Abstract
Fault identification is a key step in structural interpretation. Traditional fault identification methods are easily affected by the seismic quality and interpreter experience, and the identification methods of complex fault zones and multiscale faults require further improvement. The U-Net, frequently used at present, has achieved satisfactory results in fault identification. However, this network has a limited ability to extract and recover feature information and does not have a mechanism of concern, limiting its ability to identify complex faults. To solve these problems, this study proposes an improved U-Net network model based on a conventional U-Net network. A multiscale residual module was used to extract the features instead of the U-Net's two-layer convolution. The residual jump connection replaced the U-Net jump connection to avoid semantic loss caused by the fusion of high- and low-level semantic information. An attention mechanism was introduced to integrate the global, local, spatial, and channel features to ensure that the model could extract image features from various dimensions to the maximum extent. An improved U-Net network model was applied to train the model data and test the actual field data. Our results show that the proposed network model is better at fault identification, avoids human interference to a certain extent, and is advantageous compared to the conventional U-Net method.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig15_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11600-023-01200-7/MediaObjects/11600_2023_1200_Fig16_HTML.png)
Similar content being viewed by others
Data availability
The data used to support the findings of this study are available from the corresponding author upon request.
References
Araya-Polo M, Dahlke T, Frogner C et al (2017) Automated fault detection without seismic processing[J]. Lead Edge 36(3):208–214
Cunha A, Pochet A, Lopes H et al (2020) Seismic fault detection in real data using transfer learning from a convolutional neural network pre-trained with synthetic seismic data[J]. Comput Geosci 135:104344. https://doi.org/10.1016/j.cageo.2019.104344
Di H, Truelove L, Li C et al (2020) Accelerating seismic fault and stratigraphy interpretation with deep CNNs: a case study of the Taranaki Basin, New Zealand[J]. Lead Edge 39(10):727–733. https://doi.org/10.1190/tle39100727.1
Guo B, Li L, Luo Y (2018) A new method for automatic seismic fault detection using convolutional neural network[M]//SEG Technical Program Expanded Abstracts. Soc Explor Geophys 2018:1951–1955. https://doi.org/10.1190/segam2018-2995894.1
Huang L, Dong X, Clee TE (2017) A scalable deep learning platform for identifying geologic features from seismic attributes[J]. Leading Edge 36(3):249–256
Ibtehaz N, Rahman MS (2020) MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation[J]. Neural Netw 121:74–87. https://doi.org/10.1016/j.neunet.2019.08.025
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks[J]. Adv Neural Inf Process Syst 60:84–90. https://doi.org/10.1145/3065386
Li S, Yang C, Sun H et al (2019) Seismic fault detection using an encoder–decoder convolutional neural network with a small training set[J]. J Geophys Eng 16(01):175–189. https://doi.org/10.1093/jge/gxy015
J Long, E Shelhamer, T Darrell. (2015) Fully convolutional networks for semantic segmentation[C]. In: Proc. CVPR, 3431–3440.
Lu F, Meng R, Zhang J et al (2022) Research of complex fault recognition method based on UNet++ network and transfer learning technique. Prog Geophys 37(3):1100–1111. https://doi.org/10.6038/pg2022FF0122
Milletari F, Navab N, Ahmadi S, (2016) V-Net: Fully convolutional neural networks for volumetric medical image segmentation[C]//. In: Proceedings of the 2016 Fourth International Conference on 3D Vision, California, USA, IEEE. Stanford, 565–571. https://doi.org/10.1109/3DV.2016.79.
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation[J]. Med Image Comput Comput-Assist Intervent 9351:234–241
Szegedy C, Liu W, Jia Y, et al. (2015) Going deeper with convolutions[C]//.In: Proceedings of the IEEE conference on computer vision and pattern recognition. 1–9.
Tsotsos JK, Culhane SM, Wai WYK et al (1995) Modeling visual attention via selective tuning[J]. Artif Intell 78(1–2):507–545. https://doi.org/10.1016/0004-3702(95)00025-9
Wang Q, Wu B, Zhu P, et al. (2020) ECA-Net: Efficient channel attention for deep convolutional neural networks//. In: Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition. 2020: 1-9.
Woo S, Park J, Lee J, et al. (2018) CBAM: Convolutional block attention module[C]//. In: Proceedings of European Conference on Computer Vision. 11211: 3–19.
Wu X, Fomel S (2018) Automatic fault interpreta-tion with optimal surface voting. Geophysics 83:067–082
Wu X, Liang L, Shi Y et al (2019) FaultSeg3D: using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation[J]. Geophysics 84(03):IM35–IM45. https://doi.org/10.1190/geo2018-0646.1
**e Juan-ying, Zhang Kai-yun. (2022) XR-MSF-Unet: Automatic segmentation model of lung CT images for COVID-19 [J/OL]. Comput Sci Explor, 1–18, https://doi.org/10.3778/j.issn.1673-9418.2203023.
Zheng ZH, Kavousi P, Di HB (2014) Multi-attributes and neural network-based fault detection in 3D seismic interpretation[J]. Adv Mater Res 838:1497–1502
Zhou Z, Rahman Siddiquee M M, Tajbakhsh N, et al. (2018) Unet++: A nested u-net architecture for medical image segmentation[M]//In: Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, Cham, https://doi.org/10.1007/978-3-030-00889-5_1.
Acknowledgements
The authors are grateful to the Key Project of Natural Science Foundation of China (41930431), the Natural Science Foundation of Heilongjiang Province (LH2023D010) and the Northeast Petroleum University's special funds (2021YDQ-01) for supporting this work.
Funding
The Funding was provided by the Key Project of Natural Science Foundation of China, (41930431), Ying Shi,the Northeast Petroleum University's special funds, (2021YDQ-01), Jizhong Wu, the Natural Science Foundation of Heilongjiang Province, (LH2023D010), Jizhong Wu
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflicts of interest regarding the publication of this article.
Additional information
Edited by Prof. Qamar Yasin (ASSOCIATE EDITOR) / Prof. Gabriela Fernández Viejo (CO-EDITOR-IN-CHIEF).
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wu, J., Shi, Y., Wang, K. et al. Automatic seismic fault identification based on an improved U-Net network. Acta Geophys. 72, 2377–2389 (2024). https://doi.org/10.1007/s11600-023-01200-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11600-023-01200-7