相关论文: HIGAN: Cosmic Neutral Hydrogen with Generative Adv…

We investigate the influence of environment on the cold-gas properties of galaxies at z=0 within the TNG100 cosmological, magnetohydrodynamic simulation, part of the IllustrisTNG suite. We extend previous post-processing methods for…

We present 21-cm Spectral Line Observations of Neutral Gas with the VLA (21-SPONGE), a Karl G. Jansky Very Large Array (VLA) large project (~600 hours) for measuring the physical properties of Galactic neutral hydrogen (HI). 21-SPONGE is…

In the era of precision cosmology, the ability to generate accurate and large-scale galaxy catalogs is crucial for advancing our understanding of the universe. With the flood of cosmological data from current and upcoming missions,…

We propose a novel generative adversarial network (GAN) for the task of unsupervised learning of 3D representations from natural images. Most generative models rely on 2D kernels to generate images and make few assumptions about the 3D…

We investigate the column density distribution function of neutral hydrogen at redshift z = 3 using a cosmological simulation of galaxy formation from the OverWhelmingly Large Simulations (OWLS) project. The base simulation includes…

Detecting neutral hydrogen structures in the intergalactic medium (IGM) during cosmic reionization via absorption (21 cm forest) against a background radiation is considered independent and complementary to the three-dimensional tomography…

Generative adversarial networks (GANs) are a machine learning technique capable of producing high-quality synthetic images. In the field of materials science, when a crystallographic dataset includes inadequate or difficult-to-obtain…

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoregressive WaveNet is trained by jointly optimizing…

We measure the scale dependence and redshift dependence of 21 cm line emitted from the neutral hydrogen gas at redshift 1<z<5 using full cosmological hydrodynamic simulations by taking the ratios between the power spectra of HI-dark matter…

We report the first direct detection of the cosmological power spectrum using the intensity signal from 21-cm emission of neutral hydrogen (HI), derived from interferometric observations with the L-band receivers of the new MeerKAT radio…

Generating realistic graph-structured data is challenging due to discrete structures, variable sizes, and class-specific connectivity patterns that resist conventional generative modelling. While recent graph generation methods employ…

We use spectral stacking to measure the contribution of galaxies of different masses and in different hierarchies to the cosmic atomic hydrogen (HI) mass density in the local Universe. Our sample includes 1793 galaxies at $z < 0.11$…

One of the main challenges in the parametrization of geological models is the ability to capture complex geological structures often observed in the subsurface. In recent years, generative adversarial networks (GAN) were proposed as an…

Wasserstein Generative Adversarial Networks (WGANs) can be used to generate realistic samples from complicated image distributions. The Wasserstein metric used in WGANs is based on a notion of distance between individual images, which…

The 21-cm emission from atomic hydrogen (HI) is one of the most important tracers of the structure and dynamics of the interstellar medium. Thanks to Galactic rotation, the line is Doppler shifted and, assuming a model for the velocity…

In this paper, we propose a new adversarial training framework to address high-dimensional instantaneous channel estimation in wireless communications. Specifically, we train a generative adversarial network to predict a channel realization…

Medical Image Synthesis (MIS) plays an important role in the intelligent medical field, which greatly saves the economic and time costs of medical diagnosis. However, due to the complexity of medical images and similar characteristics of…

Understanding the nature of dark matter in the Universe is an important goal of modern cosmology. A key method for probing this distribution is via weak gravitational lensing mass-mapping - a challenging ill-posed inverse problem where one…

Generative adversarial networks (GANs) have received a tremendous amount of attention in the past few years, and have inspired applications addressing a wide range of problems. Despite its great potential, GANs are difficult to train.…

The 21cm emission line from neutral hydrogen (HI) contained within galaxies provides a way to make accurate spectroscopic redshift determinations in the radio part of the spectrum. Large radio arrays such as SKA-MID are coming online that…