A Package for the Automated Classification of Images Containing Supernova Light Echoes

TL;DR

This paper introduces ALED, a Python package utilizing capsule networks for automated detection and localization of supernova light echoes in astronomical images, significantly improving efficiency and accuracy over manual methods.

Contribution

ALED is the first package to combine capsule networks with routing visualization for detecting and localizing supernova light echoes in large astronomical datasets.

Findings

Achieved 90% classification accuracy on test data.

Successfully localized light echoes in images with routing visualization.

Identified overlooked light echoes in a large dataset.

Abstract

Context. The so-called "light echoes" of supernovae - the apparent motion of outburst-illuminated interstellar dust - can be detected in astronomical difference images; however, light echoes are extremely rare which makes manual detection an arduous task. Surveys for centuries-old supernova light echoes can involve hundreds of pointings of wide-field imagers wherein the subimages from each CCD amplifier require examination. Aims. We introduce ALED, a Python package that implements (i) a capsule network trained to automatically identify images with a high probability of containing at least one supernova light echo, and (ii) routing path visualization to localize light echoes and/or light echo-like features in the identified images. Methods. We compare the performance of the capsule network implemented in ALED (ALED-m) to several capsule and convolutional neural networks of different architectures. We also apply ALED to a large catalogue of astronomical difference images and manually inspect candidate light echo images for human verification. Results. ALED-m, was found to achieve 90% classification accuracy on the test set, and to precisely localize the identified light echoes via routing path visualization. From a set of 13,000+ astronomical images, ALED identified a set of light echoes that had been overlooked in manual classification. ALED is available via github.com/LightEchoDetection/ALED.