CaltechAUTHORS
  A Caltech Library Service

Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier

Carrasco-Davis, R. and Reyes, E. and Valenzuela, C. and Förster, F. and Estévez, P. A. and Pignata, G. and Bauer, F. E. and Reyes, I. and Sánchez-Sáez, P. and Cabrera-Vives, G. and Eyheramendy, S. and Catelan, M. and Arredondo, J. and Castillo-Navarrete, E. and Rodríguez-Mancini, D. and Ruz-Mieres, D. and Moya, A. and Sabatini-Gacitúa, L. and Sepúlveda-Cobo, C. and Mahabal, A. A. and Silva-Farfán, J. and Camacho-Iñiquez, E. and Galbany, L. (2020) Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20210204-092803262

[img] PDF - Submitted Version
See Usage Policy.

4MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210204-092803262

Abstract

We present a real-time stamp classifier of astronomical events for the ALeRCE (Automatic Learning for the Rapid Classification of Events) broker. The classifier is based on a convolutional neural network with an architecture designed to exploit rotational invariance of the images, and trained on alerts ingested from the Zwicky Transient Facility (ZTF). Using only the science, reference and difference images of the first detection as inputs, along with the metadata of the alert as features, the classifier is able to correctly classify alerts from active galactic nuclei, supernovae (SNe), variable stars, asteroids and bogus classes, with high accuracy (∼94%) in a balanced test set. In order to find and analyze SN candidates selected by our classifier from the ZTF alert stream, we designed and deployed a visualization tool called SN Hunter, where relevant information about each possible SN is displayed for the experts to choose among candidates to report to the Transient Name Server database. We have reported 3060 SN candidates to date (9.2 candidates per day on average), of which 394 have been confirmed spectroscopically. Our ability to report objects using only a single detection means that 92% of the reported SNe occurred within one day after the first detection. ALeRCE has only reported candidates not otherwise detected or selected by other groups, therefore adding new early transients to the bulk of objects available for early follow-up. Our work represents an important milestone toward rapid alert classifications with the next generation of large etendue telescopes, such as the Vera C. Rubin Observatory's Legacy Survey of Space and Time.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2008.03309arXivDiscussion Paper
ORCID:
AuthorORCID
Carrasco-Davis, R.0000-0003-4673-8791
Reyes, E.0000-0003-3455-9358
Valenzuela, C.0000-0001-5306-1390
Förster, F.0000-0003-3459-2270
Estévez, P. A.0000-0001-9164-4722
Pignata, G.0000-0003-0006-0188
Bauer, F. E.0000-0002-8686-8737
Reyes, I.0000-0003-3627-0216
Sánchez-Sáez, P.0000-0003-0820-4692
Cabrera-Vives, G.0000-0002-2720-7218
Eyheramendy, S.0000-0003-4723-9660
Catelan, M.0000-0001-6003-8877
Arredondo, J.0000-0002-2045-7134
Ruz-Mieres, D.0000-0002-1292-2374
Moya, A.0000-0002-7003-5087
Mahabal, A. A.0000-0003-2242-0244
Galbany, L.0000-0002-1296-6887
Additional Information:The authors acknowledge support from the Chilean Ministry of Economy, Development, and Tourisms Millennium Science Initiative through grant IC12009, awarded to the Millennium Institute of Astrophysics (RC, ER, CV, FF, PE, GP, FEB, IR, PSS, GC, SE, Ja, EC, DR, DRM, MC) and from the National Agency for Research and Development (ANID) grants: BASAL Center of Mathematical Modelling AFB-170001 (FF) and Centro de Astrofsica y Teconologas Afifines AFB-170002 (FEB, PSS, MC); FONDECYT Regular #1171678 (PE), #1200710 (FF), #1190818(FEB), #1200495 (FEB), #1171273 (MC), #1201793(GP); FONDECYT Postdoctorado #3200250 (PSS); Magster Nacional 2019 #22190947 (ER). Software: Aladin (Bonnarel et al. 2000), Apache ECharts8, Apache Kafka9, Apache Spark (?), ASTROIDE (BRAHEM et al. 2018), Astropy (Astropy Collaboration et al. 2013), catsHTM (Soumagnac & Ofek 2018), Dask (Rocklin 2015), Jupyter, Keras (Chollet & others 2018), Matplotlib (Hunter 2007), NED (Steer et al. 2016), Pandas (McKinney 2010), Prometheus, Python, scikit-learn (Pedregosa et al. 2011), Simbad-CDS (Wenger et al. 2000), Tensorflow (Martn Abadi et al. 2015), Vue, Vuetify, PostgreSQL.
Funders:
Funding AgencyGrant Number
Iniciativa Científica Milenio del Ministerio de EconomíaIC12009
BASAL-CATAAFB-170001
BASAL-CATAAFB-170002
Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)1171678
Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)1200710
Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)1190818
Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)1200495
Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)1171273
Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)1201793
Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)3200250
Magster Nacional 201922190947
Subject Keywords:Supernovae | Alert Broker Visualization Tools | Deep Learning
Record Number:CaltechAUTHORS:20210204-092803262
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210204-092803262
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:107920
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:05 Feb 2021 20:55
Last Modified:05 Feb 2021 20:55

Repository Staff Only: item control page