Related papers: Galaxies and Halos on Graph Neural Networks: Deep …
We present a complete forward model of a realistic weak lensing galaxy catalogue based on the 740 Mpc hydrodynamical MillenniumTNG (MTNG) simulation. Starting with a complete particle and cell lightcone covering one octant of the sky with…
Inferring model parameters from experimental data is a grand challenge in many sciences, including cosmology. This often relies critically on high fidelity numerical simulations, which are prohibitively computationally expensive. The…
We measure the galaxy-ellipticity (GI) correlations for the Slogan Digital Sky Survey DR12 LOWZ and CMASS samples with the shape measurements from the DESI Legacy Imaging Surveys. We model the GI correlations in an N-body simulation with…
Precise determination of galaxy cluster masses is crucial for establishing reliable mass-observable scaling relations in cluster cosmology. We employ graph neural networks (GNNs) to estimate galaxy cluster masses from radially sampled…
3D generative modeling is accelerating as the technology allowing the capture of geometric data is developing. However, the acquired data is often inconsistent, resulting in unregistered meshes or point clouds. Many generative learning…
Generative models have recently revolutionized image generation tasks across diverse domains, including galaxy image synthesis. This study investigates the statistical learning and consistency of three generative models: light-weight-gan (a…
This paper introduces a 3D shape generative model based on deep neural networks. A new image-like (i.e., tensor) data representation for genus-zero 3D shapes is devised. It is based on the observation that complicated shapes can be well…
Cosmological surveys aim at answering fundamental questions about our Universe, including the nature of dark matter or the reason of unexpected accelerated expansion of the Universe. In order to answer these questions, two important…
In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework…
We use weak gravitational lensing to measure mean mass profiles around Locally Brightest Galaxies (LBGs). These are selected from the SDSS/DR7 spectroscopic and photometric catalogues to be brighter than any neighbour projected within 1.0…
We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on…
In this series of papers, we present a simulation-based model for the non-linear clustering of galaxies based on separate modelling of clustering in real space and velocity statistics. In the first paper, we present an emulator for the…
Dark matter in the universe evolves through gravity to form a complex network of halos, filaments, sheets and voids, that is known as the cosmic web. Computational models of the underlying physical processes, such as classical N-body…
Morphological classification is a key piece of information to define samples of galaxies aiming to study the large-scale structure of the universe. In essence, the challenge is to build up a robust methodology to perform a reliable…
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…
The formation of Hoag-type galaxies with central spheroidal galaxies and outer stellar rings has yet to be understood in astronomy. We consider that these unique objects were formed from the past interaction between elliptical galaxies and…
Current observational and simulated large-scale structure (LSS) catalogues often lack consistency in assigning galaxies to specific structures, due to the absence of a universally accepted classification criterion. With the aim to generate…
Generating realistic graph-structured data is challenging due to discrete connectivity, varying graph sizes, and class-specific structural patterns. Recent Generative Adversarial Networks (GAN)-based graph generation methods improve edge…
Hybrid-Vlasov simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are computationally expensive. We show that graph-based machine learning emulators can learn the…
In this work, we seek to improve the velocity reconstruction of clusters by using Graph Neural Networks -- a type of deep neural network designed to analyze sparse, unstructured data. In comparison to the Convolutional Neural Network (CNN)…