Revisiting the Pushchino RRAT search using a neural network

¹ Lebedev Physical Institute, Astro Space Center, Pushchino Radio Astronomy Observatory, 142290, Radioteleskopnaya 1a, Moscow reg., Pushchino, Russia
e-mail: serg@prao.ru
² Sber, 117312, Wawilov street 19, Moscow, Russia
³ Institute of Mathematical Problems of Biology, brunch of Keldysh Institute of Applied Mathematics, 142290, Vitkevich 1, Moscow reg., Pushchino, Russia
⁴ The State University of Management, 102542, Ryazanskii prospect 99, Moscow, Russia

Received: 28 January 2022
Accepted: 18 May 2022

Abstract

The search for rotating radio transients (RRAT) at declinations from −9° to +42° was carried out based on the semi-annual monitoring data obtained on the Large Phased Array (LPA) radio telescope at a frequency of 111 MHz. A neural network was used to search for candidates. Four new RRATs were detected; they have dispersion measures of 5–16 pc cm⁻³. A comparison with an earlier RRAT search that was conducted using the same data shows that the neural network reduced the amount of interference by 80 times. It is now down to 1.3% of the initial amount of interference. The loss of real pulsar pulses does not exceed 6% of their total number.