DOI QR코드

DOI QR Code

Deep Convolutional Neural Network with Bottleneck Structure using Raw Seismic Waveform for Earthquake Classification

  • Ku, Bon-Hwa (Machine learning and Big Data Research Center, Korea University) ;
  • Kim, Gwan-Tae (Dept. of Visual Information Processing, Korea University) ;
  • Min, Jeong-Ki (School of Electrical Engineering, Korea University) ;
  • Ko, Hanseok (School of Electrical Engineering, Korea University)
  • Received : 2018.12.06
  • Accepted : 2019.01.08
  • Published : 2019.01.31

Abstract

In this paper, we propose deep convolutional neural network(CNN) with bottleneck structure which improves the performance of earthquake classification. In order to address all possible forms of earthquakes including micro-earthquakes and artificial-earthquakes as well as large earthquakes, we need a representation and classifier that can effectively discriminate seismic waveforms in adverse conditions. In particular, to robustly classify seismic waveforms even in low snr, a deep CNN with 1x1 convolution bottleneck structure is proposed in raw seismic waveforms. The representative experimental results show that the proposed method is effective for noisy seismic waveforms and outperforms the previous state-of-the art methods on domestic earthquake database.

Keywords

CPTSCQ_2019_v24n1_33_f0001.png 이미지

Fig. 1. Earthquake classifier using CNN

CPTSCQ_2019_v24n1_33_f0002.png 이미지

Fig. 2. Bottleneck structure

CPTSCQ_2019_v24n1_33_f0003.png 이미지

Fig. 3. CNN with 1x1 bottleneck structure

CPTSCQ_2019_v24n1_33_f0004.png 이미지

Fig. 4. Extract earthquake events from 24 hour continuous data

CPTSCQ_2019_v24n1_33_f0005.png 이미지

Fig. 5. Frequency histogram distribution according events

Table 1. Number of Earthquake events

CPTSCQ_2019_v24n1_33_t0001.png 이미지

Table 2. Event Dataset

CPTSCQ_2019_v24n1_33_t0002.png 이미지

Table 3.Comparison performance of proposed method (unit: %)

CPTSCQ_2019_v24n1_33_t0003.png 이미지

References

  1. Zhicheng Cui, Wenlin Chen, Yixin Chen , "Multi-Scale Convolutional Neural Networks for Time Series Classification," arXiv:1603.06995 , May 2016.
  2. Jogpil Lee, et al., "SampleCNN : End-to-End Deep Convolutional Neural Networks Using Very Small Filter for Music Classifications," Applied Science, Vol.8, No.1, pp.150, Jan. 2018. https://doi.org/10.3390/app8010150
  3. Qingxue Zhang, et al., "HeartID: a multiresolution convolutional neural network for ECG-based biometric human identification in smart health applications," IEEE Access, Vol.5, pp.11805-11816, May 2017. https://doi.org/10.1109/ACCESS.2017.2707460
  4. M. Withers, et al., "A comparison of select trigger algorithms for automated global seismic phase and event detection," Bull. Seismol. Soc. Am. Vol.88, No.1, pp.95-106 , Feb. 1998.
  5. S. J. Gibbons and F. Ringdal, "The detection of low magnitude seismic events using array-based waveform correlation," Geophys. J. Int. Vol.165, No.1 pp.149-166, Mar. 2006. https://doi.org/10.1111/j.1365-246X.2006.02865.x
  6. R. J. Skoumal, et al., "Optimizing multi-station earthquake template matching through re-examination of the Youngstown, Ohio, sequence," Earth and Planet Science Letters, Vol.405, pp.274-280, Nov. 2014. https://doi.org/10.1016/j.epsl.2014.08.033
  7. C.E. Yoon, et al., "Earthquake detection through computationally efficient similarity search," Science Advances, Vol.1, No.11, e1501057, Dec. 2015. https://doi.org/10.1126/sciadv.1501057
  8. Thibaut Perol, et al., "Convolutional neural network for earthquake detection and location," Science Advances, Vol. 4, No. 2, e1700578, Feb. 2018. https://doi.org/10.1126/sciadv.1700578
  9. Sergey Ioffe and Christian Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," arXiv:1502.03167, Mar. 2015.
  10. Nitish Srivastava, et al., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting," Journal of Machine Learning Research, Vol. 15, No.1, pp.1929-1958, Jun. 2014.
  11. Dieleman, S. and Schrauwen, B.,"End-to-end learning for music audio," In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp.6964-6968, 2014.
  12. Ardila, D., et al., "Audio deepdream: Optimizing raw audio with convolutional networks," In Proceedings of the International Society for Music Information Retrieval Conference, 2016.
  13. Thickstun, J., et al., "Learning features of music from scratch." arXiv, Apr. 2017.
  14. Y. LeCun, Y. Bengio and G. Hinton, "Deep learning," Nature, Vol.521, No.7553, pp. 436-444, May 2015. https://doi.org/10.1038/nature14539
  15. X. Cui, V. Goel and B. Kingsbury, "Data augmentation for deep neural network acoustic modeling," IEEE/ACM Trans. on Audio, Speech and Language Processing, Vol.23, No. 9, pp.1469-1477, Jun. 2015. https://doi.org/10.1109/TASLP.2015.2438544
  16. Simonyan, K. and Zisserman, A, "Very deep convolutional networks for large-scale image recognition," arXiv:1409.1556, Apr. 2015.
  17. Anastasia Borovykh, et al., "Conditional Time Series Forecasting with Convolutional Neural Networks," arXiv:1703.04691 , Sep. 2018.
  18. Nima Hatami, et al., "Classification of Time-Series Images Using Deep Convolutional Neural Networks," arXiv:1710.00886 , Oct. 2017.
  19. Hassan Ismail Fawaz, et al., "Deep learning for time series classification: a review," arXiv: 1809.04356, Sep 2018.
  20. NECIS, http://necis.kma.go.kr/