Feasibility of Deep Learning in Shear Wave Splitting analysis using Synthetic-Data Training and Waveform Deconvolution

Authors

DOI:

https://doi.org/10.26443/seismica.v3i1.1124

Keywords:

shear-wave splitting, seismic anisotropy, waveform analysis

Abstract

Teleseismic shear-wave splitting analyses are often performed by reversing the splitting process through the application of frequency- or time-domain operations aimed at minimizing the transverse-component energy of waveforms. These operations yield two splitting parameters, ɸ (fast-axis orientation) and δt (delay time). In this study, we investigate the applicability of a baseline recurrent neural network, SWSNet, for determining the splitting parameters from pre-selected waveform windows. Due to the scarcity of sufficiently labelled real waveform data, we generate our own synthetic dataset to train the model. The model is capable of determining ɸ and δt with a root mean squared error (RMSE) of 9.7° and 0.14 s on a noisy synthetic test data. The application to real data involves a deconvolution step to homogenize the waveforms. When applied to data from the USArray dataset, the results exhibit similar patterns to those found in previous studies with mean absolute differences of 9.6° and 0.16 s in the calculation of ɸ and δt respectively.

References

Agarap, A. F. (2018). Deep learning using rectified linear units (relu). ArXiv Preprint ArXiv:1803.08375.

Ammon, C. J. (1991). The isolation of receiver effects from teleseismic P waveforms. Bulletin of the Seismological Society of America, 81(6), 2504–2510. https://doi.org/10.1785/BSSA0810062504 DOI: https://doi.org/10.1785/BSSA0810062504

Barruol, G., Wuestefeld, A., & Bokelmann, G. (2009). SKS-Splitting-database. Université de Montpellier, Laboratoire Géosciences. https://doi.org/10.18715/sks_splitting_database

Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., Kruspe, A., Triebel, R., Jung, P., Roscher, R., Shahzad, M., Yang, W., Bamler, R., & Zhu, X. X. (2023). A survey of uncertainty in deep neural networks. Artificial Intelligence Reviews, 56 (Suppl 1), 1513–1589. https://doi.org/https://doi.org/10.1007/s10462-023-10562-9 DOI: https://doi.org/10.1007/s10462-023-10562-9

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press. http://www.deeplearningbook.org

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Comput., 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 DOI: https://doi.org/10.1162/neco.1997.9.8.1735

Holtzman, B. K., & Kendall, J.-M. (2010). Organized melt, seismic anisotropy, and plate boundary lubrication. Geochemistry, Geophysics, Geosystems, 11(12). https://doi.org/https://doi.org/10.1029/2010GC003296 DOI: https://doi.org/10.1029/2010GC003296

Hudson, T. S., Asplet, J., & Walker, A. M. (2023). Automated shear-wave splitting analysis for single- and multi- layer anisotropic media. Seismica. https://doi.org/https://doi.org/10.26443/seismica.v2i2.1031 DOI: https://doi.org/10.31223/X5R67Z

IRIS Transportable Array. (2003). USArray Transportable Array [Data set]. International Federation of Digital Seismograph Networks. https://doi.org/10.7914/SN/TA

Jia, Y., Liu, K. H., Kong, F., Liu, L., & Gao, S. S. (2021). A systematic investigation of piercing-point-dependent seismic azimuthal anisotropy. Geophysical Journal International, 227(3), 1496–1511. https://doi.org/10.1093/gji/ggab285 DOI: https://doi.org/10.1093/gji/ggab285

Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. ArXiv Preprint ArXiv:1412.6980.

Kiranyaz, S., Ince, T., Hamila, R., & Gabbouj, M. (2015). Convolutional Neural Networks for patient-specific ECG classification. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2608–2611. https://doi.org/10.1109/EMBC.2015.7318926 DOI: https://doi.org/10.1109/EMBC.2015.7318926

Langston, C. A. (1979). Structure under Mount Rainier, Washington, inferred from teleseismic body waves. Journal of Geophysical Research: Solid Earth, 84(B9), 4749–4762. https://doi.org/https://doi.org/10.1029/JB084iB09p04749 DOI: https://doi.org/10.1029/JB084iB09p04749

Link, F., Reiss, M. C., & Rümpker, G. (2022). An automatized XKS-splitting procedure for large data sets: Extension package for SplitRacer and application to the USArray. Computers & Geosciences, 158, 104961. https://doi.org/https://doi.org/10.1016/j.cageo.2021.104961 DOI: https://doi.org/10.1016/j.cageo.2021.104961

Liu, K. H., Elsheikh, A., Lemnifi, A., Purevsuren, U., Ray, M., Refayee, H., Yang, B. B., Yu, Y., & Gao, S. S. (2014). A uniform database of teleseismic shear wave splitting measurements for the western and central United States. Geochemistry, Geophysics, Geosystems, 15(5), 2075–2085. https://doi.org/https://doi.org/10.1002/2014GC005267 DOI: https://doi.org/10.1002/2014GC005267

Liu, Kelly H., & Gao, S. S. (2013). Making Reliable Shear‐Wave Splitting Measurements. Bulletin of the Seismological Society of America, 103(5), 2680–2693. https://doi.org/10.1785/0120120355 DOI: https://doi.org/10.1785/0120120355

Long, M. D., & Silver, P. G. (2009). Shear Wave Splitting and Mantle Anisotropy: Measurements, Interpretations, and New Directions. Surveys in Geophysics, 30, 407–461. https://doi.org/https://doi.org/10.1007/s10712-009-9075-1 DOI: https://doi.org/10.1007/s10712-009-9075-1

Nagi, J., Ducatelle, F., Di Caro, G. A., Cireşan, D., Meier, U., Giusti, A., Nagi, F., Schmidhuber, J., & Gambardella, L. M. (2011). Max-pooling convolutional neural networks for vision-based hand gesture recognition. 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 342–347. https://doi.org/10.1109/ICSIPA.2011.6144164 DOI: https://doi.org/10.1109/ICSIPA.2011.6144164

Owens, T. J., Zandt, G., & Taylor, S. R. (1984). Seismic evidence for an ancient rift beneath the cumberland plateau, Tennessee: A detailed analysis of broadband teleseismic P waveforms. J. Geophys. Res.; (United States). https://doi.org/10.1029/JB089iB09p07783 DOI: https://doi.org/10.1029/JB089iB09p07783

Prechelt, L. (2012). Early Stopping — But When? In Neural Networks: Tricks of the Trade: Second Edition (pp. 53–67). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-35289-8_5 DOI: https://doi.org/10.1007/978-3-642-35289-8_5

Reiss, M. C., & Rümpker, G. (2017). SplitRacer: MATLAB Code and GUI for Semiautomated Analysis and Interpretation of Teleseismic Shear‐Wave Splitting. Seismological Research Letters, 88(2A), 392–409. https://doi.org/10.1785/0220160191 DOI: https://doi.org/10.1785/0220160191

Rümpker, G., Kaviani, A., Link, F., Reiss, M. C., & Komeazi, A. (2023). Testing observables for teleseismic shear-wave splitting inversions: ambiguities of intensities, parameters, and waveforms. Ann. Geophys., 66. https://doi.org/https://doi.org/10.4401/ag-8870 DOI: https://doi.org/10.4401/ag-8870

Savage, M. K. (1999). Seismic anisotropy and mantle deformation: What have we learned from shear wave splitting? Reviews of Geophysics, 37(1), 65–106. https://doi.org/https://doi.org/10.1029/98RG02075 DOI: https://doi.org/10.1029/98RG02075

Savage, M. K., Wessel, A., Teanby, N. A., & Hurst, A. W. (2010). Automatic measurement of shear wave splitting and applications to time varying anisotropy at Mount Ruapehu volcano, New Zealand. Journal of Geophysical Research: Solid Earth, 115(B12). https://doi.org/https://doi.org/10.1029/2010JB007722 DOI: https://doi.org/10.1029/2010JB007722

Silver, P. G., & Chan, W. W. (1991). Shear wave splitting and subcontinental mantle deformation. Journal of Geophysical Research: Solid Earth, 96(B10), 16429–16454. https://doi.org/https://doi.org/10.1029/91JB00899 DOI: https://doi.org/10.1029/91JB00899

Silver, P. G., & Savage, M. K. (1994). The Interpretation of Shear-Wave Splitting Parameters In the Presence of Two Anisotropic Layers. Geophysical Journal International, 119(3), 949–963. https://doi.org/10.1111/j.1365-246X.1994.tb04027.x DOI: https://doi.org/10.1111/j.1365-246X.1994.tb04027.x

Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15(56), 1929–1958. http://jmlr.org/papers/v15/srivastava14a.html

Teanby, N. A., Kendall, J.-M., & van der Baan, M. (2004). Automation of Shear-Wave Splitting Measurements using Cluster Analysis. Bulletin of the Seismological Society of America, 94(2), 453–463. https://doi.org/10.1785/0120030123 DOI: https://doi.org/10.1785/0120030123

Wuestefeld, A., Al-Harrasi, O., Verdon, J. P., Wookey, J., & Kendall, J. M. (2010). A strategy for automated analysis of passive microseismic data to image seismic anisotropy and fracture characteristics. Geophysical Prospecting, 58(5), 755–773. https://doi.org/https://doi.org/10.1111/j.1365-2478.2010.00891.x DOI: https://doi.org/10.1111/j.1365-2478.2010.00891.x

Wüstefeld, A., Bokelmann, G., Zaroli, C., & Barruol, G. (2008). SplitLab: A shear-wave splitting environment in Matlab. Computers & Geosciences, 34(5), 515–528. https://doi.org/https://doi.org/10.1016/j.cageo.2007.08.002 DOI: https://doi.org/10.1016/j.cageo.2007.08.002

Zhang, Y., & Gao, S. S. (2022). Classification of Teleseismic Shear Wave Splitting Measurements: A Convolutional Neural Network Approach. Geophysical Research Letters, 49(12), e2021GL097101. https://doi.org/https://doi.org/10.1029/2021GL097101 DOI: https://doi.org/10.1029/2021GL097101

Downloads

Additional Files

Published

2024-03-23

How to Cite

Chakraborty, M., Rümpker, G., Li, W., Faber, J., Srivastava, N., & Link, F. (2024). Feasibility of Deep Learning in Shear Wave Splitting analysis using Synthetic-Data Training and Waveform Deconvolution. Seismica, 3(1). https://doi.org/10.26443/seismica.v3i1.1124

Issue

Vol. 3 No. 1 (2024)

Section

Articles

License

Copyright (c) 2024 Megha Chakraborty, Georg Rümpker, Wei Li, Johannes Faber, Nishtha Srivastava, Frederik Link

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Funding data