Radio frequency interference mitigation using deep convolutional neural\n networks

2016/09/28 by Joël Akeret, C. Chang, Akeret, Joel +5 · 3 citations
Engineering · Physics and Astronomy · #FOS: Physical sciences #GNSS positioning and interference #Instrumentation and Methods for Astrophysics (astro-ph.IM) #Radio Astronomy Observations and Technology #Superconducting and THz Device Technology

paper · pdf · doi:10.48550/arxiv.1609.09077

openalex publication_date 2016/09/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a novel approach for mitigating radio frequency interference (RFI)\nsignals in radio data using the latest advances in deep learning. We employ a\nspecial type of Convolutional Neural Network, the U-Net, that enables the\nclassification of clean signal and RFI signatures in 2D time-ordered data\nacquired from a radio telescope. We train and assess the performance of this\nnetwork using the HIDE & SEEK radio data simulation and processing packages, as\nwell as early Science Verification data acquired with the 7m single-dish\ntelescope at the Bleien Observatory. We find that our U-Net implementation is\nshowing competitive accuracy to classical RFI mitigation algorithms such as\nSEEK's SumThreshold implementation. We publish our U-Net software package on\nGitHub under GPLv3 license.\n

Cited by

• Interference Mitigation using U-Net Autoencoder based system
• Neuromorphic Astronomy: An End-to-End SNN Pipeline for RFI Detection Hardware
• ASTROFLOW: A Real-Time End-to-End Pipeline for Radio Single-Pulse Searches

Related

• RFI Identification Based On Deep-Learning]A Robust RFI Identification For Radio Interferometry based on a Convolutional Neural Network
• Detecting radio frequency interference in radio‐antenna arrays with the recurrent neural network algorithm
• RF Challenge: The Data-Driven Radio Frequency Signal Separation Challenge
• Real-Time RFI Mitigation for the Apertif Radio Transient System
• Spiking Neural Networks for Radio Frequency Interference Detection in Radio Astronomy