DeepShadows: Separating low surface brightness galaxies from artifacts using deep learning

Tanoglidis, Dimitrios; Ćiprijanović, Aleksandra; Drlica-Wagner, Alex

doi:10.1016/j.ascom.2021.100469

DeepShadows: Separating low surface brightness galaxies from artifacts using deep learning

Journal Article · Fri Apr 16 00:00:00 EDT 2021 · Astronomy and Computing

DOI:https://doi.org/10.1016/j.ascom.2021.100469· OSTI ID:1764078

^[1]; ^[2]; ^[3]

Univ. of Chicago, IL (United States)
Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
Univ. of Chicago, IL (United States); Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)

Searches for low-surface-brightness galaxies (LSBGs) in galaxy surveys are plagued by the presence of a large number of artifacts (e.g., objects blended in the diffuse light from stars and galaxies, Galactic cirrus, star-forming regions in the arms of spiral galaxies, etc.) that have to be rejected through time consuming visual inspection. In future surveys, which are expected to collect hundreds of petabytes of data and detect billions of objects, such an approach will not be feasible. We investigate the use of convolutional neural networks (CNNs) for the problem of separating LSBGs from artifacts in survey images. We take advantage of the fact that we have available a large number of labeled LSBGs and artifacts from the Dark Energy Survey, that we use to train, validate, and test a CNN model. That model, which we call DeepShadows , achieves a test accuracy of 92.0%, a significant improvement relative to feature-based machine learning models. We also study the ability to use transfer learning to adapt this model to classify objects from the deeper Hyper-Suprime-Cam survey, and we show that after the model is retrained on a very small sample from the new survey, it can reach an accuracy of 87.6%. Finally, these results demonstrate that CNNs offer a very promising path in the quest to study the low-surface-brightness universe.

View Accepted Manuscript (DOE)

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

Sponsoring Organization:: National Science Foundation (NSF); USDOE Office of Science (SC), High Energy Physics (HEP)

Grant/Contract Number:: AC02-07CH11359

OSTI ID:: 1764078

Report Number(s):: FERMILAB-PUB--20-621-AE-LDRD-SCD; arXiv:2011.12437; oai:inspirehep.net:1832838

Journal Information:: Astronomy and Computing, Journal Name: Astronomy and Computing Vol. 35; ISSN 2213-1337

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (50)

Support-vector networks Cortes, Corinna; Vapnik, Vladimir Machine Learning, Vol. 20, Issue 3 https://doi.org/10.1007/BF00994018	journal	September 1995
DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks Caldeira, J.; Wu, W. L. K.; Nord, B. Astronomy and Computing, Vol. 28 https://doi.org/10.1016/j.ascom.2019.100307	journal	July 2019
DeepMerge: Classifying high-redshift merging galaxies with deep neural networks Ćiprijanović, A.; Snyder, G. F.; Nord, B. Astronomy and Computing, Vol. 32 https://doi.org/10.1016/j.ascom.2020.100390	journal	July 2020
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
The Fornax Deep Survey with VST: III. Low surface brightness dwarfs and ultra diffuse galaxies in the center of the Fornax cluster Venhola, Aku; Peletier, Reynier; Laurikainen, Eija Astronomy & Astrophysics, Vol. 608 https://doi.org/10.1051/0004-6361/201730696	journal	December 2017
The Fornax Deep Survey with the VST: IV. A size and magnitude limited catalog of dwarf galaxies in the area of the Fornax cluster⋆ Venhola, Aku; Peletier, Reynier; Laurikainen, Eija Astronomy & Astrophysics, Vol. 620 https://doi.org/10.1051/0004-6361/201833933	journal	December 2018
A deep wide survey of faint low surface brightness galaxies in the direction of the Coma cluster of galaxies Adami, C.; Scheidegger, R.; Ulmer, M. Astronomy & Astrophysics, Vol. 459, Issue 3 https://doi.org/10.1051/0004-6361:20053758	journal	September 2006
SExtractor: Software for source extraction Bertin, E.; Arnouts, S. Astronomy and Astrophysics Supplement Series, Vol. 117, Issue 2 https://doi.org/10.1051/aas:1996164	journal	June 1996
The central region of the Fornax cluster: I. A catalog and photometric properties of galaxies in selected CCD fields Hilker, M.; Kissler-Patig, M.; Richtler, T. Astronomy and Astrophysics Supplement Series, Vol. 134, Issue 1 https://doi.org/10.1051/aas:1999433	journal	January 1999
The Number Density of Low-Surface Brightness Galaxies with 23 < mu_0 < 25 V Mag/arcsec^2. Dalcanton, Julianne J.; Spergel, David N.; Gunn, James E. The Astronomical Journal, Vol. 114 https://doi.org/10.1086/118499	journal	August 1997
The Observed Properties of Dwarf Galaxies in and Around the Local Group McConnachie, Alan W. The Astronomical Journal, Vol. 144, Issue 1 https://doi.org/10.1088/0004-6256/144/1/4	journal	June 2012
The dark Energy Camera Flaugher, B.; Diehl, H. T.; Honscheid, K. The Astronomical Journal, Vol. 150, Issue 5 https://doi.org/10.1088/0004-6256/150/5/150	journal	October 2015
A Parameterized Galaxy Catalog Simulator for Testing Cluster Finding, mass Estimation, and Photometric Redshift Estimation in Optical and Near-Infrared Surveys Song, Jeeseon; Mohr, Joseph J.; Barkhouse, Wayne A. The Astrophysical Journal, Vol. 747, Issue 1 https://doi.org/10.1088/0004-637X/747/1/58	journal	February 2012
THE PAndAS VIEW OF THE ANDROMEDA SATELLITE SYSTEM. I. A BAYESIAN SEARCH FOR DWARF GALAXIES USING SPATIAL AND COLOR-MAGNITUDE INFORMATION Martin, Nicolas F.; Ibata, Rodrigo A.; McConnachie, Alan W. The Astrophysical Journal, Vol. 776, Issue 2 https://doi.org/10.1088/0004-637X/776/2/80	journal	October 2013
A General Approach to Domain Adaptation with Applications in Astronomy Vilalta, Ricardo; Gupta, Kinjal Dhar; Boumber, Dainis Publications of the Astronomical Society of the Pacific, Vol. 131, Issue 1004 https://doi.org/10.1088/1538-3873/aaf1fc	journal	September 2019
Transfer Learning in Astronomy: A New Machine-Learning Paradigm Vilalta, Ricardo Journal of Physics: Conference Series, Vol. 1085 https://doi.org/10.1088/1742-6596/1085/5/052014	journal	September 2018
Forty-Seven Milky Way-Sized, Extremely Diffuse Galaxies in the coma Cluster van Dokkum, Pieter G.; Abraham, Roberto; Merritt, Allison The Astrophysical Journal, Vol. 798, Issue 2 https://doi.org/10.1088/2041-8205/798/2/L45	journal	January 2015
Galaxies at the Extremes: Ultra-Diffuse Galaxies in the Virgo Cluster Mihos, J. Christopher; Durrell, Patrick R.; Ferrarese, Laura The Astrophysical Journal, Vol. 809, Issue 2 https://doi.org/10.1088/2041-8205/809/2/L21	journal	August 2015
Unveiling a rich System of Faint Dwarf Galaxies in the next Generation Fornax Survey Muñoz, Roberto P.; Eigenthaler, Paul; Puzia, Thomas H. The Astrophysical Journal, Vol. 813, Issue 1 https://doi.org/10.1088/2041-8205/813/1/L15	journal	October 2015
Deep transfer learning for star cluster classification: I. application to the PHANGS– HST survey Wei, Wei; Huerta, E. A.; Whitmore, Bradley C. Monthly Notices of the Royal Astronomical Society, Vol. 493, Issue 3 https://doi.org/10.1093/mnras/staa325	journal	February 2020
Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging Cheng, Ting-Yun; Conselice, Christopher J.; Aragón-Salamanca, Alfonso Monthly Notices of the Royal Astronomical Society, Vol. 493, Issue 3 https://doi.org/10.1093/mnras/staa501	journal	February 2020
No galaxy left behind: accurate measurements with the faintest objects in the Dark Energy Survey Suchyta, E.; Huff, E. M.; Aleksić, J. Monthly Notices of the Royal Astronomical Society, Vol. 457, Issue 1 https://doi.org/10.1093/mnras/stv2953	journal	January 2016
Rotation-invariant convolutional neural networks for galaxy morphology prediction Dieleman, Sander; Willett, Kyle W.; Dambre, Joni Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 2 https://doi.org/10.1093/mnras/stv632	journal	April 2015
Star–galaxy classification using deep convolutional neural networks Kim, Edward J.; Brunner, Robert J. Monthly Notices of the Royal Astronomical Society, Vol. 464, Issue 4 https://doi.org/10.1093/mnras/stw2672	journal	October 2016
CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding Lanusse, François; Ma, Quanbin; Li, Nan Monthly Notices of the Royal Astronomical Society, Vol. 473, Issue 3 https://doi.org/10.1093/mnras/stx1665	journal	July 2017
Using transfer learning to detect galaxy mergers Ackermann, Sandro; Schawinski, Kevin; Zhang, Ce Monthly Notices of the Royal Astronomical Society, Vol. 479, Issue 1 https://doi.org/10.1093/mnras/sty1398	journal	May 2018
Improving galaxy morphologies for SDSS with Deep Learning Domínguez Sánchez, H.; Huertas-Company, M.; Bernardi, M. Monthly Notices of the Royal Astronomical Society, Vol. 476, Issue 3 https://doi.org/10.1093/mnras/sty338	journal	February 2018
Transfer learning for galaxy morphology from one survey to another Domínguez Sánchez, H.; Huertas-Company, M.; Bernardi, M. Monthly Notices of the Royal Astronomical Society, Vol. 484, Issue 1 https://doi.org/10.1093/mnras/sty3497	journal	December 2018
Using convolutional neural networks to identify gravitational lenses in astronomical images Davies, Andrew; Serjeant, Stephen; Bromley, Jane M. Monthly Notices of the Royal Astronomical Society, Vol. 487, Issue 4 https://doi.org/10.1093/mnras/stz1288	journal	May 2019
Weak lensing cosmology with convolutional neural networks on noisy data Ribli, Dezső; Pataki, Bálint Ármin; Zorrilla Matilla, José Manuel Monthly Notices of the Royal Astronomical Society, Vol. 490, Issue 2 https://doi.org/10.1093/mnras/stz2610	journal	September 2019
Finding high-redshift strong lenses in DES using convolutional neural networks Jacobs, C.; Collett, T.; Glazebrook, K. Monthly Notices of the Royal Astronomical Society, Vol. 484, Issue 4 https://doi.org/10.1093/mnras/stz272	journal	January 2019
Eliminating artefacts in polarimetric images using deep learning Paranjpye, D.; Mahabal, A.; Ramaprakash, A. N. Monthly Notices of the Royal Astronomical Society, Vol. 491, Issue 4 https://doi.org/10.1093/mnras/stz3250	journal	November 2019
The formation and evolution of low-surface-brightness galaxies Martin, G.; Kaviraj, S.; Laigle, C. Monthly Notices of the Royal Astronomical Society, Vol. 485, Issue 1 https://doi.org/10.1093/mnras/stz356	journal	February 2019
Classification and unsupervised clustering of LIGO data with Deep Transfer Learning George, Daniel; Shen, Hongyu; Huerta, E. A. Physical Review D, Vol. 97, Issue 10 https://doi.org/10.1103/PhysRevD.97.101501	journal	May 2018
A Survey on Transfer Learning Pan, Sinno Jialin; Yang, Qiang IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10 https://doi.org/10.1109/TKDE.2009.191	journal	October 2010
Classification in the Presence of Label Noise: A Survey Frenay, Benoit; Verleysen, Michel IEEE Transactions on Neural Networks and Learning Systems, Vol. 25, Issue 5 https://doi.org/10.1109/TNNLS.2013.2292894	journal	May 2014
The dwarf low surface brightness galaxy population of the Virgo Cluster - II. Colours and H i line observations Sabatini, S.; Davies, J.; van Driel, W. Monthly Notices of the Royal Astronomical Society, Vol. 357, Issue 3 https://doi.org/10.1111/j.1365-2966.2005.08608.x	journal	March 2005
Data Mining and Machine Learning in Astronomy Ball, Nicholas M.; Brunner, Robert J. International Journal of Modern Physics D, Vol. 19, Issue 07 https://doi.org/10.1142/S0218271810017160	journal	July 2010
The Connection Between Galaxies and Their Dark Matter Halos Wechsler, Risa H.; Tinker, Jeremy L. Annual Review of Astronomy and Astrophysics, Vol. 56, Issue 1 https://doi.org/10.1146/annurev-astro-081817-051756	journal	September 2018
A survey of transfer learning Weiss, Karl; Khoshgoftaar, Taghi M.; Wang, DingDing Journal of Big Data, Vol. 3, Issue 1 https://doi.org/10.1186/s40537-016-0043-6	journal	May 2016
A survey on Image Data Augmentation for Deep Learning Shorten, Connor; Khoshgoftaar, Taghi M. Journal of Big Data, Vol. 6, Issue 1 https://doi.org/10.1186/s40537-019-0197-0	journal	July 2019
Overview of the DESI Legacy Imaging Surveys Dey, Arjun; Schlegel, David J.; Lang, Dustin The Astronomical Journal, Vol. 157, Issue 5 https://doi.org/10.3847/1538-3881/ab089d	journal	April 2019
The Dragonfly Nearby Galaxies Survey. ii. Ultra-Diffuse Galaxies near the Elliptical Galaxy ngc 5485 Merritt, Allison; van Dokkum, Pieter; Danieli, Shany The Astrophysical Journal, Vol. 833, Issue 2 https://doi.org/10.3847/1538-4357/833/2/168	journal	December 2016
The Burrell Schmidt deep Virgo Survey: Tidal Debris, Galaxy Halos, and Diffuse Intracluster Light in the Virgo Cluster Mihos, J. Christopher; Harding, Paul; Feldmeier, John J. The Astrophysical Journal, Vol. 834, Issue 1 https://doi.org/10.3847/1538-4357/834/1/16	journal	December 2016
The Dragonfly Nearby Galaxies Survey. III. The Luminosity Function of the M101 Group Danieli, Shany; van Dokkum, Pieter; Merritt, Allison The Astrophysical Journal, Vol. 837, Issue 2 https://doi.org/10.3847/1538-4357/aa615b	journal	March 2017
Illuminating Low Surface Brightness Galaxies with the Hyper Suprime-Cam Survey Greco, Johnny P.; Greene, Jenny E.; Strauss, Michael A. The Astrophysical Journal, Vol. 857, Issue 2 https://doi.org/10.3847/1538-4357/aab842	journal	April 2018
The Dragonfly Nearby Galaxies Survey. V. HST /ACS Observations of 23 Low Surface Brightness Objects in the Fields of NGC 1052, NGC 1084, M96, and NGC 4258 Cohen, Yotam; Dokkum, Pieter van; Danieli, Shany The Astrophysical Journal, Vol. 868, Issue 2 https://doi.org/10.3847/1538-4357/aae7c8	journal	November 2018
The Dark Energy Survey: Data Release 1 Abbott, T. M. C.; Abdalla, F. B.; Allam, S. The Astrophysical Journal Supplement Series, Vol. 239, Issue 2 https://doi.org/10.3847/1538-4365/aae9f0	journal	November 2018
Shadows in the Dark: Low-surface-brightness Galaxies Discovered in the Dark Energy Survey Tanoglidis, D.; Drlica-Wagner, A.; Wei, K. The Astrophysical Journal Supplement Series, Vol. 252, Issue 2 https://doi.org/10.3847/1538-4365/abca89	journal	January 2021

Similar Records

Detecting Low Surface Brightness Galaxies with Mask R-CNN

Conference · Thu Dec 31 23:00:00 EST 2020 · OSTI ID:1834181

The Intrinsic Shapes of Low Surface Brightness Galaxies (LSBGs): A Discriminant of LSBG Galaxy Formation Mechanisms

Journal Article · Thu Oct 14 20:00:00 EDT 2021 · The Astrophysical Journal · OSTI ID:1983180

LSBGnet: an improved detection model for low-surface brightness galaxies

Journal Article · Thu Jan 18 19:00:00 EST 2024 · Monthly Notices of the Royal Astronomical Society · OSTI ID:2282230

Related Subjects

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
79 ASTRONOMY AND ASTROPHYSICS
convolutional neural networks
deep learning
galaxy surveys
low surface brightness galaxies

DeepShadows: Separating low surface brightness galaxies from artifacts using deep learning

Citation Formats

References (50)

Similar Records

Related Subjects