Sunspot Detection Using YOLOv5 in Spectroheliograph H-Alpha Images
Source abstract
Abstract
Solar activity has been subject to increasingly more research in the last decades. Its influence on life on Earth is now better understood. Solar winds impact the earth’s magnetic field and atmosphere. They can disrupt satellite communication and navigation tools and even electrical power grids and several other infrastructure crucial for our technology-based society. Coronal mass ejections (CMEs), solar energetic particles, and flares are the main causes of problems that affect the systems mentioned. It is possible to predict some of those by monitoring the sun and analyzing the images obtained in different spectra, thus identifying solar phenomena related to its activity, such as filaments, pores, and sunspots. Several studies have already been carried out on the subject of automation of the mentioned analysis, most of which use neural networks and other machine learning approaches. In this work, we develop a method for sunspot detection based on the YOLOv5 network, applying it to a dataset of images from the Geophysical and Astronomical Observatory of the University of Coimbra (OGAUC), which has one of the oldest and more complete datasets of sun images in the world. Our method reaches mAP@.5 over 90% with YOLOv5s, which is higher than other methods previously applied for the same dataset. This shows that CNN models can be used in spectroheliographs for detecting and tracking sunspots.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Solar and Space Plasma Dynamics · Solar Radiation and Photovoltaics · Currency Recognition and Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Coimbra Institute of Engineering, Rua Pedro Nunes-Quinta da Nora, Polytechnic Institute of Coimbra, 3030-199 Coimbra, Portugal
Instituto de Astrofísica e Ciências do Espaço, Universidade de Coimbra, 3040-004 Coimbra, Portugal
Departamento de Física, Faculdade de Ciências e Tecnologia, Universidade de Coimbra, 3004-516 Coimbra, Portugal
Departamento de Ciências da Terra, Faculdade de Ciências e Tecnologia, Universidade de Coimbra, 3030-790 Coimbra, Portugal
Centre for Informatics and Systems of the University of Coimbra, 3030-290 Coimbra, Portugal
Institute of Systems and Robotics, University of Coimbra, 3004-531 Coimbra, Portugal
References (34)
Show source-provided references
1. Space weather: The solar perspective10.12942/lrsp-2006-2 ↗
2. The SIDC: World data center for the sunspot index10.1007/s11207-005-6504-2 ↗
3. Colak, T., and Qahwaji, R. (2007, January 14–16). Automatic Sunspot Classification for Real-Time Forecasting of Solar Activities. Proceedings of the 2007 3rd International Conference on Recent Advances in Space Technologies, Istanbul, Turkey.10.1109/RAST.2007.4284089 ↗
4. Sunspots: An overview10.1007/s00159-003-0018-4 ↗
5. Statistical analysis of sunspot groups and flares for solar maximum and minimum10.1360/132012-809 ↗
6. Sunspot Catalogue of the Observatory of the University of Coimbra (1929–1941)10.1007/s11207-018-1373-7 ↗
7. Solar observations at the Coimbra Astronomical Observatory10.1515/astro-2019-0015 ↗
8. Automatic sunspots detection on full-disk solar images using mathematical morphology10.1007/s11207-008-9224-6 ↗
9. Comparison of automatic methods to detect sunspots in the Coimbra Observatory spectroheliograms10.1016/j.ascom.2020.100385 ↗
10. A simple method to check the reliability of annual sunspot number in the historical period 1610–184710.1007/s11207-011-9901-8 ↗
11. Technique for automated recognition of sunspots on full-disk solar images10.1155/ASP.2005.2573 ↗
12. Automatic detection of sunspots and extraction of their feature parameters10.1016/j.chinastron.2020.11.003 ↗
13. A multi-wavelength analysis of active regions and sunspots by comparison of automatic detection algorithms10.1007/s11207-011-9859-6 ↗
14. Evaluation of convolutional neural networks for visual recognition10.1109/72.701181 ↗
15. Solar event detection using deep-learning-based object detection methods10.1007/s11207-021-01902-5 ↗
16. Detection and classification of sunspots via deep convolutional neural network10.1016/j.gltp.2022.03.006 ↗
17. Li, M., Mehrotra, K., Mohan, C., and Ranka, S. (1990, January 5–7). Sunspot numbers forecasting using neural networks. Proceedings of the 5th IEEE International Symposium on Intelligent Control 1990, Philadelphia, PA, USA.
18. Palladino, L., Ntagiou, E., Klug, J., Palacios, J., and Keil, R. (2022, January 5–12). Sunspot Groups Detection and Classification on SDO/HMI Images using Deep Learning Techniques. Proceedings of the 2022 IEEE Aerospace Conference (AERO), Big Sky, MT, USA.10.1109/AERO53065.2022.9843222 ↗
19. Cengil, E., Çinar, A., and Yildirim, M. (2021, January 29–30). A Case Study: Cat-Dog Face Detector Based on YOLOv5. Proceedings of the 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), Zallaq, Bahrain.10.1109/3ICT53449.2021.9581987 ↗
20. A Hierarchical method for quick and automatic recognition of sunspots
21. Malta, A., Mendes, M., and Farinha, T. (2021). Augmented reality maintenance assistant using yolov5. Appl. Sci., 11.10.3390/app11114758 ↗
22. Gomes, H., Redinha, N., Lavado, N., and Mendes, M. (2022). Counting People and Bicycles in Real Time Using YOLO on Jetson Nano. Energies, 15.10.3390/en15238816 ↗
23. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
24. Software tool for automatic detection of solar plages in the Coimbra Observatory spectroheliograms10.1016/j.ascom.2018.06.003 ↗
25. Deep learning for automatic recognition of magnetic type in sunspot groups10.1155/2019/9196234 ↗
26. Camargo, T.O., Pechebovicz, D., Premebida, S.M., Soares, V.R., Baroncini, V., Siqueira, H., Oliva, D., and Martins, M. (2019, January 5–7). Detecting a predefined solar spot group with a pretrained convolutional neural network. Proceedings of the 2019 IEEE Colombian Conference on Applications in Computational Intelligence (ColCACI), Barranquilla, Colombia.10.1109/ColCACI.2019.8781990 ↗
27. Fast solar image classification using deep learning and its importance for automation in solar physics10.1007/s11207-019-1473-z ↗
28. Automatic analysis of magnetograms for identification and classification of active regions using Deep Learning
29. Du Toit, R., Drevin, G., Maree, N., and Strauss, D.T. (2020, January 29–31). Sunspot identification and tracking with OpenCV. Proceedings of the 2020 International SAUPEC/RobMech/PRASA Conference, Cape Town, South Africa.10.1109/SAUPEC/RobMech/PRASA48453.2020.9040971 ↗
30. Jha, B.K., Hegde, M., Priyadarshi, A., Mandal, S., Ravindra, B., and Banerjee, D. (2022). Extending the sunspot area series from Kodaikanal Solar Observatory. arXiv.10.3389/fspas.2022.1019751 ↗
31. Alasta, A.F., Algamudi, A., Qahwaji, R., Ipson, S., and Nagern, T.A. (2017, January 16–18). Automatic sunspots detection on SODISM solar images. Proceedings of the 2017 Seventh International Conference on Innovative Computing Technology (INTECH), Luton, UK.10.1109/INTECH.2017.8102429 ↗
32. FINI, E. (2019). A Deep Learning Approach to Sunspot Detection and Counting. [MSc Thesis, Politecnico di Milano].
33. Quan, L., Xu, L., Li, L., Wang, H., and Huang, X. (2021). Solar Active Region Detection Using Deep Learning. Electronics, 10.10.3390/electronics10182284 ↗
34. Alfonso Soler, B., Vargas Domínguez, S., and Martínez Galarza, J.R. (2020, January 18–19). Automatic Detection of Light Bridges in Solar Active Regions Based on Deep Learning Techniques. Proceedings of the AAS/Solar Physics Division Meeting, Online.