Detecting anomalies in astronomical signals using machine learning algorithms embedded in an FPGA

Alejandro F. Saez; Daniel E. Herrera

doi:10.1117/12.2231491

19 July 2016 Detecting anomalies in astronomical signals using machine learning algorithms embedded in an FPGA

Proceedings Volume 9914, Millimeter, Submillimeter, and Far-Infrared Detectors and Instrumentation for Astronomy VIII; 99143B (2016) https://doi.org/10.1117/12.2231491
Event: SPIE Astronomical Telescopes + Instrumentation, 2016, Edinburgh, United Kingdom

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.

Citation Download Citation

Alejandro F. Saez and 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); https://doi.org/10.1117/12.2231491

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available