Testing convolutional neural networks for finding strong gravitational lenses in KiDSPetrillo, C. E., Tortora, C., Chatterjee, S., Vernardos, G., Koopmans, L. V. E., Verdoes Kleijn, G., Napolitano, N. R., Covone, G., Kelvin, L. S. & Hopkins, A. M., Jan-2019, In : Monthly Notices of the Royal Astronomical Society. 482, 1, p. 807-820 14 p.
Research output: Contribution to journal › Article › Academic › peer-review
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 similar to 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.
|Number of pages||14|
|Journal||Monthly Notices of the Royal Astronomical Society|
|Publication status||Published - Jan-2019|
- EARLY-TYPE GALAXIES, INITIAL MASS FUNCTION, DIGITAL SKY SURVEY, TO-LIGHT RATIO, DARK-MATTER, PHOTOMETRIC REDSHIFTS, ACS SURVEY, 2-DIMENSIONAL KINEMATICS, AUTOMATIC DETECTION, INTERNAL STRUCTURE
No data available