# Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning

arXiv: https://arxiv.org/abs/2102.13352 · HTML: https://mlsanity.com/paper/2102.13352/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 40 references that are in the map.
- First posted on arXiv 26 Feb 2021.

## Builds on (most cited first, 4 of 4)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)

## Built on by (most cited first, 6 of 6)

- [Towards Asteroid Detection in Microlensing Surveys with Deep Learning](https://mlsanity.com/paper/2211.02239/) (2022)
- [Optimization of Artificial Neural Networks models applied to the identification of images of asteroids' resonant arguments](https://mlsanity.com/paper/2207.14181/) (2022)
- [Using neural networks to model Main Belt Asteroid albedos as a function of their proper orbital elements](https://mlsanity.com/paper/2305.16392/) (2023)
- [Detecting Moving Objects With Machine Learning](https://mlsanity.com/paper/2405.06148/) (2024)
- [Identification and Localization of Cometary Activity in Solar System Objects with Machine Learning](https://mlsanity.com/paper/2409.15261/) (2024)
- [Pre-training vision models for the classification of alerts from wide-field time-domain surveys](https://mlsanity.com/paper/2512.11957/) (2025)

## Abstract (arXiv)

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, 0.01% false positive rate, and 1-2 pixel root mean square 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).