1887
Volume 22, Issue 3
  • ISSN: 1569-4445
  • E-ISSN: 1873-0604

Abstract

Abstract

Data‐driven deep learning technology has a strong non‐linear mapping ability and has good development potential in geophysical inversion problems. Traditional inversion techniques offer broad generality, but they can remain trapped in local minima, particularly for three‐dimensional tunnelling resistivity inversion. In this work, we present an inversion methodology that combines traditional physics‐driven and deep learning data‐driven inversion approaches. To further support deep neural networks' dependability on unseen data, the interpretability of their working mechanism is explored. We execute migration learning based on small sample data after identifying the critical parameters that restrict the effectiveness of inversion by analysing the feature maps of various model data. We demonstrate, using both synthetic examples and field data, that the proposed method can improve the accuracy in detecting water‐bearing anomalies (caves and faults), which are typically encountered during tunnel excavation.

Loading

Article metrics loading...

/content/journals/10.1002/nsg.12294
2024-05-21
2024-06-20
Loading full text...

Full text loading...

References

  1. 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.
    [Google Scholar]
  2. Aleardi, M., Vinciguerra, A., Stucchi, E. & Hojat, A. (2022) Probabilistic inversions of electrical resistivity tomography data with a machine learning‐based forward operator. Geophysical Prospecting, 70(5), 938–957.
    [Google Scholar]
  3. Araya‐Polo, M., Jennings, J., Adler, A. & Dahlke, T. (2018) Deep‐learning tomography. Leading Edge, 37(1), 58–66.
    [Google Scholar]
  4. Azevedo, L. (2022) Model reduction in geostatistical seismic inversion with functional data analysis. Geophysics, 87(1), M1–M11.
    [Google Scholar]
  5. Colombo, D., Turkoglu, E., Li, W., Sandoval‐Curiel, E. & Rovetta, D. (2021) Physics‐driven deep‐learning inversion with application to transient electromagnetics. Geophysics, 86(3), E209–E224.
    [Google Scholar]
  6. Fernández‐Martínez, J.L. (2015) Model reduction and uncertainty analysis in inverse problems. The Leading Edge, 34(9), 1006–1016.
    [Google Scholar]
  7. Giampaolo, V., Rizzo, E., Titov, K., Konosavsky, P., Laletina, D., Maineult, A. & Lapenna, V. (2014) Self‐potential monitoring of a crude oil‐contaminated site (Trecate, Italy). Environmental Science and Pollution Research, 21, 8932–8947.
    [Google Scholar]
  8. Guo, Q., Liu, B., Wang, Y. & He, D. (2023) A deep learning inversion method for 3‐D electrical resistivity tomography based on neighborhood feature extraction. IEEE Sensors Journal, 23(16), 18550–18558.
    [Google Scholar]
  9. Hassanpour, J., Rostami, J., Khamehchiyan, M., Bruland, A. & Tavakoli, H. (2010) TBM performance analysis in pyroclastic rocks: a case history of Karaj water conveyance tunnel. Rock Mechanics and Rock Engineering, 43(4), 427–445.
    [Google Scholar]
  10. Huang, J. (2003) 3‐D resistivity/IP modeling and inversion based on FEM. Ph.D. thesis, Central South University.
  11. Huang, R., Liu, S., Qi, R. & Zhang, Y. (2021) Deep learning 3D sparse inversion of gravity data. Journal of Geophysical Research: Solid Earth, 126(11), e2021JB022476.
    [Google Scholar]
  12. Ismail, M.A.M., Majid, T.A., Goh, C.O., Lim, S.P. & Tan, C.G. (2019) Geological assessment for tunnel excavation under river with shallow overburden using surface site investigation data and electrical resistivity tomography. Measurement, 144, 260–274.
    [Google Scholar]
  13. Jiang, P., Liu, B., Wang, C., Chen, L., Tang, Y., et al. (2023) Deep learning joint inversion of electrical data for ahead‐prospecting in tunneling. Advances in Civil Engineering, 2023, 5639207.
    [Google Scholar]
  14. Jin, Y., Shen, Q., Wu, X., Chen, J. & Huang, Y. (2020) A physics‐driven deep‐learning network for solving nonlinear inverse problems. Petrophysics, 61(1), 86–98.
    [Google Scholar]
  15. Knyazev, A.V. (2001) Toward the optimal preconditioned eigensolver: locally optimal block preconditioned conjugate gradient method. SIAM Journal on Scientific Computing, 23(2), 517–541.
    [Google Scholar]
  16. Legault, J.M., Carriere, D. & Petrie, L. (2008) Synthetic model testing and distributed acquisition DC resistivity results over an unconformity uranium target from the Athabasca Basin, Northern Saskatchewan. The Leading Edge, 27(1), 46–51.
    [Google Scholar]
  17. Li, S., Liu, B., Xu, X., Nie, L., Liu, Z., Song, J., Sun, H., Chen, L. & Fan, K. (2017) An overview of ahead geological prospecting in tunneling. Tunnelling and Underground Space Technology, 63, 69–94.
    [Google Scholar]
  18. Li, S., Nie, L., Liu, B., Tian, M., Wang, C., Song, J., Liu, Z. & Wang, S. (2015) Advanced detection and physical model test based on multi‐electrode sources array resistivity method in tunnel. Chinese Journal of Geophysics, 58(4), 1434–1446.
    [Google Scholar]
  19. Liu, B., Guo, Q., Li, S., Liu, B. & Jiang, P. (2020) Deep learning inversion of electrical resistivity data. IEEE Transactions on Geoscience and Remote Sensing, 58(8), 5715–5728.
    [Google Scholar]
  20. Liu, B., Guo, Q., Liu, Z., Wang, C., Nie, L., Xu, X. & Chen, L. (2019) Comprehensive ahead prospecting for hard rock TBM tunneling in complex limestone geology: a case study in Jilin, China. Tunnelling and Underground Space Technology, 93, 103045.
    [Google Scholar]
  21. Liu, B., Guo, Q., Tang, Y. & Jang, P. (2023) Deep learning inversion method of tunnel resistivity synthetic data based on modelling data. Near Surface Geophysics, 21(4), 249–260.
    [Google Scholar]
  22. Liu, B., Guo, Q., Wang, K., Pang, Y., Nie, L. & Jiang, P. (2021) Adaptive convolution neural networks for electrical resistivity inversion. IEEE Sensors Journal, 21(2), 2055–2066.
    [Google Scholar]
  23. Liu, B., Jiang, P., Guo, Q. & Wang, C. (2022) Deep learning inversion of electrical resistivity data by one‐sided mapping. IEEE Signal Processing Letters, 29, 2248–2252.
    [Google Scholar]
  24. Liu, B., Liu, Z., Li, S., Fan, K., Nie, L. & Zhang, X. (2017) An improved time‐lapse resistivity tomography to monitor and estimate the impact on the groundwater system induced by tunnel excavation. Tunnelling and Underground Space Technology, 66, 107–120.
    [Google Scholar]
  25. Liu, B., Pang, Y., Jiang, P., Liu, Z., Liu, B., Zhang, Y., Cai, Y. & Liu, J. (2023) Physics‐driven deep learning inversion for direct current resistivity survey data. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–11.
    [Google Scholar]
  26. Liu, B., Ren, Y., Liu, H., Xu, H. & Jiang, P. (2021) GPRInvNet: Deep learning‐based ground‐penetrating radar data inversion for tunnel linings. IEEE Transactions on Geoscience and Remote Sensing, 59(10), 8305–8325.
    [Google Scholar]
  27. Liu, B., Yang, S., Ren, Y., Xu, X., Jiang, P. & Chen, Y. (2021) Deep‐learning seismic full‐waveform inversion for realistic structural models. Geophysics, 86(1), R31–R44.
    [Google Scholar]
  28. Liu, B., Yue, J., Zuo, Z., Xu, X. & Jiang, P. (2021) Unsupervised deep learning for random noise attenuation of seismic data. IEEE Geoscience and Remote Sensing Letters, 19, 1–5.
    [Google Scholar]
  29. Loke, M., Chambers, J., Rucker, D., Kuras, O. & Wilkinson, P. (2013) Recent developments in the direct‐current geoelectrical imaging method. Journal of Applied Geophysics, 95, 135–156.
    [Google Scholar]
  30. Loke, M.H., Acworth, I. & Dahlin, T. (2003) A comparison of smooth and blocky inversion methods in 2D electrical imaging surveys. Exploration Geophysics, 34(3), 182–187.
    [Google Scholar]
  31. Mousavi, S.M. & Beroza, G.C. (2022) Deep‐learning seismology. Science, 377(6607), eabm4470.
    [Google Scholar]
  32. Oh, S. & Byun, J. (2021) Bayesian uncertainty estimation for deep learning inversion of electromagnetic data. IEEE Geoscience and Remote Sensing Letters, 19, 1–5.
    [Google Scholar]
  33. Panthi, K.K. & Nilsen, B. (2007) Uncertainty analysis of tunnel squeezing for two tunnel cases from Nepal Himalaya. International Journal of Rock Mechanics and Mining Sciences, 44(1), 67–76.
    [Google Scholar]
  34. Perrone, A., Lapenna, V. & Piscitelli, S. (2014) Electrical resistivity tomography technique for landslide investigation: a review. Earth‐Science Reviews, 135, 65–82.
    [Google Scholar]
  35. Puzyrev, V. (2019) Deep learning electromagnetic inversion with convolutional neural networks. Geophysical Journal International, 218(2), 817–832.
    [Google Scholar]
  36. Ren, Y., Liu, B., Yang, S., Li, D. & Jiang, P. (2021) Seismic data inversion with acquisition adaptive convolutional neural network for geologic forward prospecting in tunnels acquisition adaptive CNN. Geophysics, 86(5), R659–R670.
    [Google Scholar]
  37. Ronneberger, O., Fischer, P. & Brox, T. (2015) U‐net: convolutional networks for biomedical image segmentation. In International Conference on medical image computing and computer‐assisted intervention. Berlin: Springer, pp. 234–241.
  38. Tsokas, G.N., Jung‐Ho, K., Tsourlos, P.I., Angistalis, G., Vargemezis, G., Stampolidis, A. & Diamanti, N. (2015) Investigating behind the lining of the tunnel of Eupalinus in Samos (Greece) using ERT and GPR. Near Surface Geophysics, 13(6), 571–583.
    [Google Scholar]
  39. Vu, M. & Jardani, A. (2021) Convolutional neural networks with Segnet architecture applied to three‐dimensional tomography of subsurface electrical resistivity: CNN‐3D‐ERT. Geophysical Journal International, 225(2), 1319–1331.
    [Google Scholar]
  40. Wang, Y., Wang, Q., Lu, W. & Li, H. (2021) Physics‐constrained seismic impedance inversion based on deep learning. IEEE Geoscience and Remote Sensing Letters, 19, 1–5.
    [Google Scholar]
  41. Wang, Y., Yao, H. & Zhao, S. (2016) Auto‐encoder based dimensionality reduction. Neurocomputing, 184, 232–242.
    [Google Scholar]
  42. Weiss, K., Khoshgoftaar, T.M. & Wang, D. (2016) A survey of transfer learning. Journal of Big Data, 3(1), 1–40.
    [Google Scholar]
  43. White, R., Collins, S., Denne, R., Hee, R. & Brown, P. (2001) A new survey design for 3D IP inversion modelling at Copper Hill. Exploration Geophysics, 32(3‐4), 152–155.
    [Google Scholar]
  44. Williams, M.R., Buda, A.R., Singha, K., Folmar, G.J., Elliott, H.A. & Schmidt, J.P. (2017) Imaging hydrological processes in headwater riparian seeps with time‐lapse electrical resistivity. Groundwater, 55(1), 136–148.
    [Google Scholar]
  45. Yang, S., Wang, Z., Wang, J., Cohn, A.G., Zhang, J., Jiang, P., Nie, L. & Sui, Q. (2022) Defect segmentation: mapping tunnel lining internal defects with ground penetrating radar data using a convolutional neural network. Construction and Building Materials, 319, 125658.
    [Google Scholar]
  46. Zhang, L., Zhang, G., Liu, Y. & Fan, Z. (2021) Deep learning for 3‐D inversion of gravity data. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–18.
    [Google Scholar]
  47. Zhang, Z. (2018) Improved Adam optimizer for deep neural networks. In 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS). Piscataway, NJ: IEEE, pp. 1–2.
    [Google Scholar]
/content/journals/10.1002/nsg.12294
Loading
/content/journals/10.1002/nsg.12294
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): electrical resistivity; inversion; tomography; tunnel

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