CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks

Abstract

Inferring model parameters from experimental data is a grand challenge in many sciences, including cosmology. This often relies critically on high fidelity numerical simulations, which are prohibitively computationally expensive. The application of deep learning techniques to generative modeling is renewing interest in using high dimensional density estimators as computationally inexpensive emulators of fully-fledged simulations. These generative models have the potential to make a dramatic shift in the field of scientific simulations, but for that shift to happen we need to study the performance of such generators in the precision regime needed for science applications. To this end, in this work we apply Generative Adversarial Networks to the problem of generating weak lensing convergence maps. We show that our generator network produces maps that are described by, with high statistical confidence, the same summary statistics as the fully simulated maps.

arXiv comment11 pages, 8 figures

References in corpus (28)

• The cosmological simulation code GADGET-2
• The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: cosmological analysis of the DR12 galaxy sample
• Weak Gravitational Lensing
• Deep Visual Domain Adaptation: A Survey
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• Cosmology with cosmic shear observations: a review
• Shapes and Shears, Stars and Smears: Optimal Measurements for Weak Lensing
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Baryon acoustic oscillations from the complete SDSS-III Ly$\alpha$-quasar cross-correlation function at $z=2.4$
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• The Coyote Universe II: Cosmological Models and Precision Emulation of the Nonlinear Matter Power Spectrum
• A critical look at cosmological perturbation theory techniques
• The Coyote Universe III: Simulation Suite and Precision Emulator for the Nonlinear Matter Power Spectrum
• Cosmology from Cosmic Shear with DES Science Verification Data
• Cosmology Constraints from the Weak Lensing Peak Counts and the Power Spectrum in CFHTLenS
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Baryon Acoustic Oscillations at redshift of 0.72 with the DR14 Luminous Red Galaxy Sample
• Cosmic shear results from the deep lens survey - I: Joint constraints on omega_m and sigma_8 with a two-dimensional analysis
• Probing Cosmology with Weak Lensing Peak Counts
• Non-Gaussian information from weak lensing data via deep learning
• Probing Cosmology with Weak Lensing Minkowski Functionals
• Emulating the CFHTLenS Weak Lensing data: Cosmological Constraints from moments and Minkowski functionals
• Cosmological Information in Weak Lensing Peaks
• Fast cosmic web simulations with generative adversarial networks
• Cosmological constraints from noisy convergence maps through deep learning
• Distinguishing standard and modified gravity cosmologies with machine learning
• Mocking the Weak Lensing universe: the LensTools python computing package
• Denoising Weak Lensing Mass Maps with Deep Learning

Cited by in corpus (53)

• Large-scale dark matter simulations
• StressGAN: A Generative Deep Learning Model for 2D Stress Distribution Prediction
• CFDNet: a deep learning-based accelerator for fluid simulations
• Asymptotically unbiased estimation of physical observables with neural samplers
• 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
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Super-resolution emulator of cosmological simulations using deep physical models
• Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
• Realistic galaxy image simulation via score-based generative models
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming
• Pulsar Candidate Identification Using Semi-Supervised Generative Adversarial Networks
• Machine Learning for Observational Cosmology
• Applications of Machine Learning to Predicting Core-collapse Supernova Explosion Outcomes
• The evolution of barred galaxies in the EAGLE simulations
• Generative models for sampling and phase transition indication in spin systems
• ForSE: a GAN based algorithm for extending CMB foreground models to sub-degree angular scales
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• Effective cosmic density field reconstruction with convolutional neural network
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• Cleaning our own Dust: Simulating and Separating Galactic Dust Foregrounds with Neural Networks
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• The bias of dark matter tracers: assessing the accuracy of mapping techniques
• Inpainting Galactic Foreground Intensity and Polarization maps using Convolutional Neural Network
• A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
• One simulation to have them all: performance of the Bias Assignment Method against N-body simulations
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Fast and realistic large-scale structure from machine-learning-augmented random field simulations
• Large-scale structures in the $\Lambda$CDM Universe: network analysis and machine learning
• Optimizing simulation parameters for weak lensing analyses involving non-Gaussian observables
• The Sejong Suite: Cosmological Hydrodynamical Simulations with Massive Neutrinos, Dark Radiation, and Warm Dark Matter
• Generalization Error of GAN from the Discriminator's Perspective
• A Reliable Calibration of HII Galaxies Hubble Diagram with Cosmic Chronometers and Artificial Neural Network
• Predicting 21cm-line map from Lyman $\alpha$ emitter distribution with Generative Adversarial Networks
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• MAGAZ3NE: Massive, Extremely Dusty Galaxies at $z\sim 2$ Lead to Photometric Overestimation of Number Densities of the Most Massive Galaxies at $3<z<4$
• Diffusion-HMC: Parameter Inference with Diffusion-model-driven Hamiltonian Monte Carlo
• The Weak Lensing Peak Statistics in the Mocks by the inverse-Gaussianization Method
• A Machine Learning Approach to Correct for Mass Resolution Effects in Simulated Halo Clustering Statistics
• Psi-GAN: A power-spectrum-informed generative adversarial network for the emulation of large-scale structure maps across cosmologies and redshifts
• Point Source Detection with Fully-Convolutional Networks: Performance in Realistic Simulations
• Multiqubit state learning with entangling quantum generative adversarial networks
• Neural style transfer of weak lensing mass maps
• Reconstructing the mid-infrared spectra of galaxies using ultraviolet to submillimeter photometry and Deep Generative Networks
• Fast Generation of Large-scale Structure Density Maps via Generative Adversarial Networks
• Multi-frequency point source detection with fully convolutional networks: Performance in realistic microwave sky simulations
• nuGAN: Generative Adversarial Emulator for Cosmic Web with Neutrinos
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• Global Optimisation of Black-Box Functions with Generative Models in the Wasserstein Space
• Mimicking the halo-galaxy connection using machine learning
• Replicating weak-lensing summary-statistic covariances with normalizing flows