Solar Physics

, 294:117 | Cite as

Solar Filament Recognition Based on Deep Learning

  • Gaofei ZhuEmail author
  • Ganghua Lin
  • Dongguang Wang
  • Suo Liu
  • Xiao Yang


The paper presents a reliable method using deep learning to recognize solar filaments in H\(\upalpha\) full-disk solar images automatically. This method cannot only identify filaments accurately but also minimize the effects of noise points of the solar images. Firstly, a raw filament dataset is set up, consisting of tens of thousands of images required for deep learning. Secondly, an automated method for solar filament identification is developed using the U-Net deep convolutional network. To test the performance of the method, a dataset with 60 pairs of manually corrected H\(\upalpha\) images is employed. These images are obtained from the Big Bear Solar Observatory/Full-Disk H-alpha Patrol Telescope (BBSO/FDHA) in 2013. Cross-validation indicates that the method can efficiently identify filaments in full-disk H\(\upalpha\) images.


Filaments Prominences Image processing Deep learning 



The work was funded by National Science Foundation of China (Grant Nos: u1531247 and 11427901), the 13th Five-year Informatization Plan of Chinese Academy of Sciences, (Grant No. XXH13505-04), and the special foundation work of the Ministry of Science and Technology of China (Grant No: 2014fy120300). We thank BBSO for providing full-disk H\(\upalpha\) images for the experiment.

Disclosure of Potential Conflicts of Interest

The authors declare that they have no conflicts of interest.


  1. Badrinarayanan, V., Kendall, A., Cipolla, R.: 2017, Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481. DOI. CrossRefGoogle Scholar
  2. Chen, P.: 2008, Initiation and propagation of coronal mass ejections. Astron. Astrophys. 29(1-2), 179. DOI. CrossRefGoogle Scholar
  3. Chen, P.: 2011, Coronal mass ejections: models and their observational basis. Living Rev. Solar Phys. 8(1), 1. DOI. ADSCrossRefGoogle Scholar
  4. Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: 2016, Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834. DOI. CrossRefGoogle Scholar
  5. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: 2014, Semantic image segmentation with deep convolutional nets and fully connected crfs. Computer Science, 357. DOI.
  6. Fawcett, T.: 2006, An introduction to roc analysis. Pattern Recognit. Lett. 27(8), 861. DOI. MathSciNetCrossRefGoogle Scholar
  7. Forbes, T.: 2000, A review on the genesis of coronal mass ejections. J. Geophys. Res. 105(A10), 23153. DOI. ADSCrossRefGoogle Scholar
  8. Fuller, N., Aboudarham, J., Bentley, R.: 2005, Filament recognition and image cleaning on meudon h\(\upalpha\) spectroheliograms. Solar Phys. 227(1), 61. DOI. ADSCrossRefGoogle Scholar
  9. Gao, J., Wang, H., Zhou, M.: 2002, Development of an automatic filament disappearance detection system. Solar Phys. 205(1), 93. DOI. ADSCrossRefGoogle Scholar
  10. Gilbert, H.R., Holzer, T.E., Burkepile, J.T., Hundhausen, A.J.: 2000, Active and eruptive prominences and their relationship to coronal mass ejections. Astrophys. J. 537(1), 503. DOI. ADSCrossRefGoogle Scholar
  11. Gopalswamy, N., Shimojo, M., Lu, W., Yashiro, S., Shibasaki, K., Howard, R.: 2003, Prominence eruptions and coronal mass ejection: a statistical study using microwave observations. Astrophys. J. 586(1), 562. DOI. ADSCrossRefGoogle Scholar
  12. Hao, Q., Fang, C., Chen, P.: 2013, Developing an advanced automated method for solar filament recognition and its scientific application to a solar cycle of mlso h\(\upalpha\) data. Solar Phys. 286(2), 385. DOI. ADSCrossRefGoogle Scholar
  13. He, K., Zhang, X., Ren, S., Sun, J.: 2015, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: 2015 IEEE International Conference on Computer Vision (ICCV), 1026. DOI. CrossRefGoogle Scholar
  14. Hinton, G.E., Salakhutdinov, R.R.: 2006, Reducing the dimensionality of data with neural networks. Science 313(5786), 504. DOI. ADSMathSciNetCrossRefzbMATHGoogle Scholar
  15. Jing, J., Yurchyshyn, V.B., Yang, G., Xu, Y., Wang, H.: 2004, On the relation between filament eruptions, flares, and coronal mass ejections. Astrophys. J. 614(2), 1054. DOI. ADSCrossRefGoogle Scholar
  16. Kingma, D., Ba, J.: 2014, Adam: A method for stochastic optimization. Comput. Sci.. Google Scholar
  17. Krizhevsky, A., Sutskever, I., Hinton, G.E.: 2012, Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, 1097. DOI. CrossRefGoogle Scholar
  18. Labrosse, N., Dalla, S., Marshall, S.: 2010, Automatic detection of limb prominences in 304 Å EUV images. Solar Phys. 262(2), 449. DOI. ADSCrossRefGoogle Scholar
  19. Lang, K.R.: 2001, The Cambridge Encyclopedia of the Sun, Cambridge University Press, Cambridge, 268. DOI. CrossRefGoogle Scholar
  20. Long, J., Shelhamer, E., Darrell, T.: 2015, Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431. DOI. CrossRefGoogle Scholar
  21. Nair, V., Hinton, G.E.: 2010, Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), 807. Google Scholar
  22. Noh, H., Hong, S., Han, B.: 2015, Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, 1520. DOI. CrossRefGoogle Scholar
  23. Priest, E., Forbes, T.: 2002, The magnetic nature of solar flares. Astron. Astrophys. Rev. 10(4), 313. DOI. ADSCrossRefGoogle Scholar
  24. Qu, M., Shih, F.Y., Jing, J., Wang, H.: 2005, Automatic solar filament detection using image processing techniques. Solar Phys. 228(1 – 2), 119. DOI. ADSCrossRefGoogle Scholar
  25. Ronneberger, O., Fischer, P., Brox, T.: 2015, U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, New York, 234. DOI. CrossRefGoogle Scholar
  26. Shih, F.Y., Kowalski, A.J.: 2003, Automatic extraction of filaments in H\(\upalpha\) solar images. Solar Phys. 218(1 – 2), 99. DOI. ADSCrossRefGoogle Scholar
  27. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: 2014, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929. MathSciNetzbMATHGoogle Scholar
  28. Yu, F., Koltun, V.: 2016, Multi-scale context aggregation by dilated convolutions. In: ICLR. Google Scholar
  29. Yuan, Y., Shih, F., Jing, J., Wang, H., Chae, J.: 2011, Automatic solar filament segmentation and characterization. Solar Phys. 272(1), 101. DOI. ADSCrossRefGoogle Scholar
  30. Zhang, J., Cheng, X., et al.: 2012, Observation of an evolving magnetic flux rope before and during a solar eruption. Nat. Commun. 3, 747. DOI. ADSCrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  1. 1.National Astronomical ObservatoriesChinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina
  3. 3.Key Laboratory of Solar ActivityNational Astronomical ObservatoriesBeijingChina
  4. 4.School of Astronomy and Space SciencesUniversity of Chinese Academy of SciencesBeijingChina

Personalised recommendations