skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding

Abstract

Galaxy-scale strong gravitational lensing can not only provide a valuable probe of the dark matter distribution of massive galaxies, but also provide valuable cosmological constraints, either by studying the population of strong lenses or by measuring time delays in lensed quasars. Due to the rarity of galaxy-scale strongly lensed systems, fast and reliable automated lens finding methods will be essential in the era of large surveys such as Large Synoptic Survey Telescope, Euclid and Wide-Field Infrared Survey Telescope. To tackle this challenge, we introduce CMU DeepLens, a new fully automated galaxy-galaxy lens finding method based on deep learning. This supervised machine learning approach does not require any tuning after the training step which only requires realistic image simulations of strongly lensed systems. We train and validate our model on a set of 20 000 LSST-like mock observations including a range of lensed systems of various sizes and signal-to-noise ratios (S/N). We find on our simulated data set that for a rejection rate of non-lenses of 99 per cent, a completeness of 90 per cent can be achieved for lenses with Einstein radii larger than 1.4 arcsec and S/N larger than 20 on individual g-band LSST exposures. Finally, we emphasize themore » importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations. We make our code publicly available at https://github.com/McWilliamsCenter/CMUDeepLens.« less

Authors:
ORCiD logo [1];  [2];  [3];  [4];  [2];  [2]; ORCiD logo [1];  [2]
  1. McWilliams Center for Cosmology, Department of Physics, Carnegie Mellon University, Pittsburgh, PA 15213, USA
  2. School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA
  3. High Energy Physics Division, Argonne National Laboratory, Lemont, IL 60439, USA; Department of Astronomy & Astrophysics, The University of Chicago, 5640 South Ellis Avenue, Chicago, IL 60637, USA
  4. Institute of Cosmology and Gravitation, University of Portsmouth, Burnaby Rd, Portsmouth, PO1 3FX, UK
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science - Office of High Energy Physics; National Science Foundation (NSF)
OSTI Identifier:
1476451
DOE Contract Number:  
AC02-06CH11357
Resource Type:
Journal Article
Journal Name:
Monthly Notices of the Royal Astronomical Society
Additional Journal Information:
Journal Volume: 473; Journal Issue: 3; Journal ID: ISSN 0035-8711
Publisher:
Royal Astronomical Society
Country of Publication:
United States
Language:
English
Subject:
gravitational lensing: strong; methods: statistical

Citation Formats

Lanusse, François, Ma, Quanbin, Li, Nan, Collett, Thomas E., Li, Chun-Liang, Ravanbakhsh, Siamak, Mandelbaum, Rachel, and Póczos, Barnabás. CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding. United States: N. p., 2017. Web. doi:10.1093/mnras/stx1665.
Lanusse, François, Ma, Quanbin, Li, Nan, Collett, Thomas E., Li, Chun-Liang, Ravanbakhsh, Siamak, Mandelbaum, Rachel, & Póczos, Barnabás. CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding. United States. doi:10.1093/mnras/stx1665.
Lanusse, François, Ma, Quanbin, Li, Nan, Collett, Thomas E., Li, Chun-Liang, Ravanbakhsh, Siamak, Mandelbaum, Rachel, and Póczos, Barnabás. Fri . "CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding". United States. doi:10.1093/mnras/stx1665.
@article{osti_1476451,
title = {CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding},
author = {Lanusse, François and Ma, Quanbin and Li, Nan and Collett, Thomas E. and Li, Chun-Liang and Ravanbakhsh, Siamak and Mandelbaum, Rachel and Póczos, Barnabás},
abstractNote = {Galaxy-scale strong gravitational lensing can not only provide a valuable probe of the dark matter distribution of massive galaxies, but also provide valuable cosmological constraints, either by studying the population of strong lenses or by measuring time delays in lensed quasars. Due to the rarity of galaxy-scale strongly lensed systems, fast and reliable automated lens finding methods will be essential in the era of large surveys such as Large Synoptic Survey Telescope, Euclid and Wide-Field Infrared Survey Telescope. To tackle this challenge, we introduce CMU DeepLens, a new fully automated galaxy-galaxy lens finding method based on deep learning. This supervised machine learning approach does not require any tuning after the training step which only requires realistic image simulations of strongly lensed systems. We train and validate our model on a set of 20 000 LSST-like mock observations including a range of lensed systems of various sizes and signal-to-noise ratios (S/N). We find on our simulated data set that for a rejection rate of non-lenses of 99 per cent, a completeness of 90 per cent can be achieved for lenses with Einstein radii larger than 1.4 arcsec and S/N larger than 20 on individual g-band LSST exposures. Finally, we emphasize the importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations. We make our code publicly available at https://github.com/McWilliamsCenter/CMUDeepLens.},
doi = {10.1093/mnras/stx1665},
journal = {Monthly Notices of the Royal Astronomical Society},
issn = {0035-8711},
number = 3,
volume = 473,
place = {United States},
year = {2017},
month = {7}
}

Works referenced in this record:

Space Warps– II. New gravitational lens candidates from the CFHTLS discovered through citizen science
journal, November 2015

  • More, Anupreeta; Verma, Aprajita; Marshall, Philip J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 455, Issue 2
  • DOI: 10.1093/mnras/stv1965

Rotation-invariant convolutional neural networks for galaxy morphology prediction
journal, April 2015

  • Dieleman, Sander; Willett, Kyle W.; Dambre, Joni
  • Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 2
  • DOI: 10.1093/mnras/stv632

Strong Lensing by Galaxies
journal, August 2010


Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

Learning representations by back-propagating errors
journal, October 1986

  • Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J.
  • Nature, Vol. 323, Issue 6088
  • DOI: 10.1038/323533a0

Cosmology with Strong-Lensing Systems
journal, June 2015


Multilayer feedforward networks are universal approximators
journal, January 1989


The Sloan Lens ACS Survey. III. The Structure and Formation of Early‐Type Galaxies and Their Evolution since z ≈ 1
journal, October 2006

  • Koopmans, Leon V. E.; Treu, Tommaso; Bolton, Adam S.
  • The Astrophysical Journal, Vol. 649, Issue 2
  • DOI: 10.1086/505696

The CFHTLS strong lensing legacy survey: I. Survey overview and T0002 release sample
journal, October 2006


Adjusting the Outputs of a Classifier to New a Priori Probabilities: A Simple Procedure
journal, January 2002


The Sloan lens acs Survey. x. Stellar, Dynamical, and Total mass Correlations of Massive Early-Type Galaxies
journal, November 2010


Compound lensing: Einstein zig-zags and high-multiplicity lensed images
journal, December 2015

  • Collett, Thomas E.; Bacon, David J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 456, Issue 2
  • DOI: 10.1093/mnras/stv2791

Candels Multiwavelength Catalogs: Source Identification and Photometry in the Candels Ukidss Ultra-Deep Survey Field
journal, May 2013

  • Galametz, Audrey; Grazian, Andrea; Fontana, Adriano
  • The Astrophysical Journal Supplement Series, Vol. 206, Issue 2
  • DOI: 10.1088/0067-0049/206/2/10

Models of the Cosmic Horseshoe gravitational lens J10044112
journal, July 2008


Sn Refsdal: Photometry and time Delay Measurements of the First Einstein Cross Supernova
journal, March 2016


Observational selection biases in time-delay strong lensing and their impact on cosmography
journal, July 2016

  • Collett, Thomas E.; Cunnington, Steven D.
  • Monthly Notices of the Royal Astronomical Society, Vol. 462, Issue 3
  • DOI: 10.1093/mnras/stw1856

A PCA-based automated finder for galaxy-scale strong lenses
journal, June 2014


Measuring photometric redshifts using galaxy images and Deep Neural Networks
journal, July 2016


The Sloan Lens ACS Survey. IV. The Mass Density Profile of Early‐Type Galaxies out to 100 Effective Radii
journal, September 2007

  • Gavazzi, Raphael; Treu, Tommaso; Rhodes, Jason D.
  • The Astrophysical Journal, Vol. 667, Issue 1
  • DOI: 10.1086/519237

Ringfinder: Automated Detection of Galaxy-Scale Gravitational Lenses in Ground-Based Multi-Filter Imaging data
journal, April 2014


A neural network gravitational arc finder based on the Mediatrix filamentation method
journal, January 2017


Space Warps – I. Crowdsourcing the discovery of gravitational lenses
journal, November 2015

  • Marshall, Philip J.; Verma, Aprajita; More, Anupreeta
  • Monthly Notices of the Royal Astronomical Society, Vol. 455, Issue 2
  • DOI: 10.1093/mnras/stv2009

On the Possibility of Determining Hubble's Parameter and the Masses of Galaxies from the Gravitational Lens Effect
journal, September 1964


Cosmological constraints from the double source plane lens SDSSJ0946+1006
journal, July 2014

  • Collett, Thomas E.; Auger, Matthew W.
  • Monthly Notices of the Royal Astronomical Society, Vol. 443, Issue 2
  • DOI: 10.1093/mnras/stu1190

Candels: the Cosmic Assembly Near-Infrared deep Extragalactic Legacy Survey
journal, December 2011

  • Grogin, Norman A.; Kocevski, Dale D.; Faber, S. M.
  • The Astrophysical Journal Supplement Series, Vol. 197, Issue 2
  • DOI: 10.1088/0067-0049/197/2/35

Gradient-based learning applied to document recognition
journal, January 1998

  • Lecun, Y.; Bottou, L.; Bengio, Y.
  • Proceedings of the IEEE, Vol. 86, Issue 11
  • DOI: 10.1109/5.726791

The first and second data releases of the Kilo-Degree Survey
journal, October 2015

  • de Jong, Jelte T. A.; Verdoes Kleijn, Gijs A.; Boxhoorn, Danny R.
  • Astronomy & Astrophysics, Vol. 582
  • DOI: 10.1051/0004-6361/201526601

Arcfinder: an algorithm for the automatic detection of gravitational arcs
journal, June 2007


H0LiCOW – V. New COSMOGRAIL time delays of HE 0435−1223: H 0 to 3.8 per cent precision from strong lensing in a flat ΛCDM model
journal, November 2016

  • Bonvin, V.; Courbin, F.; Suyu, S. H.
  • Monthly Notices of the Royal Astronomical Society, Vol. 465, Issue 4
  • DOI: 10.1093/mnras/stw3006

Dissecting the Gravitational lens B1608+656. ii. Precision Measurements of the Hubble Constant, Spatial Curvature, and the dark Energy Equation of State
journal, February 2010


The Sloan Lens ACS Survey. I. A Large Spectroscopically Selected Sample of Massive Early‐Type Lens Galaxies
journal, February 2006

  • Bolton, Adam S.; Burles, Scott; Koopmans, Leon V. E.
  • The Astrophysical Journal, Vol. 638, Issue 2
  • DOI: 10.1086/498884

A method to search for strong galaxy–galaxy lenses in optical imaging surveys
journal, April 2008


Pics: Simulations of Strong Gravitational Lensing in Galaxy Clusters
journal, August 2016


Two-dimensional kinematics of SLACS lenses - III. Mass structure and dynamics of early-type lens galaxies beyond z ≃ 0.1: 2D kinematics of SLACS lenses - III
journal, May 2011

  • Barnabè, Matteo; Czoske, Oliver; Koopmans, Léon V. E.
  • Monthly Notices of the Royal Astronomical Society, Vol. 415, Issue 3
  • DOI: 10.1111/j.1365-2966.2011.18842.x

The Population of Galaxy–Galaxy Strong Lenses in Forthcoming Optical Imaging Surveys
journal, September 2015


An atlas of predicted exotic gravitational lenses
journal, October 2009


Star–galaxy classification using deep convolutional neural networks
journal, October 2016

  • Kim, Edward J.; Brunner, Robert J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 464, Issue 4
  • DOI: 10.1093/mnras/stw2672

Quiescent Compact Galaxies at Intermediate Redshift in the Cosmos Field. ii. the Fundamental Plane of Massive Galaxies
journal, June 2015


Automated Detection of Galaxy-Scale Gravitational Lenses in High-Resolution Imaging data
journal, March 2009

  • Marshall, Philip J.; Hogg, David W.; Moustakas, Leonidas A.
  • The Astrophysical Journal, Vol. 694, Issue 2
  • DOI: 10.1088/0004-637X/694/2/924

The Cfhtls-Strong Lensing Legacy Survey (Sl2s): Investigating the Group-Scale Lenses with the Sarcs Sample
journal, March 2012