Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning
Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning
复制标题
DOI：
10.3847/1538-3881/abea7b
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
D. Duev
中科院分区：
文献类型：
--
作者：
D. Duev
我们介绍了Tail，一个开源的深度学习框架，用于在兹维基瞬变设施(ZTF)的图像数据中识别和定位彗星，ZTF是目前在美国加利福尼亚州帕洛玛天文台运行的机器人光学时域测量。TailS采用基于EfficientDet的定制架构，能够近乎实时地在单幅图像中发现彗星，而不是像传统方法那样需要多个历元。该系统实现了最先进的性能，召回率为99%，假阳性率为0.01%，预测位置的均方根误差为1-2像素。我们报告了基于ZTF Twilight调查数据的生产环境下Tail效率评估的初步结果，包括首次人工智能辅助发现一颗彗星(C/2020 T2)和恢复一颗彗星(P/2016 J3=P/2021 A3)。
We present Tails, an open-source deep-learning framework for the identification and localization of comets in the image data of the Zwicky Transient Facility (ZTF), a robotic optical time-domain survey currently in operation at the Palomar Observatory in California, USA. Tails employs a custom EfficientDet-based architecture and is capable of finding comets in single images in near real time, rather than requiring multiple epochs as with traditional methods. The system achieves state-of-the-art performance with 99% recall, a 0.01% false-positive rate, and a 1–2 pixel rms error in the predicted position. We report the initial results of the Tails efficiency evaluation in a production setting on the data of the ZTF Twilight survey, including the first AI-assisted discovery of a comet (C/2020 T2) and the recovery of a comet (P/2016 J3 = P/2021 A3).