Convolutional Neural Networks for Automated ULF Wave Classification in Swarm Time Series
Authors:
- Alexandra AntonopoulouAAAlexandra Antonopoulou
- Georgios BalasisGeorgios Balasis
- Constantinos PapadimitriouCPConstantinos Papadimitriou
- Adamantia Zoe BoutsiABAdamantia Zoe Boutsi
- Athanasios RontogiannisARAthanasios Rontogiannis
- Konstantinos KoutroumbasKKKonstantinos Koutroumbas
- Ioannis A. DaglisIDIoannis A. Daglis
- Omiros GiannakisOGOmiros Giannakis
Open Access
- 13 September 2022
- journal article
- research article
- Published by MDPI AG in Atmosphere
- Vol. 13 (9) , 1488
Abstract
Ultra-low frequency (ULF) magnetospheric plasma waves play a key role in the dynamics of the Earth’s magnetosphere and, therefore, their importance in Space Weather phenomena is indisputable. Magnetic field measurements from recent multi-satellite missions (e.g., Cluster, THEMIS, Van Allen Probes and Swarm) are currently advancing our knowledge on the physics of ULF waves. In particular, Swarm satellites, one of the most successful missions for the study of the near-Earth electromagnetic environment, have contributed to the expansion of data availability in the topside ionosphere, stimulating much recent progress in this area. Coupled with the new successful developments in artificial intelligence (AI), we are now able to use more robust approaches devoted to automated ULF wave event identification and classification. The goal of this effort is to use a popular machine learning method, widely used in Earth Observation domain for classification of satellite images, to solve a Space Physics classification problem, namely to identify ULF wave events using magnetic field data from Swarm. We construct a Convolutional Neural Network (ConvNet) that takes as input the wavelet spectrum of the Earth’s magnetic field variations per track, as measured by Swarm, and whose building blocks consist of two alternating convolution and pooling layers, and one fully connected layer, aiming to classify ULF wave events within four different possible signal categories: (1) Pc3 wave events (i.e., frequency range 20–100 MHz), (2) background noise, (3) false positives, and (4) plasma instabilities. Our preliminary experiments show promising results, yielding successful identification of more than 97% accuracy. The same methodology can be easily applied to magnetometer data from other satellite missions and ground-based arrays.Keywords
Funding Information
- ESA (4000109587)
This publication has 52 references indexed in Scilit:
- Swarm Absolute Scalar and Vector Magnetometer Based on Helium 4 Optical PumpingProcedia Chemistry, 2009
- Forecasting space weather: Predicting interplanetary shocks using neural networksAdvances In Space Research, 2005
- Quantitative prediction of radiation belt electrons at geostationary orbit based on solar wind measurementsGeophysical Research Letters, 2001
- A neural network‐based local model for prediction of geomagnetic disturbancesJournal of Geophysical Research: Space Physics, 2001
- Real time Kp predictions from solar wind data using neural networksPhysics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 2000
- System identification, modeling, and prediction for space weather environmentsIEEE Transactions on Plasma Science, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Substorm onset identification using neural networks and Pi2 pulsationsAnnales Geophysicae, 1997
- Prediction of magnetic storms by nonlinear modelsGeophysical Research Letters, 1996
- A critical investigation of recall and precision as measures of retrieval system performanceACM Transactions on Information Systems, 1989