Related papers: HIGAN: Cosmic Neutral Hydrogen with Generative Adv…

Latest Generative Adversarial Networks (GANs) are gathering outstanding results through a large-scale training, thus employing models composed of millions of parameters requiring extensive computational capabilities. Building such huge…

This paper is the second in a series presenting a sample of 29 late-type dwarf galaxies observed with the Westerbork Synthesis Radio Telescope in the 21-cm line of neutral hydrogen (HI). Here we present rotation curves, maps of the velocity…

We model the distribution of neutral hydrogen (HI) in the post-reionization era and investigate its detectability in 21 cm intensity mapping with the future SKA radio telescope. We rely on high resolution hydrodynamical N-body simulations.…

Realistic hyperspectral image (HSI) super-resolution (SR) techniques aim to generate a high-resolution (HR) HSI with higher spectral and spatial fidelity from its low-resolution (LR) counterpart. The generative adversarial network (GAN) has…

Quantum Generative Adversarial Networks (QGANs) have emerged as a promising direction in quantum machine learning, combining the strengths of quantum computing and adversarial training to enable efficient and expressive generative modeling.…

We demonstrate the use of deep network to learn the distribution of data from state-of-the-art hydrodynamic simulations of the CAMELS project. To this end, we train a generative adversarial network to generate images composed of three…

Real active distribution networks with associated smart meter (SM) data are critical for power researchers. However, it is practically difficult for researchers to obtain such comprehensive datasets from utilities due to privacy concerns.…

This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects. While GANs have been used in this domain previously, they are notoriously hard to train, especially for…

Observations of the 21cm line of neutral hydrogen are poised to revolutionize our knowledge of cosmic reionization and the high-redshift population of galaxies. However, harnessing such information requires robust and comprehensive…

In this work, we provide an efficient and realistic data-driven approach to simulate astronomical images using deep generative models from machine learning. Our solution is based on a variant of the generative adversarial network (GAN) with…

We introduce a new, very deep neutral hydrogen (HI) survey being performed with the Westerbork Synthesis Radio Telescope (WSRT). The Westerbork Hydrogen Accretion in LOcal GAlaxieS (HALOGAS) Survey is producing an archive of some of the…

In the last few years the realization has emerged that the universal baryons are almost equally distributed by mass in three components: (1) galactic concentrations, (2) a warm-hot intergalactic medium (WHIM) and (3) a diffuse intergalactic…

Generative adversarial networks (GANs) are an exciting alternative to algorithms for solving density estimation problems---using data to assess how likely samples are to be drawn from the same distribution. Instead of explicitly computing…

In this contribution, we present some preliminary observational results from the completed ultra-deep survey of 21cm emission from neutral hydrogen at redshifts z=0.164-0.224 with the Westerbork Synthesis Radio Telescope. In two separate…

Distribution of cold gas in the post-reionization era provides an important link between distribution of galaxies and the process of star formation. Redshifted 21 cm radiation from the Hyperfine transition of neutral Hydrogen allows us to…

Neutral Hydrogen (HI) provides a very important fuel for star formation, but is difficult to detect at high redshift due to weak emission, limited sensitivity of modern instruments, and terrestrial radio frequency interference (RFI) at low…

We present the 3DGAN for the simulation of a future high granularity calorimeter output as three-dimensional images. We prove the efficacy of Generative Adversarial Networks (GANs) for generating scientific data while retaining a high level…

In the context of Earth observation, change detection boils down to comparing images acquired at different times by sensors of possibly different spatial and/or spectral resolutions or different modalities (e.g., optical or radar). Even…

Generative-adversarial networks (GANs) have been used to produce data closely resembling example data in a compressed, latent space that is close to sufficient for reconstruction in the original vector space. The Wasserstein metric has been…

Adversarial Regression is a proposition to perform high dimensional non-linear regression with uncertainty estimation. We used Conditional Generative Adversarial Network to obtain an estimate of the full predictive distribution for a new…