Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks

The volume of data that will be produced by new-generation surveys requires automatic classification methods to select and analyze sources. Indeed, this is the case for the search for strong gravitational lenses, where the population of the detectable lensed sources is only a very small fraction of the full source population. In this paper, we present a morphological classification method for recognizing strong gravitational lenses. The method, based on a Convolutional Neural Network (CNN), is applied to $255$ square degrees of the Kilo Degree Survey (KiDS), one of the current-generation optical wide surveys conducted with the VLT survey telescope (VST). The current CNN is optimized to recognize lenses with Einstein radii $> 1.4$ arcsec, about twice the $r$-band seeing in KiDS. We construct a sample of $21789$ color-magnitude selected Luminous Red Galaxies (LRG) of which three are known lenses. From this sample the CNN retrieves 761 strong-lens candidates and correctly classifies two out of three of the known lenses. The misclassified lens has an Einstein radius well below the range on which the algorithm is trained. We down-select the most reliable 56 candidates by a joint visual inspection. This final sample is presented and discussed. A consistency check on the estimated Einstein radii of the final sample of candidates suggests that it is likely composed of $\sim$22 reliable lenses. A result consistent with what is expected from lens-statistics simulations, when applying our color-magnitude and Einstein-radius cuts. A conservative estimate based on our results shows that with our proposed method it should be possible to find $\sim100$ massive LRG-galaxy lenses at $z< 0.4$ in KiDS when completed. In the most optimistic scenario this number can grow considerably (to maximally $\sim$2400 lenses). [Abridged]