We present a novel approach for estimating cosmological parameters, $Ω_m$, $σ_8$, $w_0$, and one derived parameter, $S_8$, from 3D lightcone data of dark matter halos in redshift space covering a sky area of $40^\circ \times 40^\circ$ and redshift range of $0.3 < z < 0.8$, binned to $64^3$ voxels. Using two deep learning algorithms, Convolutional Neural Network (CNN) and Vision Transformer (ViT), we compare their performance with the standard two-point correlation (2pcf) function. Our results indicate that CNN yields the best performance, while ViT also demonstrates significant potential in predicting cosmological parameters. By combining the outcomes of Vision Transformer, Convolution Neural Network, and 2pcf, we achieved a substantial reduction in error compared to the 2pcf alone. To better understand the inner workings of the machine learning algorithms, we employed the Grad-CAM method to investigate the sources of essential information in activation maps of the CNN and ViT. Our findings suggest that the algorithms focus on different parts of the density field and redshift depending on which parameter they are predicting. This proof-of-concept work paves the way for incorporating deep learning methods to estimate cosmological parameters from large-scale structures, potentially leading to tighter constraints and improved understanding of the Universe.
Baryon acoustic oscillations reconstruction using convolutional neural networks
National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);University of Chinese Academy of Sciences(中国科学院大学);Durham University(杜伦大学);University of Edinburgh(爱丁堡大学);The Johns Hopkins University(约翰斯·霍普金斯大学);University of the Basque Country(巴斯克大学)
The superclustering of hot gas: cosmological sensitivity in the Websky simulations
Institut de Física d’Altes Energies (IFAE), The Barcelona Institute of Science and Technology(高能物理研究所(IFAE),巴塞罗那科学技术研究院);Canadian Institute for Theoretical Astrophysics, University of Toronto(加拿大理论天体物理学研究所,多伦多大学);David A. Dunlap Department of Astronomy & Astrophysics, University of Toronto(多伦多大学大卫·邓普林天文与天体物理系);Dunlap Institute of Astronomy & Astrophysics(邓普林天文与天体物理研究所);Department of Physics, University of Toronto(多伦多大学物理系);Berkeley Center for Cosmological Physics(伯克利宇宙学物理中心);School of Earth and Space Exploration, Arizona State University(亚利桑那州立大学地球与太空探索学院)
Reionisation time field reconstruction from 21-cm Maps: Investigating predictor coherence in WDM cosmology
Université de Strasbourg(斯特拉斯堡大学);CNRS UMR 7550, Observatoire Astronomique de Strasbourg(法国国家科学研究中心联合研究实验室7550号,斯特拉斯堡天文台);Institut Pluridisciplinaire Hubert Curien (IPHC), Université de Strasbourg, CNRS/IN2P3(于贝尔·居里跨学科研究所,斯特拉斯堡大学,法国国家科学研究中心/法国国家核物理及粒子物理研究所);Department of Astronomy, University of Texas at Austin(德克萨斯大学奥斯汀分校天文学系);Université Paris Cité, CNRS(/IN2P3), Astroparticule et Cosmologie(巴黎西岱大学,法国国家科学研究中心(/法国国家核物理及粒子物理研究所),亚原子粒子与宇宙学)
Bayesian Inference of Primordial Magnetic Field Parameters from CMB with Spherical Graph Neural Networks
Laboratorio de Inteligencia Artificial (SavIA Lab), Grupo Signos, Departamento de Matemáticas, Universidad El Bosque(人工智能实验室(SavIA实验室)、Signos小组、数学系、埃尔博斯克大学)
Towards a Robust Machine-Learning Pipeline for 21-cm Cosmology Data Analysis I: A Roadmap for Development and Demonstration of Robustness Against PSF Modeling Errors
Center for the Fundamental Physics of the Universe, Brown University(布朗大学宇宙基础物理中心);Department of Physics, Brown University(布朗大学物理系)
Convolutional neural network for Lyman break galaxies classification and redshift regression in DESI (Dark Energy Spectroscopic Instrument)
CEA(法国原子能与替代能源委员会);ENSTA Bretagne(布列塔尼国立高等先进技术学校);Institute of Research into the Fundamental Laws of the Universe(宇宙基本规律研究所);French Alternative Energies and Atomic Energy Commission(法国原子能与替代能源委员会)
Princeton University(普林斯顿大学);Flatiron Institute(Flatiron研究所);University of Connecticut(康涅狄格大学);Columbia University(哥伦比亚大学);Sorbonne Universite(巴黎索邦大学);CNRS(法国国家科学研究中心);Institut d’Astrophysique de Paris(巴黎天体物理研究所)