Skip navigation
  • INAF logo
  • Home
  • Communities
    & Collections
  • Research outputs
  • Researchers
  • Organization units
  • Projects
  • Explore by
    • Research outputs
    • Researchers
    • Organization units
    • Projects
  • Login:
    • My DSpace
    • Receive email
      updates
    • Edit Account details
  • Italian
  • English

  1. OA@INAF
  2. PRODOTTI RICERCA INAF
  3. 1 CONTRIBUTI IN RIVISTE (Journal articles)
  4. 1.01 Articoli in rivista
Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.12386/29539
Title: Testing convolutional neural networks for finding strong gravitational lenses in KiDS
Authors: Petrillo, C. E.
TORTORA, CRESCENZO 
Chatterjee, S.
Vernardos, G.
Koopmans, L. V. E.
Verdoes Kleijn, G.
NAPOLITANO, NICOLA ROSARIO 
Covone, G.
Kelvin, L. S.
Hopkins, A. M.
Issue Date: 2019
Journal: MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 
Number: 482
Issue: 1
First Page: 807
Abstract: Convolutional Neural Networks (ConvNets) are one of the most promising methods for identifying strong gravitational lens candidates in survey data. We present two ConvNet lens-finders that we have trained with a dataset composed of real galaxies from the Kilo Degree Survey (KiDS) and simulated lensed sources. One ConvNet is trained with single r-band galaxy images, hence basing the classification mostly on the morphology. While the other ConvNet is trained on g-r-i composite images, relying mostly on colours and morphology. We have tested the ConvNet lens-finders on a sample of 21 789 luminous red galaxies (LRGs) selected from KiDS and we have analysed and compared the results with our previous ConvNet lens-finder on the same sample. The new lens-finders achieve a higher accuracy and completeness in identifying gravitational lens candidates, especially the single-band ConvNet. Our analysis indicates that this is mainly due to improved simulations of the lensed sources. In particular, the single-band ConvNet can select a sample of lens candidates with {∼ }40{{ per cent}} purity, retrieving three out of four of the confirmed gravitational lenses in the LRG sample. With this particular setup and limited human intervention, it will be possible to retrieve, in future surveys such as Euclid, a sample of lenses exceeding in size the total number of currently known gravitational lenses.
URI: http://hdl.handle.net/20.500.12386/29539
URL: https://academic.oup.com/mnras/article/482/1/807/5116172
ISSN: 0035-8711
DOI: 10.1093/mnras/sty2683
Bibcode ADS: 2019MNRAS.482..807P
Fulltext: open
Appears in Collections:1.01 Articoli in rivista

Files in This Item:
File Description SizeFormat 
Petrillo+19_MNRAS_482_807.pdfPDF editoriale7.17 MBAdobe PDFView/Open
Show full item record

Page view(s)

4
checked on Jan 18, 2021

Download(s)

1
checked on Jan 18, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are published in Open Access, unless otherwise indicated.


Explore by
  • Communities
    & Collections
  • Research outputs
  • Researchers
  • Organization units
  • Projects

Informazioni e guide per autori

https://openaccess-info.inaf.it: tutte le informazioni sull'accesso aperto in INAF

Come si inserisce un prodotto: le guide a OA@INAF

La Policy INAF sull'accesso aperto

Documenti e modelli scaricabili

Feedback
Built with DSpace-CRIS - Extension maintained and optimized by Logo 4SCIENCE