Journal of The Korean Astronomical Society (천문학회지)

The Korean Astronomical Society (한국천문학회)
권호 표지
DOI QR코드

DOI QR Code

MODIFIED CONVOLUTIONAL NEURAL NETWORK WITH TRANSFER LEARNING FOR SOLAR FLARE PREDICTION

  • Zheng, Yanfang (College of Electrical and Information Engineering, Jiangsu University of Science and Technology) ;
  • Li, Xuebao (College of Electrical and Information Engineering, Jiangsu University of Science and Technology) ;
  • Wang, Xinshuo (College of Electrical and Information Engineering, Jiangsu University of Science and Technology) ;
  • Zhou, Ta (College of Electrical and Information Engineering, Jiangsu University of Science and Technology)
  • Received : 2019.07.03
  • Accepted : 2019.09.02
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

We apply a modified Convolutional Neural Network (CNN) model in conjunction with transfer learning to predict whether an active region (AR) would produce a ≥C-class or ≥M-class flare within the next 24 hours. We collect line-of-sight magnetogram samples of ARs provided by the SHARP from May 2010 to September 2018, which is a new data product from the HMI onboard the SDO. Based on these AR samples, we adopt the approach of shuffle-and-split cross-validation (CV) to build a database that includes 10 separate data sets. Each of the 10 data sets is segregated by NOAA AR number into a training and a testing data set. After training, validating, and testing our model, we compare the results with previous studies using predictive performance metrics, with a focus on the true skill statistic (TSS). The main results from this study are summarized as follows. First, to the best of our knowledge, this is the first time that the CNN model with transfer learning is used in solar physics to make binary class predictions for both ≥C-class and ≥M-class flares, without manually engineered features extracted from the observational data. Second, our model achieves relatively high scores of TSS = 0.640±0.075 and TSS = 0.526±0.052 for ≥M-class prediction and ≥C-class prediction, respectively, which is comparable to that of previous models. Third, our model also obtains quite good scores in five other metrics for both ≥C-class and ≥M-class flare prediction. Our results demonstrate that our modified CNN model with transfer learning is an effective method for flare forecasting with reasonable prediction performance.

Keywords

References

  1. Abadi, M., et al. 2015, TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, https://www.tensorflow.org
  2. Abraham, S., Aniyan, A. K., Kembhavi, A. K., et al. 2018, Detection of Bars in Galaxies Using a Deep Convolutional Neural Network, MNRAS, 477, 894 https://doi.org/10.1093/mnras/sty627
  3. Ahmed, O. W., Qahwaji, R., & Colak, T. 2013, Solar Flare Prediction Using Advanced Feature Extraction, Machine Learning, and Feature Selection, SoPh, 283, 157
  4. Aniyan, A. K., & Thorat, K., 2017, Classifying Radio Galaxies with the Convolutional Neural Network, ApJS, 230, 20 https://doi.org/10.3847/1538-4365/aa7333
  5. Barnes, G., Leka, K. D., Schrijver, C. J., et al. 2016, A Comparison of Flare Forecasting Methods, I: Results from the "All-Clear" Workshop, ApJ, 829, 89 https://doi.org/10.3847/0004-637X/829/2/89
  6. Bloomfield, D. S., Higgins, P. A., James McAteer, R. T., et al. 2012, Toward Reliable Benchmarking of Solar Flare Forecasting Methods, ApJL, 747, L41 https://doi.org/10.1088/2041-8205/747/2/L41
  7. Bobra, M. G., & Couvidat, S. 2015, Solar Flare Prediction Using SDO/HMI Vector Magnetic Field Data with a Machine-Learning Algorithm, ApJ, 798, 135 https://doi.org/10.1088/0004-637X/798/2/135
  8. Bobra, M. G., Sun, X., Hoeksema, J. T., et al. 2014, The Helioseismic and Magnetic Imager (HMI) Vector Magnetic Field Pipeline: SHARPs - Space-Weather HMI Active Region Patches, SoPh, 289, 3549
  9. Chollet, F., et al. 2015, Keras, https://github.com/keras-team/keras
  10. Colak, T., & Qahwaji, R. 2009, Automated Solar Activity Prediction: A Hybrid Computer Platform Using Machine Learning and Solar Imaging for Automated Prediction of Solar Flares, SpWea, 7, S06001
  11. Deng, J., Dong, W., Socher, R., et al. 2009, ImageNet: A Large-scale Hierarchical Image Database, IEEE Conference on Computer Vision and Pattern Recognition, 248, 255
  12. Florios, K., Kontogiannis, I., Park, S. H., et al. 2018, Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning, SoPh, 293, 28
  13. Gaier, A., & Ha, W. 2019, Weight Agnostic Neural Networks, arXiv:1906.04358
  14. Goodfellow I., Bengio Y., & Courville A. 2016, Deep Learning (Cambridge, MA: MIT Press)
  15. Guerra, J. A., Pulkkinen, A., & Uritsky, V. M. 2015, Ensemble Forecasting of Major Solar Flares: First Results, SpWea, 13, 626
  16. Hanssen, A. W., & Kuipers, W. J. A. 1965, On the Relationship between the Frequency of Rain and Various Meteorological Parameters, Meded. Verh., 81, 2
  17. Heidke, P. 1926, Berechnung des Erfolges und der Gute der Windstarkevorhersagen im Sturmwarnungdienst (Calculation of the Success and Goodness of Strong Wind Forecasts in the Storm Warning Service), Geogr. Ann. Stockholm, 8, 301
  18. Hinton, G. E., & Salakhutdinov, R. R. 2006, Reducing the Dimensionality of Data with Neural Networks, Science, 313, 504 https://doi.org/10.1126/science.1127647
  19. Huang, G., Liu, Z., van der Maaten, L., et al. 2016, Densely Connected Convolutional Networks, arXiv:1608.06993
  20. Huang, X., Wang, H., Xu, L., et al. 2018, Deep Learning Based Solar Flare Forecasting Model. I. Results for Line-of-sight Magnetograms, ApJ, 856, 7 https://doi.org/10.3847/1538-4357/aaae00
  21. Huang, X., Yu, D. R., Hu, Q. H., et al. 2010, Short-Term Solar Flare Prediction Using Predictor Teams, SoPh, 263, 175
  22. Ioffe, S., & Szegedy, C. 2015, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, Proc. 32nd Int. Conf. Machine Learning (ICML'15), 37, 448
  23. LeCun, Y., Bengio, Y., & Hinton, G. 2015, Deep Learning, Nature, 521, 436 https://doi.org/10.1038/nature14539
  24. LeCun, Y., Bottou, L., Orr, G., & Muller, K. 1998, Efficient BackProp, Neural Networks: Tricks of the Trade (Berlin: Springer), 9, 48
  25. Li, R., & Zhu, J. 2013, Solar Flare Forecasting Based on Sequential Sunspot Data, RAA, 13, 1118
  26. Liu, C., Deng, N.,Wang, J. T. L., et al. 2017, Predicting Solar Flares Using SDO/HMI Vector Magnetic Data Products and the Random Forest Algorithm, ApJ, 843, 104 https://doi.org/10.3847/1538-4357/aa789b
  27. Mason, J. P., & Hoeksema, J. T. 2010, Testing Automated Solar Flare Forecasting with 13 Years of Michelson Doppler Imager Magnetograms, ApJ, 723, 634 https://doi.org/10.1088/0004-637X/723/1/634
  28. Nair, V., & Hinton, G. E. 2010, Rectified Linear Units Improve Restricted Boltzmann Machines, Proc. 27th Int. Conf. on Machine Learning (ICML-10) (Madison, WI: Omnipress), 807
  29. Nishizuka, N., Sugiura, K., Kubo, Y., et al. 2017, Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms, ApJ, 835, 156 https://doi.org/10.3847/1538-4357/835/2/156
  30. Nishizuka, N., Sugiura, K., Kubo, Y., et al. 2018, Deep Flare Net (DeFN) Model for Solar Flare Prediction, ApJ, 858, 113
  31. Park, E., Moon, Y. J., Shin, S., et al. 2018, Application of the Deep Convolutional Neural Network to the Forecast of Solar Flare Occurrence Using Full-disk Solar Magnetograms, ApJ, 869, 91 https://doi.org/10.3847/1538-4357/aaed40
  32. Pesnell, W. D., Thompson, B. J., & Chamberlin, P. C. 2012, The Solar Dynamics Observatory (SDO), SoPh, 275, 3
  33. Priest, E. R., & Forbes, T. G. 2002, The Magnetic Nature of Solar Flares, A&ARv, 10, 313 https://doi.org/10.1007/s001590100013
  34. Qahwaji, R., & Colak, T. 2007, Automatic Short-Term Solar Flare Prediction Using Machine Learning and Sunspot Associations, SoPh, 241, 195
  35. Razavian, A. S., Azizpour, H., Sullivan, J., et al. 2014, CNN Features Off-the-shelf: an Astounding Baseline for Recognition, arXiv:1403.6382
  36. Sadykov, V. M., & Kosovichev, A. G. 2017, Relationships between Characteristics of the Line-of-sight Magnetic Field and Solar Flare Forecasts, ApJ, 849, 148 https://doi.org/10.3847/1538-4357/aa9119
  37. Schou, J., Scherrer, P. H., Bush, R. I., et al. 2012, Design and Ground Calibration of the Helioseismic and Magnetic Imager (HMI) Instrument on the Solar Dynamics Observatory (SDO), SoPh, 275, 229
  38. Shibata, K., & Magara, T. 2011, Solar Flares: Magnetohydrodynamic Processes, LRSP, 8, 6
  39. Simonyan, K., & Zisserman, A. 2015, Very Deep Convolutional Networks for Large-Scale Image Recognition, ICLR 2015, arXiv:1409.1556
  40. Song, H., Tan, C., Jing, J., et al. 2009, Statistical Assessment of Photospheric Magnetic Features in Imminent Solar Flare Predictions, SoPh, 254, 101
  41. Szegedy, C., Liu, W., Jia, Y., et al. 2014, Going Deeper with Convolutions, arXiv:1409.4842
  42. Tang, H. M., Scaife, A. M. M., & Leahy, J. P. 2019, Transfer Learning for Radio Galaxy Classification, arXiv:1903.11921
  43. Yu, D. R., Huang, X., Wang, H. N., et al. 2010, Short-term Solar Flare Level Prediction Using a Bayesian Network Approach, ApJ, 710, 869 https://doi.org/10.1088/0004-637X/710/1/869
  44. Yuan, Y., Shih, F. Y., Jing, J., et al. 2010, Automated Flare Forecasting Using a Statistical Learning Technique, RAA, 10, 785