Enhancing Seismic Image Segmentation Using Deep Learning Methods
Keywords:
Convolutional neural network (CNN), deep learning, GLCM, object segmentation, UNETAbstract
Accurate segmentation of seismic images remains a critical pursuit in subsurface exploration. This paper introduces an innovative methodology aiming to elevate the precision and reliability of seismic image segmentation. Leveraging the Grey Level Co-occurrence Matrix (GLCM) alongside the UNET architecture—renowned for its hierarchical feature extraction—this study presents a novel approach to delineating subsurface structures, notably salt bodies, within seismic data. The synergy between GLCM's rich textural insights and UNET's sophisticated feature extraction capabilities holds promise in significantly refining the delineation of intricate subsurface features. Motivated by the need for automation and enhanced accuracy in seismic imaging interpretation, a substantial repository containing 4,000 training seismic image patches, each complemented by corresponding segmentation masks. Evaluation was performed on a separate set of 18,000 seismic image patches, and accompanied by depth information for sample locations. The proposed methodology not only aims to enhance segmentation accuracy but also endeavors to advance seismic interpretation practices, potentially contributing to informed decision-making in subsurface exploration. Rigorous experimentation conducted within a unified training framework revealed promising results, demonstrating the proposed architecture's performance comparable to or, in most cases, surpassing established segmentation models.
Downloads
References
A. Halpert, R. Clapp, & B. Biondi, "Salt delineation via interpreter-guided 3d seismic image segmentation", Interpretation, vol. 2, no. 2, p. T79-T88, 2014. https://doi.org/10.1190/int-2013-0159.1
L. Soh and C. Tsatsoulis, "Texture analysis of sar sea ice imagery using gray level co-occurrence matrices", Ieee Transactions on Geoscience and Remote Sensing, vol. 37, no. 2, p. 780-795, 1999. https://doi.org/10.1109/36.752194
G. Liu, R. Wang, Y. Deng, R. Chen, Y. Shao, & Z. Yuan, "A new quality map for 2-d phase unwrapping based on gray level co-occurrence matrix", Ieee Geoscience and Remote Sensing Letters, vol. 11, no. 2, p. 444-448, 2014. https://doi.org/10.1109/lgrs.2013.2264857
S. Minaee, Y. Boykov, F. Porikli, A. Plaza, N. Kehtarnavaz, & D. Terzopoulos, "Image segmentation using deep learning: a survey", Ieee Transactions on Pattern Analysis and Machine Intelligence, p. 1-1, 2021. https://doi.org/10.1109/tpami.2021.3059968
Z. Wang, Q. Shen, Y. Liu, B. Zheng, & P. Sun, "Unsupervised deep learning for rapid subsurface interface identification using geophysical measurements",, 2023. https://doi.org/10.21203/rs.3.rs-2563834/v1
E. Gibson, F. Giganti, Y. Hu, E. Bonmati, S. Bandula, K. Gurusamyet al., "Automatic multi-organ segmentation on abdominal ct with dense v-networks", Ieee Transactions on Medical Imaging, vol. 37, no. 8, p. 1822-1834, 2018. https://doi.org/10.1109/tmi.2018.2806309
B. Basri, M. Assidiq, H. Karim, & A. Nuraisyah, "Extreme learning machine with feature extraction using glcm for phosphorus deficiency identification of cocoa plants", Ilkom Jurnal Ilmiah, vol. 14, no. 2, p. 112-119, 2022. https://doi.org/10.33096/ilkom.v14i2.1226.112-119
A. Mustafa, M. Alfarraj, & G. AlRegib, "Spatiotemporal modeling of seismic images for acoustic impedance estimation",, 2020. https://doi.org/10.48550/arxiv.2006.15472
H. Di, M. Shafiq, & G. AlRegib, "Multi-attribute k-means clustering for salt-boundary delineation from three-dimensional seismic data", Geophysical Journal International, vol. 215, no. 3, p. 1999-2007, 2018. https://doi.org/10.1093/gji/ggy376
W. Zhu, S. Mousavi, & G. Beroza, "Seismic signal denoising and decomposition using deep neural networks", Ieee Transactions on Geoscience and Remote Sensing, vol. 57, no. 11, p. 9476-9488, 2019. https://doi.org/10.1109/tgrs.2019.2926772
X. Wu, L. Liang, Y. Shi, & S. Fomel, "Faultseg3d: using synthetic data sets to train an end-to-end convolutional neural network for 3d seismic fault segmentation", Geophysics, vol. 84, no. 3, p. IM35-IM45, 2019. https://doi.org/10.1190/geo2018-0646.1
A. Milosavljevic, "Identification of salt deposits on seismic images using deep learning method for semantic segmentation", Isprs International Journal of Geo-Information, vol. 9, no. 1, p. 24, 2020. https://doi.org/10.3390/ijgi9010024
M. Shafiq, Z. Wang, A. Amin, T. Hegazy, M. Deriche, & G. AlRegib, "Detection of salt-dome boundary surfaces in migrated seismic volumes using gradient of textures",, 2015. https://doi.org/10.1190/segam2015-5927230.1
Y. Shi, X. Wu, & S. Fomel, "Saltseg: automatic 3d salt segmentation using a deep convolutional neural network", Interpretation, vol. 7, no. 3, p. SE113-SE122, 2019. https://doi.org/10.1190/int-2018-0235.1
J. Shi, H. Huang, S. Xue, & B. Li, "Research on seismic signal classification based on time-frequency map and deep learning", Destech Transactions on Computer Science and Engineering, no. ccnt, 2021. https://doi.org/10.12783/dtcse/ccnt2020/35396
W. Zhu, B. Yalcin, S. Khirevich, & T. Patzek, "Fault traces: generation of fault segments and estimation of their fractal dimension", Lithosphere, vol. 2021, no. Special 4, 2021. https://doi.org/10.2113/2021/4991604
H. Wu, B. Zhang, T. Lin, D. Cao, & Y. Lou, "Semiautomated seismic horizon interpretation using the encoder-decoder convolutional neural network", Geophysics, vol. 84, no. 6, p. B403-B417, 2019. https://doi.org/10.1190/geo2018-0672.1
Y. Wu, J. Wei, J. Pan, & P. Chen, "Research on microseismic source locations based on deep reinforcement learning", Ieee Access, vol. 7, p. 39962-39973, 2019. https://doi.org/10.1109/access.2019.2906066
G. Chen, "Noise reduction method for seismic data based on subspace projection and fast fourier convolution",, 2023. https://doi.org/10.1117/12.2684247
V. Puzyrev, T. Salles, G. Surma, & C. Elders, "Geophysical model generation with generative adversarial networks", Geoscience Letters, vol. 9, no. 1, 2022. https://doi.org/10.1186/s40562-022-00241-y
M. Moustafa, S. Mohamed, S. Ahmed, & A. Nasr, "Hyperspectral change detection based on modification of unet neural networks", Journal of Applied Remote Sensing, vol. 15, no. 02, 2021. https://doi.org/10.1117/1.jrs.15.028505
H. Di and D. Gao, "Nonlinear gray-level co-occurrence matrix texture analysis for improved seismic facies interpretation", Interpretation, vol. 5, no. 3, p. SJ31-SJ40, 2017. https://doi.org/10.1190/int-2016-0214.1
C. Henry, S. Azimi, & N. Merkle, "Road segmentation in sar satellite images with deep fully convolutional neural networks", Ieee Geoscience and Remote Sensing Letters, vol. 15, no. 12, p. 1867-1871, 2018. https://doi.org/10.1109/lgrs.2018.2864342
M. Matos, M. Yenugu, S. Angelo, & K. Marfurt, "Integrated seismic texture segmentation and cluster analysis applied to channel delineation and chert reservoir characterization", Geophysics, vol. 76, no. 5, p. P11-P21, 2011. https://doi.org/10.1190/geo2010-0150
Downloads
Published
How to Cite
Issue
Section
License
![Creative Commons License](http://i.creativecommons.org/l/by-sa/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.