A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs

Abstract

Traditionally, incorporating additional physics into existing cosmological simulations requires re-running the cosmological simulation code, which can be computationally expensive. We show that conditional Generative Adversarial Networks (cGANs) can be harnessed to predict how changing the underlying physics alters the simulation results. To illustrate this, we train a cGAN to learn the impact of dark matter annihilation feedback (DMAF) on the gas density distribution. The predicted gas density slices are visually difficult to distinguish from their real brethren and the peak counts differ by less than 10 per cent for all test samples (the average deviation is < 3 per cent). Finally, we invert the problem and show that cGANs are capable of endowing smooth density distributions with realistic substructure. The cGAN does however have difficulty generating new knots as well as creating/eliminating bubble-like structures. We conclude that trained cGANs can be an effective approach to provide mock samples of cosmological simulations incorporating DMAF physics from existing samples of standard cosmological simulations of the evolution of cosmic structure.

arXiv comment11 pages, 9 figures

References in corpus (52)

• Planck 2015 results. XIII. Cosmological parameters
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Gaia Data Release 2. Summary of the contents and survey properties
• The cosmological simulation code GADGET-2
• The EAGLE project: Simulating the evolution and assembly of galaxies and their environments
• Large scale bias and the peak background split
• The 2dF Galaxy Redshift Survey: Spectra and redshifts
• First results from the IllustrisTNG simulations: matter and galaxy clustering
• GADGET: A code for collisionless and gasdynamical cosmological simulations
• Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
• Properties of galaxies reproduced by a hydrodynamic simulation
• Astrophysics Source Code Library
• A Multi-Code Analysis Toolkit for Astrophysical Simulation Data
• A Semi-Analytic Model for the Co-evolution of Galaxies, Black Holes, and Active Galactic Nuclei
• How Filaments are Woven into the Cosmic Web
• GIZMO: A New Class of Accurate, Mesh-Free Hydrodynamic Simulation Methods
• Giant Gamma-ray Bubbles from Fermi-LAT: AGN Activity or Bipolar Galactic Wind?
• Precise Relic WIMP Abundance and its Impact on Searches for Dark Matter Annihilation
• Galaxy formation in the Planck Cosmology - I. Matching the observed evolution of star formation rates, colours and stellar masses
• CMB Constraints on WIMP Annihilation: Energy Absorption During the Recombination Epoch
• Current Dark Matter Annihilation Constraints from CMB and Low-Redshift Data
• GeV-Scale Thermal WIMPs: Not Even Slightly Dead
• The Coyote Universe III: Simulation Suite and Precision Emulator for the Nonlinear Matter Power Spectrum
• Clumpy Neutralino Dark Matter
• A Robust Excess in the Cosmic-Ray Antiproton Spectrum: Implications for Annihilating Dark Matter
• Cosmology constraints from shear peak statistics in Dark Energy Survey Science Verification data
• A filament of dark matter between two clusters of galaxies
• Do GANs actually learn the distribution? An empirical study
• Systematic Uncertainties In Constraining Dark Matter Annihilation From The Cosmic Microwave Background
• Scrutinizing the evidence for dark matter in cosmic-ray antiprotons
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Fast cosmic web simulations with generative adversarial networks
• The CoDECS project: a publicly available suite of cosmological N-body simulations for interacting dark energy models
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• A new model to predict weak-lensing peak counts I. Comparison with $N$-body Simulations
• Modeling the Impact of Baryons on Subhalo Populations with Machine Learning
• Machine Learning and Cosmological Simulations II: Hydrodynamical Simulations
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey
• Towards a radially-resolved semi-analytic model for the evolution of disc galaxies tuned with machine learning
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Enhancing AGN efficiency and cool-core formation with anisotropic thermal conduction
• A new model to predict weak-lensing peak counts III. Filtering technique comparisons
• Weak lensing peak statistics in the era of large scale cosmological surveys
• Effect of dark matter annihilation on gas cooling and star formation
• Self-supervised Learning with Physics-aware Neural Networks I: Galaxy Model Fitting
• Pressure from dark matter annihilation and the rotation curve of spiral galaxies
• Consequences of dark matter self-annihilation for galaxy formation
• Dark Matter Annihilation in the Circumgalactic Medium at High Redshifts
• Dark Matter Annihilation Feedback in cosmological simulations I: Code convergence and idealised halos
• A Novel Scheme for Dark Matter Annihilation Feedback in Cosmological Simulations
• Dark Matter Annihilation Feedback in Cosmological Simulations II: The Influence on Gas and Halo Structure

Cited by in corpus (9)

• Large-scale dark matter simulations
• Super-resolution emulator of cosmological simulations using deep physical models
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• Encoding large scale cosmological structure with Generative Adversarial Networks
• Learning neutrino effects in Cosmology with Convolutional Neural Networks
• Predicting 21cm-line map from Lyman $\alpha$ emitter distribution with Generative Adversarial Networks
• Uncertainties associated with GAN-generated datasets in high energy physics
• Stochastic Super-resolution of Cosmological Simulations with Denoising Diffusion Models