aiqbench analysis
This research advances AI applications in cosmology by applying conditional diffusion models to emulate complex 3D 21 cm lightcone data, addressing significant challenges like skewed voxel distributions and memory constraints. The study identifies preprocessing techniques, specifically Yeo-Johnson transformation with amplitude compression, as the critical factor for achieving stable training and high physical fidelity in these simulations. While visually plausible samples are generated, the work highlights remaining biases in higher-order statistics, establishing a necessary baseline for future AI-driven observational cosmology studies.
Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone Emulation
arXiv:2605.29016v2 Announce Type: replace-cross Abstract: We investigate conditional diffusion modeling for three-dimensional 21 cm lightcone emulation, focusing on cubes with a sky-plane size of $64\times64$ 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 ($\mathrm{MAE}_{\rm std}$) 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.
Abstract:We investigate conditional diffusion modeling for three-dimensional 21 cm lightcone emulation, focusing on cubes with a sky-plane size of $64\times64$ 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 ($\mathrm{MAE}_{\rm std}$) 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.
Accepted for publication in The Astrophysical Journal. Revised version incorporating referee comments
Instrumentation and Methods for Astrophysics (astro-ph.IM); Cosmology and Nongalactic Astrophysics (astro-ph.CO); Machine Learning (cs.LG)
arXiv:2605.29016 [astro-ph.IM]
(or arXiv:2605.29016v2 [astro-ph.IM] for this version)
https://doi.org/10.48550/arXiv.2605.29016 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.3847/1538-4357/ae9cb3 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 369 words
Related coverage
Running Variational Quantum Eigensolver with Qiskit Aer on AMD Instinct
AMD · May 29, 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026
Conditional Score-Based Modeling of Effective Langevin Dynamics
arXiv · Jun 16, 2026
Diffusion models for eye-gaze trajectory generation using position and velocity representations
arXiv · Sep 9, 2026