Skip to content
Back to outputs

Finding high-redshift strong lenses in DES using convolutional neural networks

Research output: Contribution to journalArticle

Standard

Finding high-redshift strong lenses in DES using convolutional neural networks. / Jacobs, C.; Collett, T.; Glazebrook, K.; McCarthy, C.; Qin, A. K.; Abbott, T. M. C.; Abdalla, F. B.; Annis, J.; Avila, S.; Bechtol, K.; Bertin, E.; Brooks, D.; Buckley-Geer, E.; Burke, D. L.; Rosell, A. Carnero; Kind, M. Carrasco; Carretero, J.; Costa, L. N. da; Davis, C.; Vicente, J. De; Desai, S.; Diehl, H. T.; Doel, P.; Eifler, T. F.; Flaugher, B.; Frieman, J.; Bellido, J. García-; Gaztanaga, E.; Gerdes, D. W.; Goldstein, D. A.; Gruen, D.; Gruendl, R. A.; Gschwend, J.; Gutierrez, G.; Hartley, W. G.; Hollowood, D. L.; Honscheid, K.; Hoyle, B.; James, D. J.; Kuehn, K.; Kuropatkin, N.; Lahav, O.; Li, T. S.; Lima, M.; Lin, H.; Maia, M. A. G.; Martini, P.; Miller, C. J.; Miquel, R.; Nord, B.; Plazas, A. A.; Sanchez, E.; Scarpine, V.; Schubnell, M.; Serrano, S.; Sevilla-Noarbe, I.; Smith, M.; Soares-Santos, M.; Sobreira, F.; Suchyta, E.; Swanson, M. E. C.; Tarle, G.; Vikram, V.; Walker, A. R.; Zhang, Y.; Zuntz, J.

In: MNRAS, Vol. 484, No. 4, 21.04.2019, p. 5330-5349.

Research output: Contribution to journalArticle

Harvard

Jacobs, C, Collett, T, Glazebrook, K, McCarthy, C, Qin, AK, Abbott, TMC, Abdalla, FB, Annis, J, Avila, S, Bechtol, K, Bertin, E, Brooks, D, Buckley-Geer, E, Burke, DL, Rosell, AC, Kind, MC, Carretero, J, Costa, LND, Davis, C, Vicente, JD, Desai, S, Diehl, HT, Doel, P, Eifler, TF, Flaugher, B, Frieman, J, Bellido, JG, Gaztanaga, E, Gerdes, DW, Goldstein, DA, Gruen, D, Gruendl, RA, Gschwend, J, Gutierrez, G, Hartley, WG, Hollowood, DL, Honscheid, K, Hoyle, B, James, DJ, Kuehn, K, Kuropatkin, N, Lahav, O, Li, TS, Lima, M, Lin, H, Maia, MAG, Martini, P, Miller, CJ, Miquel, R, Nord, B, Plazas, AA, Sanchez, E, Scarpine, V, Schubnell, M, Serrano, S, Sevilla-Noarbe, I, Smith, M, Soares-Santos, M, Sobreira, F, Suchyta, E, Swanson, MEC, Tarle, G, Vikram, V, Walker, AR, Zhang, Y & Zuntz, J 2019, 'Finding high-redshift strong lenses in DES using convolutional neural networks', MNRAS, vol. 484, no. 4, pp. 5330-5349. https://doi.org/10.1093/mnras/stz272

APA

Jacobs, C., Collett, T., Glazebrook, K., McCarthy, C., Qin, A. K., Abbott, T. M. C., Abdalla, F. B., Annis, J., Avila, S., Bechtol, K., Bertin, E., Brooks, D., Buckley-Geer, E., Burke, D. L., Rosell, A. C., Kind, M. C., Carretero, J., Costa, L. N. D., Davis, C., ... Zuntz, J. (2019). Finding high-redshift strong lenses in DES using convolutional neural networks. MNRAS, 484(4), 5330-5349. https://doi.org/10.1093/mnras/stz272

Vancouver

Jacobs C, Collett T, Glazebrook K, McCarthy C, Qin AK, Abbott TMC et al. Finding high-redshift strong lenses in DES using convolutional neural networks. MNRAS. 2019 Apr 21;484(4):5330-5349. https://doi.org/10.1093/mnras/stz272

Author

Jacobs, C. ; Collett, T. ; Glazebrook, K. ; McCarthy, C. ; Qin, A. K. ; Abbott, T. M. C. ; Abdalla, F. B. ; Annis, J. ; Avila, S. ; Bechtol, K. ; Bertin, E. ; Brooks, D. ; Buckley-Geer, E. ; Burke, D. L. ; Rosell, A. Carnero ; Kind, M. Carrasco ; Carretero, J. ; Costa, L. N. da ; Davis, C. ; Vicente, J. De ; Desai, S. ; Diehl, H. T. ; Doel, P. ; Eifler, T. F. ; Flaugher, B. ; Frieman, J. ; Bellido, J. García- ; Gaztanaga, E. ; Gerdes, D. W. ; Goldstein, D. A. ; Gruen, D. ; Gruendl, R. A. ; Gschwend, J. ; Gutierrez, G. ; Hartley, W. G. ; Hollowood, D. L. ; Honscheid, K. ; Hoyle, B. ; James, D. J. ; Kuehn, K. ; Kuropatkin, N. ; Lahav, O. ; Li, T. S. ; Lima, M. ; Lin, H. ; Maia, M. A. G. ; Martini, P. ; Miller, C. J. ; Miquel, R. ; Nord, B. ; Plazas, A. A. ; Sanchez, E. ; Scarpine, V. ; Schubnell, M. ; Serrano, S. ; Sevilla-Noarbe, I. ; Smith, M. ; Soares-Santos, M. ; Sobreira, F. ; Suchyta, E. ; Swanson, M. E. C. ; Tarle, G. ; Vikram, V. ; Walker, A. R. ; Zhang, Y. ; Zuntz, J. / Finding high-redshift strong lenses in DES using convolutional neural networks. In: MNRAS. 2019 ; Vol. 484, No. 4. pp. 5330-5349.

Bibtex

@article{c3007fe53f4641c0a85320f62f34cb23,
title = "Finding high-redshift strong lenses in DES using convolutional neural networks",
abstract = " We search Dark Energy Survey (DES) Year 3 imaging data for galaxy-galaxy strong gravitational lenses using convolutional neural networks. We generate 250,000 simulated lenses at redshifts > 0.8 from which we create a data set for training the neural networks with realistic seeing, sky and shot noise. Using the simulations as a guide, we build a catalogue of 1.1 million DES sources with (1.8 19, g_mag > 20 and i_mag > 18.2. We train two ensembles of neural networks on training sets consisting of simulated lenses, simulated non-lenses, and real sources. We use the neural networks to score images of each of the sources in our catalogue with a value from 0 to 1, and select those with scores greater than a chosen threshold for visual inspection, resulting in a candidate set of 7,301 galaxies. During visual inspection we rate 84 as {"}probably{"} or {"}definitely{"} lenses. Four of these are previously known lenses or lens candidates. We inspect a further 9,428 candidates with a different score threshold, and identify four new candidates. We present 84 new strong lens candidates, selected after a few hours of visual inspection by astronomers. Based on simulations we estimate our sample to contain most discoverable lenses in this imaging and at this redshift range. ",
keywords = "astro-ph.GA, astro-ph.IM, RCUK, STFC, AST-1138766, AST-1536171",
author = "C. Jacobs and T. Collett and K. Glazebrook and C. McCarthy and Qin, {A. K.} and Abbott, {T. M. C.} and Abdalla, {F. B.} and J. Annis and S. Avila and K. Bechtol and E. Bertin and D. Brooks and E. Buckley-Geer and Burke, {D. L.} and Rosell, {A. Carnero} and Kind, {M. Carrasco} and J. Carretero and Costa, {L. N. da} and C. Davis and Vicente, {J. De} and S. Desai and Diehl, {H. T.} and P. Doel and Eifler, {T. F.} and B. Flaugher and J. Frieman and Bellido, {J. Garc{\'i}a-} and E. Gaztanaga and Gerdes, {D. W.} and Goldstein, {D. A.} and D. Gruen and Gruendl, {R. A.} and J. Gschwend and G. Gutierrez and Hartley, {W. G.} and Hollowood, {D. L.} and K. Honscheid and B. Hoyle and James, {D. J.} and K. Kuehn and N. Kuropatkin and O. Lahav and Li, {T. S.} and M. Lima and H. Lin and Maia, {M. A. G.} and P. Martini and Miller, {C. J.} and R. Miquel and B. Nord and Plazas, {A. A.} and E. Sanchez and V. Scarpine and M. Schubnell and S. Serrano and I. Sevilla-Noarbe and M. Smith and M. Soares-Santos and F. Sobreira and E. Suchyta and Swanson, {M. E. C.} and G. Tarle and V. Vikram and Walker, {A. R.} and Y. Zhang and J. Zuntz",
note = "Submitted to MNRAS",
year = "2019",
month = apr
day = "21",
doi = "10.1093/mnras/stz272",
language = "English",
volume = "484",
pages = "5330--5349",
journal = "MNRAS",
issn = "0035-8711",
publisher = "Oxford University Press",
number = "4",

}

RIS

TY - JOUR

T1 - Finding high-redshift strong lenses in DES using convolutional neural networks

AU - Jacobs, C.

AU - Collett, T.

AU - Glazebrook, K.

AU - McCarthy, C.

AU - Qin, A. K.

AU - Abbott, T. M. C.

AU - Abdalla, F. B.

AU - Annis, J.

AU - Avila, S.

AU - Bechtol, K.

AU - Bertin, E.

AU - Brooks, D.

AU - Buckley-Geer, E.

AU - Burke, D. L.

AU - Rosell, A. Carnero

AU - Kind, M. Carrasco

AU - Carretero, J.

AU - Costa, L. N. da

AU - Davis, C.

AU - Vicente, J. De

AU - Desai, S.

AU - Diehl, H. T.

AU - Doel, P.

AU - Eifler, T. F.

AU - Flaugher, B.

AU - Frieman, J.

AU - Bellido, J. García-

AU - Gaztanaga, E.

AU - Gerdes, D. W.

AU - Goldstein, D. A.

AU - Gruen, D.

AU - Gruendl, R. A.

AU - Gschwend, J.

AU - Gutierrez, G.

AU - Hartley, W. G.

AU - Hollowood, D. L.

AU - Honscheid, K.

AU - Hoyle, B.

AU - James, D. J.

AU - Kuehn, K.

AU - Kuropatkin, N.

AU - Lahav, O.

AU - Li, T. S.

AU - Lima, M.

AU - Lin, H.

AU - Maia, M. A. G.

AU - Martini, P.

AU - Miller, C. J.

AU - Miquel, R.

AU - Nord, B.

AU - Plazas, A. A.

AU - Sanchez, E.

AU - Scarpine, V.

AU - Schubnell, M.

AU - Serrano, S.

AU - Sevilla-Noarbe, I.

AU - Smith, M.

AU - Soares-Santos, M.

AU - Sobreira, F.

AU - Suchyta, E.

AU - Swanson, M. E. C.

AU - Tarle, G.

AU - Vikram, V.

AU - Walker, A. R.

AU - Zhang, Y.

AU - Zuntz, J.

N1 - Submitted to MNRAS

PY - 2019/4/21

Y1 - 2019/4/21

N2 - We search Dark Energy Survey (DES) Year 3 imaging data for galaxy-galaxy strong gravitational lenses using convolutional neural networks. We generate 250,000 simulated lenses at redshifts > 0.8 from which we create a data set for training the neural networks with realistic seeing, sky and shot noise. Using the simulations as a guide, we build a catalogue of 1.1 million DES sources with (1.8 19, g_mag > 20 and i_mag > 18.2. We train two ensembles of neural networks on training sets consisting of simulated lenses, simulated non-lenses, and real sources. We use the neural networks to score images of each of the sources in our catalogue with a value from 0 to 1, and select those with scores greater than a chosen threshold for visual inspection, resulting in a candidate set of 7,301 galaxies. During visual inspection we rate 84 as "probably" or "definitely" lenses. Four of these are previously known lenses or lens candidates. We inspect a further 9,428 candidates with a different score threshold, and identify four new candidates. We present 84 new strong lens candidates, selected after a few hours of visual inspection by astronomers. Based on simulations we estimate our sample to contain most discoverable lenses in this imaging and at this redshift range.

AB - We search Dark Energy Survey (DES) Year 3 imaging data for galaxy-galaxy strong gravitational lenses using convolutional neural networks. We generate 250,000 simulated lenses at redshifts > 0.8 from which we create a data set for training the neural networks with realistic seeing, sky and shot noise. Using the simulations as a guide, we build a catalogue of 1.1 million DES sources with (1.8 19, g_mag > 20 and i_mag > 18.2. We train two ensembles of neural networks on training sets consisting of simulated lenses, simulated non-lenses, and real sources. We use the neural networks to score images of each of the sources in our catalogue with a value from 0 to 1, and select those with scores greater than a chosen threshold for visual inspection, resulting in a candidate set of 7,301 galaxies. During visual inspection we rate 84 as "probably" or "definitely" lenses. Four of these are previously known lenses or lens candidates. We inspect a further 9,428 candidates with a different score threshold, and identify four new candidates. We present 84 new strong lens candidates, selected after a few hours of visual inspection by astronomers. Based on simulations we estimate our sample to contain most discoverable lenses in this imaging and at this redshift range.

KW - astro-ph.GA

KW - astro-ph.IM

KW - RCUK

KW - STFC

KW - AST-1138766

KW - AST-1536171

U2 - 10.1093/mnras/stz272

DO - 10.1093/mnras/stz272

M3 - Article

VL - 484

SP - 5330

EP - 5349

JO - MNRAS

JF - MNRAS

SN - 0035-8711

IS - 4

ER -

ID: 12937404