Related papers: Separate Universe Super-Resolution Emulator
In recent years, deep learning models have been successfully employed for augmenting low-resolution cosmological simulations with small-scale information, a task known as "super-resolution". So far, these cosmological super-resolution…
Cosmological simulations of galaxy formation are limited by finite computational resources. We draw from the ongoing rapid advances in Artificial Intelligence (specifically Deep Learning) to address this problem. Neural networks have been…
Conservative mass limits are often imposed on the dark matter halo catalogues extracted from N-body simulations. By comparing simulations with different mass resolutions, at $z=0$ we find that even for halos resolved by 100 particles, the…
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…
We apply and test a field-level emulator for non-linear cosmic structure formation in a volume matching next-generation surveys. Inferring the cosmological parameters and initial conditions from which the particular galaxy distribution of…
We present an algorithm for quickly generating multiple realizations of N-body simulations to be used, for example, for cosmological parameter estimation from surveys of large-scale structure. Our algorithm uses a new method to resample the…
High-resolution cosmological N-body simulations are excellent tools for modelling the formation and clustering of dark matter haloes. These simulations suggest complex physical theories of halo formation governed by a set of effective…
In this work, we expand and test the capabilities of our recently developed super-resolution (SR) model to generate high-resolution (HR) realizations of the full phase-space matter distribution, including both displacement and velocity,…
Deep generative models, such as Generative Adversarial Networks (GANs) or Variational Autoencoders (VAs) have been demonstrated to produce images of high visual quality. However, the existing hardware severely limits the size of the images…
The large-scale statistics of observables such as the galaxy density are chiefly determined by their dependence on the local coarse-grained matter density. This dependence can be measured directly and efficiently in N-body simulations by…
Super-resolution (SR) models in cosmological simulations use deep learning (DL) to rapidly enhance low-resolution (LR) runs with statistically correct fine details. These models preserves large-scale structures by conditioning on an LR…
We present an extension of our recently developed Wasserstein optimized model to emulate accurate high-resolution features from computationally cheaper low-resolution cosmological simulations. Our deep physical modelling technique relies on…
We present a simple and efficient method to set up spherical structure models for N-body simulations with a multimass technique. This technique reduces by a substantial factor the computer run time needed in order to resolve a given scale…
Super-resolution is a machine-learning technique in image processing which generates high-resolution images from low-resolution images. Inspired by this approach, we perform a numerical experiment of quantum machine learning, which takes…
High-resolution (HR) simulations in cosmology, in particular when including baryons, can take millions of CPU hours. On the other hand, low-resolution (LR) dark matter simulations of the same cosmological volume use minimal computing…
We present a scheme to extend the halo mass resolution of N-body simulations of the hierarchical clustering of dark matter. The method uses the density field of the simulation to predict the number of sub-resolution dark matter haloes…
We present a neural network-based simulation super-resolution framework that can efficiently and realistically enhance a facial performance produced by a low-cost, realtime physics-based simulation to a level of detail that closely…
AI super-resolution, combining deep learning and N-body simulations has been shown to successfully reproduce the large scale structure and halo abundances in the Lambda Cold Dark Matter cosmological model. Here, we extend its use to models…
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…
Simulations of the dark matter distribution throughout the Universe are essential in order to analyse data from cosmological surveys. $N$-body simulations are computationally expensive, and many cheaper alternatives (such as lognormal…