Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning

Abstract

21cm tomography opens a window to directly study astrophysics and fundamental physics of early epochs in our Universe's history, the Epoch of Reionisation (EoR) and Cosmic Dawn (CD). Summary statistics such as the power spectrum omit information encoded in this signal due to its highly non-Gaussian nature. Here we adopt a network-based approach for direct inference of CD and EoR astrophysics jointly with fundamental physics from 21cm tomography. We showcase a warm dark matter (WDM) universe, where dark matter density parameter ${\Omega }_{\mathrm{m}}$ and WDM mass $m_{\mathrm{WDM}}$ strongly influence both CD and EoR. Reflecting the three-dimensional nature of 21cm light-cones, we present a new, albeit simple, 3D convolutional neural network for efficient parameter recovery at moderate training cost. On simulations we observe high-fidelity parameter recovery for CD and EoR astrophysics ($R^2>0.78-0.99$), together with DM density ${\Omega }_{\mathrm{m}}$ ($R^2>0.97$) and WDM mass ($R^2>0.61$, significantly better for $m_{\mathrm{WDM}}<3-4$keV). For realistic mock observed light-cones that include noise and foreground levels expected for the Square Kilometre Array, we note that in an optimistic foreground scenario parameter recovery is unaffected, while for moderate, less optimistic foreground levels (occupying the so-called wedge) the recovery of the WDM mass deteriorates, while other parameters remain robust against increased foreground levels at $R^2>0.9$. We further test the robustness of our network-based inference against modelling uncertainties and systematics by transfer learning between bare simulations and mock observations; we find robust recovery of specific X-ray luminosity and ionising efficiency, while DM density and WDM mass come with increased bias and scatter.

18 pages, 9 figures, 7 tables. Accepted for publication in MNRAS. Comments are welcome

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Too big to fail? The puzzling darkness of massive Milky Way subhaloes
• Efficient Simulations of Early Structure Formation and Reionization
• 21CMMC: an MCMC analysis tool enabling astrophysical parameter studies of the cosmic 21 cm signal
• Simulating Cosmic Reionization at Large Scales II: the 21-cm Emission Features and Statistical Signals
• Realistic sterile neutrino dark matter with keV mass does not contradict cosmological bounds
• 21cmFAST v3: A Python-integrated C code forgenerating 3D realizations of the cosmic 21cm signal
• Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
• Unveiling the nature of dark matter with high redshift 21 cm line experiments
• Constraining the reionization history using deep learning from 21cm tomography with the Square Kilometre Array
• Warm Dark Matter and Cosmic Reionization
• Constraining the Reionization History using Bayesian Normalizing Flows
• The spin-temperature dependence of the 21cm -- LAE cross-correlation

Cited by in corpus (4)

• Machine Learning for Observational Cosmology
• Machine Learning and Cosmology
• Inferring Cosmological Parameters on SDSS via Domain-Generalized Neural Networks and Lightcone Simulations
• 3D ScatterNet: Inference from 21 cm Light-cones