A Comparative Study of Convolutional Neural Networks for the Detection of Strong Gravitational Lensing
| العنوان: | A Comparative Study of Convolutional Neural Networks for the Detection of Strong Gravitational Lensing |
|---|---|
| المؤلفون: | Andrea DeMarco, Eva Sciacca, Daniel Magro, Kristian Zarb Adami, Simone Riggi |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Strong gravitational lensing, FOS: Physical sciences, Image processing, 02 engineering and technology, Astrophysics::Cosmology and Extragalactic Astrophysics, 01 natural sciences, Execution time, Convolutional neural network, Image (mathematics), Gravitation, Gravitational lenses, Very large array telescopes, 020204 information systems, Machine learning, 0103 physical sciences, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Cosmology -- Observations, Instrumentation and Methods for Astrophysics (astro-ph.IM), 010303 astronomy & astrophysics, High resolution imaging, Physics, business.industry, Image and Video Processing (eess.IV), Astrophysics::Instrumentation and Methods for Astrophysics, Astronomy and Astrophysics, Modular design, Electrical Engineering and Systems Science - Image and Video Processing, Gravitational lens, Space and Planetary Science, Artificial intelligence, business, Astrophysics - Instrumentation and Methods for Astrophysics |
| الوصف: | As we enter the era of large-scale imaging surveys with the upcoming telescopes such as the Large Synoptic Survey Telescope (LSST) and the Square Kilometre Array (SKA), it is envisaged that the number of known strong gravitational lensing systems will increase dramatically. However, these events are still very rare and require the efficient processing of millions of images. In order to tackle this image processing problem, we present machine learning techniques and apply them to the gravitational lens finding challenge. The convolutional neural networks (CNNs) presented here have been reimplemented within a new, modular, and extendable framework, Lens EXtrActor CaTania University of Malta (LEXACTUM). We report an area under the curve (AUC) of 0.9343 and 0.9870, and an execution time of 0.0061 and 0.0594 s per image, for the Space and Ground data sets, respectively, showing that the results obtained by CNNs are very competitive with conventional methods (such as visual inspection and arc finders) for detecting gravitational lenses. peer-reviewed |
| اللغة: | English |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b13884a876f450305322f89c87fee842 http://arxiv.org/abs/2106.01754 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....b13884a876f450305322f89c87fee842 |
| قاعدة البيانات: | OpenAIRE |
| الوصف غير متاح. |