HOLISMOKES. IV. Efficient mass modeling of strong lenses through deep learning
Abstract
Modeling the mass distributions of strong gravitational lenses is often necessary in order to use them as astrophysical and cosmological probes. With the large number of lens systems (≳10^{5}) expected from upcoming surveys, it is timely to explore efficient modeling approaches beyond traditional Markov chain Monte Carlo techniques that are time consuming. We train a convolutional neural network (CNN) on images of galaxyscale lens systems to predict the five parameters of the singular isothermal ellipsoid (SIE) mass model (lens center x and y, complex ellipticity e_{x} and e_{y}, and Einstein radius θ_{E}). To train the network we simulate images based on real observations from the Hyper SuprimeCam Survey for the lens galaxies and from the Hubble Ultra Deep Field as lensed galaxies. We tested different network architectures and the effect of different data sets, such as using only double or quad systems defined based on the source center and using different input distributions of θ_{E}. We find that the CNN performs well, and with the network trained on both doubles and quads with a uniform distribution of θ_{E} > 0.5″ we obtain the following median values with 1σ scatter: Δx = (0.00_{0.30}^{+0.30})″, Δy = (0.00_{0.29}^{+0.30})″, Δθ_{E} = (0.07_{0.12}^{+0.29})″, Δe_{x} = 0.01_{0.09}^{+0.08}, and Δe_{y} = 0.00_{0.09}^{+0.08}. The bias in θ_{E} is driven by systems with small θ_{E}. Therefore, when we further predict the multiple lensed image positions and timedelays based on the network output, we apply the network to the sample limited to θ_{E} > 0.8″. In this case the offset between the predicted and input lensed image positions is (0.00_{0.29}^{+0.29})″ and (0.00_{0.31}^{+0.32})″ for the x and y coordinates, respectively. For the fractional difference between the predicted and true timedelay, we obtain 0.04_{0.05}^{+0.27}. Our CNN model is able to predict the SIE parameter values in fractions of a second on a single CPU, and with the output we can predict the image positions and timedelays in an automated way, such that we are able to process efficiently the huge amount of expected galaxyscale lens detections in the near future.
 Publication:

Astronomy and Astrophysics
 Pub Date:
 February 2021
 DOI:
 10.1051/00046361/202039574
 arXiv:
 arXiv:2010.00602
 Bibcode:
 2021A&A...646A.126S
 Keywords:

 gravitational lensing: strong;
 methods: data analysis;
 Astrophysics  Astrophysics of Galaxies
 EPrint:
 17 pages, 14 Figures