DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning

We present DeepStreaks, a convolutional-neural-network, deep-learning system designed to efficiently identify streaking fast-moving near-Earth objects that are detected in the data of the Zwicky Transient Facility (ZTF), a wide-field, time-domain survey using a dedicated 47 deg2 camera attached to the Samuel Oschin 48-inch Telescope at the Palomar Observatory in California, United States. The system demonstrates a 96–98 per cent true positive rate, depending on the night, while keeping the false positive rate below 1 per cent. The sensitivity of DeepStreaks is quantified by the performance on the test data sets as well as using known near-Earth objects observed by ZTF. The system is deployed and adapted for usage within the ZTF Solar system framework and has significantly reduced human involvement in the streak identification process, from several hours to typically under 10 min per day.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  R. Wainscoat,et al.  Improved Asteroid Astrometry and Photometry with Trail Fitting , 2012, 1209.6106.

[3]  Quoc V. Le,et al.  Do Better ImageNet Models Transfer Better? , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[6]  Umaa Rebbapragada,et al.  The Zwicky Transient Facility: System Overview, Performance, and First Results , 2018, Publications of the Astronomical Society of the Pacific.

[7]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Daniel Hestroffer,et al.  Statistical and numerical study of asteroid orbital uncertainty , 2013, 1303.2946.

[9]  E. Ofek,et al.  PROPER IMAGE SUBTRACTION—OPTIMAL TRANSIENT DETECTION, PHOTOMETRY, AND HYPOTHESIS TESTING , 2016, 1601.02655.

[10]  S. Kulkarni,et al.  Small Near-Earth Asteroids in the Palomar Transient Factory Survey: A Real-Time Streak-detection System , 2016, 1609.08018.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Guy Nir,et al.  Optimal and Efficient Streak Detection in Astronomical Images , 2018, The Astronomical Journal.

[13]  M. Bershady,et al.  SparsePak: A Formatted Fiber Field Unit for the WIYN Telescope Bench Spectrograph. I. Design, Construction, and Calibration , 2004, astro-ph/0403456.

[14]  Umaa Rebbapragada,et al.  The Zwicky Transient Facility: Science Objectives , 2019, Publications of the Astronomical Society of the Pacific.

[15]  Matthew J. Graham,et al.  Toward Efficient Detection of Small Near-Earth Asteroids Using the Zwicky Transient Facility (ZTF) , 2019, Publications of the Astronomical Society of the Pacific.

[16]  Umaa Rebbapragada,et al.  The Zwicky Transient Facility: Data Processing, Products, and Archive , 2018, Publications of the Astronomical Society of the Pacific.

[17]  Steven R. Chesley,et al.  High-fidelity Simulations of the Near-Earth Object Search Performance of the Large Synoptic Survey Telescope , 2017, 1706.09398.

[18]  Michael Porter,et al.  The Zwicky Transient Facility Camera , 2016, Astronomical Telescopes + Instrumentation.

[19]  B. Altieri,et al.  Detecting Solar system objects with convolutional neural networks , 2018, Monthly Notices of the Royal Astronomical Society.