Identifying Transients in the Dark Energy Survey using Convolutional Neural Networks

TL;DR

This paper demonstrates that convolutional neural networks can effectively identify astrophysical transients in the Dark Energy Survey data, matching previous methods' efficiency without manual feature engineering and improving classification accuracy through relabeling.

Contribution

The study introduces an automated CNN-based approach for transient identification in astronomical images, eliminating the need for feature extraction and enhancing classification accuracy.

Findings

CNNs match random forest efficiency in artifact rejection

CNNs identify mislabeled images, improving data quality

Enhanced classification results after relabeling images

Abstract

The ability to discover new transients via image differencing without direct human intervention is an important task in observational astronomy. For these kind of image classification problems, machine Learning techniques such as Convolutional Neural Networks (CNNs) have shown remarkable success. In this work, we present the results of an automated transient identification on images with CNNs for an extant dataset from the Dark Energy Survey Supernova program (DES-SN), whose main focus was on using Type Ia supernovae for cosmology. By performing an architecture search of CNNs, we identify networks that efficiently select non-artifacts (e.g. supernovae, variable stars, AGN, etc.) from artifacts (image defects, mis-subtractions, etc.), achieving the efficiency of previous work performed with random Forests, without the need to expend any effort in feature identification. The CNNs also help us identify a subset of mislabeled images. Performing a relabeling of the images in this subset, the resulting classification with CNNs is significantly better than previous results.