Mass Estimation of Galaxy Clusters with Deep Learning II: CMB Cluster Lensing

Abstract

We present a new application of deep learning to reconstruct the cosmic microwave background (CMB) temperature maps from the images of microwave sky, and to use these reconstructed maps to estimate the masses of galaxy clusters. We use a feed-forward deep learning network, mResUNet, for both steps of the analysis. The first deep learning model, mResUNet-I, is trained to reconstruct foreground and noise suppressed CMB maps from a set of simulated images of the microwave sky that include signals from the cosmic microwave background, astrophysical foregrounds like dusty and radio galaxies, instrumental noise as well as the cluster's own thermal Sunyaev Zel'dovich signal. The second deep learning model, mResUNet-II, is trained to estimate cluster masses from the gravitational lensing signature in the reconstructed foreground and noise suppressed CMB maps. For SPTpol-like noise levels, the trained mResUNet-II model recovers the mass for $10^4$ galaxy cluster samples with a 1-$\sigma$ uncertainty $\Delta M_{200c}^{\mathrm{est}}/M_{200c}^{\mathrm{est}}=$ 0.108 and 0.016 for input cluster mass $M_{200c}^{\mathrm{true}}=10^{14}{\mathrm{M}}_{\odot }$ and $8\times 10^{14}{\mathrm{M}}_{\odot }$, respectively. We also test for potential bias on recovered masses, finding that for a set of $10^5$ clusters the estimator recovers $M_{200c}^{\mathrm{est}}=2.02\times 10^{14}{\mathrm{M}}_{\odot }$, consistent with the input at 1% level. The 2 $\sigma$ upper limit on potential bias is at 3.5% level.

11 pages, 6 figures

References in corpus (11)

• CMB-S4 Science Case, Reference Design, and Project Plan
• The Canadian Cluster Comparison Project: detailed study of systematics and updated weak lensing masses
• A universal model for halo concentrations
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Cluster Abundances and Weak Lensing
• A measurement of secondary cosmic microwave background anisotropies from the 2500-square-degree SPT-SZ survey
• Mass Calibration and Cosmological Analysis of the SPT-SZ Galaxy Cluster Sample Using Velocity Dispersion ${\sigma }_v$ and X-ray $Y_{\text{X}}$ Measurements
• Evidence of Lensing of the Cosmic Microwave Background by Dark Matter Halos
• A Measurement of Gravitational Lensing of the Cosmic Microwave Background by Galaxy Clusters Using Data from the South Pole Telescope
• Measuring cluster masses with CMB lensing: a statistical approach
• Improved estimation of cluster mass profiles from the cosmic microwave background
• Mass Estimation of Galaxy Clusters with Deep Learning I: Sunyaev-Zel'dovich Effect

Cited by in corpus (14)

• A Deep Learning Approach to Infer Galaxy Cluster Masses from Planck Compton$-y$ parameter maps
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• The Three Hundred project: A Machine Learning method to infer clusters of galaxies mass radial profiles from mock Sunyaev-Zel'dovich maps
• Improving cosmological constraints from galaxy cluster number counts with CMB-cluster-lensing data: Results from the SPT-SZ survey and forecasts for the future
• Machine Learning and Cosmology
• Cross-correlation between $Planck$ CMB lensing potential and galaxy catalogues from HELP
• CHEX-MATE: A non-parametric deep learning technique to deproject and deconvolve galaxy cluster X-ray temperature profiles
• Cluster profiles from beyond-the-QE CMB lensing mass maps
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• A measurement of cluster masses using Planck and SPT-SZ CMB lensing
• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• Mass scaling relations for dark halos from an analytic universal outer density profile
• Generating Galaxy Clusters Mass Density Maps from Mock Multiview Images via Deep Learning