Applying spectral decomposition to seismic facies clustering with unsupervised machine learning

Ruslan Malikov; Gulam Babayev

doi:10.24028/gj.v47i3.320290

Authors

Ruslan Malikov Ministry of Science and Education of the Republic of Azerbaijan,Institute of Geology and Geophysics ”Seismology and seismic hazard assessment” Department,PhD student, Azerbaijan
Gulam Babayev Ministry of Science and Education of the Republic of Azerbaijan,Institute of Geology and Geophysics ”Seismology and seismic hazard assessment” Department,Associate Professor,Doctor in Earth Sciences, Azerbaijan

DOI:

https://doi.org/10.24028/gj.v47i3.320290

Keywords:

seismic facies, spectral decomposition, self-organizing map, continuous wavelet transform, unsupervised learning, machine learning

Abstract

Seismic facies analysis, essential for subsurface geological exploration, has traditionally challenged the ability to capture subtle variations in complex stratigraphic environments. This study uses spectral decomposition and unsupervised machine learning, specifically the Kohonen Self-Organizing Map, to improve the identification of detailed seismic facies. Spectral decomposition enables frequency-based seismic data analysis, capturing intricate geological features often missed by traditional methods. The Continuous Wavelet Transform was applied to decompose seismic signals, and the resulting frequency components were clustered using a Self-Organizing Map to classify seismic facies. This paper validated this approach using seismic data from the South Caspian Basin. The results successfully identified channel systems and facies boundaries, enhancing their delineation and enabling a more accurate interpretation of channel systems and their internal variability. This automated methodology offers valuable insights for reservoir characterization and hydrocarbon exploration, potentially reducing exploration risks and enhancing resource estimation

References

Addison, P.S. (2017). The Illustrated Wavelet Transform Handbook. CRC Press, 464 p. https://doi.org/10.1201/9781315372556.

Brown, A.R. (2011). Interpretation of Three-Dimensional Seismic Data. Society of Exploration Geophysicists and American Association of Petroleum Geologists, 665 p. https://doi.org/10.1190/1.9781560802884.

Castagna, J.P., Sun, S., & Siegfried, R.W. (2003). Instantaneous spectral analysis: Detection of low-frequency shadows associated with hydrocarbons. The Leading Edge, 22(2), 120—127. https://doi.org/10.1190/1.1559038.

Chakraborty, A., & Okaya, D. (1995). Frequency‐time decomposition of seismic data using wavelet‐based methods. Geophysics, 60(6), 1906—1916. https://doi.org/10.1190/1.1443922.

Chopra, S., & Marfurt, K.J. (2008). Emerging and future trends in seismic attributes. The Leading Edge, 27(3), 298—318. https://doi.org/10.1190/1.2896620.

de Matos, M.C., Osorio, P.L., & Johann, P.R. (2006). Unsupervised seismic facies analysis using wavelet transform and self-organizing maps. Geophysics, 72(1), P9—P21. https://doi.org/10.1190/1.2392789.

Guo, H., Marfurt, K.J., & Liu, J. (2009). Principal component spectral analysis. Geophysics, 74(4), P35—P43. https://doi.org/10.1190/1.3119264.

Huang, Y., Zheng, X., Duan, Y., & Luan, Y. (2018). Robust time-frequency analysis of seismic data using general linear chirplet transform. Geophysics, 83(3), V197—V214. https://doi.org/10.1190/geo2017-0145.1.

Kazemeini, S.H., Juhlin, C., Zinck‐Jørgensen, K., & Norden, B. (2008). Application of the continuous wavelet transform on seismic data for mapping of channel deposits and gas detection at the CO2SINK site, Ketzin, Germany. Geophysical Prospecting, 57(10), 111—123. https://doi.org/10.1111/j.1365-2478.2008.00723.x.

Kaz’min, V.G., & Verzhbitskii, E.V. (2011). Age and origin of the South Caspian Basin. Oceanology, 51(1), 131—140. https://doi.org/10.1134/s0001437011010073.

Kohonen, T. (1982). Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43(1), 59—69. https://doi.org/10.1007/bf00337288.

Kourki, M., & Ali Riahi, M. (2014). Seismic facies analysis from pre-stack data using self-organizing maps. Journal of Geophysics and Engineering, 11(6), 065005. https://doi.org/10.1088/1742-2132/11/6/065005.

Meyer, S.G., Reading, A.M., & Bassom, A.P. (2022). The use of weighted self-organizing maps to interrogate large seismic data sets. Geophysical Journal International, 231(3), 2156—2172. https://doi.org/10.1093/gji/ggac322.

Naseer, M.T. (2021). Seismic attributes and quantitative stratigraphic simulation’ application for imaging the thin-bedded incised valley stratigraphic traps of Cretaceous sedimentary fairway, Pakistan. Marine and Petroleum Geology, 134, 105336. https://doi.org/10.1016/j.marpetgeo.2021.105336.

Ngui, W.K., Leong, M.S., Hee, L.M., & Abdelrhman, A.M. (2013). Wavelet Analysis: Mother Wavelet Selection Methods. Applied Mechanics and Materials, 393, 953—958. https://doi.org/10.4028/www.scientific.net/amm.393.953.

Qodri, M.N., Mulyani, M.C., Kaisagara, A.W., Sukmono, S., & Ambarsari, D.S. (2019). Evaluation of Continuous Wavelet Transform (CWT) Attribute in Analysis of Gas Reservoir Distribution on Talang Akar Reservoir in «QDR» Field of Northwest Java Basin. IOP Conference Series: Earth and Environmental Science (Vol. 318, Is. 1, 012043). https://doi.org/10.1088/1755-1315/318/1/012043.

Partyka, G., Gridley, J., & Lopez, J. (1999). Interpretational applications of spectral decomposition in reservoir characterization. The Leading Edge, 18(3), 353—360. https://doi.org/10.1190/1.1438295.

Ray, A.K., Khoudaiberdiev, R., Bennett, C., Bhatnagar, P., Boruah, A., Dandapani, R., Maiti, S., & Verma, S. (2022). Attribute-assisted interpretation of deltaic channel system using enhanced 3D seismic data, offshore Nova Scotia. Journal of Natural Gas Science and Engineering, 99, 104428. https://doi.org/10.1016/j.jngse. 2022.104428.

Roden, R., Smith, T., & Sacrey, D. (2015). Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing maps. Interpretation, 3(4), SAE59—SAE83. https://doi.org/10.1190/int-2015-0037.1.

Shan, X., Tian, F., Cheng, F., Yang, C., & Xin, W. (2019). Spectral Decomposition and a Waveform Cluster to Characterize Strongly Heterogeneous Paleokarst Reservoirs in the Tarim Basin, China. Water, 11(2), 256. https://doi.org/ 10.3390/w11020256.

Sinha, S., Routh, P.S., Anno, P.D., & Castagna, J.P. (2005). Spectral decomposition of seismic data with continuous-wavelet transform. Geophysics, 70(6), P19—P25. https://doi.org/10. 1190/1.2127113.

Smith, L.S.(2006).Oligocene-Miocene Maykop/Diatom total petroleum system of the South Caspian Basin province, Azerbaijan, Iran, and Turkmenistan. U.S. Geological Survey, Bulletin, 2201-I, 27 p.https://doi.org/10.3133/b2201I.

Song, C., Liu, Z., Wang, Y., Li, X., & Hu, G. (2017). Multi-waveform classification for seismic facies analysis. Computers & Geosciences, 101, 1—9. https://doi.org/10.1016/j.cageo.2016.12.014.

von Hartmann, H., Buness, H., Krawczyk, C.M., & Schulz, R. (2012). 3-D seismic analysis of a carbonate platform in the Molasse Basin — reef distribution and internal separation with seismic attributes. Tectonophysics, 572-573, 16—25. https://doi.org/10.1016/j.tecto.2012.06.033.

Wrona, T., Pan, I., Gawthorpe, R.L., & Fossen, H. (2018). Seismic facies analysis using machine learning. Geophysics, 83(5), O83—O95. https://doi.org/10.1190/geo2017-0595.1.

Wu, L., & Castagna, J. (2017). S-transform and Fourier transform frequency spectra of broadband seismic signals. Geophysics, 82(5), O71—O81). https://doi.org/10.1190/geo2016-0679.1.

Zhao, T., Zhang, J., Li, F., & Marfurt, K.J. (2016). Characterizing a turbidite system in Canterbury Basin, New Zealand, using seismic attributes and distance-preserving self-organizing maps. Interpretation, 4(1), SB79—SB89. https://doi.org/10.1190/int-2015-0094.1.

Zhou, J., & Fu, Y. (2005). Clustering High-Dimensional Data Using Growing SOM. In Lecture Notes in Computer Science (pp. 63—68). Springer Berlin Heidelberg. https://doi.org/10.1007/11427445_11.

Zhu, Z., Chen, X., Ren, H., Tao, L., Jiang, J., Wang, T., Cheng, M., Ding, S., & Du, R. (2022). Seismic Facies Analysis Using the Multiattribute SOM-K-Means Clustering. In D. Zhang (Ed.), Computational Intelligence and Neuroscience (Vol. 2022, pp. 1—11). HindawiLimited. https://doi.org/10.1155/2022/1688233.