Deep Learning Model Size Performance Evaluation for Lightning Whistler Detection on Arase Satellite Dataset
Authors:
- I Made Agus Dwi SuarjayaISI Made Agus Dwi Suarjaya
- Desy Purnami Singgih PutriDPDesy Purnami Singgih Putri
- Yuji TanakaYTYuji Tanaka
- Fajar PurnamaFPFajar Purnama
- I Putu Agung BayupatiIBI Putu Agung Bayupati
- LinawatiLILinawati
- Yoshiya KasaharaYKYoshiya Kasahara
- Shoya MatsudaSMShoya Matsuda
- Yoshizumi MiyoshiYMYoshizumi Miyoshi
- Iku ShinoharaISIku Shinohara
Open Access
- 15 November 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (22) , 4264
Abstract
The plasmasphere within Earth’s magnetosphere plays a crucial role in space physics, with its electron density distribution being pivotal and strongly influenced by solar activity. Very Low Frequency (VLF) waves, including whistlers, provide valuable insights into this distribution, making the study of their propagation through the plasmasphere essential for predicting space weather impacts on various technologies. In this study, we evaluate the performance of different deep learning model sizes for lightning whistler detection using the YOLO (You Only Look Once) architecture. To achieve this, we transformed the entirety of raw data from the Arase (ERG) Satellite for August 2017 into 2736 images, which were then used to train the models. Our approach involves exposing the models to spectrogram diagrams—visual representations of the frequency content of signals—derived from the Arase Satellite’s WFC (WaveForm Capture) subsystem, with a focus on analyzing whistler-mode plasma waves. We experimented with various model sizes, adjusting epochs, and conducted performance analysis using a partial set of labeled data. The testing phase confirmed the effectiveness of the models, with YOLOv5n emerging as the optimal choice due to its compact size (3.7 MB) and impressive detection speed, making it suitable for resource-constrained applications. Despite challenges such as image quality and the detection of smaller whistlers, YOLOv5n demonstrated commendable accuracy in identifying scenarios with simple shapes, thereby contributing to a deeper understanding of whistlers’ impact on Earth’s magnetosphere and fulfilling the core objectives of this study.Keywords
Funding Information
- PNPB Udayana University
This publication has 21 references indexed in Scilit:
- Magnetic Search Coil (MSC) of Plasma Wave Experiment (PWE) aboard the Arase (ERG) satelliteEarth, Planets and Space, 2018
- Onboard software of Plasma Wave Experiment aboard Arase: instrument management and signal processing of Waveform Capture/Onboard Frequency AnalyzerEarth, Planets and Space, 2018
- The ARASE (ERG) magnetic field investigationEarth, Planets and Space, 2018
- Wire Probe Antenna (WPT) and Electric Field Detector (EFD) of Plasma Wave Experiment (PWE) aboard the Arase satellite: specifications and initial evaluation resultsEarth, Planets and Space, 2017
- Statistical study on propagation characteristics of Omega signals (VLF) in magnetosphere detected by the Akebono satelliteEarth, Planets and Space, 2017
- Determination of global plasmaspheric electron density profile by tomographic approach using omega signals and ray tracingJournal of Atmospheric and Solar-Terrestrial Physics, 2001
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Global electron density distribution in the plasmasphere deduced from Akebono wave data and the IRI modelJournal of Atmospheric and Solar-Terrestrial Physics, 1997
- Remote sensing of the magnetospheric plasma by means of whistler mode signalsReviews of Geophysics, 1988
- An investigation of whistling atmosphericsPhilosophical Transactions of the Royal Society of London. Series A, Mathematical and Physical Sciences, 1953