Title: DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks

Abstract

Next-generation cosmic microwave background (CMB) experiments will have lower noise and therefore increased sensitivity, enabling improved constraints on fundamental physics parameters such as the sum of neutrino masses and the tensor-to-scalar ratio r. Achieving competitive constraints on these parameters requires high signal-to-noise extraction of the projected gravitational potential from the CMB maps. Standard methods for reconstructing the lensing potential employ the quadratic estimator (QE). However, the QE performs suboptimally at the low noise levels expected in upcoming experiments. Other methods, like maximum likelihood estimators (MLE), are under active development. In this work, we demonstrate reconstruction of the CMB lensing potential with deep convolutional neural networks (CNN) - ie, a ResUNet. The network is trained and tested on simulated data, and otherwise has no physical parametrization related to the physical processes of the CMB and gravitational lensing. We show that, over a wide range of angular scales, ResUNets recover the input gravitational potential with a higher signal-to-noise ratio than the QE method, reaching levels comparable to analytic approximations of MLE methods. We demonstrate that the network outputs quantifiably different lensing maps when given input CMB maps generated with different cosmologies. We also show we can use the reconstructed lensing map formore » cosmological parameter estimation. This application of CNN provides a few innovations at the intersection of cosmology and machine learning. First, while training and regressing on images, we predict a continuous-variable field rather than discrete classes. Second, we are able to establish uncertainty measures for the network output that are analogous to standard methods. We expect this approach to excel in capturing hard-to-model non-Gaussian astrophysical foreground and noise contributions.« less

Authors:

Caldeira, J.  ^[1];

• Search DOE PAGES for author "Caldeira, J."
• Search DOE PAGES for ORCID "0000-0002-5975-7230"

Wu, W. L.K. ^[2]; Nord, B. ^[3]; Avestruz, C. ^[4]; Trivedi, S. ^[5]; Story, K. T. ^[6]

---

+ Show Author Affiliations

1. Univ. of Chicago, IL (United States). Enrico Fermi Inst. and Kadanoff Center for Theoretical Physics; Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
2. Univ. of Chicago, IL (United States). Kavli Inst. for Cosmological Physics (KICP)
3. Univ. of Chicago, IL (United States). Kavli Inst. for Cosmological Physics (KICP); Univ. of Chicago, IL (United States). Dept. of Astronomy and Astropysics; Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
4. Univ. of Chicago, IL (United States). Enrico Fermi Inst. and Kadanoff Center for Theoretical Physics; Univ. of Chicago, IL (United States). Kavli Inst. for Cosmological Physics (KICP)
5. Brown Univ., Providence, RI (United States). Inst. for Computational and Experimental Research in Mathematics
6. Descartes Labs, Santa Fe, CA (United States)

Publication Date:

Mon Jul 01 00:00:00 EDT 2019

Research Org.:

Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)

Sponsoring Org.:

USDOE Office of Science (SC), High Energy Physics (HEP)

OSTI Identifier:

1487051

Alternate Identifier(s):

OSTI ID: 1780551

Report Number(s):

arXiv:1810.01483; FERMILAB-PUB-18-515-A-CD
Journal ID: ISSN 2213-1337; oai:inspirehep.net:1696852

Grant/Contract Number:  

AC02-07CH11359

Resource Type:

Accepted Manuscript

Journal Name:

Astronomy and Computing

Additional Journal Information:

Journal Volume: 28; Journal Issue: C; Journal ID: ISSN 2213-1337

Publisher:

Elsevier

Country of Publication:

United States

Language:

English

Subject:

79 ASTRONOMY AND ASTROPHYSICS; cosmic microwave background; cosmology; deep learning; convolutional neural networks