DeepAI AI Chat
Log In Sign Up

Super-resolving Dark Matter Halos using Generative Deep Learning

11/11/2021
by   David Schaurecker, et al.
0

Generative deep learning methods built upon Convolutional Neural Networks (CNNs) provide a great tool for predicting non-linear structure in cosmology. In this work we predict high resolution dark matter halos from large scale, low resolution dark matter only simulations. This is achieved by mapping lower resolution to higher resolution density fields of simulations sharing the same cosmology, initial conditions and box-sizes. To resolve structure down to a factor of 8 increase in mass resolution, we use a variation of U-Net with a conditional GAN, generating output that visually and statistically matches the high resolution target extremely well. This suggests that our method can be used to create high resolution density output over Gpc/h box-sizes from low resolution simulations with negligible computational effort.

READ FULL TEXT
06/21/2020

Mapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping

Several methods have recently been proposed for the Single Image Super-R...
11/20/2020

Deep learning insights into cosmological structure formation

While the evolution of linear initial conditions present in the early un...
10/06/2020

Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning

The goal of generative models is to learn the intricate relations betwee...
03/06/2017

Learning across scales - A multiscale method for Convolution Neural Networks

In this work we establish the relation between optimal control and train...
05/02/2023

Unpaired Downscaling of Fluid Flows with Diffusion Bridges

We present a method to downscale idealized geophysical fluid simulations...
11/01/2021

Deep learning of multi-resolution X-Ray micro-CT images for multi-scale modelling

There are inherent field-of-view and resolution trade-offs in X-Ray micr...
01/22/2019

Generation High resolution 3D model from natural language by Generative Adversarial Network

We present a method of generating high resolution 3D shapes from natural...