Title: What’s the Difference? The Potential for Convolutional Neural Networks for Transient Detection without Template Subtraction

Abstract

Abstract We present a study of the potential for convolutional neural networks (CNNs) to enable separation of astrophysical transients from image artifacts, a task known as “real–bogus” classification, without requiring a template-subtracted (or difference) image, which requires a computationally expensive process to generate, involving image matching on small spatial scales in large volumes of data. Using data from the Dark Energy Survey, we explore the use of CNNs to (1) automate the real–bogus classification and (2) reduce the computational costs of transient discovery. We compare the efficiency of two CNNs with similar architectures, one that uses “image triplets” (templates, search, and difference image) and one that takes as input the template and search only. We measure the decrease in efficiency associated with the loss of information in input, finding that the testing accuracy is reduced from ∼96% to ∼91.1%. We further investigate how the latter model learns the required information from the template and search by exploring the saliency maps. Our work (1) confirms that CNNs are excellent models for real–bogus classification that rely exclusively on the imaging data and require no feature engineering task and (2) demonstrates that high-accuracy (>90%) models can be built without the need to constructmore » difference images, but some accuracy is lost. Because, once trained, neural networks can generate predictions at minimal computational costs, we argue that future implementations of this methodology could dramatically reduce the computational costs in the detection of transients in synoptic surveys like Rubin Observatory's Legacy Survey of Space and Time by bypassing the difference image analysis entirely.« less

Authors:

Acero-Cuellar, Tatiana ;

• Search DOE PAGES for author "Acero-Cuellar, Tatiana"
• Search DOE PAGES for ORCID "0000-0002-5947-2454"

Bianco, Federica ;

• Search DOE PAGES for author "Bianco, Federica"
• Search DOE PAGES for ORCID "0000-0003-1953-8727"

Dobler, Gregory ;

• Search DOE PAGES for author "Dobler, Gregory"
• Search DOE PAGES for ORCID "0000-0002-9276-3261"

Sako, Masao ;

• Search DOE PAGES for author "Sako, Masao"
• Search DOE PAGES for ORCID "0000-0003-2764-7093"

Qu, Helen ;

• Search DOE PAGES for author "Qu, Helen"
• Search DOE PAGES for ORCID "0000-0003-1899-9791"

The LSST Dark Energy Science Collaboration

Publication Date:

Fri Aug 18 00:00:00 EDT 2023

Sponsoring Org.:

USDOE

OSTI Identifier:

1995913

Grant/Contract Number:  

FOA-0002424

Resource Type:

Published Article

Journal Name:

The Astronomical Journal

Additional Journal Information:

Journal Name: The Astronomical Journal Journal Volume: 166 Journal Issue: 3; Journal ID: ISSN 0004-6256

Publisher:

American Astronomical Society

Country of Publication:

United States

Language:

English