Cosmo-FOLD: Fast generation and upscaling of field-level cosmological maps with overlap latent diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mishra, Satvik, Trotta, Roberto, Viel, Matteo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911388746645504
author Mishra, Satvik
Trotta, Roberto
Viel, Matteo
author_facet Mishra, Satvik
Trotta, Roberto
Viel, Matteo
contents We demonstrate the capabilities of probabilistic diffusion models to reduce dramatically the computational cost of expensive hydrodynamical simulations to study the relationship between observable baryonic cosmological probes and dark matter at field level and well into the non-linear regime. We introduce a novel technique, Cosmo-FOLD (Cosmological Fields via Overlap Latent Diffusion) to rapidly generate accurate and arbitrarily large cosmological and astrophysical 3-dimensional fields, conditioned on a given input field. We are able to generate TNG300-2 dark matter density and gas temperature fields from a model trained only on ~1% of the volume (a process we refer to as `upscaling'), reproducing both large scale coherent dark matter filaments and power spectra to within 10% for wavenumbers k <= 5 h Mpc^-1. These results are obtained within a small fraction of the original simulation cost and produced on a single GPU. Beyond one and two points statistics, the bispectrum is also faithfully reproduced through the inclusion of positional encodings. Finally, we demonstrate Cosmo-FOLD's generalisation capabilities by upscaling a CAMELS volume of 25 (Mpc h^-1)^3 to a full TNG300-2 volume of 205 (Mpc h^-1)^3$ with no fine-tuning. Cosmo-FOLD opens the door to full field-level simulation-based inference on cosmological scale.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14377
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cosmo-FOLD: Fast generation and upscaling of field-level cosmological maps with overlap latent diffusion
Mishra, Satvik
Trotta, Roberto
Viel, Matteo
Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
Machine Learning
We demonstrate the capabilities of probabilistic diffusion models to reduce dramatically the computational cost of expensive hydrodynamical simulations to study the relationship between observable baryonic cosmological probes and dark matter at field level and well into the non-linear regime. We introduce a novel technique, Cosmo-FOLD (Cosmological Fields via Overlap Latent Diffusion) to rapidly generate accurate and arbitrarily large cosmological and astrophysical 3-dimensional fields, conditioned on a given input field. We are able to generate TNG300-2 dark matter density and gas temperature fields from a model trained only on ~1% of the volume (a process we refer to as `upscaling'), reproducing both large scale coherent dark matter filaments and power spectra to within 10% for wavenumbers k <= 5 h Mpc^-1. These results are obtained within a small fraction of the original simulation cost and produced on a single GPU. Beyond one and two points statistics, the bispectrum is also faithfully reproduced through the inclusion of positional encodings. Finally, we demonstrate Cosmo-FOLD's generalisation capabilities by upscaling a CAMELS volume of 25 (Mpc h^-1)^3 to a full TNG300-2 volume of 205 (Mpc h^-1)^3$ with no fine-tuning. Cosmo-FOLD opens the door to full field-level simulation-based inference on cosmological scale.
title Cosmo-FOLD: Fast generation and upscaling of field-level cosmological maps with overlap latent diffusion
topic Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
Machine Learning
url https://arxiv.org/abs/2601.14377