Issue |
A&A
Volume 699, July 2025
|
|
---|---|---|
Article Number | A54 | |
Number of page(s) | 17 | |
Section | The Sun and the Heliosphere | |
DOI | https://doi.org/10.1051/0004-6361/202453524 | |
Published online | 01 July 2025 |
Automatic detection of Ellerman bombs using deep learning
1
Institute of Theoretical Astrophysics, University of Oslo, PO Box 1029 Blindern, N-0315 Oslo, Norway
2
Rosseland Centre for Solar Physics, University of Oslo, PO Box 1029 Blindern, N-0315 Oslo, Norway
3
TNO, Oude Waalsdorperweg 63, 2597 AK Den Haag, The Netherlands
⋆ Corresponding author: i.j.s.poquet@astro.uio.noat
Received:
19
December
2024
Accepted:
6
May
2025
Context. Ellerman bombs (EBs) are observable signatures of photospheric small-scale magnetic reconnection events. They can be seen as intensity enhancements of the Hα 6563 Å line wings and as brightenings in the SDO/AIA 1600 Å and 1700 Å passbands. Reliable automatic and systematic detection of EBs would enable the study of the impact of magnetic reconnection on the Sun’s dynamics.
Aims. We aim to develop a method to automatically detect EBs in Hα observations from the Swedish 1-m Solar Telescope (SST) and in SDO/AIA observations using the 1600 Å, 1700 Å, 171 Å, and 304 Å passbands.
Methods. We trained models based on neural networks (NNs) to perform automatic detection of EBs. Additionally, we used different types of NNs to study how different properties – such as local spatial information, the spectral shape of each pixel, or the center-to-limb variation – contribute to the detection of EBs.
Results. We find that for SST observations, the NN-based models are proficient at detecting EBs. With sufficiently high spectral resolution, the spatial context is not required to detect EBs. However, as we degrade the spectral and spatial resolution, the spatial information becomes more important. Models that include both dimensions perform best. For SDO/AIA, the models struggle to reliably distinguish between EBs and bright patches of different origin. Permutation feature importance revealed that the Hα line wings (around ± 1 Å from line center) are the most informative features for EB detection. For the SDO/AIA case, the 1600 Å channel is the most relevant one when used in combination with 171 Å and 304 Å.
Conclusions. The combination of the four different SDO/AIA passbands is not informative enough to accurately classify EBs. From our analysis of a few sample SDO/AIA 1600 Å and 1700 Å light curves, we conclude that inclusion of the temporal variation may be a significant step towards establishing an effective EB detection method that can be applied to the extensive SDO/AIA database of observations.
Key words: methods: data analysis / methods: observational / techniques: image processing / Sun: activity / Sun: magnetic fields / Sun: photosphere
© The Authors 2025
Open Access article, published by EDP Sciences, under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
This article is published in open access under the Subscribe to Open model. Subscribe to A&A to support open access publication.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.