Journal
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
Volume 505, Issue 3, Pages 4362-4382Publisher
OXFORD UNIV PRESS
DOI: 10.1093/mnras/stab1547
Keywords
gravitational lensing: strong; galaxies: structure
Categories
Funding
- UK Science and Technology Facilities Council (STFC)
- UK STFC Rutherford Fellowship
Ask authors/readers for more resources
The study trains a CNN to predict mass profile parameters of galaxy-galaxy gravitational lenses, with significantly lower errors compared to traditional methods, especially when incorporating uncertainties predicted by the CNN. Combining neural networks with conventional techniques can greatly improve accuracy and speed in automated modelling.
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 in an automated fashion, where the CNN provides initial priors on the latter's parameters. On average, the CNN achieved errors 19 +/- 22 percent lower than the traditional method's blind modelling. The combination method instead achieved 27 +/- 11 percent lower errors over the blind modelling, reduced further to 37 +/- 11 percent when the priors also incorporated the CNN-predicted uncertainties, with errors also 17 +/- 21 percent 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 factors 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available