Predicting large scale cosmological structure evolution with generative adversarial network-based autoencoders

Abstract

Predicting the nonlinear evolution of cosmic structure from initial conditions is typically approached using Lagrangian, particle-based methods. These techniques excel in terms of tracking individual trajectories, but they might not be suitable for applications where point-based information is unavailable or impractical. In this work, we explore an alternative, field-based approach using Eulerian inputs. Specifically, we developed an autoencoder architecture based on a generative adversarial network (GAN) and trained it to evolve density fields drawn from dark matter N-body simulations. We tested this method on both 2D and 3D data. We find that while predictions on 2D density maps perform well based on density alone, accurate 3D predictions require the inclusion of associated velocity fields. Our results demonstrate the potential of field-based representations to model cosmic structure evolution, offering a complementary path to Lagrangian methods in contexts where field-level data is more accessible.

13 pages, 11 figures

References in corpus (39)

• The cosmological simulation code GADGET-2
• Introducing the Illustris Project: Simulating the coevolution of dark and visible matter in the Universe
• The James Webb Space Telescope
• U-Net and its variants for medical image segmentation: theory and applications
• The EAGLE simulations of galaxy formation: calibration of subgrid physics and model variations
• Resolving Cosmic Structure Formation with the Millennium-II Simulation
• Solving Large Scale Structure in Ten Easy Steps with COLA
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Learning to Predict the Cosmological Structure Formation
• Tracing the Dark Matter Sheet in Phase Space
• Photometric redshift estimation via deep learning
• Physical Bayesian modelling of the non-linear matter distribution: new insights into the Nearby Universe
• Cosmological Structure Formation with Augmented Lagrangian Perturbation Theory
• A new approach to simulating collisionless dark matter fluids
• Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning
• Automatic morphological classification of galaxy images
• Painting galaxies into dark matter halos using machine learning
• Super-resolution emulator of cosmological simulations using deep physical models
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• Star formation rates and stellar masses from machine learning
• DeepSource: Point Source Detection using Deep Learning
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Field Level Neural Network Emulator for Cosmological N-body Simulations
• Investigating Deep Learning Methods for Obtaining Photometric Redshift Estimations from Images
• Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Benchmarking and Scalability of Machine Learning Methods for Photometric Redshift Estimation
• Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
• A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
• Encoding large scale cosmological structure with Generative Adversarial Networks
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• Deep Learning in Searching the Spectroscopic Redshift of Quasars
• Modelling the galaxy-halo connection with semi-recurrent neural networks
• Learning neutrino effects in Cosmology with Convolutional Neural Networks
• Smooth stochastic density field reconstruction
• A field-level emulator for modified gravity
• COmoving Computer Acceleration (COCA): $N$-body simulations in an emulated frame of reference
• Reionisation time fields reconstruction from 21 cm signal maps
• Reconstructing Galaxy Cluster Mass Maps using Score-based Generative Modeling