19 July 2016 Detecting anomalies in astronomical signals using machine learning algorithms embedded in an FPGA
Author Affiliations +
Abstract
Taking a large interferometer for radio astronomy, such as the ALMA1 telescope, where the amount of stations (50 in the case of ALMA’s main array, which can extend to 64 antennas) produces an enormous amount of data in a short period of time – visibilities can be produced every 16msec or total power information every 1msec (this means up to 2016 baselines). With the aforementioned into account it is becoming more difficult to detect problems in the signal produced by each antenna in a timely manner (one antenna produces 4 x 2GHz spectral windows x 2 polarizations, which means a 16 GHz bandwidth signal which is later digitized using 3-bits samplers). This work will present an approach based on machine learning algorithms for detecting problems in the already digitized signal produced by the active antennas (the set of antennas which is being used in an observation). The aim of this work is to detect unsuitable, or totally corrupted, signals. In addition, this development also provides an almost real time warning which finally helps stop and investigate the problem in order to avoid collecting useless information.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alejandro F. Saez, Daniel E. Herrera, "Detecting anomalies in astronomical signals using machine learning algorithms embedded in an FPGA", Proc. SPIE 9914, Millimeter, Submillimeter, and Far-Infrared Detectors and Instrumentation for Astronomy VIII, 99143B (19 July 2016); doi: 10.1117/12.2231491; https://doi.org/10.1117/12.2231491
PROCEEDINGS
17 PAGES


SHARE
RELATED CONTENT


Back to Top