CaltechAUTHORS
  A Caltech Library Service

Effective image differencing with convolutional neural networks for real-time transient hunting

Sedaghat, Nima and Mahabal, Ashish (2018) Effective image differencing with convolutional neural networks for real-time transient hunting. Monthly Notices of the Royal Astronomical Society, 476 (4). pp. 5365-5376. ISSN 0035-8711. https://resolver.caltech.edu/CaltechAUTHORS:20180613-110454392

[img] PDF - Published Version
See Usage Policy.

5Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20180613-110454392

Abstract

Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying point-spread function (PSF) and small brightness variations in many sources, as well as artefacts resulting from saturated stars and, in general, matching errors. Very often the differencing is done with a reference image that is deeper than individual images and the attendant difference in noise characteristics can also lead to artefacts. We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image-subtraction pipeline – image registration, background subtraction, noise removal, PSF matching and subtraction – in a single real-time convolutional network. Once trained, the method works lightening-fast and, given that it performs multiple steps in one go, the time saved and false positives eliminated for multi-CCD surveys like Zwicky Transient Facility and Large Synoptic Survey Telescope will be immense, as millions of subtractions will be needed per night.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1093/mnras/sty613DOIArticle
ORCID:
AuthorORCID
Mahabal, Ashish0000-0003-2242-0244
Additional Information:© 2018 The Author(s). Published by Oxford University Press on behalf of the Royal Astronomical Society. Accepted 2018 February 25. Received 2018 February 19; in original form 2017 October 5. Published: 10 April 2018. AM was supported in part by the NSF grants AST-0909182, AST-1313422, AST-1413600 and AST-1518308, and by the Ajax Foundation.
Funders:
Funding AgencyGrant Number
NSFAST-0909182
NSFAST-1313422
NSFAST-1413600
NSFAST-1518308
Ajax FoundationUNSPECIFIED
Subject Keywords:methods: data analysis – techniques: image processing – surveys – supernovae: general
Issue or Number:4
Record Number:CaltechAUTHORS:20180613-110454392
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20180613-110454392
Official Citation:Nima Sedaghat, Ashish Mahabal; Effective image differencing with convolutional neural networks for real-time transient hunting, Monthly Notices of the Royal Astronomical Society, Volume 476, Issue 4, 1 June 2018, Pages 5365–5376, https://doi.org/10.1093/mnras/sty613
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:87064
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:13 Jun 2018 18:14
Last Modified:03 Oct 2019 19:51

Repository Staff Only: item control page