The data for "The ZTF Source Classification Project: III. A Catalog of Variable Sources"

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Healy, Brian F., Coughlin, Michael W., Mahabal, Ashish A., Jegou du Laz, Theophile, Drake, Andrew, Graham, Matthew J., Hillenbrand, Lynne A., van Roestel, Jan, Szkody, Paula, Zielske, LeighAnna, Guiga, Mohammed, Hassan, Muhammad Yusuf, Hughes, Jill L., Nir, Guy, Parikh, Saagar, Park, Sungmin, Purohit, Palak, Rebbapragada, Umaa, Reed, Draco, Warshofsky, Daniel, Wold, Avery, Bloom, Joshua S., Masci, Frank J., Riddle, Reed, Smith, Roger
Format: Recurso digital
Veröffentlicht: Zenodo 2020
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866902325746991104
author Healy, Brian F.
Coughlin, Michael W.
Mahabal, Ashish A.
Jegou du Laz, Theophile
Drake, Andrew
Graham, Matthew J.
Hillenbrand, Lynne A.
van Roestel, Jan
Szkody, Paula
Zielske, LeighAnna
Guiga, Mohammed
Hassan, Muhammad Yusuf
Hughes, Jill L.
Nir, Guy
Parikh, Saagar
Park, Sungmin
Purohit, Palak
Rebbapragada, Umaa
Reed, Draco
Warshofsky, Daniel
Wold, Avery
Bloom, Joshua S.
Masci, Frank J.
Riddle, Reed
Smith, Roger
author_facet Healy, Brian F.
Coughlin, Michael W.
Mahabal, Ashish A.
Jegou du Laz, Theophile
Drake, Andrew
Graham, Matthew J.
Hillenbrand, Lynne A.
van Roestel, Jan
Szkody, Paula
Zielske, LeighAnna
Guiga, Mohammed
Hassan, Muhammad Yusuf
Hughes, Jill L.
Nir, Guy
Parikh, Saagar
Park, Sungmin
Purohit, Palak
Rebbapragada, Umaa
Reed, Draco
Warshofsky, Daniel
Wold, Avery
Bloom, Joshua S.
Masci, Frank J.
Riddle, Reed
Smith, Roger
contents <p>The classification of variable objects provides insight into a wide variety of astrophysics ranging from stellar interiors to galactic nuclei. The Zwicky Transient Facility (ZTF) provides time series observations that record the variability of more than a billion sources. The scale of these data necessitates automated approaches to make a thorough analysis. Building on previous work, this paper reports the results of the ZTF Source Classification Project (SCoPe), which trains neural network and XGBoost machine learning (ML) algorithms to perform dichotomous classification of variable ZTF sources using a manually constructed training set containing 170,632 light curves. We find that several classifiers achieve high precision and recall scores, suggesting the reliability of their predictions for 1,648,948,910 light curves across 636 ZTF fields. We also identify the most important features for XGB classification and compare the performance of the two ML algorithms, finding a pattern of higher precision among XGB classifiers. The resulting classification catalog is available to the public, and the software developed for SCoPe is open-source and adaptable to future time-domain surveys.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19135641
institution Zenodo
language
publishDate 2020
publisher Zenodo
record_format zenodo
spellingShingle The data for "The ZTF Source Classification Project: III. A Catalog of Variable Sources"
Healy, Brian F.
Coughlin, Michael W.
Mahabal, Ashish A.
Jegou du Laz, Theophile
Drake, Andrew
Graham, Matthew J.
Hillenbrand, Lynne A.
van Roestel, Jan
Szkody, Paula
Zielske, LeighAnna
Guiga, Mohammed
Hassan, Muhammad Yusuf
Hughes, Jill L.
Nir, Guy
Parikh, Saagar
Park, Sungmin
Purohit, Palak
Rebbapragada, Umaa
Reed, Draco
Warshofsky, Daniel
Wold, Avery
Bloom, Joshua S.
Masci, Frank J.
Riddle, Reed
Smith, Roger
<p>The classification of variable objects provides insight into a wide variety of astrophysics ranging from stellar interiors to galactic nuclei. The Zwicky Transient Facility (ZTF) provides time series observations that record the variability of more than a billion sources. The scale of these data necessitates automated approaches to make a thorough analysis. Building on previous work, this paper reports the results of the ZTF Source Classification Project (SCoPe), which trains neural network and XGBoost machine learning (ML) algorithms to perform dichotomous classification of variable ZTF sources using a manually constructed training set containing 170,632 light curves. We find that several classifiers achieve high precision and recall scores, suggesting the reliability of their predictions for 1,648,948,910 light curves across 636 ZTF fields. We also identify the most important features for XGB classification and compare the performance of the two ML algorithms, finding a pattern of higher precision among XGB classifiers. The resulting classification catalog is available to the public, and the software developed for SCoPe is open-source and adaptable to future time-domain surveys.</p>
title The data for "The ZTF Source Classification Project: III. A Catalog of Variable Sources"
url https://doi.org/10.5281/zenodo.19135641