New High-quality Strong Lens Candidates with Deep Learning in the Kilo-Degree Survey
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
We report new high-quality galaxy-scale strong lens candidates found in the Kilo-Degree Survey data release 4 using machine learning. We have developed a new convolutional neural network (CNN) classifier to search for gravitational arcs, following the prescription by Petrillo et al. and using only r-band images. We have applied the CNN to two “predictive samples”: a luminous red galaxy (LRG) and a “bright galaxy” (BG) sample (r < 21). We have found 286 new high-probability candidates, 133 from the LRG sample and 153 from the BG sample. We have ranked these candidates based on a value that combines the CNN likelihood of being a lens and the human score resulting from visual inspection (P-value), and here we present the highest 82 ranked candidates with P-values ≥0.5. All of these high-quality candidates have obvious arc or pointlike features around the central red defector. Moreover, we define the best 26 objects, all with P-values ≥0.7, as a “golden sample” of candidates. This sample is expected to contain very few false positives; thus, it is suitable for follow-up observations. The new lens candidates come partially from the more extended footprint adopted here with respect to the previous analyses and partially from a larger predictive sample (also including the BG sample). These results show that machine-learning tools are very promising for finding strong lenses in large surveys and more candidates can be found by enlarging the predictive samples beyond the standard assumption of LRGs. In the future, we plan to apply our CNN to the data from next-generation surveys such as the Large Synoptic Survey Telescope, Euclid, and the Chinese Space Station Optical Survey.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
Bonvin, V., Courbin, F., Suyu, S. H., Marshall, P. J., Rusu, C. E., Sluse, D., Tewes, M., Wong, K. C., Collett, T., Fassnacht, C. D., et al. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stw3006 · Cited by 457 · cited 1×
“In particular, this is possible by measuring the luminosity variation of lensed quasars, and using the time delay of the occurrence of their peak luminosity, which is highly sensitive to H0 and little sensitive to other parameters (see e.g. the H0LiCOW project, Suyu et al. 2017; Bonvin et al. 2017).”
MethodSelf-citationGravitational detection of a low-mass dark satellite galaxy at cosmological distance
Vegetti, S., Lagattuta, D. J., McKean, J. P., Auger, M. W., Fassnacht, C. D., & Koopmans, L. V. E. (2012) · Nature · doi:10.1038/nature10669 · Cited by 386
Self-citationA precise extragalactic test of General Relativity
Collett, T. E., Oldham, L. J., Smith, R. J., Auger, M. W., Westfall, K. B., Bacon, D., Nichol, R. C., Masters, K. L., Koyama, K., & van den Bosch, R. (2018) · Science · doi:10.1126/science.aao2469 · Cited by 157
The strong gravitational lens finding challenge
Metcalf, R. B., Meneghetti, M., Avestruz, C., Bellagamba, F., Bom, C. R., Bertin, E., Cabanac, R., Courbin, F., Davies, A., Decencière, E., et al. (2019) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201832797 · Cited by 152
Self-citationFinding strong lenses in CFHTLS using convolutional neural networks
Jacobs, C., Glazebrook, K., Collett, T., More, A., & McCarthy, C. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx1492 · Cited by 133 · cited 2×
“In fact, more than 1000 lens candidates have been found in the last three years in recent ground-based surveys (e.g., Petrillo et al. 2017, 2019a; Jacobs et al. 2017, 2019; Pourrahmani et al. 2018; Khramtsov et al. 2019), such as the Kilo-Degree Survey (de Jong et al. 2013), the Hyper Suprime-Cam…”
BackgroundSpace Warps – I. Crowdsourcing the discovery of gravitational lenses
Marshall, P. J., Verma, A., More, A., Davis, C. P., More, S., Kapadia, A., Parrish, M., Snyder, C., Wilcox, J., Baeten, E., et al. (2016) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv2009 · Cited by 117
Research works printed but not linked: 69
- Agnello, 2015, MNRAS, 448, 1446, 10.1093/mnras/stv037 · DOI
- Agnello, 2018, MNRAS, 479, 4345, 10.1093/mnras/sty1419 · DOI
- Agnello, 2019, MNRAS, 489, 2525, 10.1093/mnras/stz2200 · DOI
- ALMA Partnership, 2015, ApJL, 808, L4, 10.1088/2041-8205/808/1/L4 · DOI
- Amendola, 2018, LRR, 21, 2, 10.1007/s41114-017-0010-3 · DOI · Paper page
- Auger, 2009, ApJ, 705, 1099, 10.1088/0004-637X/705/2/1099 · DOI · Paper page
- Auger, 2010, ApJ, 724, 511, 10.1088/0004-637X/724/1/511 · DOI · Paper page
- Barnabè, 2012, MNRAS, 423, 1073, 10.1111/j.1365-2966.2012.20934.x · DOI · Paper page
- Bertin, 1996, A&AS, 117, 393, 10.1051/aas:1996164 · DOI · Paper page
- Blandford, 1992, ARA&A, 30, 311, 10.1146/annurev.aa.30.090192.001523 · DOI · Paper page
- Bolton, 2012, ApJ, 757, 82, 10.1088/0004-637X/757/1/82 · DOI · Paper page
- Bolton, 2006, ApJ, 638, 703, 10.1086/498884 · DOI · Paper page
- Bolton, 2008, ApJ, 682, 964, 10.1086/589327 · DOI · Paper page
- Brownstein, 2012, ApJ, 744, 41, 10.1088/0004-637X/744/1/41 · DOI · Paper page
- Cao, 2017, ApJ, 835, 92, 10.3847/1538-4357/835/1/92 · DOI
- Chen, 2019, ApJ, 881, 8, 10.3847/1538-4357/ab297d · DOI
- Claeyssens, 2019, MNRAS, 489, 5022, 10.1093/mnras/stz2492 · DOI
- Closson Ferguson, 2009, AAS Meeting, 213, 460.07
- Collett, 2015, ApJ, 811, 20, 10.1088/0004-637X/811/1/20 · DOI · Paper page
- Congdon, 2018, 10.1007/978-3-030-02122-1 · doi:10.1007/978-3-030-02122-1
- Cornachione, 2018, ApJ, 853, 148, 10.3847/1538-4357/aaa412 · doi:10.3847/1538-4357/aaa412
- de Jong, 2013, Msngr, 154, 44
- Dobler, 2008, ApJ, 685, 57, 10.1086/589958 · DOI
- Eisenstein, 2001, AJ, 122, 2267, 10.1086/323717 · DOI · Paper page
- Fukugita, 1992, ApJ, 393, 3, 10.1086/171481 · DOI · Paper page
- Gilman, 2018, MNRAS, 481, 819, 10.1093/mnras/sty2261 · DOI
- Hartley, 2017, MNRAS, 471, 3378, 10.1093/mnras/stx1733 · DOI · Paper page
- Hsueh, 2020, MNRAS, 492, 3047, 10.1093/mnras/stz3177 · DOI · Paper page
- Ivezić, 2014, 10.1515/9781400848911 · DOI
- Jacobs, 2019, ApJS, 243, 17, 10.3847/1538-4365/ab26b6 · DOI
- Khramtsov, 2019, A&A, 632, A56, 10.1051/0004-6361/201936006 · DOI
- Kochanek, 2020, MNRAS, 493, 1725, 10.1093/mnras/staa344 · DOI · Paper page
- Koopmans, 2009, ApJL, 703, L51, 10.1088/0004-637X/703/1/L51 · DOI · Paper page
- Koopmans, 2006, ApJ, 649, 599, 10.1086/505696 · DOI · Paper page
- Kuijken, 2019, A&A, 625, A2, 10.1051/0004-6361/201834918 · DOI · Paper page
- La Barbera, 2008, PASP, 120, 681, 10.1086/588614 · DOI
- Lemon, 2020, MNRAS, 494, 3491, 10.1093/mnras/staa652 · DOI
- Li, 2017, MNRAS, 468, 1426, 10.1093/mnras/stx554 · DOI
- Li, 2019, MNRAS, 482, 313, 10.1093/mnras/sty2708 · DOI
- Li, 2018, MNRAS, 480, 431, 10.1093/mnras/sty1813 · DOI · Paper page
- Miyazaki, 2012, Proc. SPIE, 8446, 10.1117/12.926844 · DOI · Paper page
- Moster, 2010, ApJ, 710, 903, 10.1088/0004-637X/710/2/903 · DOI · Paper page
- Nightingale, 2019, MNRAS, 489, 2049, 10.1093/mnras/stz2220 · DOI
- Oguri, 2010, MNRAS, 405, 2579, 10.1111/j.1365-2966.2010.16639.x · DOI · Paper page
- Petrillo, 2017, MNRAS, 472, 1129, 10.1093/mnras/stx2052 · DOI · Paper page
- Petrillo, 2019a, MNRAS, 482, 807, 10.1093/mnras/sty2683 · DOI
- Petrillo, 2019b, MNRAS, 484, 3879, 10.1093/mnras/stz189 · DOI · Paper page
- Pourrahmani, 2018, ApJ, 856, 68, 10.3847/1538-4357/aaae6a · DOI · Paper page
- Refsdal, 1964, MNRAS, 128, 307, 10.1093/mnras/128.4.307 · DOI · Paper page
- Roy, 2018, MNRAS, 480, 1057, 10.1093/mnras/sty1917 · DOI
- Rydberg, 2020, MNRAS, 491, 2447, 10.1093/mnras/stz3203 · doi:10.1093/mnras/stz3203
- Schuldt, 2019, A&A, 631, A40, 10.1051/0004-6361/201935042 · DOI
- Schwab, 2010, ApJ, 708, 750, 10.1088/0004-637X/708/1/750 · DOI · Paper page
- Seidel, 2007, A&A, 472, 341, 10.1051/0004-6361:20066097 · DOI · Paper page
- Shu, 2015, ApJ, 803, 71, 10.1088/0004-637X/803/2/71 · DOI · Paper page
- Shu, 2016, ApJ, 833, 264, 10.3847/1538-4357/833/2/264 · DOI
- Shu, 2017, ApJ, 851, 48, 10.3847/1538-4357/aa9794 · DOI · Paper page
- Sluse, 2019, MNRAS, 490, 613, 10.1093/mnras/stz2483 · DOI · Paper page
- Sonnenfeld, 2013, ApJ, 777, 98, 10.1088/0004-637X/777/2/98 · DOI · Paper page
- Spiniello, 2018, MNRAS, 480, 1163, 10.1093/mnras/sty1923 · DOI
- Spiniello, 2019, MNRAS, 483, 3888, 10.1093/mnras/sty3407 · doi:10.1093/mnras/sty3407
- Spiniello, 2011, MNRAS, 417, 3000, 10.1111/j.1365-2966.2011.19458.x · DOI
- Suyu, 2013, ApJ, 766, 70, 10.1088/0004-637X/766/2/70 · DOI · Paper page
- Suyu, 2017, MNRAS, 468, 2590, 10.1093/mnras/stx483 · DOI · Paper page
- Tortora, 2010, ApJL, 721, L1, 10.1088/2041-8205/721/1/L1 · DOI · Paper page
- SWELLS Team, 2012, AAS Meeting, 219, 311.06
- Turner, 1984, ApJ, 284, 1, 10.1086/162379 · DOI · Paper page
- Wong, 2020, MNRAS, 10.1093/mnras/stz3094 · DOI · Paper page
- Wong, 2013, ApJ, 769, 52, 10.1088/0004-637X/769/1/52 · DOI
Cited by
Mining for Strong Gravitational Lenses with Self-supervised Learning
Stein, G., Blaum, J., Harrington, P., Medan, T., & Lukić, Z. (2022) · The Astrophysical Journal · doi:10.3847/1538-4357/ac6d63 · Cited by 52
Pearson, J., Maresca, J., Li, N., & Dye, S. (2021) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stab1547 · Cited by 31
Pearce-Casey, R., Nagam, B. C., Wilde, J., Busillo, V., Ulivi, L., Andika, I. T., Manjón-García, A., Leuzzi, L., Matavulj, P., Serjeant, S., et al. (2025) · Astronomy & Astrophysics · doi:10.1051/0004-6361/202453152 · Cited by 18
Self-citationEuclid Collaboration, Lines, N. E. P., Collett, T. E., Walmsley, M., Rojas, K., Li, T., Leuzzi, L., Manjón-García, A., Vincken, S. H., Wilde, J., et al. (2026) · Astronomy & Astrophysics · doi:10.1051/0004-6361/202554542 · Cited by 14
Self-citationNagam, B. C., Acevedo Barroso, J. A., Wilde, J., Andika, I. T., Manjón-García, A., Pearce-Casey, R., Stern, D., Nightingale, J. W., Moustakas, L. A., McCarthy, K., et al. (2025) · Astronomy & Astrophysics · doi:10.1051/0004-6361/202554132 · Cited by 8
Self-citation
Metadata
- Authors
- Li, R., Napolitano, N. R., Tortora, C., Spiniello, C., Koopmans, L. V. E., Huang, Z., Roy, N., Vernardos, G., Chatterjee, S., Giblin, B., Getman, F., Radovich, M., Covone, G., & Kuijken, K.
- Venue
- The Astrophysical Journal
- Publisher
- American Astronomical Society
- Published
- 2020-08-01
- Volume
- 899
- Issue
- 1
- Pages
- 30
- ISSN
- 0004-637X (ISSN-L)
- 1538-4357
- OpenAlex
- W3015167836
- Cited by
- 77
- References
- 13
- FWCI
- 4.90
- Type
- journal article
- Language
- en
- Open access
- bronze
- Licence
- iopscience.iop.org/page/copyright (vor, 9 d)
- iopscience.iop.org/info/page/text-and-data-mining (tdm, 9 d)
- Funders
- Sun Yat-sen University (71000-18841229)
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: New High-quality Strong Lens Candidates with Deep Learning in the Kilo-Degree Survey. https://app.cochat.ai/papers/10.3847/1538-4357/ab9dfa
- The paper
- Li, R., Napolitano, N. R., Tortora, C., Spiniello, C., Koopmans, L. V. E., Huang, Z., Roy, N., Vernardos, G., Chatterjee, S., Giblin, B., Getman, F., Radovich, M., Covone, G., & Kuijken, K. (2020). New High-quality Strong Lens Candidates with Deep Learning in the Kilo-Degree Survey. The Astrophysical Journal. https://doi.org/10.3847/1538-4357/ab9dfa
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.