A search for galaxy-scale strong gravitational lenses in the Ultraviolet Near Infrared Optical Northern Survey (UNIONS)

We present a search for galaxy-scale strong gravitational lenses in the initial 2 500 square degrees of the Canada-France Imaging Survey (CFIS). We design a convolutional neural network (CNN) committee that we apply on a selection of 2 344 002 exquisite-seeing r-band images of color-selected luminous red galaxies (LRGs). Our training set is particularly realistic, since the deflector and source images of our mock lensing systems are taken from real CFIS r-band and Hubble Space Telescope (HST) images. Only the lensing effect is simulated. A total of 9 460 candidates obtain a score above 0.5 with the CNN committee. After a visual inspection of the candidates, we find a total of 133 lens candidates, among which 104 are completely new. The set of false positives mainly contains ring, spiral and merger galaxies and to a smaller extent galaxies with nearby companions. We classify 32 of the lens candidates as secure lenses and 101 as maybe lenses. For the 32 best-quality lenses, we also fit a singular isothermal ellipsoid mass profile with external shear along with an elliptical Sersic profile for the lens and source light. This modeling step is fully automated and provides distributions of properties for both sources and lenses. We also use auto-encoders to provide a lens/source deblended image of the best lens candidates.