Semi-Supervised Multi-Facies Object Retrieval in Seismic Data

  • Pauline Le BouteillerEmail author
  • Jean Charléty


Characterizing buried sedimentary structures through the use of seismic data is part of many geoscientific projects. The evolution of seismic acquisition and processing capabilities has made it possible to acquire ever-growing amounts of data, increasing the image resolution so that sedimentary objects (geobodies) can be imaged with greater precision within sedimentary layers. However, exploring and interpreting them in large datasets can be tedious work. Recent practice has shown the potential of automated methods to assist interpreters in this task. In this paper, a new semi-supervised methodology is presented for identifying multi-facies geobodies in three-dimensional seismic data, while preserving their internal facies variability and keeping track of the input uncertainty. The approach couples a nonlinear data-driven method with a novel supervised learning method. It requires a prior delineation of the geobodies on a few seismic images, along with a priori confidence in that delineation. The methodology relies on a learning of an appropriate data representation, and propagates the prior confidence to posterior probabilities attached to the final delineation. The proposed methodology was applied to three-dimensional real data, showing consistently effective retrieval of the targeted multi-facies geobodies mass-transport deposits in the present case.


Seismic interpretation Object recognition Semi-supervised analysis Multi-facies geobody 



The authors are grateful to the CGG Houston office for the provision of and permission to publish data, and to Karine Labat for proofreading the article.


  1. Alves TM, Kurtev K, Moore GF, Strasser M (2014) Assessing the internal character, reservoir potential, and seal competence of mass-transport deposits using seismic texture: a geophysical and petrophysical approach. AAPG Bull 98(4):793–824. CrossRefGoogle Scholar
  2. Berthelot A, Solberg AH, Gelius LJ (2013) Texture attributes for detection of salt. J Appl Geophys 88:52–69. CrossRefGoogle Scholar
  3. Bishop CM, Svensén M, Williams CKI (1998) GTM: the generative topographic mapping. Neural Comput 10(1):215–234. CrossRefGoogle Scholar
  4. Chopra S, Marfurt KJ (2014) Seismic facies analysis using generative topographic mapping. In: Birkelo B (ed) SEG technical program expanded abstracts 2014, pp 1390–1394.
  5. Clausi DA, Zhao Y (2003) Grey level co-occurrence integrated algorithm (GLCIA): a superior computational method to rapidly determine co-occurrence probability texture features. Comput Geosci 29(7):837–850. CrossRefGoogle Scholar
  6. de Matos MC, Osorio PL, Johann PR (2007) Unsupervised seismic facies analysis using wavelet transform and self-organizing maps. Geophysics 72(1):P9–P21. CrossRefGoogle Scholar
  7. de Silva AM, Leong PHW (2015) Feature selection. In: de Silva AM, Leong PHW (eds) Grammar-based feature generation for time-series prediction. SpringerBriefs in applied sciences and technology. Springer, Singapore, pp 13–24. CrossRefGoogle Scholar
  8. Eichkitz CG, Davies J, Amtmann J, Schreilechner MG, de Groot P (2015) Grey level co-occurrence matrix and its application to seismic data. First Break 33:71–77Google Scholar
  9. Gao D (2008) Application of seismic texture model regression to seismic facies characterization and interpretation. Lead Edge 27(3):394–397CrossRefGoogle Scholar
  10. Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610–621. CrossRefGoogle Scholar
  11. Hashemi H, de Beukelaar P, Beiranvand B, Seiedali M (2017) Clustering seismic datasets for optimized facies analysis using a sscsom technique. In: 79th EAGE conference and exhibition 2017, proceedings. EAGE Publications BV, Netherlands.
  12. Kohonen T (1986) Learning vector quantization for pattern recognition: technical report TKK-F- A601. Helsinki University of TechnologyGoogle Scholar
  13. Le Bouteiller P, Charléty J (2018) Procédé pour la détection d’objets géologiques dans une image sismique (patent pending)Google Scholar
  14. Long Z, Alaudah Y, Qureshi MA, Farraj MA, Wang Z, Amin A, Deriche M, AlRegib G (2015) Characterization of migrated seismic volumes using texture attributes: a comparative study. In: Schneider RV (ed) SEG technical program expanded abstracts 2015, pp 1744–1748.
  15. Lu Y, Cohen I, Zhou XS, Tian Q (2007) Feature selection using principal feature analysis. In: Lienhart R, Prasad AR, Hanjalic A, Choi S, Bailey B, Sebe N (eds) The 15th international conference, p 301.
  16. Marroquín ID, Brault JJ, Hart BS (2009) A visual data-mining methodology for seismic facies analysis: part 1—testing and comparison with other unsupervised clustering methods. Geophysics 74(1):P1–P11. CrossRefGoogle Scholar
  17. Nivlet P (2007) Uncertainties in seismic facies analysis for reservoir characterisation or monitoring: causes and consequences. Oil Gas Sci Technol Rev IFP 62(2):225–235. CrossRefGoogle Scholar
  18. Ogiesoba O, Hammes U (2012) Seismic interpretation of mass-transport deposits within the upper oligocene frio formation, south Texas Gulf Coast. AAPG Bull 96(5):845–868. CrossRefGoogle Scholar
  19. Pitas I, Kotropoulos C (1992) A texture-based approach to the segmentation of seismic images. Pattern Recognit 25(9):929–945. CrossRefGoogle Scholar
  20. Qi J, Lin T, Zhao T, Li F, Marfurt K (2016) Semisupervised multiattribute seismic facies analysis. Interpretation 4(1):SB91–SB106. CrossRefGoogle Scholar
  21. Roy A, Romero-Peláez AS, Kwiatkowski TJ, Marfurt KJ (2014) Generative topographic mapping for seismic facies estimation of a carbonate wash, Veracruz basin, southern Mexico. Interpretation 2(1):SA31–SA47. CrossRefGoogle Scholar
  22. Shafiq MA, Wang Z, Amin A, Hegazy T, Deriche M, AlRegib G (2015) Detection of salt-dome boundary surfaces in migrated seismic volumes using gradient of textures. In: Schneider RV (ed) SEG technical program expanded abstracts 2015, pp 1811–1815.
  23. Shipp RC, Weimer P, Posamentier HW (eds) (2011) Mass-transport deposits in deepwater settings. SEPM (Society for Sedimentary Geology), Tusla. CrossRefGoogle Scholar
  24. Soille P (2010) Morphological image analysis: principles and applications, 2nd edn. Springer, BerlinGoogle Scholar
  25. Sokal RR, Rohlf FJ (1962) The comparison of dendrograms by objective methods. Taxon 11(2):33. CrossRefGoogle Scholar
  26. Taha AA, Hanbury A (2015) Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging 15:29. CrossRefGoogle Scholar
  27. Wang Z, Hegazy T, Long Z, AlRegib G (2015) Noise-robust detection and tracking of salt domes in postmigrated volumes using texture, tensors, and subspace learning. Geophysics 80(6):WD101–WD116. CrossRefGoogle Scholar
  28. Wang S, Yuan S, Yan B, He Y, Sun W (2016) Directional complex-valued coherence attributes for discontinuous edge detection. J Appl Geophys. CrossRefGoogle Scholar
  29. Ward JH (1963) Hierarchical grouping to optimize an objective function. J Am Stat Assoc 58(301):236–244. CrossRefGoogle Scholar
  30. West BP, May SR, Eastwood JE, Rossen C (2002) Interactive seismic facies classification using textural attributes and neural networks. Lead Edge 21(10):1042–1049. CrossRefGoogle Scholar
  31. Zhao T, Zhang J, Li F, Marfurt KJ (2016) Characterizing a turbidite system in Canterbury basin, New Zealand, using seismic attributes and distance-preserving self-organizing maps. Interpretation 4(1):SB79–SB89. CrossRefGoogle Scholar
  32. Zhao T, Li F, Marfurt KJ (2017) Constraining self-organizing map facies analysis with stratigraphy: an approach to increase the credibility in automatic seismic facies classification. Interpretation 5(2):T163–T171CrossRefGoogle Scholar

Copyright information

© International Association for Mathematical Geosciences 2019

Authors and Affiliations

  1. 1.IFP Energies NouvellesRueil-MalmaisonFrance
  2. 2.CNRS-INSU, Institut des Sciences de la Terre Paris, ISTeP UMR 719Sorbonne UniversitéParisFrance

Personalised recommendations