1887
Volume 73, Issue 6
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

A comprehensive deep learning approach was introduced, encompassing data denoising, inversion imaging and uncertainty analysis. For denoising transient electromagnetic (TEM) data, we utilized a Bidirectional Long Short‐Term Memory (BiLSTM) network. In the data inversion process, a combination of convolutional neural network (CNN) and BiLSTM structures was employed, and their outputs were consolidated using a multi‐head attention mechanism. To ensure robust performance under challenging noise conditions, we implemented a specialized multi‐channel noise training protocol during model optimization. The framework incorporates Monte Carlo (MC) dropout techniques to systematically evaluate prediction reliability throughout the inversion pipeline. This approach has not only been validated on test datasets but has also been successfully applied to the field dataset collected at the Narenbaolige Coalfield in Inner Mongolia, China. The deep learning inversion results obtained from both raw and denoised data exhibit reduced vertical continuity and increased roughness characteristics. In contrast, the Occam's inversion method with smoothness constraints yields results demonstrating superior lateral continuity and vertical smoothness. It is noteworthy that both inversion approaches show consistent interpretations regarding the scale of basalt formations and their contact interfaces with underlying sedimentary layers. Further uncertainty analysis reveals relatively higher uncertainty characteristics in the transition zones between basalt and sedimentary layers, as well as in deeper formations. The elevated uncertainty at interface regions may be attributed to model resolution limitations and inversion ill‐posedness issues, whereas the higher uncertainty in deeper formations is more likely caused by the volumetric effects of electromagnetic field detection and the influence of observational data noise.

© 2025 European Association of Geoscientists & Engineers. © 2025 European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.70069
2025-08-25
2026-02-15

  • From This Site

    /content/journals/10.1111/1365-2478.70069
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Alqatari, H., E.Turkoglu, D.Colombo, and E.Sandoval‐Curiel. 2025. “Machine Learning for Robust Velocity Interpretation of Uphole and Check‐Shot Data.” The Leading Edge44, no. 4: 288–294.
     [Google Scholar]
  2. Asif, M. R., T. S.Bording, P. K.Maurya, B.Zhang, G.Fiandaca, and D. J.Grombacher. 2021. “A Neural Network‐Based Hybrid Framework for Least‐Squares Inversion of Transient Electromagnetic Data.” IEEE Transactions on Geoscience and Remote Sensing60: 4503610.
     [Google Scholar]
  3. Asif, M. R., N.Foged, T.Bording, J. J.Larsen, and A. V.Christiansen. 2023. “DL‐RMD: A Geophysically Constrained Electromagnetic Resistivity Model Database (RMD) for Deep Learning (DL) Applications.” Earth System Science Data15, no. 3: 1389–1401.
     [Google Scholar]
  4. Asif, M. R., N.Foged, P. K.Maurya, et al. 2022. “Integrating Neural Networks in Least‐Squares Inversion of Airborne Time‐Domain Electromagnetic Data.” Geophysics87, no. 4: E177–E187.
     [Google Scholar]
  5. Bai, P., G.Vignoli, A.Viezzoli, J.Nevalainen, and G.Vacca. 2020. “(Quasi‐)Real‐Time Inversion of Airborne Time‐Domain Electromagnetic Data via Artificial Neural Network.” Remote Sensing12, no. 20: 3440.
     [Google Scholar]
  6. Bishop, C. M.1995. “Training With Noise Is Equivalent to Tikhonov Regularization.” Neural Computation7, no. 1: 108–116.
     [Google Scholar]
  7. Blatter, D., K.Key, A.Ray, N.Foley, S.Tulaczyk, and E.Auken. 2018. “Trans‐Dimensional Bayesian Inversion of Airborne Transient EM Data From Taylor Glacier, Antarctica.” Geophysical Journal International214, no. 3: 1919–1936.
     [Google Scholar]
  8. Brescianini, R. F., M. W.Asten, and N.McLean. 1992. “Geophysical Characteristics of the Eloise Cu‐Au Deposit North‐West Queensland.” Exploration Geophysics23, no. 1–2: 33–42.
     [Google Scholar]
  9. Christiansen, A. V., E.Auken, N.Foged, and K. I.Sørensen. 2007. “Mutually and Laterally Constrained Inversion of CVES and TEM Data: A Case Study.” Near Surface Geophysics5, no. 2: 115–123.
     [Google Scholar]
  10. Colombo, D., E.Turkoglu, W.Li, E.Sandoval‐Curiel, and D.Rovetta. 2021. “Physics‐Driven Deep‐Learning Inversion With Application to Transient Electromagnetics.” Geophysics86, no. 3: E209–E224.
     [Google Scholar]
  11. Colombo, D., E.Turkoglu, E.Sandoval‐Curiel, D.Rovetta, and W.Li. 2023. “Machine‐Learning Inversion via Adaptive Learning and Statistical Sampling: Application to Airborne Micro‐TEM for Seismic Sand Corrections.” Geophysics88, no. 3: K51–K68.
     [Google Scholar]
  12. Dechesne, C., P.Lassalle, and S.Lefèvre. 2021. “Bayesian Deep Learning With Monte Carlo Dropout for Qualification of Semantic Segmentation.” In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2536–2539. IEEE.
  13. Effersø, F., E.Auken, and K. I.Sørensen. 1999. “Inversion of Band‐Limited TEM Responses.” Geophysical Prospecting47, no. 4: 551–564.
     [Google Scholar]
  14. Farquharson, C., and D. W.Oldenburg. 1993. “Inversion of Time‐Domain Electromagnetic Data for a Horizontally Layered Earth.” Geophysical Journal International114, no. 3: 433–442.
     [Google Scholar]
  15. Farquharson, C. G., X.Hu, Q.Huang, et al. 2023. “Advances in Transient Electromagnetic Methods.” Journal of Geophysics and Engineering20, no. 6: 1305–1307.
     [Google Scholar]
  16. Fitterman, D. V., and W. L.Anderson. 1987. “Effect of Transmitter Turn‐Off Time on Transient Soundings.” Geoexploration24, no. 2: 131–146.
     [Google Scholar]
  17. Gal, Y., and Z.Ghahramani. 2016. “Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning.” In International Conference on Machine Learning, 1050–1059. ICML.
  18. Haber, E., D. W.Oldenburg, and R.Shekhtman. 2007. “Inversion of Time Domain Three‐Dimensional Electromagnetic Data.” Geophysical Journal International171, no. 2: 550–564.
     [Google Scholar]
  19. Huang, Z., W.Xu, and K.Yu. 2015. “Bidirectional LSTM‐CRF Models for Sequence Tagging.” arXiv preprint arXiv:1508.01991.
  20. Junhwan, C., O.Seokmin, and B.Joongmoo. 2022. “Uncertainty Estimation in AVO Inversion Using Bayesian Dropout Based Deep Learning.” Journal of Petroleum Science and Engineering208, no. pt. A: 109288.
     [Google Scholar]
  21. Kafri, U., M.Goldman, and B.Lang. 1997. “Detection of Subsurface Brines, Freshwater Bodies and the Interface Configuration In‐Between by the Time Domain Electromagnetic Method in the Dead Sea Rift, Israel.” Environmental Geology31, no. 1–2: 42–49.
     [Google Scholar]
  22. Kang, H., M.Bang, S. J.Seol, and J.Byun. 2024. “Deep‐Learning‐Based Airborne Transient Electromagnetic Inversion Providing the Depth of Investigation.” Geophysics89, no. 2: E31–E45.
     [Google Scholar]
  23. Kendall, A., and Y.Gal. 2017. “What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?.” In Advances in Neural Information Processing Systems30: 5580–5590. Association for Computing Machinery.
     [Google Scholar]
  24. Kiranyaz, S., O.Avci, O.Abdeljaber, T.Ince, M.Gabbouj, and D. J.Inman. 2021. “1D Convolutional Neural Networks and Applications: A Survey.” Mechanical Systems and Signal Processing151: 107398.
     [Google Scholar]
  25. Kumar, A., U. K.Singh, and B.Pradhan. 2024. “Enhancing Subsurface Contamination Assessment via Ensemble Prediction of Ground Electrical Property: A Colorado AMD‐Impacted Wetland Case Study.” Journal of Environmental Management351: 119943.
     [Google Scholar]
  26. Lan, X., C.Zou, C.Peng, and C.Wu. 2023. “Uncertainty Quantification in Intelligent‐Based Electrical Resistivity Tomography Image Reconstruction With Monte Carlo Dropout Strategy.” IEEE Transactions on Geoscience and Remote Sensing61: 5906116.
     [Google Scholar]
  27. Li, H., Q.Di, and K.Li. 2024. “Adaptive Laterally Constrained Inversion of Time‐Domain Electromagnetic Data Using Hierarchical Bayes.” Geophysics89, no. 4: E129–E140.
     [Google Scholar]
  28. Li, H., G.Xue, and Y.He. 2019. “Decoupling Induced Polarization Effect From Time Domain Electromagnetic Data in a Bayesian Framework.” Geophysics84, no. 6: A59–A63.
     [Google Scholar]
  29. Li, J., C. G.Farquharson, and X.Hu. 2016. “Three Effective Inverse Laplace Transform Algorithms for Computing Time‐Domain Electromagnetic Responses.” Geophysics81, no. 2: E113–E128.
     [Google Scholar]
  30. Li, J., X.Hu, K.Zhang, W.Yuan, and T.Gang. 2020. “Synthesizing TEM Data by a 3D FETD Approach: A Case Study of Delineating a Resistive Basaltic Body Located in the Narenbaolige Coalfield, China.” In SEG Technical Program Expanded Abstracts, 621–625. Society of Exploration Geophysicists.
  31. Li, J., Y.Liu, C.Yin, X.Ren, and Y.Su. 2020. “Fast Imaging of Time‐Domain Airborne EM Data Using Deep Learning Technology.” Geophysics85, no. 5: E163–E170.
     [Google Scholar]
  32. Li, Z., Q.Huang, X.Xie, X.Tang, and L.Chang. 2016. “A Generic 1D Forward Modeling and Inversion Algorithm for TEM Sounding With an Arbitrary Horizontal Loop.” Pure and Applied Geophysics173, no. 8: 2869–2883.
     [Google Scholar]
  33. Liu, W., H.Wang, Z.Xi, and L.Wang. 2024. “Physics‐Informed Deep Learning Inversion With Application to Noisy Magnetotelluric Measurements.” Remote Sensing16, no. 1: 62.
     [Google Scholar]
  34. Liu, Y., and C.Yin. 2016. “3D Inversion for Multipulse Airborne Transient Electromagnetic Data.” Geophysics81, no. 6: E401–E408.
     [Google Scholar]
  35. Liu, Y., C.Yin, C.Qiu, et al. 2019. “3‐D Inversion of Transient EM Data With Topography Using Unstructured Tetrahedral Grids.” Geophysical Journal International217, no. 1: 301–318.
     [Google Scholar]
  36. Lu, X., C. G.Farquharson, and P.Lelièvre. 2024. “Surface Geometry Inversion of Transient Electromagnetic Data.” Geophysics89, no. 4: E177–E192.
     [Google Scholar]
  37. Mikucki, J. A., E.Auken, S.Tulaczyk, et al. 2015. “Deep Groundwater and Potential Subsurface Habitats Beneath an Antarctic Dry Valley.” Nature Communications6, no. 1: 6831.
     [Google Scholar]
  38. Mosser, L., and E. Z.Naeini. 2022. “A Comprehensive Study of Calibration and Uncertainty Quantification for Bayesian Convolutional Neural Networks—An Application to Seismic Data.” Geophysics87, no. 4: IM157–IM176.
     [Google Scholar]
  39. Noh, K., D.Pardo, and C.Torres‐Verdín. 2023. “Physics‐Guided Deep‐Learning Inversion Method for the Interpretation of Noisy Logging‐While‐Drilling Resistivity Measurements.” Geophysical Journal International235, no. 1: 150–165.
     [Google Scholar]
  40. Oh, S., and J.Byun. 2021. “Bayesian Uncertainty Estimation for Deep Learning Inversion of Electromagnetic Data.” IEEE Geoscience and Remote Sensing Letters19: 8010705.
     [Google Scholar]
  41. Peng, R., P.Yogeshwar, Y.Liu, and X.Hu. 2021. “Transdimensional Markov Chain Monte Carlo Joint Inversion of Direct Current Resistivity and Transient Electromagnetic Data.” Geophysical Journal International224, no. 2: 1429–1442.
     [Google Scholar]
  42. Puzyrev, V., and A.Swidinsky. 2021. “Inversion of 1D Frequency‐ and Time‐Domain Electromagnetic Data With Convolutional Neural Networks.” Computers & Geosciences149: 104681.
     [Google Scholar]
  43. Rogers, S.2006. System 2000.Net User Guide. Phoenix Geophysics Limited.
     [Google Scholar]
  44. Scholl, C., S. L.Helwig, B.Tezkan, M.Goldman, and U.Kafri. 2009. “1‐D Multimodel Joint Inversion of TEM‐Data Over Multidimensional Structures.” Geophysical Journal International176, no. 1: 81–94.
     [Google Scholar]
  45. Vaswani, A., N.Shazeer, N.Parmar, et al. 2017. “Attention is All You Need” In Advances in Neural Information Processing Systems30: 5999–6009. Association for Computing Machinery.
  46. Viezzoli, A., A. V.Christiansen, E.Auken, and K.Sørensen. 2008. “Quasi‐3D Modeling of Airborne TEM Data by Spatially Constrained Inversion.” Geophysics73, no. 3: F105–F113.
     [Google Scholar]
  47. Vincent, P., H.Larochelle, I.Lajoie, Y.Bengio, P. A.Manzagol, and L.Bottou. 2010. “Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network With a Local Denoising Criterion.” Journal of Machine Learning Research11, no. 12: 3371–3408.
     [Google Scholar]
  48. Wu, S., Q.Huang, and L.Zhao. 2021a. “Convolutional Neural Network Inversion of Airborne Transient Electromagnetic Data.” Geophysical Prospecting69, no. 8–9: 1761–1772.
     [Google Scholar]
  49. Wu, S., Q.Huang, and L.Zhao. 2021b. “De‐Noising of Transient Electromagnetic Data Based on the Long Short‐Term Memory‐Autoencoder.” Geophysical Journal International224, no. 1: 669–681.
     [Google Scholar]
  50. Wu, S., Q.Huang, and L.Zhao. 2022. “Instantaneous Inversion of Airborne Electromagnetic Data Based on Deep Learning.” Geophysical Research Letters49, no. 10: e2021GL097165.
     [Google Scholar]
  51. Wu, S., Q.Huang, and L.Zhao. 2023. “Fast Bayesian Inversion of Airborne Electromagnetic Data Based on the Invertible Neural Network.” IEEE Transactions on Geoscience and Remote Sensing61: 5907211.
     [Google Scholar]
  52. Wu, S., Q.Huang, and L.Zhao. 2024. “Physics‐Guided Deep Learning‐Based Inversion for Airborne Electromagnetic Data.” Geophysical Journal International238, no. 3: 1774–1789.
     [Google Scholar]
  53. Wu, X., G.Xue, Y.Zhao, P.Lv, Z.Zhou, and J.Shi. 2022. “A Deep Learning Estimation of the Earth Resistivity Model for the Airborne Transient Electromagnetic Observation.” Journal of Geophysical Research: Solid Earth127, no. 3: e2021JB023185.
     [Google Scholar]
  54. Yogeshwar, P., M.Küpper, B.Tezkan, et al. 2020. “Innovative Boat‐Towed Transient Electromagnetics—Investigation of the Furnas Volcanic Lake Hydrothermal System, Azores.” Geophysics85, no. 2: E41–E56.
     [Google Scholar]
  55. Zeng, S., X.Hu, J.Li, et al. 2019. “Effects of Full Transmitting‐Current Waveforms on Transient Electromagnetics: Insights From Modeling the Albany Graphite Deposit.” Geophysics84, no. 4: E255–E268.
     [Google Scholar]
  56. Zhang, B., K. W.Engebretsen, G.Fiandaca, H.Cai, and E.Auken. 2021. “3D Inversion of Time‐Domain Electromagnetic Data Using Finite Elements and a Triple Mesh Formulation.” Geophysics86, no. 3: E257–E267.
     [Google Scholar]
  57. Zhang, S., and N.Zhou. 2023. “Extraction of Multiple Electrical Parameters From IP‐Affected Transient Electromagnetic Data Based on LSTM‐ResNet.” IEEE Transactions on Geoscience and Remote Sensing61: 4501614.
     [Google Scholar]
/content/journals/10.1111/1365-2478.70069
Loading
A Deep Learning Approach for Transient Electromagnetic Data Denoising, Inversion and Uncertainty Analysis With Monte Carlo Dropout Technique
Geophysical Prospecting 73, e70069 (2025); https://doi.org/10.1111/1365-2478.70069
/content/journals/10.1111/1365-2478.70069
/content/journals/10.1111/1365-2478.70069
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): deep learning; denoising and inversion; Monte Carlo dropout; transient electromagnetic method; uncertainty analysis

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