DeepRFQC: automating quality control for P-wave receiver function analysis using a U-net inspired network

Authors

  • Sina Sabermahani University of Manitoba
  • Andrew Frederiksen University of Manitoba

DOI:

https://doi.org/10.26443/seismica.v3i2.1341

Keywords:

Receiver Function, Deep Learning, quality control, U-net, H-k stacking

Abstract

This paper introduces DeepRFQC, an automated method for quality control in P-wave receiver function analysis. Leveraging a U-Net inspired deep learning model, which has previously shown promise in denoising and phase detection, DeepRFQC efficiently distinguishes usable from noisy receiver functions. We examine a Proterozoic Trans-Hudson Orogen dataset from northern Canada, including seismic events from 1990 to 2023, which is expanded for training purposes by data augmentation techniques. With 1,508,449 trainable parameters, the DeepRFQC model attains a commendable 96.6% validation accuracy, on a test dataset from the X5 seismic network; tests on stations from different tectonic environments indicate that the model is effective even in environments very different from the training set. Validation through the H-κ stacking method shows consistent and plausible results. As manual quality control is a major bottleneck in receiver-function processing, automated methods such as this one will allow for efficient examination of large data sets.

References

Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., & Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. https://www.tensorflow.org/

Adler, A., Araya-Polo, M., & Poggio, T. (2021). Deep learning for seismic inverse problems: toward the acceleration of geophysical analysis workflows. IEEE Signal Processing Magazine, 38(2), 89–119. https://doi.org/10.1109/msp.2020.3037429

Ammon, C. J. (1992). A comparison of deconvolution techniques.

Audet, P., Schutt, D., Schaeffer, A. J., Cubley, J. F., Pellerin, L., & Buiter, S. J. H. (2020). Moho variations across the Northern Canadian Cordillera. Seismological Research Letters, 91(6). https://doi.org/10.1785/0220200166

Audet, Pascal. (2020). RfPy: Teleseismic receiver function calculation and post-processing (0.1.0). https://doi.org/10.5281/zenodo.4302558

Basha, S. M., & Rajput, D. S. (2019). Aspects of deep learning: hyper-parameter tuning, regularization, and normalization. In Intelligent systems (pp. 171–188). Apple Academic Press.

Bastow, I. D., Kendall, J., Helffrich, G., Thompson, D., Wookey, J., Brisbourne, A., & Snyder, D. B. (2011). The Hudson Bay lithospheric experiment. Astronomy & Geophysics, 52(6), 6.21-6.24. https://doi.org/10.1111/j.1468-4004.2011.52621.x

Bensen, G. D., Ritzwoller, M. H., Barmin, M. P., Levshin, A. L., Lin, F., Moschetti, M. P., Shapiro, N. M., & Yang, Y. (2007). Processing seismic ambient noise data to obtain reliable broad-band surface wave dispersion measurements. Geophysical Journal International, 169(3), 1239–1260. https://doi.org/10.1111/j.1365-246X.2007.03374.x

Bloch, W., Bostock, M. G., & Audet, P. (2023). A Cascadia Slab Model from Receiver Functions. Geochemistry, Geophysics, Geosystems, 24(10), e2023GC011088. https://doi.org/10.1029/2023GC011088

Chang, D., Zhang, G., Yong, X., Gao, J., Wang, Y., & Wang, W. (2022). Deep learning using synthetic seismic data by Fourier domain adaptation in seismic structure interpretation. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. https://doi.org/10.1109/lgrs.2022.3218911

Crotwell, H. P., & Owens, T. J. (2005). Automated Receiver Function Processing. Seismological Research Letters, 76(6), 702–709. https://doi.org/10.1785/gssrl.76.6.702

Dozat, T. (2016, February 18). Incorporating Nesterov Momentum into Adam. ICLR 2016 Workshop: Workshop on Optimization for Machine Learning.

Dreiling, J., Tilmann, F., Yuan, X., Haberland, C., & Seneviratne, S. W. M. (2020). Crustal Structure of Sri Lanka Derived from Joint Inversion of Surface Wave Dispersion and Receiver Functions Using a Bayesian Approach. Journal of Geophysical Research: Solid Earth, 125(5), e2019JB018688. https://doi.org/10.1029/2019JB018688

Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul), 2121–2159.

Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 9, 249–256.

Gong, C., Chen, L., Xiao, Z., & Wang, X. (2022). Deep learning for quality control of receiver functions. Frontiers in Earth Science. https://doi.org/10.3389/feart.2022.921830

Gower, R. M., Loizou, N., Qian, X., Sailanbayev, A., Shulgin, E., & Richtárik, P. (2019). SGD: General analysis and improved rates. In H. Wallach, H. Larochelle, A. Courville, M. Ranzato, R. Pascanu, & V. Lapouge (Eds.), Proceedings of the 36th International Conference on Machine Learning (pp. 5200–5209).

Hansen, S., & Schmandt, B. (2017). P and S wave receiver function imaging of subduction with scattering kernels. Geochemistry Geophysics Geosystems, 18(12), 4487–4502. https://doi.org/10.1002/2017gc007120

Harris, C. R., Millman, K. J., van der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., Smith, N. J., Kern, R., Picus, M., Hoyer, S., van Kerkwijk, M. H., Brett, M., Haldane, A., Fernández del Río, J., Wiebe, M., Peterson, P., & ... Oliphant, T. E. (2020). Array programming with NumPy. Nature, 585(7825), 357–362. https://doi.org/10.1038/s41586-020-2649-2

He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. 2015 IEEE International Conference on Computer Vision (ICCV), 1026–1034. https://doi.org/10.1109/ICCV.2015.123

Hopper, E., Fischer, K., Wagner, L., & Hawman, R. (2017). Reconstructing the end of the Appalachian orogeny. Geology, 45(1), 15–18. https://doi.org/10.1130/g38453.1

Iwana, B. K., & Uchida, S. (2021). An empirical survey of data augmentation for time series classification with neural networks. Plos One, 16(7), e0254841. https://doi.org/10.1371/journal.pone.0254841

Kikuchi, M., & Kanamori, H. (1982). Inversion of complex body waves. Bulletin of the Seismological Society of America, 72(2), 491–506. https://doi.org/10.1785/BSSA0720020491

Kind, R., Mooney, W. D., & Yuan, X. (2020). New insights into the structural elements of the upper mantle beneath the contiguous United States from S-to-P converted seismic waves. Geophysical Journal International, 222(1), 646–659. https://doi.org/10.1093/gji/ggaa203

Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization. CoRR, abs/1412.6980. https://doi.org/10.48550/arXiv.1412.6980

Kou, C., Li, W., Liang, W., Yu, Z., & Hao, J. (2019). Microaneurysms segmentation with a U-net based on recurrent residual convolutional neural network. Journal of Medical Imaging, 6(2), 025008. https://doi.org/10.1117/1.jmi.6.2.025008

Krueger, H. E., Gama, I., & Fischer, K. M. (2021). Global patterns in cratonic mid-lithospheric discontinuities from Sp receiver functions. Geochemistry, Geophysics, Geosystems, 22(6). https://doi.org/10.1029/2021GC009819

Lawrence, J., & Shearer, P. (2006). A global study of transition zone thickness using receiver functions. Journal of Geophysical Research Atmospheres, 111(B6). https://doi.org/10.1029/2005jb003973

Ligorría, J. P., & Ammon, C. J. (1999). Iterative deconvolution and receiver-function estimation. Bulletin of the Seismological Society of America, 89(5), 1395–1400. https://doi.org/10.1785/BSSA0890051395

Luo, Y., Long, M. D., Karabinos, P., Kuiper, Y. D., Rondenay, S., Aragon, J. C., Sawade, L., & Makus, P. (2021). High-Resolution Ps Receiver Function Imaging of the Crust and Mantle Lithosphere Beneath Southern New England and Tectonic Implications. Journal of Geophysical Research: Solid Earth, 126(7). https://doi.org/10.1029/2021JB022170

Mousavi, S., Sheng, Y., Zhu, W., & Beroza, G. (2019). Stanford earthquake dataset (STEAD): a global dataset of seismic signals for AI. IEEE Access, 7, 179464–179476. https://doi.org/10.1109/access.2019.2947848

Mukkamala, M. C., & Hein, M. (2017). Variants of RMSProp and Adagrad with Logarithmic Regret Bounds. Proceedings of the 34th International Conference on Machine Learning, 70, 2545–2553. https://proceedings.mlr.press/v70/mukkamala17a.html

Natural Resources Canada. (1975). Canadian National Seismograph Network. [Data set]. Natural Resources Canada. https://doi.org/10.7914/SN/CN

Park, J., & Levin, V. (2000). Receiver functions from multiple-taper spectral correlation estimates. Bulletin of the Seismological Society of America, 90(6), 1507–1520. https://doi.org/10.1785/0119990122

Ramadanti, F. (2023). Preliminary results on receiver function study in Mt. Merapi, Central Java, Indonesia. In IOP Conference Series: Earth and Environmental Science (Vol. 1227, p. 012049). https://doi.org/10.1088/1755-1315/1227/1/012049

Rodriguez, E. E., & Russo, R. M. (2020). Southern Chile crustal structure from teleseismic receiver functions: Responses to ridge subduction and terrane assembly of Patagonia. Geosphere, 16(1), 378–391. https://doi.org/10.1130/GES01692.1

Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In N. Navab, J. Hornegger, W. Wells, & A. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 (Vol. 9351, pp. 234–241). Springer, Cham. https://doi.org/10.1007/978-3-319-24574-4_28

Sabermahani, S., & Frederiksen, A. (2023). DeepRFQC: automating quality control for P-wave receiver function analysis using a U-net inspired network. Zenodo. https://doi.org/10.5281/zenodo.10087652

Schimmel, M., & Paulssen, H. (1997). Noise reduction and detection of weak, coherent signals through phase-weighted stacks. Geophysical Journal International, 130(2), 497–505.

Scripps Institution of Oceanography. (1986). IRIS/IDA Seismic Network. International Federation of Digital Seismograph Networks. Other/Seismic Network. https://doi.org/10.7914/SN/II

Shen, W., Ritzwoller, M. H., Schulte-Pelkum, V., & Lin, F.-C. (2013). Joint inversion of surface wave dispersion and receiver functions: A Bayesian Monte-Carlo approach. Geophysical Journal International, 192(2), 807–836. https://doi.org/10.1093/gji/ggs050

Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(60). https://doi.org/10.1186/s40537-019-0197-0

Snyder, D. B., Craven, J. A., Pilkington, M., & Hillier, M. J. (2015). The 3-dimensional construction of the Rae craton, central Canada. Geochemistry, Geophysics, Geosystems, 16(10), 3555–3574. https://doi.org/10.1002/2015GC005957

Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006). Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation. In A. Sattar & B. H. Kang (Eds.), AI 2006: Advances in Artificial Intelligence (Vol. 4304, pp. 1015–1021). Springer, Berlin, Heidelberg. https://doi.org/10.1007/11941439_114

The ObsPy Development Team. (2022). ObsPy 1.4.0 (1.4.0). Zenodo. https://doi.org/10.5281/zenodo.6645832

The Pandas development team. (2024). Pandas-dev/pandas: Pandas (v2.2.2). Zenodo. https://doi.org/10.5281/zenodo.10957263

Thompson, D. A., Bastow, I. D., Helffrich, G., Kendall, J.-M., Wookey, J., Snyder, D. B., & Eaton, D. W. (2010). Precambrian crustal evolution: Seismic constraints from the Canadian Shield. Earth and Planetary Science Letters, 297(3–4), 655–666. https://doi.org/10.1016/j.epsl.2010.07.021

Tribolet, J., Oppenheim, A., & Kopec, G. (1975). Deconvolution by homomorphic prediction. 45th Annual International Meeting of the Society of Exploration Geophysicists.

Vinnik, L. P. (1977). Detection of waves converted from P to SV in the mantle. Physics of the Earth and Planetary Interiors, 15(1), 39–45. https://doi.org/10.1016/0031-9201(77)90008-5

Vinnik, L. P., Reigber, C., Aleshin, I. M., Kosarev, G. L., Kaban, M. K., Oreshin, S. I., & Roecker, S. W. (2004). Receiver function tomography of the central Tien Shan. Earth and Planetary Science Letters, 225(1–2), 131–146. https://doi.org/10.1016/j.epsl.2004.05.039

Wessel, P., Luis, J. F., Uieda, L., Scharroo, R., Wobbe, F., Smith, W. H. F., & Tian, D. (2019). The Generic Mapping Tools Version 6. Geochemistry, Geophysics, Geosystems, 20(11). https://doi.org/10.1029/2019GC008515

Whitmeyer, S., & Karlstrom, K. E. (2007). Tectonic model for the Proterozoic growth of North America. Geosphere, 3(4), 220–259. https://doi.org/10.1130/GES00055.1

Wilson, D. C., & Aster, R. C. (2005). Seismic imaging of the crust and upper mantle using regularized joint receiver functions, frequency–wave number filtering, and multimode Kirchhoff migration. Journal of Geophysical Research: Solid Earth, 110(B5). https://doi.org/10.1029/2004jb003430

Yang, X., Pavlis, G. L., & Wang, Y. (2016). A Quality Control Method for Teleseismic P-Wave Receiver Functions. Bulletin of the Seismological Society of America, 106(5), 1948–1962. https://doi.org/10.1785/0120150347

Zanjani, A. A., Zhu, L., Herrmann, R. B., Liu, Y., Gu, Z., & Conder, J. A. (2019). Crustal Structure Beneath the Wabash Valley Seismic Zone from the Joint Inversion of Receiver Functions and Surface-Wave Dispersion: Implications for Continental Rifts and Intraplate Seismicity. Journal of Geophysical Research: Solid Earth, 124(7), 7028–7039. https://doi.org/10.1029/2018JB016989

Zeiler, M. D. (2012). ADADELTA: An adaptive learning rate method. [arXiv preprint abs/1212.5701]. https://doi.org/10.48550/arXiv.1212.5701

Zhu, L., & Kanamori, H. (2000). Moho depth variation in southern California from teleseismic receiver functions. Journal of Geophysical Research, 105(B2), 2969–2980. https://doi.org/10.1029/1999JB900322

Zhu, W., & Beroza, G. C. (2019). PhaseNet: a deep-neural-network-based seismic arrival-time picking method. Geophysical Journal International, 216(1), 261–273. https://doi.org/10.1093/gji/ggy423

Downloads

Additional Files

Published

2024-11-12

How to Cite

Sabermahani, S., & Frederiksen, A. (2024). DeepRFQC: automating quality control for P-wave receiver function analysis using a U-net inspired network. Seismica, 3(2). https://doi.org/10.26443/seismica.v3i2.1341

Issue

Vol. 3 No. 2 (2024)

Section

Articles

License

Copyright (c) 2024 Sina Sabermahani, Andrew Frederiksen

Creative Commons License

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

Funding data