1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 69, Issue 8
  5. Article
Volume 69, Issue 8-9
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

As an efficient geophysical exploration technique, airborne transient electromagnetics shows strong adaptability to complex terrains and can provide subsurface resistivity information rapidly with a dense spatial coverage. However, the huge volume of airborne transient electromagnetic data obtained from a large number of spatial locations presents a great challenge to real‐time airborne transient electromagnetic interpretation due to the high computational cost. Moreover, the inherent non‐uniqueness of the inverse problem also limits our ability to constrain the underground resistivity structure. In this study, we develop an entirely data‐driven convolutional neural network to solve the airborne transient electromagnetic inverse problem. Synthetic tests show that the convolutional neural network is computationally efficient and yields robust results. Compared with the Gauss–Newton method, convolutional neural network inversion does not depend on the choices of an initial model and the regularization parameters and is less prone to getting trapped in a local minimum. We also demonstrate the general applicability of the convolutional neural network to three‐dimensional synthetic airborne transient electromagnetic responses and the field observations acquired from Leach Lake Basin, Fort Irwin, California. The efficient convolutional neural network inversion framework can support real‐time resistivity imaging of subsurface structures from airborne transient electromagnetic observations, providing a powerful tool for field explorations.

© 2021 European Association of Geoscientists & Engineers © 2021 European Association of Geoscientists & Engineers
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13136
2021-10-08
2024-04-24

  • From This Site

    /content/journals/10.1111/1365-2478.13136
    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., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y. and Zheng, X. (2016) Tensorflow: a system for large‐scale machine learning. 12th USENIX Symposium on Operating Systems Design and Implementation, Georgia, USA, 265‐283. Accessed August 15, 2021. https://arxiv.org/abs/1605.08695v2
  2. Auken, E. and Christiansen, A. (2004) Layered and laterally constrained 2D inversion of resistivity data. Geophysics, 69(3), 752–761. https://doi.org/10.1190/1.1759461.
     [Google Scholar]
  3. Auken, E., Christiansen, A., Jacobsen, B., Foged, N. and Sørensen, K. (2005) Piecewise 1D laterally constrained inversion of resistivity data. Geophysical Prospecting, 53, 497–506. https://doi.org/10.1111/j.1365‐2478.2005.00486.x.
     [Google Scholar]
  4. Bai, P., Vignoli, G., Viezzoli, A., Nevalainen, J. and VaccaG. (2020) (Quasi‐) Real‐time inversion of airborne time‐domain electromagnetic data via artificial neural network. Remote Sensing, 12(20), 3440. https://doi.org/10.3390/rs12203440.
     [Google Scholar]
  5. Beamish, D. and White, J. (2012) Mapping and predicting electrical conductivity variations across southern England using airborne electromagnetic data. Quarterly Journal of Engineering Geology and Hydrogeology, 45(1), 99–110. https://doi.org/10.1144/1470‐9236/11‐026.
     [Google Scholar]
  6. Bedrosian, P., Ball, L. and Bloss, B. (2014) Airborne electromagnetic data and processing within Leach Lake Basin, Fort Irwin, California. In: Buesch, D. (Ed.) Geology and Geophysics Applied to Groundwater Hydrology at Fort Irwin, California. U.S. Geological Survey Open File Report 2013‐1024. Menlo Park, CA: U.S. Geological Survey; Chap. G, 20 p. http://doi.org/10.3133/ofr20131024G.
  7. Blatter, D., Key, K., Ray, A., Foley, M.Tulaczyk, S. and Auken, E. (2018) Trans‐dimensional Bayesian inversion of airborne transient EM data from Taylor Glacier, Antarctica. Geophysical Journal International, 214, 1919–1936. https://doi.org/10.1093/gji/ggy255.
     [Google Scholar]
  8. Cox, L., Wilson, G. and Zhdanov, M. (2012) 3D inversion of airborne electromagnetic data. Geophysics, 77(4), WB59‐WB69. https://doi.org/10.1190/geo2011‐0370.1.
     [Google Scholar]
  9. Dickinson, J., Pool, D., Groom, R. and Davis, L. (2010) Inference of lithologic distributions in an alluvial aquifer using airborne transient electromagnetic surveys. Geophysics, 75(4), WA149‐WA161. https://doi.org/10.1190/1.3464325.
     [Google Scholar]
  10. Feng, B., Zhang, J., Li, D. and Bai, Y. (2020) Resistivity‐depth imaging with the airborne transient electromagnetic method based on an artificial neural network. Journal of Environmental and Engineering Geophysics, 25(3), 355–368. https://doi.org/10.32389/JEEG19‐087.
     [Google Scholar]
  11. Gao, Z., Yin, C., Qi, Y., Zhang, B., Ren, X. and Lu, Y. (2018) Transdimensional Bayesian inversion of time domain airborne EM data. Applied Geophysics, 15(2), 318–331. https://doi.org/10.1007/s11770‐018‐0684‐7.
     [Google Scholar]
  12. Guo, R., Li, M, Yang, F., Xu, S. and Abubakar, A. (2020) Application of supervised descent method for 2D magnetotelluric data inversion. Geophysics, 85(4), WA53‐WA65. https://doi.org/10.1190/geo2019‐0409.1.
     [Google Scholar]
  13. Hauser, J., Gunning, J. and Annetts, D. (2015) Probabilistic inversion of airborne electromagnetic data under spatial constraints. Geophysics, 80(2), E135‐E146. https://doi.org/10.1190/GEO2014‐0389.1.
     [Google Scholar]
  14. Huang, H. and Rudd, J. (2008) Conductivity‐depth imaging of helicopter‐borne TEM data based on a pseudolayer half‐space model. Geophysics, 73(3), F115‐F120. https://doi.org/10.1190/1.2904984.
     [Google Scholar]
  15. Ioffe, S. and Szegedy, C. (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. 32nd International Conference on Machine Learning, Lille, France, 37, 448‐456. Accessed August 15, 2021. https://arxiv.org/abs/1502.03167v3.
  16. Kingma, D. and Ba, J. (2015) Adam: a method for stochastic optimization. 3rd International Conference for Learning Representations, San Diego, USA. Accessed August 15, 2021. https://arxiv.org/abs/1412.6980v8.
  17. LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998) Gradient‐based learning applied to document recognition. Proceedings of the IEEE, 186(11), 2278–2324. https://doi.org/10.1109/5.726791.
     [Google Scholar]
  18. Li, J., Liu, Y., Yin, C., Ren, X. and Su, Y. (2020) Fast imaging of time‐domain airborne EM data using deep learning technology. Geophysics, 85(5), E163‐170. https://doi.org/10.1190/GEO2019‐0015.1.
     [Google Scholar]
  19. Li, S., Yang, C., Sun, H. and ZhangH. (2019) Seismic fault detection using an encoder–decoder convolutional neural network with a small training set. Journal of Geophysics and Engineering, 16(1), 175–189. https://doi.org/10.1093/jge/gxy015.
     [Google Scholar]
  20. Li, Z. (2014). A study of 2.5D and 3D forward modeling and inversion of transient electromagnetic method with a loop source. Ph.D. thesis (in Chinese). Peking University, Beijing, China.
  21. Li, Z., Huang, Q., Xie, X., Tang, X. and Chang, L. (2016) A generic 1D forward modeling and inversion algorithm for TEM sounding with an arbitrary horizontal loop. Pure and Applied Geophysics, 173, 2869–2883. https://doi.org/10.1007/s00024‐015‐1336‐6.
     [Google Scholar]
  22. Li, Z. and Huang, Q. (2018) 1D forward modeling and inversion algorithm for grounded galvanic source TEM sounding with horizontal wire. Progress in Geophysics, 33(4), 1515–1525 (in Chinese). https://doi.org/10.6038/pg2018BB0226.
     [Google Scholar]
  23. Liu, G. and Asten, M. (1993) Conductance depth imaging of airborne TEM data. Exploration Geophysics, 24(4), 655–662. https://doi.org/10.1071/EG993655.
     [Google Scholar]
  24. Liu, Y. and Yin, C. (2016) 3D inversion for multipulse airborne transient electromagnetic data. Geophysics, 81(6), E401‐E408. https://doi.org/10.1190/GEO2015‐0481.1.
     [Google Scholar]
  25. Mao, L., Wang, X. and Li, W. (2011) Research on 1D inversion method of fix‐wing airborne transient electromagnetic record with flight altitude inversion simultaneously. Chinese Journal of Geophysics, 54(8), 2136–2147 (in Chinese). https://doi.org/10.3969/j.issn.0001‐5733.2011.08.02.
     [Google Scholar]
  26. McCulloch, W. and Pitts, W. (1943) A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5(4), 115–133. https://doi.org/10.1007/BF02478259.
     [Google Scholar]
  27. Moghadas, D. (2020) One‐dimensional deep learning inversion of electromagnetic induction data using convolutional neural network. Geophysical Journal International, 222(1), 247–259. https://doi.org/10.1093/gji/ggaa161.
     [Google Scholar]
  28. Nair, V. and Hinton, G. (2010) Rectified linear units improve restricted Boltzmann machines. 27th International Conference on Machine Learning, Haifa, Isarael, 807–814. Accessed August 15, 2021. https://icml.cc/Conferences/2010/papers/432.pdf.
  29. Noh, K., Yoon, D. and Byun, J. (2020) Imaging subsurface resistivity structure from airborne electromagnetic induction data using deep neural network. Exploration Geophysics, 51(2), 214–220. https://doi.org/10.1080/08123985.2019.1668240.
     [Google Scholar]
  30. Pan, S. and Yang, Q. (2009) A survey on transfer learning. IEEE Transaction on Knowledge and Data Engineering, 22(10), 1345–1359. https://doi.org/10.1109/TKDE.2009.191.
     [Google Scholar]
  31. Pfaffhuber, A., Monstad, S. and Rudd, J. (2009) Airborne electromagnetic hydrocarbon mapping in Mozambique. Exploration Geophysics, 40, 237–245. https://doi.org/10.1071/EG09011.
     [Google Scholar]
  32. Puzyrev, V. (2019) Deep learning electromagnetic inversion with convolutional neural networks. Geophysical Journal International, 218(2), 817–832. https://doi.org/10.1093/gji/ggz204.
     [Google Scholar]
  33. Puzyrev, V. and Swidinsky, A. (2021) Inversion of 1D frequency‐ and time‐ domain electromagnetic data with convolutional neural networks. Computers and Geosciences, 149, 104681. https://doi.org/10.1016/j.cageo.2020.104681.
     [Google Scholar]
  34. Qiang, J., Man, K., Long, J., Lu, K., Zhu, Y., Chen, L., Li, J. and Mao, X. (2016) 2.5D inversion of time domain airborne electromagnetic data using nonlinear conjugate gradients. Chinese Journal of Geophysics, (in Chinese), 59(12), 4701–4709. https://doi.org/10.6038/cjg20161229.
     [Google Scholar]
  35. Rao, L., Wu, X., Wu, C., Zhang, X. and Fang, G. (2016) A rapid 3D inversion based on TEM moment transformation. Chinese Journal of Geophysics, 59(11), 4339–4348 (in Chinese). https://doi.org/10.6038/cjg20161133.
     [Google Scholar]
  36. Ren, X., Yin, C., Macnae, J., Liu, Y. and Zhang, B. (2018) 3D time‐domain airborne electromagnetic inversion based on secondary field finite‐volume method. Geophysics, 83(4), E219‐E228. https://doi.org/10.1190/GEO2017‐0585.1.
     [Google Scholar]
  37. Richardson, A. (2018) Seismic full‐waveform inversion using deep learning tools and techniques. arXiv e‐prints, Accessed August 15, 2021. https://arxiv.org/abs/1801.07232v2.
  38. Rosenblatt, F. (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65, 386–408. https://doi.org/10.1037/h0042519.
     [Google Scholar]
  39. Rumelhart, D., Hinton, G. and Williams, R. (1986) Learning representations by back‐propagating errors. Nature, 323(6088), 533–536. https://doi.org/10.1038/323533a0.
     [Google Scholar]
  40. Sun, J., Niu, Z., Innanen, K. and Li, J. (2019) A theory‐guided deep learning formulation and optimization of seismic waveform inversion. Geophysics, 85(2), 1–63. https://doi.org/10.1190/geo2019‐0138.1.
     [Google Scholar]
  41. Viezzoli, A., Auken, E. and Munday, T. (2009) Spatially constrained inversion for quasi 3D modelling of airborne electromagnetic data – an application for environmental assessment in the Lower Murray Region of South Australia. Exploration Geophysics, 40, 173–183. https://doi.org/10.1071/EG08027.
     [Google Scholar]
  42. Wang, K., Huang, Q. and Wu, S. (2020) Application of long short‐term memory neural network in geoelectric field data processing. Chinese Journal of Geophysics, 63(8), 3015–3024 (in Chinese). https://doi.org/10.6038/cjg2020O0119.
     [Google Scholar]
  43. Wessel, P., Luis, J., Uieda, L., Scharroo, R., Wobbe, F., Smith, W. and Tian, D. (2019) The Generic Mapping Tools version 6. Geochemistry, Geophysics, Geosystems, 20, 5556–5564. https://doi.org/10.1029/2019GC008515.
     [Google Scholar]
  44. Wu, S., Huang, Q. and Zhao, L. (2021) De‐noising of transient electromagnetic data based on the long short‐term memory‐autoencoder. Geophysical Journal International, 224, 669–681. https://doi.org/10.1093/gji/ggaa424.
     [Google Scholar]
  45. Xiong, W., Ji, W., Ma, Y., Wang, Y., BenHassan, N., Ali, M. and Luo, Y. (2018) Seismic fault detection with convolutional neural network. Geophysics, 83(5), 1–28. https://doi.org/10.1190/geo2017‐0666.1.
     [Google Scholar]
  46. Yang, D. and Oldenburg, D. (2012) Three‐dimensional inversion of airborne time‐domain electromagnetic data with applications to a porphyry deposit. Geophysics, 77, B23‐B34. https://doi.org/10.1190/geo2011‐0194.1.
     [Google Scholar]
  47. Yang, D. and Oldenburg, D. (2013) 3D conductivity models of Lalor Lake VMS deposit from ground loop and airborne EM data sets. 23rd International Geophysical Conference and Exhibition, Melbourne, Australia, 1–4. Accessed August 15, 2021. https://doi.org/10.1071/ASEG2013ab296.
  48. Yu, X., Wang, X., Lu, C. and Liu, C. (2018) A combining regularization strategy for the inversion of airborne time‐domain electromagnetic data. Journal of Applied Geophysics, 150, 110–121. https://doi.org/10.1016/j.jappgeo.2018.06.007.
     [Google Scholar]
  49. Zhou, Y., Yue, H., Kong, Q. and Zhou, S. (2019) Hybrid event detection and phase‐picking algorithm using convolutional and recurrent neural networks. Seismological Research Letter, 90(3), 1079–1087. https://doi.org/10.1785/0220180319.
     [Google Scholar]
  50. Zhu, K., Ma, M., Che, H., Yang, E., Ji, Y., Yu, S. and Lin, J. (2012) PC‐based artificial neural network inversion for airborne time‐domain electromagnetic data. Applied Geophysics, 9(1), 1–8. https://doi.org/10.1007/s11770‐012‐0307‐7.
     [Google Scholar]
  51. Zhu, W. and Beroza, G. (2018) 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.
     [Google Scholar]
http://instance.metastore.ingenta.com/content/journals/10.1111/1365-2478.13136
Loading
Convolutional neural network inversion of airborne transient electromagnetic data
Geophysical Prospecting 69, 1761 (2021); https://doi.org/10.1111/1365-2478.13136
/content/journals/10.1111/1365-2478.13136
/content/journals/10.1111/1365-2478.13136
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Electromagnetics; Imaging; Inverse problem; Numerical study; Resistivity

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