Machine learning for radio frequency interference mitigation using polarization

Radio frequency interference (RFI) is electromagnetic interference (EMI) from signals in the radio frequencies of the electromagnetic spectrum. RFI reduces the sensitivity of radio telescope and produces artefacts in the observed data. We present the result of applying machine learning techniques to detect confidently man made RFI. We confirm that not all the features selected to characterise RFI are always important. We further investigated the Random Forest Classifier (RFC) to characterize RFI and conclude by showing that features having both polarized information are more useful as compared to features carrying single polarization information.