Conditional Diffusion-Flow models for generating 3D cosmic density fields: applications to f(R) cosmologies

Export Citation

Riveros, JK orcid iconORCID: 0009-0009-2627-5516, Saavedra, PA orcid iconORCID: 0009-0006-6623-1057, Hortua, HJ orcid iconORCID: 0000-0002-3396-2404, Garcia Farieta, J and Olier, I orcid iconORCID: 0000-0002-5679-7501 (2025) Conditional Diffusion-Flow models for generating 3D cosmic density fields: applications to f(R) cosmologies. Machine Learning: Science and Technology, 6 (3).

[thumbnail of Conditional Diffusion Flow models for generating 3D cosmic density fields applications to fR cosmologies.pdf]
Preview
 Text
Conditional Diffusion Flow models for generating 3D cosmic density fields applications to fR cosmologies.pdf - Published Version
Available under License Creative Commons Attribution.
Download (8MB) | Preview

Abstract

Next-generation galaxy surveys promise unprecedented precision in testing gravity at cosmological scales. However, realising this potential requires accurately modelling the non-linear cosmic web. We address this challenge by exploring conditional generative modelling to create 3D dark matter density fields via score-based (diffusion) and flow-based methods. Our results demonstrate the power of diffusion models to accurately reproduce the matter power spectra and bispectra, even for unseen configurations. They also offer a significant speed-up with slightly reduced accuracy, when flow-based reconstructing the probability distribution function, but they struggle with higher-order statistics. To improve conditional generation, we introduce a novel multi-output model to develop feature representations of the cosmological parameters. Our findings offer a powerful tool for exploring deviations from standard gravity, combining high precision with reduced computational cost, thus paving the way for more comprehensive and efficient cosmological analyses.

Item Type: Article
Uncontrolled Keywords: 46 Information and Computing Sciences; 4601 Applied Computing; 4611 Machine Learning; 4601 Applied computing; 4611 Machine learning
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Computer Science and Mathematics
Publisher: IOP Publishing
Date of acceptance: 5 August 2025
Date of first compliant Open Access: 15 August 2025
Date Deposited: 15 Aug 2025 09:30
Last Modified: 15 Aug 2025 09:45
DOI or ID number: 10.1088/2632-2153/adf8b1
URI: https://researchonline.ljmu.ac.uk/id/eprint/26940
View Item View Item
CORE (COnnecting REpositories)