DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning. Issue 3 (17th April 2019)

• Record Type: Journal Article
• Authors: Duev, Dmitry A; Mahabal, Ashish; Ye, Quanzhi; Tirumala, Kushal; Belicki, Justin; Dekany, Richard; Frederick, Sara; Graham, Matthew J; Laher, Russ R; Masci, Frank J; Prince, Thomas A; Riddle, Reed; Rosnet, Philippe; Soumagnac, Maayane T
• Is Part Of: Monthly notices of the Royal Astronomical Society. Volume 486:Issue 3(2019)
• Page Start: 4158
• Page End: 4165
• Publication Date: 2019-04-17
• Subjects: methods: data analysis -- surveys -- minor planets, asteroids: general; Astronomy -- Periodicals; Periodicals; 520.5
• DOI: 10.1093/mnras/stz1096
• Languages: English
• ISSNs: 0035-8711

Abstract

ABSTRACT: 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 deg 2 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.