Automatic detection of low-magnitude earthquakes has become an increasingly important research topic in recent years due to a sharp increase in induced seismicity around the globe. The detection of low-magnitude seismic events is essential for microseismic monitoring of hydraulic fracturing, carbon capture and storage, and geothermal operations for hazard detection and mitigation. Moreover, the detection of micro-earthquakes is crucial to understanding the underlying mechanisms of larger earthquakes. Various algorithms, including deep learning methods, have been proposed over the years to detect such low-magnitude events. However, there is still a need for improving the robustness of these methods in discriminating between local sources of noise and weak seismic events. In this study, we propose a convolutional neural network (CNN) to detect seismic events from shallow borehole stations in Groningen, the Netherlands. We train a CNN model to detect low-magnitude earthquakes, harnessing the multi-level sensor configuration of the G-network in Groningen. Each G-network station consists of four geophones at depths of 50, 100, 150, and 200 m. Unlike prior deep learning approaches that use 3-component seismic records only at a single sensor level, we use records from the entire borehole as one training example. This allows us to train the CNN model using moveout patterns of the energy traveling across the borehole sensors to discriminate between events originating in the subsurface and local noise arriving from the surface. We compare the prediction accuracy of our trained CNN model to that of the STA/LTA and template matching algorithms on a two-month continuous record. We demonstrate that the CNN model shows significantly better performance than STA/LTA and template matching in detecting new events missing from the catalog and minimizing false detections. Moreover, we find that using the moveout feature allows us to effectively train our CNN model using only a fraction of the data that would be needed otherwise, saving plenty of manual labor in preparing training labels. The proposed approach can be easily applied to other microseismic monitoring networks with multi-level sensors.

Department of Geosciences King Fahd University of Petroleum and Minerals Dhahran 31261 Saudi Arabia

Earth Resources Laboratory Department of Earth Atmospheric and Planetary Sciences Massachusetts Institute of Technology Cambridge MA 02139 USA

Seismik s r o 12800 Prague Czech Republic

Zobrazit více v PubMed

Brodsky E.E. The importance of studying small earthquakes. Science. 2019;364:736–737. doi: 10.1126/science.aax2490. PubMed DOI

Allen R.V. Automatic earthquake recognition and timing from single traces. Bull. Seismol. Soc. Am. 1978;68:1521–1532. doi: 10.1785/BSSA0680051521. DOI

Shelly D.R., Beroza G.C., Ide S. Non-volcanic tremor and low-frequency earthquake swarms. Nature. 2007;446:305–307. doi: 10.1038/nature05666. PubMed DOI

Yoon C.E., O’Reilly O., Bergen K.J., Beroza G.C. Earthquake detection through computationally efficient similarity search. Sci. Adv. 2015;1:e1501057. doi: 10.1126/sciadv.1501057. PubMed DOI PMC

Poliannikov O.V., Fehler M.C. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists; Tulsa, OK, USA: 2018. Instantaneous phase-based statistical method for detecting seismic events with application to Groningen gas field data; pp. 2907–2911.

Mukuhira Y., Poliannikov O.V., Fehler M.C., Moriya H. Low-SNR Microseismic Detection Using Direct P-Wave Arrival Polarization. Bull. Seismol. Soc. Am. 2020;110:3115–3129. doi: 10.1785/0120190192. DOI

Akram J., Ovcharenko O., Peter D. SEG Technical Program Expanded Abstracts 2017. Society of Exploration Geophysicists; Tulsa, OK, USA: 2017. A robust neural network-based approach for microseismic event detection; pp. 2929–2933.

Qu S., Verschuur E., Chen Y. Seg Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists; Tulsa, OK, USA: 2018. Automatic microseismic-event detection via supervised machine learning; pp. 2287–2291.

LeCun Y., Bengio Y., Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539. PubMed DOI

Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., Rabinovich A. Going deeper with convolutions; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Boston, MA, USA. 7–12 June 2015; pp. 1–9.

Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv. 20141409.1556

Kong Q., Trugman D.T., Ross Z.E., Bianco M.J., Meade B.J., Gerstoft P. Machine learning in seismology: Turning data into insights. Seismol. Res. Lett. 2019;90:3–14. doi: 10.1785/0220180259. DOI

Perol T., Gharbi M., Denolle M. Convolutional neural network for earthquake detection and location. Sci. Adv. 2018;4:e1700578. doi: 10.1126/sciadv.1700578. PubMed DOI PMC

Keranen K.M., Savage H.M., Abers G.A., Cochran E.S. Potentially induced earthquakes in Oklahoma, USA: Links between wastewater injection and the 2011 Mw 5.7 earthquake sequence. Geology. 2013;41:699–702. doi: 10.1130/G34045.1. DOI

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. 2019;9:1–14. PubMed PMC

Mousavi S.M., Ellsworth W.L., Zhu W., Chuang L.Y., Beroza G.C. Earthquake transformer—An attentive deep-learning model for simultaneous earthquake detection and phase picking. Nat. Commun. 2020;11:1–12. doi: 10.1038/s41467-020-17591-w. PubMed DOI PMC

Othman A., Iqbal N., Hanafy S.M., Waheed U.B. Automated Event Detection and Denoising Method for Passive Seismic Data Using Residual Deep Convolutional Neural Networks. IEEE Trans. Geosci. Remote Sens. 2021 doi: 10.1109/TGRS.2021.3054071. DOI

van Thienen-Visser K., Breunese J. Induced seismicity of the Groningen gas field: History and recent developments. Lead. Edge. 2015;34:664–671. doi: 10.1190/tle34060664.1. DOI

Netherlands to halt Groningen gas production by 2022. [(accessed on 27 October 2021)]. Available online: https://www.reuters.com/article/us-netherlands-gas-idUSKCN1VV1KE.

Dost B., Ruigrok E., Spetzler J. Development of seismicity and probabilistic hazard assessment for the Groningen gas field. Neth. J. Geosci. 2017;96:s235–s245. doi: 10.1017/njg.2017.20. DOI

KNMI . Netherlands Seismic and Acoustic Network. Royal Netherlands Meteorological Institute (KNMI) KNMI; De Bilt, The Netherlands: 1993. Other/Seismic Network.

Wyer P., Fehler M., Poliannikov O., Mukuhira Y., de Martin B., Nakata N. AGU Fall Meeting Abstracts. Volume 2019 American Geophysical Union; San Francisco, CA, USA: 2019. Comparative Study of Low-magnitude Earthquake Detection Techniques for Use with Dense Seismic Monitoring.

Hubel D.H., Wiesel T.N. Receptive fields of single neurones in the cat’s striate cortex. J. Physiol. 1959;148:574–591. doi: 10.1113/jphysiol.1959.sp006308. PubMed DOI PMC

Hubel D.H., Wiesel T.N. Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 1968;195:215–243. doi: 10.1113/jphysiol.1968.sp008455. PubMed DOI PMC

Rumelhart D.E., Hinton G.E., Williams R.J. Learning Internal Representations by Error Propagation. California University of San Diego La Jolla, Institute for Cognitive Science; La Jolla, CA, USA: 1985. Technical report.

Abadi M., Agarwal A., Barham P., Brevdo E., Chen Z., Citro C., Corrado G.S., Davis A., Dean J., Devin M., et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. [(accessed on 27 October 2021)]. Available online: https://www.tensorflow.org/

Ross Z.E., Meier M.A., Hauksson E. P wave arrival picking and first-motion polarity determination with deep learning. J. Geophys. Res. Solid Earth. 2018;123:5120–5129. doi: 10.1029/2017JB015251. DOI