combined. To accelerate training, we implement a novel data compression strategy that incorporates our prior knowledge of the morphology of typical convergence map features. Our method fully distinguishes $\Lambda$CDM from its most similar MG model on noise-free data, and it correctly identifies among the MG models with at least 80% accuracy when using the full redshift information. Adding noise lowers the correct classification rate of all models, but the neural network still significantly outperforms the peak statistics used in a previous analysis.

arXiv comment12 pages, 10 figures, 1 table. Text updated and expanded throughout

References in corpus (46)

• Models of f(R) Cosmic Acceleration that Evade Solar-System Tests
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Galaxy Clustering and Weak Lensing
• KiDS-450: Cosmological parameter constraints from tomographic weak gravitational lensing
• CFHTLenS tomographic weak lensing cosmological parameter constraints: Mitigating the impact of intrinsic galaxy alignments
• Planck 2015 results. XIV. Dark energy and modified gravity
• Cosmology with the shear-peak statistics
• Testing General Relativity with Current Cosmological Data
• Weak Lensing Probes of Modified Gravity
• Cosmology constraints from shear peak statistics in Dark Energy Survey Science Verification data
• KiDS-450: Cosmological Constraints from Weak Lensing Peak Statistics - II: Inference from Shear Peaks using N-body Simulations
• Probing Cosmology with Weak Lensing Peak Counts
• Cosmic Degeneracies I: Joint N-body Simulations of Modified Gravity and Massive Neutrinos
• Non-Gaussian information from weak lensing data via deep learning
• KiDS-450: Cosmological Constraints from Weak Lensing Peak Statistics-I: Inference from Analytical Prediction of High Signal-to-Noise Ratio Convergence Peaks
• Cosmological Information in Weak Lensing Peaks
• Constraining $f(R)$ Gravity Theory Using Weak Lensing Peak Statistics from the Canada-France-Hawaii-Telescope Lensing Survey
• Cosmological constraints from noisy convergence maps through deep learning
• Cosmology Based on f(R) Gravity Admits 1 eV Sterile Neutrinos
• Weak Lensing Mass Reconstruction using Wavelets
• A new model to predict weak-lensing peak counts II. Parameter constraint strategies
• Painting galaxies into dark matter halos using machine learning
• Breaking degeneracies in modified gravity with higher (than 2nd) order weak-lensing statistics
• Weak Lensing Light-Cones in Modified Gravity simulations with and without Massive Neutrinos
• The effect of modified gravity on weak lensing
• Machine learning cosmological structure formation
• Modeling the Impact of Baryons on Subhalo Populations with Machine Learning
• Constraining neutrino mass with tomographic weak lensing peak counts
• High Resolution Weak Lensing Mass-Mapping Combining Shear and Flexion
• COLA with massive neutrinos
• Optimized detection of shear peaks in weak lensing maps
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Machine Learning and Cosmological Simulations I: Semi-Analytical Models
• Cosmological constraints with weak lensing peak counts and second-order statistics in a large-field survey
• Joint halo mass function for modified gravity and massive neutrinos I: simulations and cosmological forecasts
• Weak lensing predictions for modified gravities at non-linear scales
• Cosmological constraints from the capture of non-Gaussianity in Weak Lensing data
• GLIMPSE: Accurate 3D weak lensing reconstructions using sparsity
• COSMOS weak-lensing constraints on modified gravity
• Weighing Neutrinos in $f(R)$ gravity
• Exploring degeneracies in modified gravity with weak lensing
• A new model to predict weak-lensing peak counts III. Filtering technique comparisons
• Disentangling dark sector models using weak lensing statistics
• Constraining cosmology with shear peak statistics: tomographic analysis
• Weak lensing peak statistics in the era of large scale cosmological surveys
• Tomography from the Next Generation of Cosmic Shear Experiments for Viable f(R) Models
• Fast Calculation of the Weak Lensing Aperture Mass Statistic

Cited by in corpus (37)

• Machine learning and the physical sciences
• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• Large-scale dark matter simulations
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Weak lensing cosmology with convolutional neural networks on noisy data
• What can Machine Learning tell us about the background expansion of the Universe?
• Cosmic voids in modified gravity models with massive neutrinos
• Gravitational-Wave Detector Networks: Standard Sirens on Cosmology and Modified Gravity Theory
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• On the road to percent accuracy V: the non-linear power spectrum beyond $\Lambda$CDM with massive neutrinos and baryonic feedback
• Probing dark energy with tomographic weak-lensing aperture mass statistics
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Neural network reconstructions for the Hubble parameter, growth rate and distance modulus
• Observational cosmology with Artificial Neural Networks
• Starlet l1-norm for weak lensing cosmology
• Cosmic Velocity Field Reconstruction Using AI
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• Higher order statistics of shear field: a machine learning approach
• Breaking cosmic degeneracies: Disentangling neutrinos and modified gravity with kinematic information
• Estimation of the masses in the Local Group by Gradient Boosted Decision Trees
• Learning neutrino effects in Cosmology with Convolutional Neural Networks
• Dark energy reconstruction analysis with artificial neural networks: Application on simulated Supernova Ia data from Rubin Observatory
• Towards unveiling the large-scale nature of gravity with the wavelet scattering transform
• A Reliable Calibration of HII Galaxies Hubble Diagram with Cosmic Chronometers and Artificial Neural Network
• A representation learning approach to probe for dynamical dark energy in matter power spectra
• Distinguishing Coupled Dark Energy Models with Neural Networks
• A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks
• Simultaneous measurements on cosmic curvature and opacity using latest HII regions and $H(z)$ observations
• Bayesian deep learning for cosmic volumes with modified gravity
• Breaking the Dark Degeneracy with the Drifting Coefficient of the Field Cluster Mass Function
• Clusternets: A deep learning approach to probe clustering dark energy
• Euclid: Constraints on f(R) cosmologies from the spectroscopic and photometric primary probes
• Neural Networks for cosmological model selection and feature importance using Cosmic Microwave Background data
• Individual halo bias in models of $f(R)$ gravity
• Impact of astrophysical effects on the dark matter mass constraint with 21cm intensity mapping