O'Dwyer, Elizabeth (2023) Machine Learning for the Automatic Classification of Radio Spectra. Masters thesis, National University of Ireland Maynooth.

Download (28MB)

Abstract

SKR is a non-thermal, auroral emission with peak emission occurring at 100-400 kHz. Its properties have been extensively studied since Cassini’s arrival at Saturn until mission end with its Radio and Plasma Wave Science (RPWS) experiment. Low Frequency Extensions (LFEs) of SKR, which consist of global intensifications of SKR accompanied by extensions of the main SKR band down to lower frequencies have been studied in particular. LFEs result from internally-driven tail reconnection and from solar wind compressions of the magnetosphere, which also trigger tail reconnection. They have been previously identified with two approaches: through visual inspection and using an intensity threshold for LFEs occurring in 2006 (Reed et al., 2018). In this work, we describe the method used to develop a visual criterion for LFE selection, and use this method to select a sample of LFEs detected by Cassini/RPWS by fitting their exact frequency-time coordinates with polygons. We use this sample of LFEs as a training set for an imagebased machine learning algorithm to classify all LFEs detected by Cassini/RPWS. The inputs to the model are multi-channel images consisting of spectrogram images in flux density and degree of circular polarisation. The outputs of the model are binary masks showing the exact location of the LFE in frequency-time space. The median IoU (Intersection Over Union) across the testing and training set were calculated to be 0.97 and 0.98 respectively. 4874 LFEs were detected using this method and the catalogue in the form of frequency-time coordinates is available for use amongst the scientific community.

Item Type:	Thesis (Masters)
Keywords:	Machine Learning; Automatic Classification; Radio Spectra;
Academic Unit:	Faculty of Science and Engineering > Mathematics and Statistics
Item ID:	18634
Depositing User:	IR eTheses
Date Deposited:	10 Jun 2024 15:06
URI:
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads