PERFORMANCE COMPARISON OF NEURAL NETWORKS IN GRAVITATIONAL LENSING DETECTION
DOI:
https://doi.org/10.37943/13PQRV7503Keywords:
cosmology, gravitational field, Dark Matter, gravitational lensing, machine learning, image classification, fully connected neural networks, convolutional neural networksAbstract
A gravitational lens is a distribution of matter, such as dark matter halos, galaxies, or quasars, between a distant light source and an observer that can bend the light from the source as the light travels toward the observer. Nowadays, it is slightly complicated to identify gravitational lenses without powerful computing devices and groups of scientists working together. In addition, future surveys will have orders of magnitude more data and more lenses to find. With up-to-date algorithms such as neural networks, detecting and classifying them for a single human being will be possible. The neural networks described in this paper make the first steps in that direction. The primary purpose of this work was to develop three different neural networks and determine which one could detect gravitational lensing more quickly and precisely. For training, testing, and validation we used a dataset of 2000 images. Half of these images were downloaded from Bologna Lens Factory, a database of simulated gravitational lenses based on galaxies lensed by galaxies (i.e., no clusters and no quasars). We simulated the second half of the images using Python-based code to simulate mock strong lensed galaxies. We used Python-based code to mock strong lensing with different source parameters. Next, we built three types of artificial neural networks and compared their efficiency. Firstly, we developed a fully convolutional neural network (CNN) and a fully connected neural network (FCNN). The third neural network was a combination of these two approaches. In this algorithm, the FCNN layer replaced the last layer of CNN. Next, we compared the learning rates of these algorithms and applied all neural networks to validation images. As a result of the study, we determined which of the developed neural networks fit better for searching gravitational lenses.
References
Sjur Refsdal. (1964). On the Possibility of Determining Hubble’s Parameter and the Masses of Galaxies from the Gravitational Lens Effect, Monthly Notices of the Royal Astronomical Society, 128(4), 307-310. https://doi.org/10.1093/mnras/128.4.307
Bisnovatyi-Kogan G.S., Tsupko O.Yu. (2015). Gravitational lensing in plasmic medium, Plasma Physics Reports, 41(7), 562-581.
Thomas E. Collett. (2015). The population of galaxy–galaxy strong lenses in forthcoming optical imaging surveys, Astrophysical Journal 811: 20. https://doi.org/10.1134/S1063780X15070016
Ellis Richard S. (2010). Gravitational lensing: a unique probe of dark matter and dark energy, Philosophical Transactions of the Royal Society, A.368, 970. https://doi.org/10.1098/rsta.2009.0209
Barnabè M., Czoske O., Koopmans L.V.E., Treu T. & Bolton A.S. (2011). Two-dimensional kinematics of SLACS lenses – III. Mass structure and dynamics of early-type lens galaxies beyond z ≃ 0.1, Monthly Notices of the Royal Astronomical Society, 415, 2215-2232. https://doi.org/10.1111/j.1365-2966.2011.18842.x
Barone-Nugent, R.L., et al. (2015). The impact of strong gravitational lensing on observed Lyman break galaxy numbers at 4≤ z≤ 8 in the GOODS and the XDF blank fields, Monthly Notices of the Royal Astronomical Society 450.2, 1224-1236. https://doi.org/10.1093/mnras/stv633
Collett, Thomas E. (2015). The population of galaxy–galaxy strong lenses in forthcoming optical imaging surveys, Astrophysical Journal 811.1, 20. https://doi.org/10.1088/0004-637X/811/1/20
Kuhlen, Michael, Charles R. Keeton, and Piero Madau. (2004). Gravitational lensing statistics in universes dominated by dark energy, Astrophysical Journal 601.1: 104. https://doi.org/10.1086/380303
Sonnenfeld, Alessandro, et al. (2013). The SL2S galaxy-scale lens sample. III. Lens models, surface photometry, and stellar masses for the final sample, Astrophysical Journal 777.2, 97. https://doi.org/10.1088/0004-637X/777/2/97
Laureijs, Rene, et al. (2011). Euclid definition study report, arXiv: 1110.3193: 8. https://doi.org/10.48550/arXiv.1110.3193
Braun, Robert & Bourke, T & Green, James & Keane, Evan & Wagg, Jeff. (2015). Advancing Astrophysics with the Square Kilometre Array, 174.
Metcalf, R.B., Meneghetti, M.A.S.S.I.M.O., Avestruz, C., Bellagamba, F., Bom, C.R., Bertin, E., ... & Vernardos, G. (2019). The strong gravitational lens finding challenge. Astronomy & Astrophysics, A119, 625. https://doi.org/10.1051/0004-6361/201832797
Petrillo, C.E., Tortora, Chatterjee, S., Vernardos, G., Koopmans, L.V.E., Verdoes Kleijn, G., ... & McFarland, J. (2017). Finding strong gravitational lenses in the kilo degree survey with convolutional neural networks. Monthly Notices of the Royal Astronomical Society, 472(1), 1129-1150. https://doi.org/10.1093/mnras/stx2052
de Jong, J.T., Verdoes Kleijn, G.A., Kuijken, K.H., & Valentijn, E.A. (2013). The kilo-degree survey. Experimental Astronomy, 35(1), 25-44. https://doi.org/10.1007/s10686-012-9306-1
Lanusse, F., Ma, Q., Li, N., Collett, T., Li, C., Ravanbakhsh, S., ... & Póczos, B. (2018). CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding. Monthly Notices of the Royal Astronomical Society, 473(3), 3895-3906. https://doi.org/10.1093/mnras/stx1665
Jacobs, C., Glazebrook, K., Collett, T., More, A., & McCarthy, C. (2017). Finding strong lenses in CFHTLS using convolutional neural networks. Monthly Notices of the Royal Astronomical Society, 471(1), 167-181. https://doi.org/10.1093/mnras/stx1492
Jaeger-Erben, M., Rückert-John, J., & Schäfer, M. (2017). Soziale Innovationen für nachhaltigen Konsum: Wissenschaftliche Perspektiven, Strategien der Förderung und gelebte Praxis. In Soziale Innovationen für nachhaltigen Konsum (pp. 9-21). Springer VS, Wiesbaden. https://doi.org/10.1007/978-3-658-16545-1_1
Hezaveh, Y.D., Levasseur, L. P., & Marshall, P. J. (2017). Fast automated analysis of strong gravitational lenses with convolutional neural networks. Nature, 548(7669), 555-557. https://doi.org/10.1038/nature23463
Levasseur, L.P., Hezaveh, Y.D., & Wechsler, R.H. (2017). Uncertainties in parameters estimated with neural networks: Application to strong gravitational lensing. The Astrophysical Journal Letters, 850(1), L7. https://doi.org/10.3847/2041-8213/aa9704
Davies, A., Serjeant, S., & Bromley, J.M. (2019). Using convolutional neural networks to identify gravitational lenses in astronomical images. Monthly Notices of the Royal Astronomical Society, 487(4), 5263-5271. https://doi.org/10.1093/mnras/stz1288
Wilde, J., Serjeant, S., Bromley, J. M., Dickinson, H., Koopmans, L.V., & Metcalf, R.B. (2022). Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations. Monthly Notices of the Royal Astronomical Society, 512(3), 3464-3479. https://doi.org/10.1093/mnras/stac562
Overzier, R., Lemson, G., Angulo, R.E., Bertin, E., Blaizot, J., Henriques, B.M.B., ... & White, S.D.M. (2013). The millennium run observatory: first light. Monthly Notices of the Royal Astronomical Society, 428(1), 778-803. https://doi.org/10.1093/mnras/sts076
Glenn, J., Bradford, C.M., Rosolowsky, E., Amini, R., Alatalo, K., Armus, L., ... & Zmuidzinas, J. (2021). Galaxy evolution probe. Journal of Astronomical Telescopes, Instruments, and Systems, 7(3), 034004- 034004. https://doi.org/10.1117/1.JATIS.7.3.034004
Petkova, M., Metcalf, R.B., & Giocoli, C. (2014). glamer–ii. multiple-plane gravitational lensing. Monthly Notices of the Royal Astronomical Society, 445(2), 1954-1966. https://doi.org/10.1093/mnras/stu1860
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Articles are open access under the Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish a manuscript in this journal agree to the following terms:
- The authors reserve the right to authorship of their work and transfer to the journal the right of first publication under the terms of the Creative Commons Attribution License, which allows others to freely distribute the published work with a mandatory link to the the original work and the first publication of the work in this journal.
- Authors have the right to conclude independent additional agreements that relate to the non-exclusive distribution of the work in the form in which it was published by this journal (for example, to post the work in the electronic repository of the institution or publish as part of a monograph), providing the link to the first publication of the work in this journal.
- Other terms stated in the Copyright Agreement.