Development of a machine learning-based radio source localization algorithm for tri-axial antenna configuration

Accurately determining the origin of radio emissions is essential for numerous scientific experiments, particularly in radio astronomy. Conventional techniques, such as antenna arrays, encounter significant challenges, especially at very low frequencies, due to factors like the substantial size of the antennas and ionospheric interference. To address these challenges, we employ a space-based single-telescope that utilizes co-located antennas complemented by goniopolarimetric techniques for precise source localization. This study explores a novel and elementary machine learning technique to improve and estimate direction of arrival (DoA), leveraging a tri-axial antenna arrangement for radio source localization. Employing a simplistic emission and receiving antenna model, our study involves training an artificial neural network (ANN) using synthetic radio signals. These synthetic signals can originate from any location in the sky and cover an incoherent frequency range of 0.3–30 MHz, with a signal-to-noise ratio between 0 and 60 dB. A large synthetic data set was generated to train the ANN model catering to the possible signal configurations and variations. After training, the developed ANN model demonstrated exceptional performance, achieving loss levels in the training (\({\sim }0.02\)), validation (\({\sim }0.23\%\)), and testing (\({\sim }0.21\%\)) phases. The machine learning-based approach, remarkably, exhibits substantially quicker inference times (\({\sim }5\) ms) in contrast to analytically derived DoA methods, which typically range from 100 ms to a few seconds. This underscores its practicality for real-time applications in radio source localization, particularly in scenarios with a limited number of sensors.