Alert Classification for the ALeRCE Broker System: The Light Curve Classifier. (arXiv:2008.03311v1 [astro-ph.IM])
<a href="http://arxiv.org/find/astro-ph/1/au:+Sanchez_Saez_P/0/1/0/all/0/1">P. S&#xe1;nchez-S&#xe1;ez</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Reyes_I/0/1/0/all/0/1">I. Reyes</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Valenzuela_C/0/1/0/all/0/1">C. Valenzuela</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Forster_F/0/1/0/all/0/1">F. F&#xf6;rster</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Eyheramendy_S/0/1/0/all/0/1">S. Eyheramendy</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Elorrieta_F/0/1/0/all/0/1">F. Elorrieta</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Bauer_F/0/1/0/all/0/1">F. E. Bauer</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Cabrera_Vives_G/0/1/0/all/0/1">G. Cabrera-Vives</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Estevez_P/0/1/0/all/0/1">P. A. Est&#xe9;vez</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Catelan_M/0/1/0/all/0/1">M. Catelan</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Pignata_G/0/1/0/all/0/1">G. Pignata</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Huijse_P/0/1/0/all/0/1">P. Huijse</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Cicco_D/0/1/0/all/0/1">D. De Cicco</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Arevalo_P/0/1/0/all/0/1">P. Ar&#xe9;valo</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Carrasco_Davis_R/0/1/0/all/0/1">R. Carrasco-Davis</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Abril_J/0/1/0/all/0/1">J. Abril</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kurtev_R/0/1/0/all/0/1">R. Kurtev</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Borissova_J/0/1/0/all/0/1">J. Borissova</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Arredondo_J/0/1/0/all/0/1">J. Arredondo</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Castillo_Navarrete_E/0/1/0/all/0/1">E. Castillo-Navarrete</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Rodriguez_D/0/1/0/all/0/1">D. Rodriguez</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Ruz_Mieres_D/0/1/0/all/0/1">D. Ruz-Mieres</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Moya_A/0/1/0/all/0/1">A. Moya</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Sabatini_Gacitua_L/0/1/0/all/0/1">L. Sabatini-Gacit&#xfa;a</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Sepulveda_Cobo_C/0/1/0/all/0/1">C. Sep&#xfa;lveda-Cobo</a>

We present the first version of the ALeRCE (Automatic Learning for the Rapid
Classification of Events) broker light curve classifier. ALeRCE is currently
processing the Zwicky Transient Facility (ZTF) alert stream, in preparation for
the Vera C. Rubin Observatory. The ALeRCE light curve classifier uses
variability features computed from the ZTF alert stream, and colors obtained
from AllWISE and ZTF photometry. We apply a Balanced Hierarchical Random Forest
algorithm with a two-level scheme, where the top level classifies each source
as periodic, stochastic, or transient, and the bottom level further resolve
each hierarchical class, yielding a total of 15 classes. This classifier
corresponds to the first attempt to classify multiple classes of stochastic
variables (including nucleus- and host-dominated active galactic nuclei,
blazars, young stellar objects, and cataclysmic variables) in addition to
different classes of periodic and transient sources, using real data. We
created a labeled set using various public catalogs (such as the Catalina
Surveys and {em Gaia} DR2 variable stars catalogs, and the Million Quasars
catalog), and we classify all objects with $geq6$ $g$-band or $geq6$ $r$-band
detections in ZTF (868,371 sources as of 2020/06/09), providing updated
classifications for sources with new alerts every day. For the top level we
obtain macro-averaged precision and recall scores of 0.96 and 0.99,
respectively, and for the bottom level we obtain macro-averaged precision and
recall scores of 0.57 and 0.76, respectively. Updated classifications from the
light curve classifier can be found at this http URL

We present the first version of the ALeRCE (Automatic Learning for the Rapid
Classification of Events) broker light curve classifier. ALeRCE is currently
processing the Zwicky Transient Facility (ZTF) alert stream, in preparation for
the Vera C. Rubin Observatory. The ALeRCE light curve classifier uses
variability features computed from the ZTF alert stream, and colors obtained
from AllWISE and ZTF photometry. We apply a Balanced Hierarchical Random Forest
algorithm with a two-level scheme, where the top level classifies each source
as periodic, stochastic, or transient, and the bottom level further resolve
each hierarchical class, yielding a total of 15 classes. This classifier
corresponds to the first attempt to classify multiple classes of stochastic
variables (including nucleus- and host-dominated active galactic nuclei,
blazars, young stellar objects, and cataclysmic variables) in addition to
different classes of periodic and transient sources, using real data. We
created a labeled set using various public catalogs (such as the Catalina
Surveys and {em Gaia} DR2 variable stars catalogs, and the Million Quasars
catalog), and we classify all objects with $geq6$ $g$-band or $geq6$ $r$-band
detections in ZTF (868,371 sources as of 2020/06/09), providing updated
classifications for sources with new alerts every day. For the top level we
obtain macro-averaged precision and recall scores of 0.96 and 0.99,
respectively, and for the bottom level we obtain macro-averaged precision and
recall scores of 0.57 and 0.76, respectively. Updated classifications from the
light curve classifier can be found at this http URL

http://arxiv.org/icons/sfx.gif