GLCM and k-means clustering for texture-based recognition of salt bodies in seismic images
Contenido principal del artículo
Resumen
La obtención de imágenes e interpretación de estructuras subsalinas sigue siendo una tarea compleja para la exploración de petróleo y gas, así como para la identificación de sitios adecuados para almacenar grandes cantidades de dióxido de carbono atmosférico. La geometría irregular de los cuerpos salinos y la baja visibilidad de las estructuras bajo la sal generan gran incertidumbre en la interpretación sísmica manual, en especial al definir la base de las formaciones salinas. Para abordar este desafío, presentamos una metodología semiautomática, interpretable y ligera para la delimitación de cuerpos salinos en secciones sísmicas 2D. Esta combina características de textura derivadas de la matriz de coocurrencia de niveles de gris (GLCM) con agrupamiento mediante k-means. Realizamos un análisis exhaustivo de parámetros, explorando distintos tamaños de ventana y números de clústeres, evaluados con etiquetas de consenso derivadas de interpretaciones de dos expertos. Mediante validación cruzada de 5 pliegues, identificamos configuraciones con puntuaciones F1 consistentemente altas, alcanzando un máximo de 0.78. Para mayor robustez, integramos una estrategia de consenso que combina resultados de configuraciones destacadas. El mapa de consenso resultante ofrece una medida continua de confianza sobre la probabilidad de presencia de sal, destacando límites claros y rasgos sutiles que suelen pasarse por alto en las interpretaciones manuales. Este enfoque refuerza la hipótesis de que los cuerpos salinos poseen una firma textural distintiva en el espacio de características GLCM y muestra el potencial del aprendizaje no supervisado interpretable para complementar el trabajo de los expertos en tectónica salina.
Publication Facts
Reviewer profiles N/D
Author statements
- Editor & editorial board
- profiles
- Academic society
- Geofísica Internacional
Para obtener más información sobre un dato, haga clic
PF is maintained by the Public Knowledge Project
Detalles del artículo
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Citas
Babakhin, Y., Sanakoyeu, A., & Kitamura, H. (2019). Semi-supervised segmentation of salt bodies in seismic images using an ensemble of convolutional neural networks. [Presentación de paper] Pattern Recognition: 41st DAGM German Conference, DAGM GCPR 2019, Dortmund, Germany, September 10--13, 2019, Proceedings 41, 218–231. doi: https://doi.org/10.1007/978-3-030-33676-9_15 DOI: https://doi.org/10.1007/978-3-030-33676-9_15
Berthelot, A., Solberg, A. H. S., & Gelius, L.-J. J. (2013). Texture attributes for detection of salt. Journal of Applied Geophysics, 88, 52-69. doi: https://doi.org/10.1016/j.jappgeo.2012.09.006 DOI: https://doi.org/10.1016/j.jappgeo.2012.09.006
Berthelot, A., Solberg, A. H. S., Morisbak, E., & Gelius, L.-J. (2011). Salt diapirs without well defined boundaries--a feasibility study of semi-automatic detection. Geophysical Prospecting, 59(4), 682–696. doi: https://doi.org/10.1111/j.1365-2478.2011.00950.x DOI: https://doi.org/10.1111/j.1365-2478.2011.00950.x
Cavalin, P., & Oliveira, L. S. (2017). A review of texture classification methods and databases. 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T), 1–8. doi: 10.1109/SIBGRAPI-T.2017.10. DOI: https://doi.org/10.1109/SIBGRAPI-T.2017.10
Chopra, S., & Alexeev, V. (2006). Applications of texture attribute analysis to 3D seismic data. The Leading Edge, 25(8), 934–940. doi: https://doi.org/10.1190/1.2335155 DOI: https://doi.org/10.1190/1.2335155
Cohen, I., Coult, N., & Vassiliou, A. A. (2006). Detection and extraction of fault surfaces in 3D seismic data. Geophysics, 71(4), P21--P27. doi: https://doi.org/10.1190/1.2215357 DOI: https://doi.org/10.1190/1.2215357
Couder-Castañeda, C., Orozco-Del-Castillo, M., Padilla-Perez, D., & Medina, I. (2025). A parallel texture-based region-growing algorithm implemented in OpenMP. Scientific Reports, 15(1), 5563. doi: https://doi.org/10.1038/s41598-025-89960-8 DOI: https://doi.org/10.1038/s41598-025-89960-8
Di, H., Shafiq, M., & AlRegib, G. (2018). Multi-attribute k-means clustering for salt-boundary delineation from three-dimensional seismic data. Geophysical Journal International, 215(3), 1999–2007. doi: https://doi.org/10.1093/gji/ggy376 DOI: https://doi.org/10.1093/gji/ggy376
Farrokhnia, F., Kahoo, A. R., & Soleimani, M. (2018). Automatic salt dome detection in seismic data by combination of attribute analysis on CRS images and IGU map delineation. Journal of Applied Geophysics, 159, 395–407. doi: https://doi.org/10.1016/j.jappgeo.2018.09.018 DOI: https://doi.org/10.1016/j.jappgeo.2018.09.018
Gao, D. (2004). Texture model regression for effective feature discrimination: Application to seismic facies visualization and interpretation. Geophysics, 69(4), 958–967. doi: https://doi.org/10.1190/1.1778239 DOI: https://doi.org/10.1190/1.1778239
Geng, Z., Hu, Z., Wu, X., Liang, L., & Fomel, S. (2022). Semisupervised salt segmentation using mean teacher. Interpretation, 10(3), SE21–SE29. doi: https://doi.org/10.1190/INT-2021-0191.1 DOI: https://doi.org/10.1190/INT-2021-0191.1
Hall-Beyer, M. (2000). GLCM texture: a tutorial. National Council on Geographic Information and Analysis Remote Sensing Core Curriculum, 3(1), 75. doi: http://dx.doi.org/10.13140/RG.2.2.12424.21767
Ji, X., BenHasan, N., Luo, Y., Gashawbeza, E., & Saleh, S. M. (2020). Recognition of salt zones in 3D seismic images using machine learning. SEG Technical Program Expanded Abstracts, 1626-1630. doi: https://doi.org/10.1190/segam2020-3426105.1 DOI: https://doi.org/10.1190/segam2020-3426105.1
Jones, I. F., & Davison, I. (2014). Seismic imaging in and around salt bodies. Interpretation, 2(4), SL1-SL20. doi: https://doi.org/10.1190/INT-2014-0033.1 DOI: https://doi.org/10.1190/INT-2014-0033.1
Lomask, J., Biondi, B., & Shragge, J. (2004). Image segmentation for tracking salt boundaries. SEG Technical Program Expanded Abstracts 2004, October, 2443–2446. doi: https://doi.org/10.1190/1.1851242 DOI: https://doi.org/10.1190/1.1851242
Love, P. L., & Simaan, M. (1985). Segmentation of a seismic section using image processing and artificial intelligence techniques. Pattern Recognition, 18(6), 409–419. doi: https://doi.org/10.1016/0031-3203(85)90011-1 DOI: https://doi.org/10.1016/0031-3203(85)90011-1
Musgrave, M. J. P. (1960). Reflexion and refraction of plane elastic waves at a plane boundary between aeolotropic media. Geophysical Journal International, 3(4), 406–418. doi: https://doi.org/10.1111/j.1365-246X.1960.tb01714.x DOI: https://doi.org/10.1111/j.1365-246X.1960.tb01714.x
Ng, I., Kittler, J., & Illingworth, J. (1993). Supervised Segmentation Using a Multiresolution Data Representation. Signal Processing, 31(2), 133–163. doi: https://doi.org/10.1016/0165-1684(93)90062-F DOI: https://doi.org/10.1016/0165-1684(93)90062-F
Orozco‐del‐Castillo, M. G., Cárdenas‐Soto, M., Ortiz‐Alemán, C., Couder‐Castañeda, C., Urrutia‐Fucugauchi, J., & Trujillo‐Alcántara, A. (2017). A texture‐based region growing algorithm for volume extraction in seismic data. Geophysical Prospecting, 65(1), 97–105. doi: https://doi.org/10.1111/1365-2478.12381 DOI: https://doi.org/10.1111/1365-2478.12381
Orozco-del-Castillo, M. G., Ortiz-Alemán, C., Urrutia-Fucugauchi, J., & Rodríguez-Castellanos, A. (2011). Fuzzy logic and image processing techniques for the interpretation of seismic data. Journal of Geophysics and Engineering, 8(2), 185–194. Doi: https://doi.org/10.1088/1742-2132/8/2/006 DOI: https://doi.org/10.1088/1742-2132/8/2/006
Patterson, J., & Gibson, A. (2017). Deep learning: A practitioner’s approach. O’Reilly Media, Inc.
Ratcliff, D. W., Gray, S. H., & Whitmore Jr, N. D. (1992). Seismic imaging of salt structures in the Gulf of Mexico. The Leading Edge, 11(4), 15–31. doi: https://doi.org/10.1190/1.1436876 DOI: https://doi.org/10.1190/1.1436876
Steklain, A. F., Ganacim, F., Adames, M. R., Gonçalves, J. L., & Oliveira, D. S. (2022). Structure-oriented filtering in unsupervised multiattribute seismic facies analysis. The Leading Edge, 41(6), 411–4171. doi: https://doi.org/10.1190/tle41060411.1 DOI: https://doi.org/10.1190/tle41060411.1
Tan, P.-N., Steinbach, M., & Kumar, V. (2016). Introduction to data mining. Pearson Education India.
Tavakolizadeh, N., & Bagheri, M. (2022). Multi-attribute Selection for Salt Dome Detection Based on SVM and MLP Machine Learning Techniques. Natural Resources Research, 31(1), 353–370. doi: https://doi.org/10.1007/s11053-021-09973-8 DOI: https://doi.org/10.1007/s11053-021-09973-8
Wang, Q., Wang, C., Feng, Z., & Ye, J. (2012). Review of K-means clustering algorithm. Electronic Design Engineering, 20(7), 21–24.
West, B. P., May, S. R., Eastwood, J. E., & Rossen, C. (2002).
Interactive seismic facies classification using textural attributes and neural networks. The Leading Edge, 21(10), 1042–1049. doi: https://doi.org/10.1190/1.1518444 DOI: https://doi.org/10.1190/1.1518444
Xu, Z., Li, K., Yin, R., Fan, Y., & Ma, J. (2025). 3D Saltseg-CL: Unsupervised embedding characterization based multi-task dense prediction method for 3D salt bodies. Expert Systems with Applications, 267, 126249. doi: https://doi.org/10.1016/j.eswa.2024.126249 DOI: https://doi.org/10.1016/j.eswa.2024.126249
Zhang, Z., Zhu, Q., & others. (2012). Fuzzy time series forecasting based on k-means clustering. Open Journal of Applied Sciences, 2(04), 100–103. doi: http://dx.doi.org/10.4236/ojapps.2012.24B024 DOI: https://doi.org/10.4236/ojapps.2012.24B024