Transfer Learning-Based Electromagnetic Inversion for LWD
DOI:
https://doi.org/10.62051/ijcsit.v8n2.07Keywords:
Logging-while-drilling electromagnetic, Three-dimensional inversion, Transfer learning, Bayesian neural networkAbstract
Three-dimensional inversion of logging-while-drilling (LWD) data serves as a key technology for boundary detection and reservoir characterization under complex geological conditions. Currently, inversion methods based on deep neural networks are prone to overfitting, often yielding unreliable results when training samples are limited. To address this issue, this paper proposes a transfer learning-based electromagnetic inversion approach for LWD, adopting a strategy of 2D pre-training followed by 3D fine-tuning. This strategy enables efficient transfer of electromagnetic features learned from 2D models to 3D networks, thereby reducing the dependency of 3D inversion on large-scale datasets. Furthermore, a Bayesian Neural Network (BNN) is integrated to construct a unified 3D inversion framework, achieving simultaneous prediction of resistivity distribution and quantification of uncertainty. Numerical experiments demonstrate that the proposed method achieves fast and stable convergence even with a limited number of 3D training samples, while maintaining high inversion accuracy under varying noise levels. In addition, uncertainty estimation effectively reveals the impact of inadequate prior knowledge and noise interference on the inversion results. By ensuring inversion accuracy and significantly improving computational efficiency, the proposed method provides robust technical support for electromagnetic LWD inversion in complex geological settings.
Downloads
References
[1] Kang Z, Zhang Y, Qin H, et al. An intelligent inversion method for azimuth electromagnetic logging while drilling measurements [J]. IEEE Access, 2023, 11: 79285-79294.
[2] Wang Nanzhe, Chang Haibin, Zhang Dongxiao. Deep-Learning-Based Inverse Modeling Approaches: A Subsurface Flow Example [J]. Journal of Geophysical Research: Solid Earth, 2021, 126(2): e2020JB020549.
[3] Jin Y, Wu X, Chen J, et al. A physics-driven deep learning network for subsurface inversion [C]//2019 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM). IEEE, 2019: 1-2.
[4] LIU B, GUO Q, LI S, et al. Deep Learning Inversion of Electrical Resistivity Data [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(8): 5715-5728.
[5] Wu X, Shi Y, Fomel S, et al. 2019b. FaultNet3D: Predicting fault probabilities, strikes, and dips with a single convolutional neural network [J]. IEEE Transactions on Geoscience and Remote Sensing, 57(11): 9138–9155.
[6] Gao K, Huang L, Zheng Y. Fault detection on seismic structural images using a nested residual U-Net [J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 1-15.
[7] Ma X, Yao G, Zhang F, et al. 3-D seismic fault detection using recurrent convolutional neural networks with compound loss [J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-15.
[8] Shan Z, Ling D, Xie Z, et al. A semianalytical solution for one‐dimensional transient wave propagation in a saturated single‐layer porous medium with a fluid surface layer [J]. International Journal for Numerical and Analytical Methods in Geomechanics, 2019, 43(13): 2184-2199.
[9] Cui Z D, Zhang Z L, Yuan L, et al. Design of underground structures [M]. Springer Singapore, 2020.
[10] PUZYREV V. Deep learning electromagnetic inversion with convolutional neural networks [J]. Geophysical Journal International, 2019, 218(2): 817-832.
[11] Hu Y, Guo R, Jin Y, et al. A supervised descent learning technique for solving directional electromagnetic logging-while-drilling inverse problems [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(11): 8013-8025.
[12] Noh K, Pardo D, Torres-Verdín C. Physics-guided deep-learning inversion method for the interpretation of noisy logging-while-drilling resistivity measurements [J]. Geophysical Journal International, 2023, 235(1): 150-165.
[13] Zhao Ning, Shen Songning, Li Ning, et al. Deep learning inversion of ultra-deep azimuthal electromagnetic logging while drilling based on physical driving [J]. Petroleum Geophysical Exploration, 2024, 59(5): 1069-1079.
[14] Dominguez-Cruz M A, España-Pinto J A, Valdiviezo-Mijangos O C, et al. Petroelastic modeling of well logging and seismic inversion data combining rock physics templates and conventional petrophysical analysis for 1D, 2D, and 3D supervised reservoir characterization of the Stybarrow Field in Exmouth sub-basin inner Carnarvon Basin, Australia [J]. Modeling Earth Systems and Environment, 2025, 11(2): 97.
[15] Noh K, Pardo D, Torres-Verdín C. 2.5-D deep learning inversion of LWD and deep-sensing EM measurements across formations with dip faults [J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19: 1-5.
[16] Zhao N, Li N, Xiao Z, et al. Physics-driven deep learning pixel-based inversion of logging while drilling in anisotropic formation [J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 1-12.
[17] Qin H, Kang Z, Chen R, et al. A novel inversion method of logging while drilling azimuthal electromagnetic data in anisotropic formations based on BiLSTM [J]. Journal of Geophysics and Engineering, 2025: gxaf063.
[18] Jamil A. Machine Learning Methods for 2D Electrical Resistivity Inversion Applied to Hydrogeological Subsurface Characterization[D]. New Mexico State University, 2025.
[19] Singh S K. Optimising mobile laser scanning for underground mines [D]. University of New South Wales (Australia), 2022.
[20] Liu Y, Yin C, Qiu C, et al. 3-D inversion of transient EM data with topography using unstructured tetrahedral grids [J]. Geophysical Journal International, 2019, 217(1): 301-318.
[21] Maleki F, Ovens K, Gupta R, et al. Generalizability of machine learning models: quantitative evaluation of three methodological pitfalls [J]. Radiology: Artificial Intelligence, 2022, 5(1): e220028.
[22] Puzyrev V, Swidinsky A. Inversion of marine electromagnetic data using a deep learning-based approach with transfer learning [J]. Geophysical Journal International, 2022, 231(1): 214-229.
[23] Yosinski J, Clune J, Bengio Y, et al. How transferable are features in deep neural networks? [J]. Advances in neural information processing systems, 2014, 27.
[24] Zhang Z, Alkhalifah T. High-resolution reservoir characterization using deep learning-aided elastic full-waveform inversion: The North Sea field data example [J]. Geophysics, 2020, 85(4): WA137-WA146.
[25] Gooneratne C P, Li B, Deffenbaugh M, et al. Instruments, measurement principles and communication technologies for downhole drilling environments [M]. Cham, Switzerland: Springer International Publishing, 2019.
[26] Kaura A M, Andrawus Y, Ibrahim A Y. Geophysics, Geology, Formation Evaluation, and Reservoir Characterization in Unconventional Resources [M]//Unconventional Resources. CRC Press, 2025: 40-122.
[27] Yang Xuemin, Peng Chengbin. A new seismic steering drilling technology for reducing drilling risk and increasing reservoir penetration rate [J]. Petroleum Exploration, 2018, 57 (04):627-636.
[28] Liu Cheng. Challenges and countermeasures of wellbore stability control by drilling fluid in extended reach wells [J]. Petrochemical Technology, 2024, 31 (11):256-258+275.
[29] Gal Y, Ghahramani Z. Dropout as a bayesian approximation: Representing model uncertainty in deep learning [C]//international conference on machine learning. PMLR, 2016: 1050-1059.
[30] Kendall A, Gal Y. What uncertainties do we need in bayesian deep learning for computer vision? [J]. Advances in neural information processing systems, 2017, 30.
[31] Oh S, Byun J. Bayesian uncertainty estimation for deep learning inversion of electromagnetic data [J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19: 1-5.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Computer Science and Information Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
