Mass Estimation of Galaxy Clusters with Deep Learning II: CMB Cluster Lensing. (arXiv:2005.13985v2 [astro-ph.CO] UPDATED)

Mass Estimation of Galaxy Clusters with Deep Learning II: CMB Cluster Lensing. (arXiv:2005.13985v2 [astro-ph.CO] UPDATED)
<a href="http://arxiv.org/find/astro-ph/1/au:+Gupta_N/0/1/0/all/0/1">N. Gupta</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Reichardt_C/0/1/0/all/0/1">C. L. Reichardt</a>

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 $Delta M_{rm 200c}^{rm est}/M_{rm 200c}^{rm est} =$ 0.108 and
0.016 for input cluster mass $M_{rm 200c}^{rm true}=10^{14}~rm M_{odot}$
and $8times 10^{14}~rm M_{odot}$, respectively. We also test for potential
bias on recovered masses, finding that for a set of $10^5$ clusters the
estimator recovers $M_{rm 200c}^{rm est} = 2.02 times 10^{14}~rm
M_{odot}$, consistent with the input at 1% level. The 2 $sigma$ upper limit
on potential bias is at 3.5% level.

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 $Delta M_{rm 200c}^{rm est}/M_{rm 200c}^{rm est} =$ 0.108 and
0.016 for input cluster mass $M_{rm 200c}^{rm true}=10^{14}~rm M_{odot}$
and $8times 10^{14}~rm M_{odot}$, respectively. We also test for potential
bias on recovered masses, finding that for a set of $10^5$ clusters the
estimator recovers $M_{rm 200c}^{rm est} = 2.02 times 10^{14}~rm
M_{odot}$, consistent with the input at 1% level. The 2 $sigma$ upper limit
on potential bias is at 3.5% level.

http://arxiv.org/icons/sfx.gif