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 »
- Authors:
-
- Univ. of Chicago, IL (United States). Enrico Fermi Inst. and Kadanoff Center for Theoretical Physics; Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- Univ. of Chicago, IL (United States). Kavli Inst. for Cosmological Physics (KICP)
- 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)
- 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)
- Brown Univ., Providence, RI (United States). Inst. for Computational and Experimental Research in Mathematics
- Descartes Labs, Santa Fe, CA (United States)
- Publication Date:
- 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
Citation Formats
Caldeira, J., Wu, W. L.K., Nord, B., Avestruz, C., Trivedi, S., and Story, K. T. DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks. United States: N. p., 2019.
Web. doi:10.1016/j.ascom.2019.100307.
Caldeira, J., Wu, W. L.K., Nord, B., Avestruz, C., Trivedi, S., & Story, K. T. DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks. United States. https://doi.org/10.1016/j.ascom.2019.100307
Caldeira, J., Wu, W. L.K., Nord, B., Avestruz, C., Trivedi, S., and Story, K. T. Mon .
"DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks". United States. https://doi.org/10.1016/j.ascom.2019.100307. https://www.osti.gov/servlets/purl/1487051.
@article{osti_1487051,
title = {DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks},
author = {Caldeira, J. and Wu, W. L.K. and Nord, B. and Avestruz, C. and Trivedi, S. and Story, K. T.},
abstractNote = {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 for 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.},
doi = {10.1016/j.ascom.2019.100307},
journal = {Astronomy and Computing},
number = C,
volume = 28,
place = {United States},
year = {Mon Jul 01 00:00:00 EDT 2019},
month = {Mon Jul 01 00:00:00 EDT 2019}
}
Web of Science
Figures / Tables:
Works referenced in this record:
Measurement of the Cosmic Microwave Background Polarization Lensing Power Spectrum with the POLARBEAR Experiment
journal, July 2014
- Ade, P. A. R.; Akiba, Y.; Anthony, A. E.
- Physical Review Letters, Vol. 113, Issue 2
NINE-YEAR WILKINSON MICROWAVE ANISOTROPY PROBE ( WMAP ) OBSERVATIONS: FINAL MAPS AND RESULTS
journal, September 2013
- Bennett, C. L.; Larson, D.; Weiland, J. L.
- The Astrophysical Journal Supplement Series, Vol. 208, Issue 2
Constraints on Primordial Gravitational Waves Using , WMAP, and New BICEP2/ Observations through the 2015 Season
journal, November 2018
- Ade, P. A. R.; Ahmed, Z.; Aikin, R. W.
- Physical Review Letters, Vol. 121, Issue 22
Bicep2/ KECK ARRAY VIII: MEASUREMENT OF GRAVITATIONAL LENSING FROM LARGE-SCALE B -MODE POLARIZATION
journal, December 2016
- Ade, P. A. R.; Ahmed, Z.; Aikin, R. W.
- The Astrophysical Journal, Vol. 833, Issue 2
Improved Constraints on Cosmology and Foregrounds from BICEP2 and Keck Array Cosmic Microwave Background Data with Inclusion of 95 GHz Band
journal, January 2016
- Ade, P. A. R.; Ahmed, Z.; Aikin, R. W.
- Physical Review Letters, Vol. 116, Issue 3
Learning the hidden structure of speech
journal, April 1988
- Elman, Jeffrey L.; Zipser, David
- The Journal of the Acoustical Society of America, Vol. 83, Issue 4
Deep Residual Learning for Image Recognition
conference, June 2016
- He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Measurements of the Temperature and E-mode Polarization of the CMB from 500 Square Degrees of SPTpol Data
journal, January 2018
- Henning, J. W.; Sayre, J. T.; Reichardt, C. L.
- The Astrophysical Journal, Vol. 852, Issue 2
NINE-YEAR WILKINSON MICROWAVE ANISOTROPY PROBE ( WMAP ) OBSERVATIONS: COSMOLOGICAL PARAMETER RESULTS
journal, September 2013
- Hinshaw, G.; Larson, D.; Komatsu, E.
- The Astrophysical Journal Supplement Series, Vol. 208, Issue 2
Reducing the Dimensionality of Data with Neural Networks
journal, July 2006
- Hinton, G. E.
- Science, Vol. 313, Issue 5786
Reconstruction of lensing from the cosmic microwave background polarization
journal, October 2003
- Hirata, Christopher M.; Seljak, Uroš
- Physical Review D, Vol. 68, Issue 8
Weak lensing of the CMB: A harmonic approach
journal, July 2000
- Hu, Wayne
- Physical Review D, Vol. 62, Issue 4
Mass Reconstruction with Cosmic Microwave Background Polarization
journal, August 2002
- Hu, Wayne; Okamoto, Takemi
- The Astrophysical Journal, Vol. 574, Issue 2
A Probe of Primordial Gravity Waves and Vorticity
journal, March 1997
- Kamionkowski, Marc; Kosowsky, Arthur; Stebbins, Albert
- Physical Review Letters, Vol. 78, Issue 11
MEASUREMENTS OF SUB-DEGREE B -MODE POLARIZATION IN THE COSMIC MICROWAVE BACKGROUND FROM 100 SQUARE DEGREES OF SPTPOL DATA
journal, July 2015
- Keisler, R.; Hoover, S.; Harrington, N.
- The Astrophysical Journal, Vol. 807, Issue 2
Lensing reconstruction with CMB temperature and polarization
journal, June 2003
- Kesden, Michael; Cooray, Asantha; Kamionkowski, Marc
- Physical Review D, Vol. 67, Issue 12
Cosmological parameters from the first results of Boomerang
journal, January 2001
- Lange, A. E.; Ade, P. A. R.; Bock, J. J.
- Physical Review D, Vol. 63, Issue 4
Weak gravitational lensing of the CMB
journal, June 2006
- Lewis, A.; Challinor, A.
- Physics Reports, Vol. 429, Issue 1
Efficient Computation of Cosmic Microwave Background Anisotropies in Closed Friedmann‐Robertson‐Walker Models
journal, August 2000
- Lewis, Antony; Challinor, Anthony; Lasenby, Anthony
- The Astrophysical Journal, Vol. 538, Issue 2
The Atacama Cosmology Telescope: two-season ACTPol spectra and parameters
journal, June 2017
- Louis, Thibaut; Grace, Emily; Hasselfield, Matthew
- Journal of Cosmology and Astroparticle Physics, Vol. 2017, Issue 06
CMB Polarization B -mode Delensing with SPTpol and Herschel
journal, August 2017
- Manzotti, A.; Story, K. T.; Wu, W. L. K.
- The Astrophysical Journal, Vol. 846, Issue 1
Measurement of the cosmic microwave background spectrum by the COBE FIRAS instrument
journal, January 1994
- Mather, J. C.; Cheng, E. S.; Cottingham, D. A.
- The Astrophysical Journal, Vol. 420
Mission Design of LiteBIRD
journal, January 2014
- Matsumura, T.; Akiba, Y.; Borrill, J.
- Journal of Low Temperature Physics, Vol. 176, Issue 5-6
A high-bias, low-variance introduction to Machine Learning for physicists
journal, May 2019
- Mehta, Pankaj; Bukov, Marin; Wang, Ching-Hao
- Physics Reports, Vol. 810
Bayesian delensing of CMB temperature and polarization
journal, July 2019
- Millea, Marius; Anderes, Ethan; Wandelt, Benjamin D.
- Physical Review D, Vol. 100, Issue 2
A 2500 deg 2 CMB Lensing Map from Combined South Pole Telescope and Planck Data
journal, November 2017
- Omori, Y.; Chown, R.; Simard, G.
- The Astrophysical Journal, Vol. 849, Issue 2
DeepSphere: Efficient spherical convolutional neural network with HEALPix sampling for cosmological applications
journal, April 2019
- Perraudin, N.; Defferrard, M.; Kacprzak, T.
- Astronomy and Computing, Vol. 27
Planck 2015 results : XIII. Cosmological parameters
journal, September 2016
- Ade, P. A. R.; Aghanim, N.; Arnaud, M.
- Astronomy & Astrophysics, Vol. 594
Planck 2015 results : XV. Gravitational lensing
journal, September 2016
- Ade, P. A. R.; Aghanim, N.; Arnaud, M.
- Astronomy & Astrophysics, Vol. 594
A Measurement of the Cosmic Microwave Background B -mode Polarization Power Spectrum at Subdegree Scales from Two Years of polarbear Data
journal, October 2017
- Ade, P. A. R.; Aguilar, M.; Akiba, Y.
- The Astrophysical Journal, Vol. 848, Issue 2
U-Net: Convolutional Networks for Biomedical Image Segmentation
book, November 2015
- Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas
- Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III
Signature of Gravity Waves in the Polarization of the Microwave Background
journal, March 1997
- Seljak, Uros̆; Zaldarriaga, Matias
- Physical Review Letters, Vol. 78, Issue 11
Two-season Atacama Cosmology Telescope polarimeter lensing power spectrum
journal, June 2017
- Sherwin, Blake D.; van Engelen, Alexander; Sehgal, Neelima
- Physical Review D, Vol. 95, Issue 12
Mastering the game of Go without human knowledge
journal, October 2017
- Silver, David; Schrittwieser, Julian; Simonyan, Karen
- Nature, Vol. 550, Issue 7676
Delensing CMB polarization with external datasets
journal, June 2012
- Smith, Kendrick M.; Hanson, Duncan; LoVerde, Marilena
- Journal of Cosmology and Astroparticle Physics, Vol. 2012, Issue 06
A Measurement of the Cosmic Microwave Background Gravitational Lensing Potential from 100 Square Degrees of Sptpol data
journal, August 2015
- Story, K. T.; Hanson, D.; Ade, P. A. R.
- The Astrophysical Journal, Vol. 810, Issue 1
The Simons Observatory: science goals and forecasts
journal, February 2019
- Ade, Peter; Aguirre, James; Ahmed, Zeeshan
- Journal of Cosmology and Astroparticle Physics, Vol. 2019, Issue 02
A Guide to Designing Future Ground-Based Cosmic Microwave Background Experiments
journal, June 2014
- Wu, W. L. K.; Errard, J.; Dvorkin, C.
- The Astrophysical Journal, Vol. 788, Issue 2
A guide to convolution arithmetic for deep learning
preprint, January 2016
- Dumoulin, Vincent; Visin, Francesco
- arXiv
Self-Normalizing Neural Networks
text, January 2017
- Klambauer, Günter; Unterthiner, Thomas; Mayr, Andreas
- arXiv
Bayesian delensing of CMB temperature and polarization
text, January 2017
- Millea, Marius; Anderes, Ethan; Wandelt, Benjamin D.
- arXiv
Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
preprint, January 2017
- de Bezenac, Emmanuel; Pajot, Arthur; Gallinari, Patrick
- arXiv
Averaging Weights Leads to Wider Optima and Better Generalization
preprint, January 2018
- Izmailov, Pavel; Podoprikhin, Dmitrii; Garipov, Timur
- arXiv
Works referencing / citing this record:
Learning to predict the cosmological structure formation
journal, June 2019
- He, Siyu; Li, Yin; Feng, Yu
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 28
Learning to Predict the Cosmological Structure Formation
text, January 2018
- He, Siyu; Li, Yin; Feng, Yu
- arXiv
Figures / Tables found in this record: