Auto-identification of unphysical source reconstructions in strong gravitational lens modelling

TL;DR

This paper presents a CNN-based method to identify and correct unphysical source reconstructions in automated strong gravitational lens modelling, significantly improving the reliability and automation of the process.

Contribution

The study introduces a CNN that detects unphysical reconstructions and automatically re-initializes lens models, enhancing automation in lens modelling workflows.

Findings

CNN classifies source reconstructions with >99% precision and recall for simple sources.

The CNN achieves 89% precision and recall on complex HUDF sources without retraining.

Using CNN predictions reduces unphysical reconstructions by 69%.

Abstract

With the advent of next-generation surveys and the expectation of discovering huge numbers of strong gravitational lens systems, much effort is being invested into developing automated procedures for handling the data. The several orders of magnitude increase in the number of strong galaxy-galaxy lens systems is an insurmountable challenge for traditional modelling techniques. Whilst machine learning techniques have dramatically improved the efficiency of lens modelling, parametric modelling of the lens mass profile remains an important tool for dealing with complex lensing systems. In particular, source reconstruction methods are necessary to cope with the irregular structure of high-redshift sources. In this paper, we consider a Convolutional Neural Network (CNN) that analyses the outputs of semi-analytic methods which parametrically model the lens mass and linearly reconstruct the source surface brightness distribution. We show the unphysical source reconstructions that arise as a result of incorrectly initialised lens models can be effectively caught by our CNN. Furthermore, the CNN predictions can be used to automatically re-initialise the parametric lens model, avoiding unphysical source reconstructions. The CNN, trained on reconstructions of lensed S\'ersic sources, accurately classifies source reconstructions of the same type with a precision $P > 0.99$ and recall $R > 0.99$. The same CNN, without re-training, achieves $P=0.89$ and $R=0.89$ when classifying source reconstructions of more complex lensed HUDF sources. Using the CNN predictions to re-initialise the lens modelling procedure, we achieve a 69 per cent decrease in the occurrence of unphysical source reconstructions. This combined CNN and parametric modelling approach can greatly improve the automation of lens modelling.