Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting.

The vast quantity of strong galaxy-galaxy gravitational lenses expected by future large-scale surveys necessitates the development of automated methods to efficiently model their mass profiles. For this purpose, we train an approximate Bayesian convolutional neural network (CNN) to predict mass profile parameters and associated uncertainties, and compare its accuracy to that of conventional parametric modelling for a range of increasingly complex lensing systems. These include standard smooth parametric density profiles, hydrodynamical EAGLE galaxies and the inclusion of foreground mass structures, combined with parametric sources and sources extracted from the Hubble Ultra Deep Field. In addition, we also present a method for combining the CNN with traditional parametric density profile fitting where the CNN provides initial priors on the latter's parameters. Across the test sets of images, the CNN achieved errors 19 $\pm$ 22 per cent lower than the traditional method's blind modelling. Using these CNN-predicted parameters as priors for this method to use in an automated fashion instead achieved 27 $\pm$ 11 per cent lower errors over the latter. This was reduced further to 37 $\pm$ 11 per cent when also incorporating the CNN-predicted uncertainties into the priors, helping it to avoid local minima in parameter space, with errors also 17 $\pm$ 21 per cent lower than the CNN by itself. While the CNN is undoubtedly the fastest modelling method, the combination of the two increases the speed of conventional fitting alone by a factor of 1.73 and 1.19 with and without CNN-predicted uncertainties, respectively. This, combined with greatly improved accuracy, highlights the benefits one can obtain through combining neural networks with conventional techniques in order to achieve an efficient automated modelling approach.