EMBER-2: emulating baryons from dark matter across cosmic time with deep modulation networks
Rattachement africain : ch, uz, gb, us. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
ABSTRACT Galaxy formation is a complex problem that connects large-scale cosmology with small-scale astrophysics over cosmic time-scales. Hydrodynamical simulations are the most principled approach to model galaxy formation, but have large computational costs. Recently, emulation techniques based on convolutional neural networks (CNNs) have been proposed to predict baryonic properties directly from dark matter simulations. The advantage of these emulators is their ability to capture relevant correlations, but at a fraction of the computational cost compared to simulations. However, training basic CNNs over large redshift ranges is challenging, due to the increasing non-linear interplay between dark matter and baryons paired with the memory inefficiency of CNNs. This work introduces EMBER-2, an improved version of the EMBER (EMulating Baryonic EnRichment) framework, to simultaneously emulate multiple baryon channels including gas density, velocity, temperature, and H i density over a large redshift range, from $z=6$ to $z=0$. EMBER-2 incorporates a context-based styling network paired with Modulated Convolutions for fast, accurate, and memory efficient emulation capable of interpolating the entire redshift range with a single CNN. Although EMBER-2 uses fewer than 1/6 the number of trainable parameters than the previous version, the model improves in every tested summary metric including gas mass conservation and cross-correlation coefficients. The EMBER-2 framework builds the foundation to produce mock catalogues of field level data and derived summary statistics that can directly be incorporated in future analysis pipelines. We release the source code at the official website https://maurbe.github.io/ember2/.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé, mais le titre doit être comparé manuellement.
- Titre Crossref
- <tt>EMBER-2</tt>: emulating baryons from dark matter across cosmic time with deep modulation networks
- Date Crossref
- 27/02/2025
- Éditeur
- Oxford University Press (OUP)
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
University of Zurich Department of Astrophysics pays non établi dans la noticeUniversité ou école supérieure
-
Centre for Theoretical Physics and Astrophysics pays non établi dans la noticeStructure de recherche
-
Royal Observatory pays non établi dans la noticeStructure de recherche
-
University of Edinburgh Institute for Astronomy pays non établi dans la noticeUniversité ou école supérieure
-
University of Connecticut Department of Physics pays non établi dans la noticeUniversité ou école supérieure
-
Flatiron Health (United States) pays non établi dans la noticeEntreprise
-
Flatiron Institute Center for Computational Astrophysics pays non établi dans la noticeOrganisation à but non lucratif
-
Northwestern University Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA) and Department of Physics and Astronomy pays non établi dans la noticeUniversité ou école supérieure
Department of Astrophysics — University of Zurich, Centre for Theoretical Physics and Astrophysics et Royal Observatory, avec 5 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.