Deep Learning Approach for Earthquake Parameters Classification in Earthquake Early Warning System

Magnitude determination of earthquakes is a mandatory step before an earthquake early warning (EEW) system sends an alarm. Beneficiary users of EEW systems depend on how far they are located from such strong events. Therefore, determining the locations of these shakes is an important issue for the tranquility of citizens as well. In light of that, this article proposes a magnitude, location, depth, and origin time categorization using earthquake Ml magnitudes between 2 and 9. The dataset used is the fore and aftershocks of the great Tohoku earthquake of March 11, 2011, recorded by three stations from the Japanese Hi-net seismic network. The proposed algorithm depends on a convolutional neural network (CNN) which has the ability to extract significant features from waveforms that enabled the classifier to reach a robust performance in the required earthquake parameters. The classification accuracies of the suggested approach for magnitude, origin time, depth, and location are $93.67\%, 89.55\%, 92.54\%$ , and 89.50%, respectively.

[1]  Tohru Kohda,et al.  Clear P-wave arrival of weak events and automatic onset determination using wavelet filter banks , 2010, Digit. Signal Process..

[2]  H. S. Kuyuk,et al.  Real-Time Classification of Earthquake using Deep Learning , 2018 .

[3]  Richard M. Allen,et al.  The deterministic nature of earthquake rupture , 2005, Nature.

[4]  Li Zhao,et al.  Magnitude estimation using the first three seconds P‐wave amplitude in earthquake early warning , 2006 .

[5]  G. Roe,et al.  REAL-TIME SEISMOLOGY AND EARTHQUAKE DAMAGE MITIGATION , 2005 .

[6]  Anthony Lomax,et al.  An Investigation of Rapid Earthquake Characterization Using Single‐Station Waveforms and a Convolutional Neural Network , 2019, Seismological Research Letters.

[7]  Min Bai,et al.  Automatic Waveform Classification and Arrival Picking Based on Convolutional Neural Network , 2019, Earth and Space Science.

[8]  Geociênicias.  Japan Meteorological Agency , 2011 .

[9]  Ramin M. H. Dokht,et al.  Seismic Event and Phase Detection Using Time–Frequency Representation and Convolutional Neural Networks , 2019, Seismological Research Letters.

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Ahmed Shalaby,et al.  Automatic arrival time detection for earthquakes based on Modified Laplacian of Gaussian filter , 2018, Comput. Geosci..

[12]  Michaël Gharbi,et al.  Convolutional neural network for earthquake detection and location , 2017, Science Advances.

[13]  Yangkang Chen,et al.  Deep learning for seismic lithology prediction , 2018 .

[14]  Peng Jiang,et al.  Deep Learning Inversion of Electrical Resistivity Data , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[15]  M. Furumoto,et al.  Hierarchy in earthquake size distribution , 1985 .

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[18]  Tohru Kohda,et al.  Seismic noise study for accurate P-wave arrival detection via MODWT , 2013, Comput. Geosci..

[19]  J. Brune.  Implications of earthquake triggering and rupture propagation for earthquake prediction based on premonitory phenomena , 1979 .

[20]  Koji Inoue,et al.  Automatic Arrival Time Detection for Earthquakes Based on Stacked Denoising Autoencoder , 2018, IEEE Geoscience and Remote Sensing Letters.