AI-assisted super-resolution cosmological simulations III: Time evolution

Abstract

In this work, we extend our recently developed super-resolution (SR) model for cosmological simulations to produce fully time consistent evolving representations of the particle phase-space distribution. We employ a style-based constrained generative adversarial network (Style-GAN) where the changing cosmic time is an input style parameter to the network. The matter power spectrum and halo mass function agree well with results from high-resolution N-body simulations over the full trained redshift range ($10\le z\le 0$). Furthermore, we assess the temporal consistency of our SR model by constructing halo merger trees. We examine progenitors, descendants and mass growth along the tree branches. All statistical indicators demonstrate the ability of our SR model to generate satisfactory high-resolution simulations based on low-resolution inputs.

arXiv comment12 pages, 11 figures, code and movie available in https://github.com/sagasv5-xw/map2map on styled srsgan branch

References in corpus (27)

• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
• Deep Residual Learning for Image Recognition
• Generative Adversarial Networks
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Galaxies on FIRE (Feedback In Realistic Environments): Stellar Feedback Explains Cosmologically Inefficient Star Formation
• The Rockstar Phase-Space Temporal Halo Finder and the Velocity Offsets of Cluster Cores
• Wasserstein GAN
• nbodykit: an open-source, massively parallel toolkit for large-scale structure
• AbacusSummit: A Massive Set of High-Accuracy, High-Resolution $N$-Body Simulations
• Learning to Predict the Cosmological Structure Formation
• Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
• Sussing Merger Trees: The Merger Trees Comparison Project
• TreePM: A code for Cosmological N-Body Simulations
• AI-assisted super-resolution cosmological simulations
• Fast cosmic web simulations with generative adversarial networks
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Deep Learning for Image Super-resolution: A Survey
• Super-resolution emulator of cosmological simulations using deep physical models
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• AI-assisted super-resolution cosmological simulations II: Halo substructures, velocities and higher order statistics
• Predicting dark matter halo formation in N-body simulations with deep regression networks
• Effects of Self-Calibration of Intrinsic Alignment on Cosmological Parameter Constraints from Future Cosmic Shear Surveys
• Machine Learning and Cosmology
• Normalizing flows for random fields in cosmology
• Can denoising diffusion probabilistic models generate realistic astrophysical fields?

Cited by in corpus (1)

• nuGAN: Generative Adversarial Emulator for Cosmic Web with Neutrinos