Palavras-chave
Solar flares
Deep learning
Object detection
Deep learning
Object detection
Como Citar
OLIVEIRA, Letícia de; GRADVOHL, Andre. Using deep learning to identify and classify sunspots in magnetograms. Revista dos Trabalhos de Iniciação Científica da UNICAMP, Campinas, SP, n. 27, p. 1–1, 2019. DOI: 10.20396/revpibic2720192309. Disponível em: https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/2309. Acesso em: 13 mar. 2026.
Resumo
Some of the solar activities, such as solar flares, release large amounts of radiation and energy that impact on Earth's life and technological systems. These flares usually come from sunspots, which derive from solar magnetic activities. Currently, some solar data allow predicting when a solar flare will occur. This paper reports the use of the Deep Learning technique to identify and classify sunspots using solar magnetograms automatically. Our results show an accuracy greater than 80%.
Referências
GRADVOHL, A. L. S&FERNANDES,M.E.R.(2017).Samplesofsolar flares classes, active regions and time of occurrence (Version 0.1) [Dataset]. Available at: http://doi.org/10.5281/ zenodo.1048995. Access on June 29, 2019.
NVIDIA DIGITS. Interactive Deep Learning GPU Training System. NVIDIA Corporation, [2016]. Available at: https://developer.nvidia.com/ digits. Access on June 29, 2019.
NVIDIA DIGITS. Interactive Deep Learning GPU Training System. NVIDIA Corporation, [2016]. Available at: https://developer.nvidia.com/ digits. Access on June 29, 2019.
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
Copyright (c) 2019 Revista dos Trabalhos de Iniciação Científica da UNICAMP