Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking

S. Mostafa Mousavi; William L. Ellsworth; Weiqiang Zhu; Lindsay Y. Chuang; Gregory C. Beroza

doi:10.1038/s41467-020-17591-w

journal article Open Access Aug 07, 2020

Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking

S. Mostafa Mousavi

William L. Ellsworth

Weiqiang Zhu

Lindsay Y. Chuang Gregory C. Beroza

Nature Communications Vol. 11 No. 1 · Springer Science and Business Media LLC

View at Publisher Save 10.1038/s41467-020-17591-w

Abstract

AbstractEarthquake signal detection and seismic phase picking are challenging tasks in the processing of noisy data and the monitoring of microearthquakes. Here we present a global deep-learning model for simultaneous earthquake detection and phase picking. Performing these two related tasks in tandem improves model performance in each individual task by combining information in phases and in the full waveform of earthquake signals by using a hierarchical attention mechanism. We show that our model outperforms previous deep-learning and traditional phase-picking and detection algorithms. Applying our model to 5 weeks of continuous data recorded during 2000 Tottori earthquakes in Japan, we were able to detect and locate two times more earthquakes using only a portion (less than 1/3) of seismic stations. Our model picks P and S phases with precision close to manual picks by human analysts; however, its high efficiency and higher sensitivity can result in detecting and characterizing more and smaller events.

Topics

No keywords indexed for this article. Browse by subject →

References

54

[1]

Deep learning

Yann LeCun, Yoshua Bengio, Geoffrey Hinton

Nature 2015 10.1038/nature14539

[2]

Wang, J., Xiao, Z., Liu, C., Zhao, D. & Yao, Z. Deep-learning for picking seismic arrival times. J. Geophys. Res. 124, 6612–6624 (2019). 10.1029/2019jb017536

[3]

Dokht, R. M., Kao, H., Visser, R. & Smith, B. Seismic event and phase detection using time-frequency representation and convolutional neural networks. Seismol. Res. Lett.90, 481–490 (2019). 10.1785/0220180308

[4]

Zhu, L. et al. Deep learning for seismic phase detection and picking in the aftershock zone of 2008 Mw7. 9 Wenchuan Earthquake. Phys. Earth Planet. Interiors.293, 106261 (2019). 10.1016/j.pepi.2019.05.004

[5]

Zhou, Y., Yue, H., Kong, Q. & Zhou, S. Hybrid event detection and phase-picking algorithm using convolutional and recurrent neural networks. Seismol. Res. Lett.90, 1079–1087 (2019). 10.1785/0220180319

[6]

Pardo, E., Garfias, C. & Malpica, N., Seismic phase picking using convolutional networks. IEEE Trans. Geosci. Remote Sensing57, 7086–7092 (2019). 10.1109/tgrs.2019.2911402

[7]

Mousavi, S. M., Zhu, W., Sheng, Y. & Beroza, G. C. CRED: a deep residual network of convolutional and recurrent units for earthquake signal detection. Sci. Rep.9, 10267 (2019). 10.1038/s41598-019-45748-1

[8]

Zhu, W. & Beroza, G. C. PhaseNet: a deep-neural-network-based seismic arrival-time picking method. Geophys. J. Int.216, 261–273 (2018).

[9]

Ross, Z. E., Meier, M.-A. & Hauksson, E. P wave arrival picking and first-motion polarity determination with deep learning. J. Geophys. Res.123, 5120–5129 (2018). 10.1029/2017jb015251

[10]

Generalized Seismic Phase Detection with Deep Learning

Zachary E. Ross, Men‐Andrin Meier, Egill Hauksson et al.

Bulletin of the Seismological Society of America 2018 10.1785/0120180080

[11]

Allen, R. V. Automatic earthquake recognition and timing from single traces. Bull. Seismol. Soc. Am.68, 1521–1532 (1978). 10.1785/bssa0680051521

[12]

Gibbons, S. J. & Ringdal, F. The detection of low magnitude seismic events using array-based waveform correlation. Geophys. J. Int.165, 149–166 (2006). 10.1111/j.1365-246x.2006.02865.x

[13]

Mousavi, S. M., Sheng, Y., Zhu, W. & Beroza, G. C. In STanford EArthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AI (IEEE, 2019). 10.1109/access.2019.2947848

[14]

Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res.9, 249–256 (2010).

[15]

Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https://arxiv.org/pdf/1412.6980.pdf (2014).

[16]

Abadi, M. et al. Tensorflow: a system for large-scale machine learning. In 12th Symposium on Operating Systems Design and Implementation (16), 265–283 (Savannah, 2016).

[17]

Saragiotis, C. D., Hadjileontiadis, L. J. & Panas, S. M. PAI-S/K: a robust automatic seismic P phase arrival identification scheme. IEEE Trans. Geosci. Remote Sens.40, 1395–1404 (2002). 10.1109/tgrs.2002.800438

[18]

Lomax, A., Satriano, C. & Vassallo, M. Automatic picker developments and optimization: FilterPicker—A robust, broadband picker for real-time seismic monitoring and earthquake early warning. Seismol. Res. Lett.83, 531–540 (2012). 10.1785/gssrl.83.3.531

[19]

Maeda, N. A method for reading and checking phase times in autoprocessing system of seismic wave data. Zisin38, 365–379 (1985). 10.4294/zisin1948.38.3_365

[20]

Klein, F. W. Userʼs Guide to HYPOINVERSE-2000, a Fortran Program to Solve for Earthquake Locations and Magnitudes 4/2002 version. USGS, Open File Report 02-171 Version, 1, 123. (2002). 10.3133/ofr02171

[21]

Waldhauser, F. & Ellsworth, W. L. A double-difference earthquake location algorithm: method and application to the northern Hayward fault, California. Bull. Seismol. Soc. Am.90, 1353–1368 (2000). 10.1785/0120000006

[22]

Fukuyama, E., Ellsworth, W. L., Waldhauser, F. & Kubo, A. Detailed fault structure of the 2000 western Tottori, Japan, earthquake sequence. Bull. Seismological Soc. Am.93, 1468–1478 (2003). 10.1785/0120020123

[23]

Bakun, W. H. & Joyner, W. B. The ML scale in central California. Bull. Seismological Soc. Am.74, 1827–1843 (1984). 10.1785/bssa0740051827

[24]

Minimum Magnitude of Completeness in Earthquake Catalogs: Examples from Alaska, the Western United States, and Japan

S. Wiemer

Bulletin of the Seismological Society of America 2000 10.1785/0119990114

[25]

Mousavi, S. M. Comment on “Recent developments of the Middle East catalog” by Zare et al. J. Seismol.21, 257–268 (2017). 10.1007/s10950-016-9625-1

[26]

Mousavi, S. M. Mapping seismic moment and b-value within the continental-collision orogenic-belt region of the Iranian Plateau. J. Geodynamics103, 26–41 (2017). 10.1016/j.jog.2016.12.001

[27]

Mousavi, S. M. & Beroza, G. C. Bayesian-Deep-Learning Estimation of Earthquake Location From Single-Station Observations. IEEE. Trans. Geosci. Remote. Sens. https://doi.org/10.1109/TGRS.2020.2988770 (2020). 10.1109/tgrs.2020.2988770

[28]

Chen, C. & Holland, A. A. PhasePApy: a robust pure Python package for automatic identification of seismic phases. Seismol. Res. Lett.87, 1384–1396 (2016). 10.1785/0220160019

[29]

Yeck, W. L. et al. Glass3: a standalone multiscale seismic detection associator. Bull. Seismol. Soc. Am.109, 1469–1478 (2019). 10.1785/0120180308

[30]

Convolutional neural network for earthquake detection and location

Thibaut Perol, Michaël Gharbi, Marine Denolle

Science Advances 2018 10.1126/sciadv.1700578

[31]

Wu, Y. et al. DeepDetect: a cascaded region-based densely connected network for seismic event detection. IEEE Trans. Geosci. Remote Sens.57, 62–75 (2018). 10.1109/tgrs.2018.2852302

[32]

Hu, D. An introductory survey on attention mechanisms in NLP problems. In Proceedings of SAI Intelligent Systems Conference, pp. 432–448 (Springer, Cham, 2019). 10.1007/978-3-030-29513-4_31

[33]

Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. Preprint at https://arxiv.org/abs/1409.0473 (2014).

[34]

Xu, K. et al. Show, attend and tell: neural image caption generation with visual attention. In International Conference on Machine Learning, 2048–2057 (2015).

[35]

Hermann, K. M. et al. Teaching machines to read and comprehend. In Advances in Neural Information Processing Systems, 1693–1701 (2015).

[36]

Zhang, Y., Chan, W. & Jaitly, N., Very deep convolutional networks for end-to-end speech recognition. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4845–4849 (2017). 10.1109/icassp.2017.7953077

[37]

Tan, T. et al. Adaptive very deep convolutional residual network for noise robust speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process.26, 1393–1405 (2018). 10.1109/taslp.2018.2825432

[38]

Dai, W., Dai, C., Qu, S., Li, J. & Das, S. Very deep convolutional neural networks for raw waveforms. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 421–425 (2017). 10.1109/icassp.2017.7952190

[39]

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.90

[40]

Long Short-Term Memory

Sepp Hochreiter, Jürgen Schmidhuber

Neural Computation 1997 10.1162/neco.1997.9.8.1735

[41]

Lin, M., Chen, Q. & Yan, S. Network in network. Preprint at https://arxiv.org/abs/1312.4400 (2013).

[42]

Sperber, M., Niehues, J., Neubig, G., Stüker, S. & Waibel, A. Self-attentional acoustic models. Preprint at https://arxiv.org/abs/1803.09519 (2018). 10.21437/interspeech.2018-1910

[43]

Listen, attend and spell: A neural network for large vocabulary conversational speech recognition

William Chan, Navdeep Jaitly, Quoc Le et al.

2016 IEEE International Conference on Acoustics, S... 10.1109/icassp.2016.7472621

[44]

Yang, Z., He, X., Gao, J., Deng, L. & Smola, A. Stacked attention networks for image question answering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 21–29 (IEEE, 2016). 10.1109/cvpr.2016.10

[45]

Effective Approaches to Attention-based Neural Machine Translation

Thang Luong, Hieu Pham, Christopher D. Manning

Proceedings of the 2015 Conference on Empirical Me... 10.18653/v1/d15-1166

[46]

Yang, Z., et al. Hierarchical attention networks for document classification. In Proceedings of the 2016 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1480–1489 (2016). 10.18653/v1/n16-1174

[47]

Vaswani, A., et al. Attention is all you need. In Advances in Neural Information Processing Systems, 5998–6008 (2017).

[48]

Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. Preprint at https://arxiv.org/abs/1810.04805 (2018).

[49]

Ji, J. et al. A nested attention neural hybrid model for grammatical error correction. Preprint at https://arxiv.org/abs/1707.02026 (2017). 10.18653/v1/p17-1070

[50]

Yu, L., Bansal, M. & Berg, T. L. Hierarchically-attentive RNN for album summarization and storytelling. Preprint at https://arxiv.org/abs/1708.02977 (2017). 10.18653/v1/d17-1101

Showing 50 of 54 references

Cited By

846

EQAnomalyNet: Unsupervised Seismic Phase Picking via Transformer Autoencoder

Hanling Wang, Qiang Ma · 2026

IEEE Transactions on Geoscience and...

Crustal differential thickening and incomplete mechanical decoupling in the eastern Qilian Shan, NE Tibetan Plateau: Insights from a dense seismic profile

Ruizhi Jin, Xuzhang Shen · 2026

Earth and Planetary Science Letters

An AIoT System for Earthquake Early Warning on Resource Constrained Devices

Marco Esposito, Alberto Belli · 2025

IEEE Internet of Things Journal

High-resolution monitoring of hydraulically induced acoustic emission activities using neural phase picking and matched filter analysis

Makoto Naoi, Shiro Hirano · 2025

Progress in Earth and Planetary Sci...

Characterisation of precursory seismic activity towards early warning of landslides via semi-supervised learning

David Murray, Lina Stankovic · 2025

Scientific Reports

Sensing Optical Fibers for Earthquake Source Characterization Using Raw DAS Records

Claudio Strumia, Alister Trabattoni · 2024

Journal of Geophysical Research: So...

Multiple noise reduction for distributed acoustic sensing data processing through densely connected residual convolutional networks

Tianye Huang, Aopeng Li · 2024

Journal of Applied Geophysics

Seismic reflection imaging of deep crustal structures using local earthquakes in the Kanto region, Japan

Kazuya Shiraishi, Toshiki Watanabe · 2023

Earth, Planets and Space

Scientific discovery in the age of artificial intelligence

Hanchen Wang, Tianfan Fu · 2023

Nature

Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning

Weiqiang Zhu, Ettore Biondi · 2023

Nature Communications

Elastic Seismic Imaging Enhancement of Sparse 4C Ocean-Bottom Node Data Using Deep Learning

Shijun Cheng, Xingchen Shi · 2023

IEEE Transactions on Geoscience and...

Imaging the Western Edge of the Aegean Shear Zone: The South Evia 2022-2023 Seismic Sequence

Christos Evangelidis, Ioannis Fountoulakis · 2023

Seismica

Revealing the Potential of Deep Learning for Detecting Submarine Pipelines in Side-Scan Sonar Images: An Investigation of Pre-Training Datasets

Xing Du, Yongfu Sun · 2023

Remote Sensing

Sensing prior constraints in deep neural networks for solving exploration geophysical problems

Xinming Wu, Jianwei Ma · 2023

Proceedings of the National Academy...

Machine learning in microseismic monitoring

Denis Anikiev, Claire Birnie · 2023

Earth-Science Reviews

Deep-learning seismology

S. Mostafa Mousavi, Gregory C. Beroza · 2022

Science

A review of Earth Artificial Intelligence

Ziheng Sun, Laura Sandoval · 2022

Computers & Geosciences

SeisBench—A Toolbox for Machine Learning in Seismology

Jack Woollam, Jannes Münchmeyer · 2022

Seismological Research Letters

Early Earthquake Detection Using Batch Normalization Graph Convolutional Neural Network (BNGCNN)

Muhammad Atif Bilal, Yanju Ji · 2022

Applied Sciences

INSTANCE – the Italian seismic dataset for machine learning

Alberto Michelini, Spina Cianetti · 2021

Earth System Science Data

Metrics

846

Citations

54

References

Details

Published: Aug 07, 2020
Vol/Issue: 11(1)
License: View

Authors

S

S. Mostafa Mousavi

Department of Geophysics Stanford University Stanford CA USA

W

William L. Ellsworth

1Department of Geophysics, Stanford University, Stanford, California, U.S.A.

W

Weiqiang Zhu

Department of Geophysics Stanford University Stanford CA USA

Department of Geophysics, Stanford University, Stanford, CA 94305, USA.

Cite This Article

S. Mostafa Mousavi, William L. Ellsworth, Weiqiang Zhu, et al. (2020). Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nature Communications, 11(1). https://doi.org/10.1038/s41467-020-17591-w

Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking

You May Also Like