Classification of Well Log Data Using Vanishing Component Analysis

Abstract

This study reports the application of the novel supervised learning approach called vanishing component analysis (VCA) for the classification of lithologies from well log signal data. Geophysical well log data is always non-linear due to anisotropy and heterogeneity of the earth. The main purpose of this study is to test the applicability of the VCA algorithm on non-linear geophysical data of Siraj South-01, Middle Indus Basin, Pakistan for classification of lithologies/facies. We demonstrate the performance and stability of the novel approach on a case study before applying it on well log data. Our analysis demonstrates that VCA algorithm is able to linearly separate such a complex non-linear well log data and clearly distinguish between different classes of well log data coming from different rock units. Furthermore, we show that the average accuracies of the classification methods of linear support vector machines, eXtreme gradient boosting, random forest, neural network and linear discriminant analysis on the VCA feature space are much better than the average accuracy obtained by the same methods on the original data.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

References

  1. Abbasi, S. A., Kalwar, Z., & Solangi, S. H. (2016). Study of structural styles and hydrocarbon potential of RajanPur area, middle indus Basin, Pakistan. BU J ES,1(1), 36–41.

    Google Scholar 

  2. Abbasi, A. H., Mehmood, F., & Kamal, M. (2014). Shale oil and gas: Lifeline for Pakistan (pp. 85–87). Islamabad: Sustainable Development Policy Institute.

    Google Scholar 

  3. Ali, A., Alves, T. M., Saad, F. A., Ullah, M., Toqeer, M., & Hussain, M. (2018). Resource potential of gas reservoirs in South Pakistan and adjacent Indian subcontinent revealed by post-stack inversion techniques. Journal of Natural Gas Science and Engineering,49, 41–55.

    Article  Google Scholar 

  4. Ali, A., Hussain, M., Rehman, K., & Toqeer, M. (2016). Effect of shale distribution on hydrocarbon sands integrated with anisotropic rock physics for AVA modelling: A case study. Acta Geophysica,64(4), 1139–1163.

    Article  Google Scholar 

  5. Alves, T. M., Kurtev, K., Moore, G. F., & 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 Bulletin,98(4), 793–824.

    Article  Google Scholar 

  6. Anxionnaz, H., Delfiner, P., & Delhomme, J. P. (1990). Computer-generated corelike descriptions from open-hole logs (1). AAPG Bulletin,74(4), 375–393.

    Google Scholar 

  7. Aster, R. C., Borchers, B., & Thurber, C. H. (2005). Parameter estimation and inverse problems. Oxford: Elsevier.

    Google Scholar 

  8. Aziz, O., Hussain, T., Ullah, M., Bhatti, A. S., & Ali, A. (2018). Seismic based characterization of total organic content from the marine Sembar shale, Lower Indus Basin, Pakistan. Marine Geophysical Research,39(4), 491–508.

    Article  Google Scholar 

  9. Baldwin, J. L., Bateman, R. M., & Wheatley, C. L. (1990). Application of a neural network to the problem of mineral identification from well logs. The Log Analyst,31(05), 279–293.

    Google Scholar 

  10. Bender, F. K., & Raza, H. A. (1995). Geology of Pakistan. Cambridge: Cambridge University Press.

    Google Scholar 

  11. Burke, J. A., Campbell Jr, R. L., & Schmidt, A. W. (1969). The lithoporosity crossplot: Society of professional well log analysts tenth annual logging symposium transactions, pp. 1–29.

  12. Chenping, H., Feiping, N., & Dacheng, T. (2016). Discriminative vanishing component analysis. In Proceeding of the thirtieth AAAI conference on artificial intelligence.

  13. Collinson, J. D. (1969). The sedimentology of the Grindslow shales and the kinderscout Grit: A deltaic complex in the Namurian of northern England. Journal of Sedimentary Petrology,39, 194–221.

    Google Scholar 

  14. Cox, D. A., Little, J., & O’Shea, D. (2007). Ideals, varieties, and algorithms: An introduction to computational algebraic geometry and commutative algebra. Berlin: Springer.

    Google Scholar 

  15. Doveton, J. H. (1986). Log analysis of subsurface geology: Concepts and computer methods (p. 273). New York: Wiley.

    Google Scholar 

  16. Doveton, J. H. (1994). Geological log analysis using computer methods. Journal of Petroleum Science and Engineering,12(2), 168–169.

    Google Scholar 

  17. Ellis, D. V., & Singer, J. M. (2007). Well logging for earth scientists. Berlin: Springer.

    Google Scholar 

  18. Griffiths, C. H., & Bakke, S. (1988). Semi-automated well matching using gene-typing algorithms and a numerical lithology derived from wire-line logs. In SPWLA 29th Annual Logging Symposium. Society of Petrophysicists and Well-Log Analysts, pp. 1–24.

  19. Guguen, Y., & Palciauskas, V. (1994). Introduction to the physics of rocks. Princeton: Princeton University Press.

    Google Scholar 

  20. Hall, B. (2016). Facies classification using machine learning. The Leading Edge. Geophisical tutorial. Octuber 2016.

  21. Harilal, Biswal, S. K., Sood, A., & Rangachari, V. (2008). Identification of reservoir facies within a carbonate and mixed carbonate-siliciclastic sequence: Application of seismic stratigraphy, seismic attributes, and 3D visualization. The Leading Edge,27(1), 18–29.

    Article  Google Scholar 

  22. Humphreys, B., & Lott, G. K. (1990). An investigation into nuclear log responses of North Sea Jurrasic reservoirs using mineralogical analysis. In A. Hurst, M. A. Lovell, & A. C. Morton (Eds.), Geological applications of well logs (Vol. 48, pp. 223–240). London: Geological Society of London Special Publication.

    Google Scholar 

  23. Hurst, A., Lovell, M. A., & Morton, A. C. (1990). Geological application of wire-line logs. Geological Society of London Special Publication,48, 357–371.

    Article  Google Scholar 

  24. Kazmi, A. H., & Abbasi, I. A. (2008). Stratigraphy & historical geology of Pakistan (p. 524). Department & National Centre of Excellence in Geology.

  25. Kazmi, A. H., & Snee, L. W. (1989). Geology of world emerald deposits: A brief review (pp. 165–228). The Netherland: Van Nostrand Reinhold publishers.

    Google Scholar 

  26. Krygowski. D.A. (2003). Guide to petrophysical interpretation: Austin Texas USA.

  27. Li, P., & Zhang, Y. (2001). Facies characterization of a reservoir in the North sea using machine learning techniques. Geophysics,66, 1157–1176.

    Article  Google Scholar 

  28. Liu, S., Zhan, R., Zhang, J., & Zhuang, Z. (2014). Radar automatic target recognition based on sequential vanishing component analysis. Progress in Electromagnetics Research,145, 241–250.

    Article  Google Scholar 

  29. Livni, R., Lehavi, D., Schein, S., Nachliely, H., Shalev-Shwartz, S., & Globerson, A. (2013). Vanishing component analysis. In Proceedings of the 30th International Conference on Machine Learning (ICML-13) (pp. 597–605).

  30. Moline, G. R., Drzewiecki, P. A., & Bahr, J. M. (1991). Identification and characterization of pressure seals through the use of wireline logs: A multivariate statistical approach. AAPG Bulletin Log Analyst,33(4), 362–372.

    Google Scholar 

  31. Mollajan, A., Memarian, H., & Nabi-Bidhendi, M. (2018). Fuzzy classifier fusion: An application to reservoir facies identification. Neural Computing and Applications,30, 825–834.

    Article  Google Scholar 

  32. Mwenifumbo, C. J. (1993). Kernel density estimation in the analysis and of borehole geophysical data. The Log Analyst,34(05), 34–45.

    Google Scholar 

  33. Passey, Q.R., Creaney, S., Kulla, J.B., Moretti, F.J., & Stroud, J.D. (1990). A practical Model for the Organic richness from porosity and resistivity logs. American association of petroleum geologists (AAPG) Bulletin, Vol. 74.

  34. Raynolds, A. D. (1993). Sequence Stratigraphy from core and wire-line log data: The Viking Formation, Albian, South central Alberta, and Canada. Marine and Petroleum Geology,11, 258–282.

    Article  Google Scholar 

  35. Rider, M. (2002). The geological interpretation of well logs (2nd ed.). London: Rider-French Consulting Limited.

    Google Scholar 

  36. Rita, J., Sanjeev, L., Manoj, K., Bharat, S., Asim, S., & Cewell, O. (2013). A new approach to interpret Shaly/Silty reservoirs. In 10th Biennial international conference and exposition, pp 53–59.

  37. Serra, O. E. (1983). Fundamentals of well-log interpretation. United States: N. p., Web.

    Google Scholar 

  38. Serra, O. T., & Abbott, H. T. (1982). The contribution of logging data to sedimentology and stratigraphy. Society of Petroleum Engineers Journal,22(01), 117–131.

    Article  Google Scholar 

  39. Tarantola, A. (2005). Inverse problem theory and methods for model parameter estimation. Philadelphia: Society for Industrial and Applied Mathematics.

    Google Scholar 

  40. Tiab, D., & Donaldson, E. C. (2015). Petrophysics: Theory and practice of measuring reservoir rock and fluid transport properties. Houston: Gulf Professional Publishing.

    Google Scholar 

  41. Van Wagoner, J. C., Mitchum, R. M., Campion, K. M., & Rahmanian, V. D. (1990). Siliciclastic sequence stratigraphy in well logs, cores, and outcrops: Concepts for high-resolution correlation of time and facies. III-55.

  42. Walker, R. G., & James, N. P. (1992). Facies models “Response to sea-level Change”. Geological Association of Canada,992, 7–23.

    Google Scholar 

  43. Wolf, M. & Pelissier-Combescure, J. (1982). Faciolog-automatic electrofacies determination. In SPWA 23rd annual logging symposium. Society of petrophysicists and well log analysts, pp 1–23.

  44. Zhang, X. (2018). Improvement on the vanishing component analysis by grouping strategy. Journal of Wireless Networking,2018, 111. https://doi.org/10.1186/s13638-018-1112-7.

    Article  Google Scholar 

Download references

Acknowledgements

We thank the anonymous referees for their valuable comments and suggestions. The authors thank the Directorate General of Petroleum Concessions (DGPC), Pakistan, being a data source for this work. The authors would also like to thank Hiroshi Tsukahara for making the Matlab code available and for useful scientific discussions.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Aamir Ali.

Ethics declarations

Conflict of interest

The authors declare that they do not have any conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix: Matlab Code for the Toy Example

Appendix: Matlab Code for the Toy Example

figurec
figured

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Hayat, U., Ali, A., Murtaza, G. et al. Classification of Well Log Data Using Vanishing Component Analysis. Pure Appl. Geophys. 177, 2719–2737 (2020). https://doi.org/10.1007/s00024-019-02374-2

Download citation

Keywords

  • Vanishing component analysis
  • feature extraction
  • classification of lithologies
  • classification algorithms
  • reservoir
  • geophysical logs