1887
Volume 54, Issue 2
  • ISSN: 0812-3985
  • E-ISSN: 1834-7533

Abstract

Microseismic monitoring is widely used to analyze the locations and growth directions of fractures formed at sites of hydraulic fracturing treatment and CO geologic sequestration. Because moment tensors can provide focal mechanisms, moment tensor inversion has received considerable attention in microseismic monitoring; the real-time processing of moment tensor inversion is important for rapid decision-making. Pre-trained machine learning (ML) models can make nearly instantaneous predictions in the application stage and thus present an attractive alternative to real-time processing. However, prior information regarding the velocity model at the target site is a prerequisite for generating the dataset used to train the ML model that is applied in moment tensor inversion. In addition, it is difficult to create the training dataset because it requires three-dimensional numerical modelling when the velocity model is complex; numerous simulations must be executed for sources with various locations and moment tensors. To overcome these limitations, we applied the domain adaptation technique to the convolutional neural network (CNN)-based moment tensor inversion method, which uses peak amplitudes and arrival times of P- and S-waves as input features. The CNN model was pre-trained with the dataset generated from a homogeneous velocity model. Then, in the domain adaptation stage, the pre-trained model was fine-tuned along with the target dataset. To validate the performance of the domain adaptation, moment tensors from both horizontal and tilted three-layer models were predicted. In each case, the domain-adapted model performance was similar to the performances of the CNN-based models that had been trained using the dataset generated with the exact target velocity models.

© 2022 Australian Society of Exploration Geophysicists
Loading

Article metrics loading...

/content/journals/10.1080/08123985.2022.2086798
2023-03-04
2026-01-14

  • From This Site

    /content/journals/10.1080/08123985.2022.2086798
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Abadi, M., P.Barham, J.Chen, Z.Chen, A.Davis, J.Dean, M.Devin, S.Ghemawat, G.Irving, M.Isard, et al.2016. Tensorflow: A system for large-scale machine learning. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI'16), 265–83.
     [Google Scholar]
  2. Baig, A., and T.Urbancic. 2010. Microseismic moment tensors: A path to understanding frac growth. The Leading Edge29: 320–24.
     [Google Scholar]
  3. Binder, G.2018. Neural networks for moment-tensor inversion of surface microseismic data. SEG Technical Program Expanded Abstracts, 2917–21.
     [Google Scholar]
  4. Bousmalis, K., G.Trigeorgis, N.Silberman, D.Krishnan, and D.Erhan. 2016. Domain separation networks. Advances in Neural Information Processing Systems29: 343–51.
     [Google Scholar]
  5. Chen, Y.2020. Automatic microseismic event picking via unsupervised machine learning. Geophysical Journal International222: 1750–64.
     [Google Scholar]
  6. Chen, Y., and L.Huang. 2019. Adaptive moment-tensor joint inversion of clustered microseismic events for monitoring geological carbon storage. Geophysical Journal International219: 80–93.
     [Google Scholar]
  7. Choi, J., J.Byun, and S.J.Seol. 2020. Sensitivity analysis for successful microseismic moment tensor inversion using machine learning. SEG Technical Program Expanded Abstracts, 1359–63.
     [Google Scholar]
  8. Eaton, D.W., M.van der Baan, B.Birkelo, and J.B.Tary. 2014. Scaling relations and spectral characteristics of tensile microseisms: Evidence for opening/closing cracks during hydraulic fracturing. Geophysical Journal International196: 1844–57.
     [Google Scholar]
  9. Ganin, Y., and V.Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. International Conference on Machine Learning (ICML), 1180–89.
     [Google Scholar]
  10. Guo, C., T.Zhu, Y.Gao, S.Wu, and J.Sun. 2020. Aenet: Automatic picking of P-wave first arrivals using deep learning. IEEE Transactions on Geoscience and Remote Sensing59: 5293–303.
     [Google Scholar]
  11. Hardebeck, J.L., and P.M.Shearer. 2003. Using S/P amplitude ratios to constrain the focal mechanisms of small earthquakes. Bulletin of the Seimological Society of America93: 2432–44.
     [Google Scholar]
  12. Jian, P., T.Tseng, W.Liang, and P.Huang. 2018. A new automatic full-waveform regional moment tensor inversion algorithm and Its applications in the Taiwan area. Bulletin of the Seismological Society of America108: 573–87.
     [Google Scholar]
  13. Kim, M.2016. Estimation of the focal mechanisms using moment tensor inversion in viscoelastic anisotropic media. PhD diss., Hanyang Univ.
     [Google Scholar]
  14. Kuang, W., M.Zoback, and J.Zhang. 2017. Estimating geomechanical parameters from microseismic plane focal mechanisms recorded during multistage hydraulic fracturing. Geophysics82: KS1–11.
     [Google Scholar]
  15. Long, M., Y.Cao, J.Wang, and M.Jordan. 2015. Learning transferable features with deep adaptation networks. International Conference on Machine Learning (ICML), 97–105.
     [Google Scholar]
  16. López-Comino, J.A., S.Casa, M.Kriegerowski, S.Heimann, T.Dahm, J.Mirek, and S.Lasocki. 2017. Monitoring performance using synthetic data for induced microseismicity by hydrofracking at the Wysin site (Poland). Geophysical Journal International210: 42–55.
     [Google Scholar]
  17. Miller, A.D., B.R.Julian, and G.R.Foulger. 1998. Three-dimensional seismic structure and moment tensors of non-double-couple earthquakes at the Hengill-Grensdalur volcanic complex, Iceland. Geophysical Journal International133: 309–25.
     [Google Scholar]
  18. Ovcharenko, O., J.Akram, and D.Peter. 2018. Feasibility of moment tensor inversion from a single borehole data using artificial neural networks. Search and Discovery.
     [Google Scholar]
  19. Qu, S., Z.Guan, E.Verschuur, and Y.Chen. 2019. Automatic high-resolution microseismic event detection via supervised machine learning. Geophysical Journal International222: 1881–95.
     [Google Scholar]
  20. Šílený, J., and A.Milev. 2008. Source mechanism of mining induced seismic events — resolution of double couple and non double couple models. Tectonophysics456: 3–15.
     [Google Scholar]
  21. Vavryčuk, V., and D.Kühn. 2012. Moment tensor inversion of waveforms: A two-step time-frequency approach. Geophysical Journal International190: 1761–76.
     [Google Scholar]
  22. Verdon, J.P., A.L.Stork, R.C.Bissell, C.E.Bond, and M.J.Werner. 2015. Simulation of seismic events induced by CO2 injection at In Salah, Algeria. Earth and Planetary Science Letters426: 118–29.
     [Google Scholar]
  23. Wamriew, D., M.Charara, and E.Maltsev. 2020. Deep neural network for real-time location and moment tensor inversion of borehole microseismic events induced by hydraulic fracturing. Spe Russian petroleum technology conference.
     [Google Scholar]
  24. Wang, R.1999. A simple orthonormalization method for stable and efficient computation of Green’s functions. Bulletin of the Seismological Society of America89: 733–41.
     [Google Scholar]
  25. Wang, M., and W.Deng. 2018. Deep visual domain adaptation: A survey. Neurocomputing312: 135–53.
     [Google Scholar]
  26. Wu, Y., J.Wei, J.Pan, and P.Chen. 2019. Research on microseismic source locations based on deep reinforcement learning. IEEE Access7: 39962–73.
     [Google Scholar]
  27. Yu, J., J.Byun, and S.J.Seol. 2021. Imaging discrete fracture networks using the location and moment tensors of microseismic events. Exploration Geophysics52: 42–53.
     [Google Scholar]
  28. Yu, X., J.Rutledge, S.Leaney, and S.Maxwell. 2016. Discrete-Fracture-Network generation from microseismic data by use of moment-tensor- and event-location-constrained hough transforms. SPE Journal21: 221–32.
     [Google Scholar]
  29. Zhang, C., and van der Baan, M.2019, Microseismic denoising and reconstruction by unsupervised machine learning. IEEE Geoscience and Remote Sensing Letters17: 1114–18.
     [Google Scholar]
  30. Zhao, Z., L.Gross, Y.Zhou, L.Li, H.Li, and R.Yang. 2019. Automatic microseismic event detection using deep learning: A classification is detection method. 81st eage conference and exhibition.
     [Google Scholar]
  31. Zhu, L., L.Chuang, J.H.McClellan, E.Liu, and Z.Peng. 2021. A multi-channel approach for automatic microseismic event association using ransac-based arrival time event clustering (RATEC). Earthquake Research Advances1: 100008.
     [Google Scholar]
/content/journals/10.1080/08123985.2022.2086798
Loading
Convolutional neural network-based moment tensor inversion using domain adaptation for microseismicity monitoring
Exploration Geophysics 54, 133 (2023); https://doi.org/10.1080/08123985.2022.2086798
/content/journals/10.1080/08123985.2022.2086798
/content/journals/10.1080/08123985.2022.2086798
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): domain adaptation; focal mechanism; microseismic monitoring; microseismicity; Neural network

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error