# Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone Emulation

arXiv: https://arxiv.org/abs/2605.29016 · HTML: https://mlsanity.com/paper/2605.29016/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 1 of its 38 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 1 of 1)

- [A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs](https://mlsanity.com/paper/2002.07940/) (2020)

## Abstract (arXiv)

We investigate conditional diffusion modeling for three-dimensional 21 cm lightcone emulation, focusing on cubes with a sky-plane size of 64×64 and a line-of-sight depth up to 1024 cells. Relative to earlier 2D studies, the 3D setting is substantially harder because memory limits enforce very small micro-batches while the underlying voxel distribution is highly skewed and long tailed. We perform controlled comparisons across preprocessing choices, dynamic-range compression settings, architecture depth, and training duration using 25,600 training lightcones and validation ensembles at fixed parameter points. For validation, each reference parameter point contains 800 21cmFAST realizations with independent initial conditions, and we use 800 samples per model and per reference set for the reported ensemble comparisons. We evaluate generated lightcones with complementary diagnostics in both image and summary-statistic spaces: brightness-temperature slices, the global signal, the power spectrum, and reduced scattering coefficients. Across the tested configurations, preprocessing is the dominant factor governing stable training and the resulting physical fidelity. Among the configurations explored here, Yeo-Johnson preprocessing combined with moderate amplitude compression gives the most consistently favorable trade-off, with the strongest quantitative support coming from rankings based on the standard-deviation-normalized mean absolute error (MAErm std) of the global signal and qualitatively compatible behavior in the complementary diagnostics. At the same time, visually plausible 3D samples still retain measurable biases in two-point and higher-order statistics. We therefore view the present work as a simulation-level baseline for three-dimensional 21 cm emulation and for future studies that incorporate more realistic observational effects.