Automated Solar Radio Burst Detection Using Deep Learning on Augmented e-Callisto Data
Vincenzo Timmel, André Csillaghy, Christian Monstein
astro-ph.SR, astro-ph.IM
Submitted: 2026-07-28
Code: https://github.com/i4Ds/FlareSense-v2
License: http://creativecommons.org/licenses/by/4.0/
The gist: Solar radio bursts are signatures of energetic events associated with solar flares and coronal mass ejections and can interfere with terrestrial and space-based communication systems.
Terminology
Abstract
Solar radio bursts are signatures of energetic events associated with solar flares and coronal mass ejections and can interfere with terrestrial and space-based communication systems. Real-time automatic burst monitoring enables early warnings tens of minutes to hours before associated particles reach Earth and provides the basis for long-term statistical studies. The e-Callisto network is a worldwide system of solar radio spectrometers providing continuous observations, with its instruments collectively covering frequencies from approximately 20 MHz to 1 GHz. Burst detection and labeling currently rely largely on human experts, limiting scalability and real-time applicability due to hardware heterogeneity and low signal-to-noise ratios.
Sources
- Solar Radio Bursts and Space Weather
- Deep Residual Learning for Image Recognition
- Decoupled Weight Decay Regularization
- How Does Learning Rate Decay Help Modern Neural Networks?
- Practical Bayesian Optimization of Machine Learning Algorithms
- Captum: A unified and generic model interpretability library for PyTorch
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- On Calibration of Modern Neural Networks
Related papers
- HXI-DLA2: A Physics-Constrained Deep Learning Algorithm for the ASO-S Hard X-ray Imager
- Effect of Neutron Star Jets on Common Envelope Evolution
- Constraining the origin of magnetic white dwarfs
- JW-FD: A 15-Year Multimodal Dataset for Solar Flare Forecasting
- Phlegethon: a fully compressible magnetohydrodynamic code for simulations in stellar astrophysics
- Can MHD Oscillations Modulate Quasi-Periodic Plasma Release from Coronal Streamers?