Combining neural networks with galaxy light subtraction for discovering strong lenses in the HSC SSP

TL;DR

This paper introduces a new technique that subtracts galaxy light from images to enhance the detection of strong gravitational lenses using neural networks, leading to improved classification accuracy in large imaging surveys.

Contribution

The study demonstrates that combining light-subtracted images with original images enhances CNN performance in identifying strong lenses in the HSC SSP dataset.

Findings

Improved AUC to 0.841 with combined images

Light subtraction increases contrast of lensed sources

Combining images mitigates residual subtraction artifacts

Abstract

Galaxy-scale strong gravitational lenses are valuable objects for a variety of astrophysical and cosmological applications. Strong lensing galaxies are rare, so efficient search methods, such as convolutional neural networks, are often used on large imaging datasets. In this work, we apply a new technique to improve the performance of supervised neural networks by subtracting the central (lensing) galaxy light from both the training and test datasets. We use multiband imaging data from the Hyper Suprime-Cam Subaru Strategic Program (HSC SSP) as our training and test datasets. By subtracting the lensing galaxy light, we increase the contrast of the lensed source compared to the original imaging data. We also apply the light subtraction to non-lenses in order to compare them to the light-subtracted lenses. Residual features resulting from poor light subtraction can adversely affect the performance of networks trained on the subtracted images alone. We find that combining the light-subtracted images with the original gri-band images for training and classification can overcome this and improve the overall classification accuracy. We find the area under the receiver operating characteristic curve can be improved to 0.841 using the combination of the fiducial images and light-subtracted images, compared to 0.808 for the fiducial imaging dataset alone. This may be a promising technique for improving future lens searches using CNNs.