Abstract
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.
| Original language | English (US) |
|---|---|
| Article number | 038002 |
| Journal | Publications of the Astronomical Society of the Pacific |
| Volume | 131 |
| Issue number | 997 |
| DOIs | |
| State | Published - Mar 2019 |
Fingerprint
Keywords
- Machine learning
- Sky surveys
- Time domain
Cite this
Machine learning for the Zwicky transient facility. / Mahabal, Ashish; Rebbapragada, Umaa; Walters, Richard; Masci, Frank J.; Blagorodnova, Nadejda; van Roestel, Jan; Ye, Quan Zhi; Biswas, Rahul; Burdge, Kevin; Chang, Chan Kao; Duev, Dmitry A.; Zach Golkhou, V.; Miller, Adam A.; Nordin, Jakob; Ward, Charlotte; Adams, Scott; Bellm, Eric C.; Branton, Doug; Bue, Brian; Cannella, Chris; Connolly, Andrew; Dekany, Richard; Feindt, Ulrich; Hung, Tiara; Fortson, Lucy; Frederick, Sara; Fremling, C.; Gezari, Suvi; Graham, Matthew; Groom, Steven; Kasliwal, Mansi M.; Kulkarni, Shrinivas; Kupfer, Thomas; Lin, Hsing Wen; Lintott, Chris; Lunnan, Ragnhild; Parejko, John; Prince, Thomas A.; Riddle, Reed; Rusholme, Ben; Saunders, Nicholas; Sedaghat, Nima; Shupe, David L.; Singer, Leo P.; Soumagnac, Maayane T.; Szkody, Paula; Tachibana, Yutaro; Tirumala, Kushal; van Velzen, Sjoert; Wright, Darryl.
In: Publications of the Astronomical Society of the Pacific, Vol. 131, No. 997, 038002, 03.2019.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Machine learning for the Zwicky transient facility
AU - Mahabal, Ashish
AU - Rebbapragada, Umaa
AU - Walters, Richard
AU - Masci, Frank J.
AU - Blagorodnova, Nadejda
AU - van Roestel, Jan
AU - Ye, Quan Zhi
AU - Biswas, Rahul
AU - Burdge, Kevin
AU - Chang, Chan Kao
AU - Duev, Dmitry A.
AU - Zach Golkhou, V.
AU - Miller, Adam A.
AU - Nordin, Jakob
AU - Ward, Charlotte
AU - Adams, Scott
AU - Bellm, Eric C.
AU - Branton, Doug
AU - Bue, Brian
AU - Cannella, Chris
AU - Connolly, Andrew
AU - Dekany, Richard
AU - Feindt, Ulrich
AU - Hung, Tiara
AU - Fortson, Lucy
AU - Frederick, Sara
AU - Fremling, C.
AU - Gezari, Suvi
AU - Graham, Matthew
AU - Groom, Steven
AU - Kasliwal, Mansi M.
AU - Kulkarni, Shrinivas
AU - Kupfer, Thomas
AU - Lin, Hsing Wen
AU - Lintott, Chris
AU - Lunnan, Ragnhild
AU - Parejko, John
AU - Prince, Thomas A.
AU - Riddle, Reed
AU - Rusholme, Ben
AU - Saunders, Nicholas
AU - Sedaghat, Nima
AU - Shupe, David L.
AU - Singer, Leo P.
AU - Soumagnac, Maayane T.
AU - Szkody, Paula
AU - Tachibana, Yutaro
AU - Tirumala, Kushal
AU - van Velzen, Sjoert
AU - Wright, Darryl
PY - 2019/3
Y1 - 2019/3
N2 - 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.
AB - 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.
KW - Machine learning
KW - Sky surveys
KW - Time domain
UR - http://www.scopus.com/inward/record.url?scp=85063447442&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063447442&partnerID=8YFLogxK
U2 - 10.1088/1538-3873/aaf3fa
DO - 10.1088/1538-3873/aaf3fa
M3 - Article
AN - SCOPUS:85063447442
VL - 131
JO - Publications of the Astronomical Society of the Pacific
JF - Publications of the Astronomical Society of the Pacific
SN - 0004-6280
IS - 997
M1 - 038002
ER -