Abstract
We present a new application of deep learning to reconstruct the cosmic microwave background (CMB) temperature maps from images of the 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 CMB, 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 104 galaxy cluster samples with a 1σ uncertainty
Δ
M
200
c
est
/
M
200
c
est
=
0.108 and 0.016 for input cluster mass
M
200
c
true
=
10
14
M
⊙
and 8 × 1014
M
⊙, respectively. We also test for potential bias on recovered masses, finding that for a set of 105 clusters the estimator recovers
M
200
c
est
=
2.02
×
10
14
M
⊙
, consistent with the input at 1% level. The 2σ upper limit on potential bias is at 3.5% level.
Search for Galaxy Cluster Candidates in the Cosmic Microwave Background Maps of the Planck Space Mission Using a Convolutional Neural Network Based on the Method of Tracing the Sunyaev–Zeldovich Effect
