Identification of low surface brightness tidal features in galaxies using convolutional neural networks
Open accessThe DOI matches its Crossref record; 85 of the 92 references it cites were found in a registry or an index.
Abstract
Faint tidal features around galaxies record their merger and interaction histories over cosmic time. Due to their low surface brightnesses and complex morphologies, existing automated methods struggle to detect such features and most work to date has heavily relied on visual inspection. This presents a major obstacle to quantitative study of tidal debris features in large statistical samples, and hence the ability to be able to use these features to advance understanding of the galaxy population as a whole. This paper uses convolutional neural networks (CNNs) with dropout and augmentation to identify galaxies in the CFHTLS-Wide Survey that have faint tidal features. Evaluating the performance of the CNNs against previously published expert visual classifications, we find that our method achieves high (76 per cent) completeness and low (20 per cent) contamination, and also performs considerably better than other automated methods recently applied in the literature. We argue that CNNs offer a promising approach to effective automatic identification of low surface brightness tidal debris features in and around galaxies. When applied to forthcoming deep wide-field imaging surveys (e.g. LSST, Euclid), CNNs have the potential to provide a several order-of-magnitude increase in the sample size of morphologically perturbed galaxies and thereby facilitate a much-anticipated revolution in terms of quantitative low surface brightness science.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Walmsley et al. (2019) found that their method outperformed other automated methods of tidal feature detection, reaching 76% completeness (or TPR) and 22% contamination (or FPR).”
From Detecting galaxy tidal features using self-supervised representation learning (2024) · cites this paper as Walmsley et al. (2019)
In the citing paper
“They used a sample of 305 galaxies with tidal features and 1316 galaxies without tidal features, assembled by Atkinson et al. (2013), to train a CNN, using augmentations such as image flipping, rotation, and translation to expand their dataset.”
From Detecting galaxy tidal features using self-supervised representation learning (2024) · cites this paper as Walmsley et al. (2019)
In the citing paper
“The authors test a CNN model on the Dark Energy Survey data and report a ∼ 95% accuracy in separating artefacts from real LSB structures.”
From The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys (2023) · cites this paper as Walmsley et al. (2019)
In the citing paper
“Some works (e.g. Ackermann et al. 2018; Walmsley et al. 2019) have demonstrated that reliable results can be obtained with small training samples.”
From The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys (2023) · cites this paper as Walmsley et al. 2019
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“They routinely show state-of-the-art performance on various image classification benchmarks that require making discerning distinctions between classes and ignoring background effects (Russakovsky et al. 2015).”
BackgroundMatplotlib: a 2D graphics environment
Hunter, J. D. (2007) · Computing in Science & Engineering · doi:10.1109/mcse.2007.55 · Cited by 39,249 · cited 1×
“This research made use of the open-source Python scientific computing ecosystem, including SciPy (Jones et al. 01 ), Matplotlib (Hunter 2007), scikit-learn (Pedregosa et al. MNRAS 000, 1–17 (2017) 2011), scikit-image (van der Walt et al. 2014) and Pandas (McKinney 2010).”
MethodLecture Notes in Computer Science 1205
(1999) · Industrial Robot: An International Journal · doi:10.1108/ir.1999.04926fae.001 · Cited by 38,662
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Astropy: A community Python package for astronomy
The Astropy Collaboration, Robitaille, T. P., Tollerud, E. J., Greenfield, P., Droettboom, M., Bray, E., Aldcroft, T., Davis, M., Ginsburg, A., Price-Whelan, A. M., et al. (2013) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201322068 · Cited by 14,620
Data Structures for Statistical Computing in Python
McKinney, W. (2010) · Proceedings of the Python in Science Conference · doi:10.25080/majora-92bf1922-00a · Cited by 11,032 · cited 1×
“This research made use of the open-source Python scientific computing ecosystem, including SciPy (Jones et al. 01 ), Matplotlib (Hunter 2007), scikit-learn (Pedregosa et al. MNRAS 000, 1–17 (2017) 2011), scikit-image (van der Walt et al. 2014) and Pandas (McKinney 2010).”
MethodThe Astropy Project: Building an Open-science Project and Status of the v2.0 Core Package*
The Astropy Collaboration, Price-Whelan, A. M., Sipőcz, B. M., Günther, H. M., Lim, P. L., Crawford, S. M., Conseil, S., Shupe, D. L., Craig, M. W., Dencheva, N., et al. (2018) · The Astronomical Journal · doi:10.3847/1538-3881/aabc4f · Cited by 7,687
scikit-image: image processing in Python
van der Walt, S., Schönberger, J. L., Nunez-Iglesias, J., Boulogne, F., Warner, J. D., Yager, N., Gouillart, E., & Yu, T. (2014) · PeerJ · doi:10.7717/peerj.453 · Cited by 6,794
THE SEVENTH DATA RELEASE OF THE SLOAN DIGITAL SKY SURVEY
Abazajian, K. N., Adelman-McCarthy, J. K., Agüeros, M. A., Allam, S. S., Prieto, C. A., An, D., Anderson, K. S. J., Anderson, S. F., Annis, J., Bahcall, N. A., et al. (2009) · The Astrophysical Journal Supplement Series · doi:10.1088/0067-0049/182/2/543 · Cited by 5,341 · cited 1×
“When applied to a sample of 70 starburst and post-starburst galaxies imaged by the Sloan Digital Sky Survey (Abazajian et al. 2009), Pawlik et al. (2016) report an accuracy of 95% in detecting post-merger tidal features.”
MethodDeepPose: Human Pose Estimation via Deep Neural Networks
Toshev, A., & Szegedy, C. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.214 · Cited by 3,185
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.351 · Cited by 2,743
Toomre, A., & Toomre, J. (1972) · The Astrophysical Journal · doi:10.1086/151823 · Cited by 2,555 · cited 1×
“It is well established that such events leave long-lasting observational signatures in the form of low surface brightness tidal streams, shells and perturbations (e.g. Toomre & Toomre 1972; Quinn 1984; Cooper et al. 2010).”
BackgroundGalaxy formation through hierarchical clustering
White, S. D. M., & Frenk, C. S. (1991) · The Astrophysical Journal · doi:10.1086/170483 · Cited by 2,354 · cited 1×
“Hierarchical models of galaxy formation suggest that present-day galaxies assemble their mass through the repeated aggregation of smaller systems and through the smooth accretion of gas which fuels in situ star formation (e.g. White & Frenk 1991; Abadi et al. 2002).”
BackgroundUsing AUC and accuracy in evaluating learning algorithms
Huang, J., & Ling, C. X. (2005) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2005.50 · Cited by 2,148 · cited 1×
“The AUC score is frequently used in machine learning literature as a scalar summary metric of classifier quality (Huang & Ling 2005).”
MethodSecular Evolution and the Formation of Pseudobulges in Disk Galaxies
Kormendy, J., & Kennicutt, R. C. (2004) · Annual Review of Astronomy and Astrophysics · doi:10.1146/annurev.astro.42.053102.134024 · Cited by 1,732 · cited 1×
“…from resulting morphological transformations (e.g. bulge growth) can provide sensitivity to events that have occurred over longer timescales but it is often difficult to distinguish these transformations from secular processes (e.g. Hopkins et al. 2009; Kormendy & Kennicutt 2004; Conselice 2003).”
BackgroundLintott, C. J., Schawinski, K., Slosar, A., Land, K., Bamford, S., Thomas, D., Raddick, M. J., Nichol, R. C., Szalay, A., Andreescu, D., et al. (2008) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2008.13689.x · Cited by 1,488 · cited 2×
“Crowd-sourcing efforts like Galaxy Zoo (Lintott et al. 2008; Willett et al. 2013) could be an effec- tive way to accomplish this but we note that tidal features from minor mergers and accretions are often rather subtle in appearance and visual identifications typically require some degree of interactive manipulation o…”
BackgroundSelf-citationSECULAR EVOLUTION AND THE FORMATION OF PSEUDOBULGES IN DISK GALAXIES
Kormendy, J., Kennicutt, R. C., & words, K. (2004) · CERN Document Server (European Organization for Nuclear Research) · Cited by 1,133
FIRE-2 simulations: physics versus numerics in galaxy formation
Hopkins, P. F., Wetzel, A., Kereš, D., Faucher-Giguère, C.-A., Quataert, E., Boylan-Kolchin, M., Murray, N., Hayward, C. C., Garrison-Kimmel, S., Hummels, C., et al. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty1690 · Cited by 1,127 · cited 1×
“E-mail: mike.walmsley@physics.ox.ac.uk (MW) cussion in Hopkins et al. 2018), a purely empirical measure of the frequency and nature of galaxy mergers and accretions is highly desirable.”
BackgroundTransfer learning using computational intelligence: A survey
Lu, J., Behbood, V., Hao, P., Zuo, H., Xue, S., & Zhang, G. (2015) · Knowledge-Based Systems · doi:10.1016/j.knosys.2015.01.010 · Cited by 968 · cited 1×
“CNNs have tuneable design values (e.g layer count = 4, first layer width = 256) called hyperparameters (Lu et al. 2015).”
BackgroundThe Field of Streams: Sagittarius and Its Siblings
Belokurov, V., Zucker, D. B., Evans, N. W., Gilmore, G., Vidrih, S., Bramich, D. M., Newberg, H. J., Wyse, R. F. G., Irwin, M. J., Fellhauer, M., et al. (2006) · The Astrophysical Journal · doi:10.1086/504797 · Cited by 915
The Relationship between Stellar Light Distributions of Galaxies and Their Formation Histories
Conselice, C. J. (2003) · The Astrophysical Journal Supplement Series · doi:10.1086/375001 · Cited by 875 · cited 3×
“…from resulting morphological transformations (e.g. bulge growth) can provide sensitivity to events that have occurred over longer timescales but it is often difficult to distinguish these transformations from secular processes (e.g. Hopkins et al. 2009; Kormendy & Kennicutt 2004; Conselice 2003).”
BackgroundMethodA New Nonparametric Approach to Galaxy Morphological Classification
Lotz, J. M., Primack, J., & Madau, P. (2004) · The Astronomical Journal · doi:10.1086/421849 · Cited by 832 · cited 1×
“…extraction methods measure one or several hand-crafted image parameters thought to correlate with post-merger disruption (e.g. Conselice 2003; Lotz et al. 2004; Freeman et al. 2013; Pawlik et al. 2016), and then apply selection cuts or machine learning estimation to identify the most likely…”
MethodRotation-invariant convolutional neural networks for galaxy morphology prediction
Dieleman, S., Willett, K. W., & Dambre, J. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv632 · Cited by 781 · cited 5×
“Various authors (e.g. Dieleman et al. 2015; Sánchez et al. 2017) have demonstrated that CNNs can accurately classify general galaxy morphology and recently Ackermann et al. (2018) showed that CNNs can be used to identify merging galaxy pairs in SDSS Data Release 7 images (Darg et al. 2010).”
BackgroundMethodInfluentialEnsemble Machine Learning: Methods and Applications
(2012) · doi:10.1007/978-1-4419-9326-7 · Cited by 746 · cited 1×
“This information is exploited through averaging over the individual predictions (e.g. Zhang & Ma 2012).”
MethodWillett, K. W., Lintott, C. J., Bamford, S. P., Masters, K. L., Simmons, B. D., Casteels, K. R. V., Edmondson, E. M., Fortson, L. F., Kaviraj, S., Keel, W. C., et al. (2013) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stt1458 · Cited by 659 · cited 2×
“Crowd-sourcing efforts like Galaxy Zoo (Lintott et al. 2008; Willett et al. 2013) could be an effec- tive way to accomplish this but we note that tidal features from minor mergers and accretions are often rather subtle in appearance and visual identifications typically require some degree of…”
BackgroundSelf-citationGalactic stellar haloes in the CDM model
Cooper, A. P., Cole, S., Frenk, C. S., White, S. D. M., Helly, J., Benson, A. J., De Lucia, G., Helmi, A., Jenkins, A., Navarro, J. F., et al. (2010) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2010.16740.x · Cited by 594 · cited 1×
“It is well established that such events leave long-lasting observational signatures in the form of low surface brightness tidal streams, shells and perturbations (e.g. Toomre & Toomre 1972; Quinn 1984; Cooper et al. 2010).”
BackgroundThe Evolution of Galaxy Structure Over Cosmic Time
Conselice, C. J. (2014) · Annual Review of Astronomy and Astrophysics · doi:10.1146/annurev-astro-081913-040037 · Cited by 489 · cited 1×
“First, following Conselice (2003) and Conselice (2014), the minimal asymmetry centroid is identified and asymmetry parameter A is recorded.”
Rodriguez-Gomez, V., Pillepich, A., Sales, L. V., Genel, S., Vogelsberger, M., Zhu, Q., Wellons, S., Nelson, D., Torrey, P., Springel, V., et al. (2016) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stw456 · Cited by 478 · cited 1×
“…have acquired almost all of their stars through mergers, the relative contribution of in situ star formation and directly accreted stellar mass remains an open question across much of the galaxy mass spectrum (e.g. Rodriguez-Gomez et al. 2016; Qu et al. 2017; Lee & Yi 2017; Fitts et al. 2018).”
BackgroundThe Evolution of Galaxy Mergers and Morphology at z< 1.2 in the Extended Groth Strip
Lotz, J. M., Davis, M., Faber, S. M., Guhathakurta, P., Gwyn, S., Huang, J., Koo, D. C., Le Floc’h, E., Lin, L., Newman, J., et al. (2008) · The Astrophysical Journal · doi:10.1086/523659 · Cited by 466
THE MAJOR AND MINOR GALAXY MERGER RATES AT z < 1.5
Lotz, J. M., Jonsson, P., Cox, T. J., Croton, D., Primack, J. R., Somerville, R. S., & Stewart, K. (2011) · The Astrophysical Journal · doi:10.1088/0004-637x/742/2/103 · Cited by 450 · cited 3×
“Furthermore, the rates of major (mass ratio ≥1:4) and minor merger events, and their role in shaping various galaxy components, are also not yet well understood (e.g. Lotz et al. 2011; Martin et al. 2017; Lofthouse et al. 2017).”
BackgroundMethodGalaxy merger morphologies and time-scales from simulations of equal-mass gas-rich disc mergers
Lotz, J. M., Jonsson, P., Cox, T. J., & Primack, J. R. (2008) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2008.14004.x · Cited by 442 · cited 2×
“G A ] 2 8 N ov problem stems from the fact that morphological merger signatures only persist for a finite duration after an interaction has taken place, with the exact timescale dependent on the details of the orbital interaction as well as the properties of the host galaxy (Lotz et al. 2008a).”
BackgroundMethodAbadi, M. G., Navarro, J. F., Steinmetz, M., & Eke, V. R. (2003) · The Astrophysical Journal · doi:10.1086/375512 · Cited by 432
Johnston, K. V., Bullock, J. S., Sharma, S., Font, A., Robertson, B. E., & Leitner, S. N. (2008) · The Astrophysical Journal · doi:10.1086/592228 · Cited by 416 · cited 1×
“Individual tidal features can be simulated in exquisite detail (e.g. Johnston et al. 2008; Hendel & Johnston 2015 and large-scale hydrodynamical simulations of galaxy formation now have the resolution to resolve these features in populations of several thousand galaxies (e.g. Pop et al. 2017).”
BackgroundCFHTLenS: the Canada–France–Hawaii Telescope Lensing Survey – imaging data and catalogue products
Erben, T., Hildebrandt, H., Miller, L., van Waerbeke, L., Heymans, C., Hoekstra, H., Kitching, T. D., Mellier, Y., Benjamin, J., Blake, C., et al. (2013) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stt928 · Cited by 412
The Recent and Continuing Assembly of Field Elliptical Galaxies by Red Mergers
van Dokkum, P. G. (2005) · The Astronomical Journal · doi:10.1086/497593 · Cited by 407 · cited 1×
“Model subtraction methods work by removing the expected flux using a parametric light profile and then quantifying the amount of residual light (e.g. van Dokkum 2005; Tal et al. 2009; Adams et al. 2012).”
MethodMartínez-Delgado, D., Gabany, R. J., Crawford, K., Zibetti, S., Majewski, S. R., Rix, H.-W., Fliri, J., Carballo-Bello, J. A., Bardalez-Gagliuffi, D. C., Peñarrubia, J., et al. (2010) · The Astronomical Journal · doi:10.1088/0004-6256/140/4/962 · Cited by 396
Data mining and machine learning in astronomy
BALL, N. M., & BRUNNER, R. J. (2010) · International Journal of Modern Physics D · doi:10.1142/s0218271810017160 · Cited by 383
Improving galaxy morphologies for SDSS with Deep Learning
Domínguez Sánchez, H., Huertas-Company, M., Bernardi, M., Tuccillo, D., & Fischer, J. L. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty338 · Cited by 382
Duc, P.-A., Cuillandre, J.-C., Karabal, E., Cappellari, M., Alatalo, K., Blitz, L., Bournaud, F., Bureau, M., Crocker, A. F., Davies, R. L., et al. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stu2019 · Cited by 352 · cited 1×
“Indeed, much stellar substructure of this nature has already been detected in the peripheral regions of the Milky Way (e.g. Belokurov et al. 2006), M31 (see the review by Ferguson & Mackey (2016)), and other nearby galaxies (e.g. Mart́ınez-Delgado et al. 2010; Duc et al. 2015).”
BackgroundA catalog of elliptical galaxies with shells
Malin, D. F., & Carter, D. (1983) · The Astrophysical Journal · doi:10.1086/161467 · Cited by 329 · cited 1×
“Most work to date has focused on visual inspection of individual galaxies or relatively small samples (e.g. Malin & Carter 1983; Mart́ınez-Delgado et al. 2010; Sheen et al. 2012), often on images that have been specifically manipulated in order to enhance the appearance of low surface brightness…”
BackgroundOn the formation and dynamics of shells around elliptical galaxies
Quinn, P. J. (1984) · The Astrophysical Journal · doi:10.1086/161924 · Cited by 328 · cited 1×
“It is well established that such events leave long-lasting observational signatures in the form of low surface brightness tidal streams, shells and perturbations (e.g. Toomre & Toomre 1972; Quinn 1984; Cooper et al. 2010).”
BackgroundSupporting user-oriented analysis for multi-view domain-specific visual languages
Guerra, E., de Lara, J., Malizia, A., & Díaz, P. (2009) · Information and Software Technology · doi:10.1016/j.infsof.2008.09.005 · Cited by 322
Fossil Signatures of Ancient Accretion Events in the Halo
Johnston, K. V., Hernquist, L., & Bolte, M. (1996) · The Astrophysical Journal · doi:10.1086/177418 · Cited by 294 · cited 1×
“In galaxy outskirts, where the dynamical timescales are several gigayears or longer, these features are predicted to be particularly apparent (Johnston et al. 1996; Cooper et al. 2013).”
BackgroundA CATALOG OF VISUAL-LIKE MORPHOLOGIES IN THE 5 CANDELS FIELDS USING DEEP LEARNING
Huertas-Company, M., Gravet, R., Cabrera-Vives, G., Pérez-González, P. G., Kartaltepe, J. S., Barro, G., Bernardi, M., Mei, S., Shankar, F., Dimauro, P., et al. (2015) · The Astrophysical Journal Supplement Series · doi:10.1088/0067-0049/221/1/8 · Cited by 285 · cited 2×
“CNNs are typically applied to samples of 104 to 1010 images - see for example, Simonyan & Zisserman (2014); Dieleman et al. (2015); Huertas-Company et al. (2015); Kim & Brunner (2017) and Petrillo et al. (2017) - while our CFHTLS-Wide sample contains only 1621 galaxies, of which a mere 305 have…”
BackgroundMethodTal, T., van Dokkum, P. G., Nelan, J., & Bezanson, R. (2009) · The Astronomical Journal · doi:10.1088/0004-6256/138/5/1417 · Cited by 274 · cited 1×
“Model subtraction methods work by removing the expected flux using a parametric light profile and then quantifying the amount of residual light (e.g. van Dokkum 2005; Tal et al. 2009; Adams et al. 2012).”
MethodWND-CHARM: Multi-purpose image classification using compound image transforms
Orlov, N., Shamir, L., Macura, T., Johnston, J., Eckley, D. M., & Goldberg, I. G. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.04.013 · Cited by 265 · cited 13×
“To provide a fair comparison, we train and test WND-CHARM on subsets of 25,000 images preprocessed and augmented through the same procedure.”
BackgroundMethodInfluentialOn the Consistency of Multiclass Classification Methods
Tewari, A., & Bartlett, P. L. (2005) · Lecture Notes in Computer Science · doi:10.1007/11503415_10 · Cited by 228
Star–galaxy classification using deep convolutional neural networks
Kim, E. J., & Brunner, R. J. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stw2672 · Cited by 221
Hopkins, P. F., Somerville, R. S., Cox, T. J., Hernquist, L., Jogee, S., Kereš, D., Ma, C.-P., Robertson, B., & Stewart, K. (2009) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2009.14983.x · Cited by 213 · cited 1×
“…from resulting morphological transformations (e.g. bulge growth) can provide sensitivity to events that have occurred over longer timescales but it is often difficult to distinguish these transformations from secular processes (e.g. Hopkins et al. 2009; Kormendy & Kennicutt 2004; Conselice 2003).”
BackgroundDarg, D. W., Kaviraj, S., Lintott, C. J., Schawinski, K., Sarzi, M., Bamford, S., Silk, J., Andreescu, D., Murray, P., Nichol, R. C., et al. (2010) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2009.15786.x · Cited by 202 · cited 1×
“Various authors (e.g. Dieleman et al. 2015; Sánchez et al. 2017) have demonstrated that CNNs can accurately classify general galaxy morphology and recently Ackermann et al. (2018) showed that CNNs can be used to identify merging galaxy pairs in SDSS Data Release 7 images (Darg et al. 2010).”
MethodSelf-citationGalactic accretion and the outer structure of galaxies in the CDM model
Cooper, A. P., D'Souza, R., Kauffmann, G., Wang, J., Boylan-Kolchin, M., Guo, Q., Frenk, C. S., & White, S. D. M. (2013) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stt1245 · Cited by 200 · cited 1×
“In galaxy outskirts, where the dynamical timescales are several gigayears or longer, these features are predicted to be particularly apparent (Johnston et al. 1996; Cooper et al. 2013).”
BackgroundCMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding
Lanusse, F., Ma, Q., Li, N., Collett, T. E., Li, C.-L., Ravanbakhsh, S., Mandelbaum, R., & Póczos, B. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx1665 · Cited by 191 · cited 1×
“We provide here a brief overview of how these methods work and refer the interested reader to LeCun et al. (2015) and references therein for detailed descriptions of CNNs, and to Dieleman et al. (2015); Lanusse et al. (2018) and Kim & Brunner (2017) for particular astrophysical applications.”
MethodFinding strong gravitational lenses in the Kilo Degree Survey with Convolutional Neural Networks
Petrillo, C. E., Tortora, C., Chatterjee, S., Vernardos, G., Koopmans, L. V. E., Verdoes Kleijn, G., Napolitano, N. R., Covone, G., Schneider, P., Grado, A., et al. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx2052 · Cited by 187 · cited 1×
“…applied to samples of 104 to 1010 images - see for example, Simonyan & Zisserman (2014); Dieleman et al. (2015); Huertas-Company et al. (2015); Kim & Brunner (2017) and Petrillo et al. (2017) - while our CFHTLS-Wide sample contains only 1621 galaxies, of which a mere 305 have tidal features.”
MethodA chronicle of galaxy mass assembly in the EAGLE simulation
Qu, Y., Helly, J. C., Bower, R. G., Theuns, T., Crain, R. A., Frenk, C. S., Furlong, M., McAlpine, S., Schaller, M., Schaye, J., et al. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stw2437 · Cited by 186 · cited 1×
“…have acquired almost all of their stars through mergers, the relative contribution of in situ star formation and directly accreted stellar mass remains an open question across much of the galaxy mass spectrum (e.g. Rodriguez-Gomez et al. 2016; Qu et al. 2017; Lee & Yi 2017; Fitts et al. 2018).”
BackgroundKartaltepe, J. S., Sanders, D. B., Floc'h, E. L., Frayer, D. T., Aussel, H., Arnouts, S., Ilbert, O., Salvato, M., Scoville, N. Z., Surace, J., et al. (2010) · The Astrophysical Journal · doi:10.1088/0004-637x/721/1/98 · Cited by 176 · cited 1×
“These methods allow for a broader range of morphologies to be classified but can be easily confused by complex features such as spiral arms (e.g. Kartaltepe et al. 2010) and are typically only sensitive to certain major merger stages (Lotz et al. 2008b, 2011; Snyder et al. 2015).”
MethodChristensen, N. L., Meyer, R., Knox, L., & Luey, B. (2000) · Cited by 170
Pawlik, M. M., Wild, V., Walcher, C. J., Johansson, P. H., Villforth, C., Rowlands, K., Mendez-Abreu, J., & Hewlett, T. (2016) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv2878 · Cited by 163 · cited 7×
“…methods recently applied in the literature, namely the shape asymmetry method, a nonparametric approach developed for identifying post-merger galaxies by Pawlik et al. 2016), and WND-CHRM, a generic machine learning approach previously applied to image classification in astronomy (Shamir 2012).”
MethodInfluentialTHE CANADA-FRANCE-HAWAII TELESCOPE LEGACY SURVEY: STACKED IMAGES AND CATALOGS
Gwyn, S. D. J. (2012) · The Astronomical Journal · doi:10.1088/0004-6256/143/2/38 · Cited by 162
Using transfer learning to detect galaxy mergers
Ackermann, S., Schawinski, K., Zhang, C., Weigel, A. K., & Turp, M. D. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty1398 · Cited by 137 · cited 2×
“Various authors (e.g. Dieleman et al. 2015; Sánchez et al. 2017) have demonstrated that CNNs can accurately classify general galaxy morphology and recently Ackermann et al. (2018) showed that CNNs can be used to identify merging galaxy pairs in SDSS Data Release 7 images (Darg et al. 2010).”
MethodTHE CFHTLS-DEEP CATALOG OF INTERACTING GALAXIES. I. MERGER RATE EVOLUTION TO z= 1.2
Bridge, C. R., Carlberg, R. G., & Sullivan, M. (2010) · The Astrophysical Journal · doi:10.1088/0004-637x/709/2/1067 · Cited by 130 · cited 2×
“For example, Bridge et al. (2010) and A13 both use data from the CFHTLS to identify tidal features through visual inspection.”
MethodFAINT TIDAL FEATURES IN GALAXIES WITHIN THE CANADA-FRANCE-HAWAII TELESCOPE LEGACY SURVEY WIDE FIELDS
Atkinson, A. M., Abraham, R. G., & Ferguson, A. M. N. (2013) · The Astrophysical Journal · doi:10.1088/0004-637x/765/1/28 · Cited by 122 · cited 1×
“Atkinson et al. (2013) (hereafter A13) used visual classfications to study the incidence of faint tidal features in a sample of ∼ 1800 luminous galaxies drawn from this survey, making it an ideal sample against which to benchmark the performance of CNNs.”
BackgroundSelf-citationTidal debris morphology and the orbits of satellite galaxies
Hendel, D., & Johnston, K. V. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv2035 · Cited by 99 · cited 2×
“Individual tidal features can be simulated in exquisite detail (e.g. Johnston et al. 2008; Hendel & Johnston 2015 and large-scale hydrodynamical simulations of galaxy formation now have the resolution to resolve these features in populations of several thousand galaxies (e.g. Pop et al. 2017).”
BackgroundFormation and incidence of shell galaxies in the Illustris simulation
Pop, A.-R., Pillepich, A., Amorisco, N. C., & Hernquist, L. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty1932 · Cited by 99
New image statistics for detecting disturbed galaxy morphologies at high redshift
Freeman, P. E., Izbicki, R., Lee, A. B., Newman, J. A., Conselice, C. J., Koekemoer, A. M., Lotz, J. M., & Mozena, M. (2013) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stt1016 · Cited by 89 · cited 1×
“…methods measure one or several hand-crafted image parameters thought to correlate with post-merger disruption (e.g. Conselice 2003; Lotz et al. 2004; Freeman et al. 2013; Pawlik et al. 2016), and then apply selection cuts or machine learning estimation to identify the most likely candidates.”
MethodNo assembly required: mergers are mostly irrelevant for the growth of low-mass dwarf galaxies
Fitts, A., Boylan-Kolchin, M., Bullock, J. S., Weisz, D. R., El-Badry, K., Wheeler, C., Faucher‐Giguère, C., Quataert, E., Hopkins, P. F., Kereš, D., et al. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty1488 · Cited by 77 · cited 1×
“…have acquired almost all of their stars through mergers, the relative contribution of in situ star formation and directly accreted stellar mass remains an open question across much of the galaxy mass spectrum (e.g. Rodriguez-Gomez et al. 2016; Qu et al. 2017; Lee & Yi 2017; Fitts et al. 2018).”
BackgroundDiverse structural evolution at z > 1 in cosmologically simulated galaxies
Snyder, G. F., Lotz, J., Moody, C., Peth, M., Freeman, P., Ceverino, D., Primack, J., & Dekel, A. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv1231 · Cited by 73 · cited 1×
“These methods allow for a broader range of morphologies to be classified but can be easily confused by complex features such as spiral arms (e.g. Kartaltepe et al. 2010) and are typically only sensitive to certain major merger stages (Lotz et al. 2008b, 2011; Snyder et al. 2015).”
MethodKado-Fong, E., Greene, J. E., Hendel, D., Price-Whelan, A. M., Greco, J. P., Goulding, A. D., Huang, S., Johnston, K. V., Komiyama, Y., Lee, C.-H., et al. (2018) · The Astrophysical Journal · doi:10.3847/1538-4357/aae0f0 · Cited by 69 · cited 3×
“Indeed, most work in detecting and classifying tidal features in galaxies is still wholly or partially dependent on expert visual identification (e.g. Kado-Fong et al. 2018; Hood et al. 2018; Morales et al. 2018).”
BackgroundInfluentialLofthouse, E. K., Kaviraj, S., Conselice, C. J., Mortlock, A., & Hartley, W. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stw2895 · Cited by 64 · cited 1×
“Furthermore, the rates of major (mass ratio ≥1:4) and minor merger events, and their role in shaping various galaxy components, are also not yet well understood (e.g. Lotz et al. 2011; Martin et al. 2017; Lofthouse et al. 2017).”
BackgroundThe Origin of Faint Tidal Features around Galaxies in the RESOLVE Survey
Hood, C. E., Kannappan, S. J., Stark, D. V., Dell’Antonio, I. P., Moffett, A. J., Eckert, K. D., Norris, M. A., & Hendel, D. (2018) · The Astrophysical Journal · doi:10.3847/1538-4357/aab719 · Cited by 64 · cited 3×
“Indeed, most work in detecting and classifying tidal features in galaxies is still wholly or partially dependent on expert visual identification (e.g. Kado-Fong et al. 2018; Hood et al. 2018; Morales et al. 2018).”
BackgroundInfluentialMorales, G., Martínez-Delgado, D., Grebel, E. K., Cooper, A. P., Javanmardi, B., & Miskolczi, A. (2018) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201732271 · Cited by 64 · cited 4×
“Indeed, most work in detecting and classifying tidal features in galaxies is still wholly or partially dependent on expert visual identification (e.g. Kado-Fong et al. 2018; Hood et al. 2018; Morales et al. 2018).”
BackgroundInfluentialTidal streams around galaxies in the SDSS DR7 archive: I. First results
Miskolczi, A., Bomans, D. J., & Dettmar, R.-J. (2011) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201116716 · Cited by 60 · cited 1×
“…(e.g. Malin & Carter 1983; Mart́ınez-Delgado et al. 2010; Sheen et al. 2012), often on images that have been specifically manipulated in order to enhance the appearance of low surface brightness features (e.g. Miskolczi et al. 2011; Kado-Fong et al. 2018; Morales et al. 2018; Hood et al. 2018).”
BackgroundPOST-MERGER SIGNATURES OF RED-SEQUENCE GALAXIES IN RICH ABELL CLUSTERS AT z ≲ 0.1
Sheen, Y.-K., Yi, S. K., Ree, C. H., & Lee, J. (2012) · The Astrophysical Journal Supplement Series · doi:10.1088/0067-0049/202/1/8 · Cited by 57 · cited 1×
“…to date has focused on visual inspection of individual galaxies or relatively small samples (e.g. Malin & Carter 1983; Mart́ınez-Delgado et al. 2010; Sheen et al. 2012), often on images that have been specifically manipulated in order to enhance the appearance of low surface brightness features…”
Background13CO/C18O Gradients across the Disks of Nearby Spiral Galaxies
Jiménez-Donaire, M. J., Cormier, D., Bigiel, F., Leroy, A. K., Gallagher, M., Krumholz, M. R., Usero, A., Hughes, A., Kramer, C., Meier, D. S., et al. (2017) · The Astrophysical Journal Letters · doi:10.3847/2041-8213/836/2/l29 · Cited by 51
Star-galaxy classification in the Dark Energy Survey Y1 dataset
Sevilla-Noarbe, I., Hoyle, B., Marchã, M. J. M., Soumagnac, M. T., Bechtol, K., Drlica-Wagner, A., Abdalla, F. B., Aleksić, J., Avestruz, C., Balbinot, E., et al. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty2579 · Cited by 51 · cited 1×
“However, automatic identification of contaminating stars is straightforward (Soumagnac 2015; Kennamer et al. 2018; Cabayol et al. 2018; Sevilla-Noarbe et al. 2018).”
BackgroundThe limited role of galaxy mergers in driving stellar mass growth over cosmic time
Martin, G., Kaviraj, S., Devriendt, J. E. G., Dubois, Y., Laigle, C., & Pichon, C. (2017) · Monthly Notices of the Royal Astronomical Society: Letters · doi:10.1093/mnrasl/slx136 · Cited by 46 · cited 1×
“Furthermore, the rates of major (mass ratio ≥1:4) and minor merger events, and their role in shaping various galaxy components, are also not yet well understood (e.g. Lotz et al. 2011; Martin et al. 2017; Lofthouse et al. 2017).”
BackgroundYu, H., Li, B., Chen, S.-X., Xiong, M., & Guo, M.-Z. (2017) · The Astrophysical Journal · doi:10.3847/1538-4357/836/1/1 · Cited by 41
Substructure and Tidal Streams in the Andromeda Galaxy and its Satellites
Ferguson, A. M. N., & Mackey, D. (2015) · Astrophysics and space science library · doi:10.1007/978-3-319-19336-6_8 · Cited by 39 · cited 1×
“Indeed, much stellar substructure of this nature has already been detected in the peripheral regions of the Milky Way (e.g. Belokurov et al. 2006), M31 (see the review by Ferguson & Mackey (2016)), and other nearby galaxies (e.g. Mart́ınez-Delgado et al. 2010; Duc et al. 2015).”
BackgroundSelf-citationGalaxy morphology — An unsupervised machine learning approach
Schutter, A., & Shamir, L. (2015) · Astronomy and Computing · doi:10.1016/j.ascom.2015.05.002 · Cited by 37 · cited 2×
“It has been successfully used to classify peculiar galaxies (Shamir 2012) and general galaxy morphology (Schutter & Shamir 2015) and so could be reasonably expected to perform well on the problem of faint tidal debris.”
MethodTHE ENVIRONMENTAL DEPENDENCE OF THE INCIDENCE OF GALACTIC TIDAL FEATURES
Adams, S. M., Zaritsky, D., Sand, D. J., Graham, M. L., Bildfell, C., Hoekstra, H., & Pritchet, C. (2012) · The Astronomical Journal · doi:10.1088/0004-6256/144/5/128 · Cited by 35 · cited 1×
“Model subtraction methods work by removing the expected flux using a parametric light profile and then quantifying the amount of residual light (e.g. van Dokkum 2005; Tal et al. 2009; Adams et al. 2012).”
MethodLarge Synoptic Survey Telescope Galaxies Science RoadmapPreprint
Robertson, B. E., Banerji, M., Cooper, M. C., Davies, R. L., Driver, S. P., Ferguson, A. M. N., Ferguson, H. C., Gawiser, E., Kaviraj, S., Knapen, J. H., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.01617 · Cited by 28 · cited 1×
“This strategy is completely inadequate for the next generation of deep wide field surveys, such as LSST and Euclid, which will cover ∼ 15, 000−20, 000 square degrees at unprecedented photometric depth (Laureijs et al. 2011; Robertson et al. 2017).”
BackgroundSelf-citationAutomatic detection of peculiar galaxies in large datasets of galaxy images
Shamir, L. (2012) · Journal of Computational Science · doi:10.1016/j.jocs.2012.03.004 · Cited by 25 · cited 4×
“…methods recently applied in the literature, namely the shape asymmetry method, a nonparametric approach developed for identifying post-merger galaxies by Pawlik et al. 2016), and WND-CHRM, a generic machine learning approach previously applied to image classification in astronomy (Shamir 2012).”
MethodInfluentialA Bayesian perspective on estimating mean, variance, and standard-deviation from data
Oliphant, T. E. (2006) · ScholarsArchive (Brigham Young University) · Cited by 23
Lee, J., & Yi, S. K. (2017) · The Astrophysical Journal · doi:10.3847/1538-4357/aa5b87 · Cited by 18
Research works printed but not linked: 17
- Abadi, 2015, TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems
- Bradley, 2018, astropy/photutils: v0.5
- Chollet, 2016, Building Powerful Image Classification Models Using Very Little Data
- Chollet, 2015, Keras
- Huang, 2017, Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 3296
- Jones, 2001, SciPy: Open source scientific tools for Python
- Kennamer, 2018, Proc. 35th Int. Conf. Mach. Learn, 2582
- Pedregosa, 2011, J. Mach. Learn. Res., 12, 2825
- Pedregosa, 2012, J. Mach. Learn. Res., 12, 2825
- Sevilla-Noarbe, 2018, MNRAS, 481, 5451
- Simonyan, 2015, International Conference on Learning Representations
- Soumagnac, 2015, Doctoral thesis
- Tewari, 2005, J. Mach. Learn. Res., 8, 143
- The Astropy Collaboration, 2013, A&A, 558, 9
- Toshev, 2014, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit, 1653
- Walmsley, 2018, Tidal Features Classifier: Initial public release - updated account
- Yosinski, 2014, Advances in Neural Information Processing Systems 27, 3320
Cited by
Ellison, S. L., Viswanathan, A., Patton, D. R., Bottrell, C., McConnachie, A. W., Gwyn, S., & Cuillandre, J.-C. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz1431 · Cited by 193
“…even at high redshifts (e.g. Lin et al. 2007; Wong et al. 2011), visual classifications (e.g. Darg et al. 2010; Kartaltepe et al. 2015), automated parametric morphology metrics (Lotz et al. 2004; Pawlik et al. 2016), or machine learning techniques (e.g. Ackermann et al. 2018; Walmsley et al. 2019).”
Galaxy Zoo: probabilistic morphology through Bayesian CNNs and active learning
Walmsley, M., Smith, L., Lintott, C., Gal, Y., Bamford, S., Dickinson, H., Fortson, L., Kruk, S., Masters, K., Scarlata, C., et al. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz2816 · Cited by 160
Self-citationDeep learning predictions of galaxy merger stage and the importance of observational realism
Bottrell, C., Hani, M. H., Teimoorinia, H., Ellison, S. L., Moreno, J., Torrey, P., Hayward, C. C., Thorp, M., Simard, L., & Hernquist, L. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz2934 · Cited by 113
“The level of intricacy in the features that can be identified by CNN and other ma- MNRAS 000, 1–25 (2019) The importance of realism 3 chine learning models has made them an attractive tool for merger identification (e.g. Ackermann et al. 2018; Walmsley et al. 2019).”
MethodThe Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys
Huertas-Company, M., & Lanusse, F. (2023) · Publications of the Astronomical Society of Australia · doi:10.1017/pasa.2022.55 · Cited by 102
Identifying galaxy mergers in observations and simulations with deep learning
Pearson, W. J., Wang, L., Trayford, J. W., Petrillo, C. E., & van der Tak, F. F. S. (2019) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201935355 · Cited by 90
“There has also been work using deep learning techniques to identifying mergers and tidal features in optical data from the Canada-France-Hawaii Telescope Legacy Survey (Gwyn 2012; Walmsley et al. 2019).”
MethodInfluential
Metadata
- Authors
- Walmsley, M., Ferguson, A. M. N., Mann, R. G., & Lintott, C. J.
- Affiliations
- University of Oxford (GB)
- Royal Observatory (GB)
- Corresponding author
- Walmsley, Mike
- Venue
- Monthly Notices of the Royal Astronomical Society
- Publisher
- Oxford University Press (OUP)
- Published
- 2018-11-29
- Volume
- 483
- Issue
- 3
- Pages
- 2968-2982
- ISSN
- 0035-8711 (ISSN-L)
- 1365-2966
- OpenAlex
- W2902203455
- Cited by
- 66
- References
- 92
- Citations by year
- 2026: 4 · 2025: 6 · 2024: 15 · 2023: 9 · 2022: 12 · 2021: 7 · 2020: 5 · 2019: 8
- FWCI
- 2.68
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Monthly Notices of the Royal Astronomical Society (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Science and Technology Facilities Council (ST/R505006/1)
- National Science Foundation
- Centre National de la Recherche Scientifique
- Topics
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Galaxies: Formation, Evolution, Phenomena
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Stellar, planetary, and galactic studies
- Keywords
- tidal features, low surface brightness, galaxy mergers, galaxy interactions, convolutional neural networks, automated feature detection, galaxy morphology
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.