Machine Learning for the Zwicky Transient Facility. (arXiv:1902.01936v1 [astro-ph.IM])

Machine Learning for the Zwicky Transient Facility. (arXiv:1902.01936v1 [astro-ph.IM])
<a href="http://arxiv.org/find/astro-ph/1/au:+Mahabal_A/0/1/0/all/0/1">Ashish Mahabal</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Rebbapragada_U/0/1/0/all/0/1">Umaa Rebbapragada</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Walters_R/0/1/0/all/0/1">Richard Walters</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Masci_F/0/1/0/all/0/1">Frank J. Masci</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Blagorodnova_N/0/1/0/all/0/1">Nadejda Blagorodnova</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Roestel_J/0/1/0/all/0/1">Jan van Roestel</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Ye_Q/0/1/0/all/0/1">Quan-Zhi Ye</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Biswas_R/0/1/0/all/0/1">Rahul Biswas</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Burdge_K/0/1/0/all/0/1">Kevin Burdge</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Chang_C/0/1/0/all/0/1">Chan-Kao Chang</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Duev_D/0/1/0/all/0/1">Dmitry A. Duev</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Golkhou_V/0/1/0/all/0/1">V. Zach Golkhou</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Miller_A/0/1/0/all/0/1">Adam A. Miller</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Nordin_J/0/1/0/all/0/1">Jakob Nordin</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Ward_C/0/1/0/all/0/1">Charlotte Ward</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Adams_S/0/1/0/all/0/1">Scott Adams</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Bellm_E/0/1/0/all/0/1">Eric C. Bellm</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Branton_D/0/1/0/all/0/1">Doug Branton</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Bue_B/0/1/0/all/0/1">Brian Bue</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Cannella_C/0/1/0/all/0/1">Chris Cannella</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Connolly_A/0/1/0/all/0/1">Andrew Connolly</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Dekany_R/0/1/0/all/0/1">Richard Dekany</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Feindt_U/0/1/0/all/0/1">Ulrich Feindt</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Hung_T/0/1/0/all/0/1">Tiara Hung</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Fortson_L/0/1/0/all/0/1">Lucy Fortson</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Frederick_S/0/1/0/all/0/1">Sara Frederick</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Fremling_C/0/1/0/all/0/1">C. Fremling</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Gezari_S/0/1/0/all/0/1">Suvi Gezari</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Graham_M/0/1/0/all/0/1">Matthew Graham</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Groom_S/0/1/0/all/0/1">Steven Groom</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kasliwal_M/0/1/0/all/0/1">Mansi M. Kasliwal</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kulkarni_S/0/1/0/all/0/1">Shrinivas Kulkarni</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kupfer_T/0/1/0/all/0/1">Thomas Kupfer</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Lin_H/0/1/0/all/0/1">Hsing Wen Lin</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Lintott_C/0/1/0/all/0/1">Chris Lintott</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Lunnan_R/0/1/0/all/0/1">Ragnhild Lunnan</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Parejko_J/0/1/0/all/0/1">John Parejko</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Prince_T/0/1/0/all/0/1">Thomas A. Prince</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Riddle_R/0/1/0/all/0/1">Reed Riddle</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Rusholme_B/0/1/0/all/0/1">Ben Rusholme</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Saunders_N/0/1/0/all/0/1">Nicholas Saunders</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Sedaghat_N/0/1/0/all/0/1">Nima Sedaghat</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Shupe_D/0/1/0/all/0/1">David L. Shupe</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Singer_L/0/1/0/all/0/1">Leo P. Singer</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Soumagnac_M/0/1/0/all/0/1">Maayane T. Soumagnac</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Szkody_P/0/1/0/all/0/1">Paula Szkody</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Tachibana_Y/0/1/0/all/0/1">Yutaro Tachibana</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Tirumala_K/0/1/0/all/0/1">Kushal Tirumala</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Velzen_S/0/1/0/all/0/1">Sjoert van Velzen</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Wright_D/0/1/0/all/0/1">Darryl Wright</a>

The Zwicky Transient Facility is a large optical survey in multiple filters
producing hundreds of thousands of transient alerts per night. We describe here
various machine learning (ML) implementations and plans to make the maximal use
of the large data set by taking advantage of the temporal nature of the data,
and further combining it with other data sets. We start with the initial steps
of separating bogus candidates from real ones, separating stars and galaxies,
and go on to the classification of real objects into various classes. Besides
the usual methods (e.g., based on features extracted from light curves) we also
describe early plans for alternate methods including the use of domain
adaptation, and deep learning. In a similar fashion we describe efforts to
detect fast moving asteroids. We also describe the use of the Zooniverse
platform for helping with classifications through the creation of training
samples, and active learning. Finally we mention the synergistic aspects of ZTF
and LSST from the ML perspective.

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