Home »
Academic Articles »
Astronomy »
Detection of short-term peaks in VLF/LF signals around the time of gamma-ray burst detections using deep learning
Detection of short-term peaks in VLF/LF signals around the time of gamma-ray burst detections using deep learning
Sarnovský M.
(Department of Cybernetics and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia)
iD
Nina A.
(Institute of Physics Belgrade, National Institute of the Republic of Serbia, University of Belgrade, Belgrade, Serbia)
iD
Popović L.Č.
(Astronomical Observatory, Belgrade, Serbia)
iD
Srećković V.
(Institute of Physics Belgrade, National Institute of the Republic of Serbia, University of Belgrade, Belgrade, Serbia)
iD
Khudevych A.
(Department of Cybernetics and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia)
iD
Krešňáková V.
(Department of Cybernetics and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia)
iD
Butka P.
(Department of Cybernetics and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia)
iD
Bednár P.
(Department of Cybernetics and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia)
iD
Journal: Serbian Astronomical Journal
•
• Astronomical Observatory, Department of Astronomy, Belgrade
• ISSN: 1450-698X
Abstract
Gamma-ray bursts (GRBs) are recognized as the most energetic and luminous astrophysical phenomena whose high-energy photons can ionize atmospheric
particles and thus affect electrical conductivity. Consequently,
electromagnetic waves such as Very Low and Low Frequency (VLF/LF) radio
signals used for the lower ionosphere monitoring can be used to detect
disturbances, i.e. the impact of GRBs on the area in which these signals
propagate. This paper addresses application of deep learning for automatic
detection the short-term peaks in VLF/LF signals around the time of
satellite registration of GRBs. We utilized a refined hybrid architecture
combining Convolutional Neural Networks (CNN) for automatic feature
extraction and Long Short-Term Memory network (LSTM) for modeling sequential
dependencies in the multi-channel time-series data. We used derived,
peak-based representations of the raw ionospheric waveforms and trained the
proposed neural network architecture on such pre-processed data
representations. The experiments with the sample of 54 short-lasting GRBs
revealed limitations due to extreme class imbalance; however, a refined
approach utilizing manual adjustment of positive-class weights and
optimization of the classification threshold achieved the best detection
performance. The final CNN-LSTM model demonstrated strong performance
metrics, confirming the viability of CNN-LSTM approaches in this task.
Sarnovský M., Nina A., Popović L.Č., et al. (2026). "Detection of short-term peaks in VLF/LF signals around the time of gamma-ray burst detections using deep learning". Serbian Astronomical Journal. https://doi.org/10.2298/saj2612107s