RaFIDe: A Machine Learning based RFI free observation planner for the SKA Era

Abstract

Signal anomalies in astronomical data mainly come from Radio Frequency Interference (RFI). Radio Frequency Interference (RFI) has plagued the field of radio astronomy. RFI can be either internal (generated by instruments) or external that originates from intentional or unintentional radio emission generated by human activity. Radio Telescopes are known to generate massive amounts of astronomical data. With the huge amount of data being available, a clustering technique can be applied to detect RFI. The quality of the incoming radio signal will be determined by the clustering technique. This will enable us to detect the anomalies in the signal at a particular instant of time. This effort will further enable us to build a database and subsequently apply reinforced time-series machine learning models to predict the quality of the signal. This paper proposes a machine learning approach to study the signal quality over the recent past and make use of this knowledge to plan the near-future observation slots in frequency spectrum and time.