Abstract
The paper considers the problem of velocity model acquisition for a complex media based on boundary measurements. The acoustic model is used to describe the media. We used an open-source dataset of velocity distributions to compare the presented results with the previous works directly. Forward modeling is performed using the grid-characteristic numerical method. The inverse problem is solved using deep convolutional neural networks. Modifications for a baseline UNet architecture are proposed to improve both structural similarity index measure and quantitative correspondence of the velocity profiles with the ground truth. We evaluate our enhancements and demonstrate the statistical significance of the results.
REFERENCES
J. Ye, S. Ito, and N. Toyama, ‘‘Computerized ultrasonic imaging inspection: From shallow to deep learning,’’ Sensors 18, 3820 (2018). https://doi.org/10.3390/s18113820
G. Tripathi, H. Anowarul, K. Agarwal, and D. K. Prasad, ‘‘Classification of micro-damage in piezoelectric ceramics using machine learning of ultrasound signals,’’ Sensors 19, 4216 (2019). https://doi.org/10.3390/s19194216
D. Perdios, M. Vonlanthen, F. Martinez, M. Arditi, and J.-P. Thiran, ‘‘Single-shot CNN-based ultrasound imaging with sparse linear arrays,’’ in Proceedings of the 2020 IEEE International Ultrasonics Symposium IUS (2020), pp. 1–4. https://doi.org/10.1109/IUS46767.2020.9251442
A. S. Stankevich, I. B. Petrov, and A. V. Vasyukov, ‘‘Numerical solution of inverse problems of wave dynamics in heterogeneous media with convolutional neural networks,’’ in Smart Modeling for Engineering Systems (2021), pp. 235–246. https://doi.org/10.1007/978-981-33-4619-2_18
D. Patel, R. Tibrewala, A. Vega, L. Dong, N. Hugenberg, and A. A. Oberai, ‘‘Circumventing the solution of inverse problems in mechanics through deep learning: Application to elasticity imaging,’’ Comput. Methods Appl. Mech. Eng. 353, 448–466 (2019). https://doi.org/10.1016/j.cma.2019.04.045
A. U. Waldeland and A. H. S. Solberg, ‘‘Salt classification using deep learning,’’ in Proceedings of the 79th EAGE Conference and Exhibition 2017 (2017), pp. 1–5. https://doi.org/10.3997/2214-4609.201700918
A. U. Waldeland, A. C. Jensen, L. J. Gelius, and A. H. S. Solberg, ‘‘Convolutional neural networks for automated seismic interpretation,’’ Leading Edge 37, 529–537 (2018). https://doi.org/10.1190/tle37070529.1
Y. Shi, X. Wu, and S. Fomel, ‘‘Automatic salt-body classification using deep-convolutional neural network,’’ in SEG Technical Program Expanded Abstracts 2018 (2018), pp. 1971–1975. https://doi.org/10.1190/segam2018-2997304.1
T. Zhao, ‘‘Seismic facies classification using different deep convolutional neural networks,’’ in SEG Technical Program Expanded Abstracts 2018 (2018), pp. 2046–2050. https://doi.org/10.1190/segam2018-2997085.1
Y. Alaudah, P. Michalowicz, M. Alfarraj, and G. AlRegib, ‘‘A machine-learning benchmark for facies classification,’’ Interpretation 7, SE175–SE187 (2019). https://doi.org/10.1190/INT-2018-0249.1
L. Baroni, R. M. Silva, R. S. Ferreira, D. Civitarese, D. Szwarcman, and E. V. Brazil, ‘‘Penobscot dataset: Fostering machine learning development for seismic interpretation,’’ arXiv: 1903.12060 (2019).
M. Salvaris, M. Kaznady, V. Paunic, I. Karmanov, A. Bhatia, W. H. Tok, and S. Chikkerur, ‘‘Deepseismic: A deep learning library for seismic interpretation,’’ in Proceedings of the 1st EAGE Digitalization Conference and Exhibition (2020), pp. 1–5. https://doi.org/10.3997/2214-4609.202032086
M. Alfarraj and G. AlRegib, ‘‘Semi-supervised learning for acoustic impedance inversion,’’ in SEG Technical Program Expanded Abstracts 2019 (2019), pp. 2298–2302. https://doi.org/10.1190/segam2019-3215902.1
L. Wang, D. Meng, B. Wu, and N. Liu, ‘‘Seismic inversion via closed-loop fully convolutional residual network and transfer learning,’’ in SEG Technical Program Expanded Abstracts 2020 (2020), pp. 1521–1525. https://doi.org/10.1190/segam2020-3428004.1
F. Yang and J. Ma, ‘‘Deep-learning inversion: A next-generation seismic velocity model building method,’’ Geophysics 84, R583–R599 (2019). https://doi.org/10.1190/geo2018-0249.1
V. Das, A. Pollack, U. Wollner, and T. Mukerji, ‘‘Convolutional neural network for seismic impedance inversion,’’ Geophysics 84, R869–R880 (2019). https://doi.org/10.1190/geo2018-0838.1
M. Araya-Polo, S. Farris, and M. Florez, ‘‘Deep learning-driven velocity model building workflow,’’ Leading Edge 38, 822–900 (2019). https://doi.org/10.1190/tle38110872a1.1
M. J. Park and M. D. Sacchi, ‘‘Automatic velocity analysis using convolutional neural network and transfer learning,’’ Geophysics 85, V33–V43 (2020). https://doi.org/10.1190/geo2018-0870.1
K. A. Beklemysheva, A. V. Vasyukov, A. O. Kazakov, and I. B. Petrov, ‘‘Grid-characteristic numerical method for low-velocity impact testing of fiber-metal laminates,’’ Lobachevskii J. Math. 39, 874–883 (2018). https://doi.org/10.1134/S1995080218070065
K. Beklemysheva, V. Golubev, I. Petrov, and A. Vasyukov, ‘‘Determining effects of impact loading on residual strength of fiber-metal laminates with grid-characteristic numerical method,’’ Chin. J. Aeronaut. 34, 1–12 (2021). https://doi.org/10.1016/j.cja.2020.07.013
V. I. Golubev, ‘‘The usage of grid-characteristic method in seismic migration problems,’’ in Smart Modeling for Engineering Systems (2019), pp. 143–155. https://doi.org/10.1007/978-3-030-06228-6_13
V. Golubev, I. Nikitin, and A. Ekimenko, ‘‘Simulation of seismic responses from fractured MARMOUSI2 model,’’ AIP Conf. Proc. 2312, 050006 (2020). https://doi.org/10.1063/5.0035495
V. Golubev, A. Shevchenko, and I. Petrov, ‘‘Simulation of seismic wave propagation in a multicomponent oil deposit model,’’ Int. J. Appl. Mech. 12, 2050084 (2020). https://doi.org/10.1142/S1758825120500842
A. Stankevich, I. Nechepurenko, A. Shevchenko, L. Gremyachikh, A. Ustyuzhanin, and A. Vasyukov, ‘‘Numerical nine-shot seismo records for 1600 acoustic impedance distributions,’’ Zenodo, 5515485 (2021). https://doi.org/10.5281/zenodo.5515485
O. Ronneberger, P. Fischer, and T. Brox, ‘‘U-Net: Convolutional networks for biomedical image segmentation,’’ in Medical Image Computing and Computer-Assisted Intervention (2015), pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
N. Kanopoulos, N. Vasanthavada, and R. L. Baker, ‘‘Design of an image edge detection filter using the Sobel operator,’’ IEEE J. Solid-state Circuits 23, 358–367 (1988). https://doi.org/10.1109/4.996
D. P. Kingma and J. Ba, ‘‘Adam: A method for stochastic optimization,’’ arXiv: 1412.6980 (2014).
Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, ‘‘Image quality assessment: From error visibility to structural similarity,’’ IEEE Trans. Image Process. 13, 600–612 (2004). https://doi.org/10.1109/TIP.2003.819861
A. Paszke, S. Gross, et al., ‘‘PyTorch: An imperative style, high-performance deep learning library,’’ arXiv: 1912.01703 (2019).
S. S. Shapiro and M. B. Wilk, ‘‘An analysis of variance test for normality (complete samples),’’ Biometrika 52, 591–611 (1965). https://doi.org/10.2307/2333709
H. Scheffe, The Analysis of Variance (Wiley, New York, 1999).
Funding
AV and AS are supported by RFBR project 18-29-02127 for their work on establishing a numerical pipeline and creating the dataset. LG is supported by the Basic Research Program at the National Research University Higher School of Economics for his work on forward-modeling, and inverse problem approaches. AU is supported by RSF project 19-71-30020 for his work on ablation study.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Publisher’s Note.
Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
(Submitted by A. V. Lapin)
Rights and permissions
About this article
Cite this article
Stankevich, A.S., Nechepurenko, I.O., Shevchenko, A.V. et al. Learning Velocity Model for Complex Media with Deep Convolutional Neural Networks. Lobachevskii J Math 45, 336–345 (2024). https://doi.org/10.1134/S1995080224010499
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1995080224010499