1887

Abstract

Summary

The problem of rocks thermal conductivity determination from well-logging data is highly important for many branches of petroleum geology and geophysics (basin modelling, thermal EOR modelling, thermal logging interpretation, etc.). Literature review revealed that there are only several studies performed to assess the applicability of neural network-based algorithms to predict rock thermal conductivity from well-logging data. In this research, we aim to define the most effective machine-learning algorithms for well-log based determination of rock thermal conductivity. Well-logging data acquired at a heavy oil reservoir together with results of thermal logging on cores extracted from two wells were the basis for our research. Eight different regression models were developed and tested to predict vertical variations of rock conductivity from well-logging data. Among considered machine-learning techniques, the Random Forest algorithm was found to be the most accurate at well-log based determination of rock thermal conductivity. From a comparison of the thermal conductivity depth profile predicted from well-logging data with the experimental data it can be concluded that thermal conductivity can be determined with a total relative uncertainty of 11.5%. The available data allows concluding that machine-learning algorithms are a promising framework for accurate well-log based predictions of rock thermal conductivity.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202054002
2020-10-19
2024-03-28
Loading full text...

Full text loading...

References

  1. 1.Breiman, L. [2001] Random forests. Mach. Learn., 45(1), 5–32.
    [Google Scholar]
  2. 2.Chekhonin, Е., Peshkov, G., Myasnikov, A., Rupke, L., Podladchikov, Y., Musikhin, K., Shuvaev, A. Bogdanov, O. Kostenko, O. [2017] Automated thermal history reconstruction of basin in West Siberia using 2D inverse modeling (in Russian). Proc. Geomodel-2017. doi:10.3997/2214‑4609.201702248.
    https://doi.org/10.3997/2214-4609.201702248 [Google Scholar]
  3. 3.Freund, Y. & Schapire, R.E. [1997] A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci., 55(1), 119–139.
    [Google Scholar]
  4. 4.Friedman, H. [1999]. Stochastic gradient boosting. Comput. Stat. Data Anal., 38, 367–378.
    [Google Scholar]
  5. 5.Fuchs, S., Balling, N., Forster, A. [2015] Calculation of thermal conductivity, thermal diffusivity and specific heat capacity of sedimentary rocks using petrophysical well logs. Geophys. J. Int., 203, 1977–2000.
    [Google Scholar]
  6. 6.Gasior, I. & Przelaskowska, A. [2014] Estimating thermal conductivity from core and well log data. Acta Geophys., 62(4), 785–801.
    [Google Scholar]
  7. 7.Goutorbe, B., Lucazeau, F., Bonneville, A. [2006] Using neural networks to predict thermal conductivity from geophysical well logs. Geophys. J. Int., 166(1), 115–125.
    [Google Scholar]
  8. 8.Hartmann, A., Pechnig, R. Clauser, C. [2008] Petrophysical analysis of regional-scale thermal properties for improved simulations of geothermal installations and basin-scale heat and fluid flow. Int. J. Earth Sci., 97, 421–433, doi.org/10.1007/s00531‑007‑0283‑y.
    https://doi.org/10.1007/s00531-007-0283-y [Google Scholar]
  9. 9.Hinton, G. [1989] Connectionist learning procedures. Artif. Intell., 40, 185–234.
    [Google Scholar]
  10. 10.Larose, D. [2014] Discovering Knowledge in Data: An Introduction to Data Mining. Wiley.
    [Google Scholar]
  11. 11.Meshalkin, Y., Koroteev, D., Popov, E., Chekhonin, E., Popov, Yu. [2018] Robotized petrophysics: Machine learning and thermal profiling for automated mapping of lithotypes in unconventionals. Journal of Petroleum Science and Engineering, 167, 10.1016/j.petrol.2018.03.110.
    https://doi.org/10.1016/j.petrol.2018.03.110 [Google Scholar]
  12. 12.Meshalkin, Y., Shakirov, A., Popov, E., Koroteev, D., Gurbatova, I. [2020] Robust well-log based determination of rock thermal conductivity through machine learning. Geophysical Journal International, 222 (2), 978–988, https://doi.org/10.1093/gii/ggaa209.
    [Google Scholar]
  13. 13.Pierre, G., Damien, E., Lois, W. [2006] Extremely randomized trees. Artif. Intell., 63, 3–42.
    [Google Scholar]
  14. 14.Popov, E., Chekhonin, E., Safonov, S., Ursegov, S., Gurbatova, I. [2016] Core thermal profiling application to additional geology structure appraisal of Permian-Carboniferous deposits at Usinsk oilfield. Geology and Exploration, 6, 38–49.
    [Google Scholar]
  15. 15.Popov, Y. [2012] Evolution in the reliability of experimental geothermal data. Proc. Australian Geothermal Energy Conf., 138–146.
    [Google Scholar]
  16. 16.Popov, Y., Beardsmore, G., Clauser, C., Roy, S. [2016] ISRM Suggested Methods for Determining Thermal Properties of Rocks from Laboratory Tests at Atmospheric Pressure. Rock Mech. and Rock Eng., 49, 4179–4207.
    [Google Scholar]
  17. 17.Popov, Y., Spasennykh, M., Valiullin, R., Yarullin, R., Ramazanov, A., Zagranovskaya, D., Zakharova, O., Golovanova, I., Chekhonin, E., Savelev, E., Gabova, A., Popov, E., Shakirov, A. [2018] First experience of maintenance of basin modeling with up-to-date complex of experimental geothermic investigations (in Russian). Proc.Geomodel-2018, doi:10.3997/2214‑4609.201802427.
    https://doi.org/10.3997/2214-4609.201802427 [Google Scholar]
  18. 18.Pribnow, D., Williams, C.F., Burkhardt, H. [1993] Well log-derived estimates of thermal conductivity in crystalline rocks penetrated by the 4-KM deep KTB Vorbohrung. Geoph. Res. Let., 20(12), 1155–1158.
    [Google Scholar]
  19. 19.Rasmussen, C. & Williams, C. [2006] Gaussian Processes for Machine Learning. The MIT Press.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202054002
Loading
/content/papers/10.3997/2214-4609.202054002
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error