Software Open Access

dmitryduev/tails: chasing comets with ZTF and deep learning

Dmitry A. Duev; Stéfan J. van der Walt; Matthew J. Graham; Ashish Mahabal

Tails is a deep-learning framework for the identification and localization of comets in the image data of the Zwicky Transient Facility (ZTF), a robotic optical sky survey at the Palomar Observatory in California, USA.

Tails uses a custom EfficientDet-based architecture and is thus capable of finding comets in single images in near real time, rather than requiring multiple epochs as with traditional methods. In production, we have observed 99% recall, <0.01% false positive rate, and 1-2 pixel root mean square error in the predicted position.

Tails enabled the first AI-assisted discovery of a comet - C/2020 T2.

This version of Tails is aligned with the article accepted for publication in The Astronomical Journal on February 25, 2021.

Files (66.4 kB)
Name Size
dmitryduev/tails-v0.2.zip
md5:61375fcae7418cd296270f4cc45d073f
66.4 kB Download
45
0
views
downloads
All versions This version
Views 4545
Downloads 00
Data volume 0 Bytes0 Bytes
Unique views 3535
Unique downloads 00

Share

Cite as