Work

21cmEMUv3: A hybrid diffusion and long short-term memory emulator of 21cmFAST summary observables

Year: 2026
Type: article
Abstract: We are witnessing a surge in observations of the cosmic dawn and the epoch of reionisation, driving an increasing demand for fast and robust theoretical interpretation frameworks. In response, machine learning -- emulation in particular -- has emerged as a powerful approach for accelerating and enhancing inference pipelines. In this work, we present 21cmEMUv3, an emulator trained on 21cmFASTv3 simulations that model both atomically and molecularly cooling galaxies. 21cmEMUv3 is conditioned on σ_8 and ten astrophysical parameters to produce seven summary observables: (i) the cylindrical 21cm power spectrum (PS), emulated for the first time at high resolution and accuracy across a wide redshift range of z ∼ 6--30; (ii) the spherically averaged 21cm PS; (iii) the mean neutral fraction of the intergalactic medium; (iv) the mean 21cm spin temperature; (v) the global 21cm signal; (vi) the ultraviolet luminosity functions; and (vii) the Thomson scattering optical depth. Notably, the cylindrical 21cm PS is emulated via score-based diffusion, while the remaining six summaries are emulated via long short-term memory networks, all achieving łesssim1% median accuracy. We used the emulator to reinterpret current 21cm PS upper limits from HERA, for the first time using state-of-the-art hydrodynamical simulations to inform priors on star formation inside molecularly cooling galaxies. We find that our inferred soft-band X-ray luminosity per unit star formation rate is consistent with extrapolations of high-mass X-ray binaries to the low-metallicity regimes expected in the first galaxies, excluding values below 10^39.4 erg s -1 M^ -1 _⊙ $ at $95% confidence. Finally, we produced forecasts for the detection of the cosmic 21cm PS with the Square Kilometre Array for different array configurations. The 21cmEMU package is publicly available. yr
Language: English
Open Access status: gold
Estimated APC paid: $1,865
OpenAlex ID: W7223232610
FWCI: 2.463
Cites: 19
Cited by: 3
Related to: 10