Практичний зміст елементів петрофізичної моделі теригенних пісковиків-колекторів нафти і газу в методах нейронних мереж, глибинного навчання та регресії

Serhiy Vyzhva; Andriy Gozhyk; Oleksandr Shabatura; Viktor Onyshchuk; Dmytro Onyshchuk; Ivan Onyshchuk

doi:10.24028/gj.v47i3.309312

Authors

Serhiy Vyzhva Taras Shevchenko National University of Kyiv, Institute of Geology, Kyiv, Ukraine, Ukraine
Andriy Gozhyk Taras Shevchenko National University of Kyiv, Institute of Geology, Kyiv, Ukraine, Ukraine
Oleksandr Shabatura Taras Shevchenko National University of Kyiv, Institute of Geology, Kyiv, Ukraine, Ukraine
Viktor Onyshchuk Taras Shevchenko National University of Kyiv, Institute of Geology, Kyiv, Ukraine, Ukraine
Dmytro Onyshchuk Taras Shevchenko National University of Kyiv, Institute of Geology, Kyiv, Ukraine, Ukraine
Ivan Onyshchuk Taras Shevchenko National University of Kyiv, Institute of Geology, Kyiv, Ukraine, Ukraine

DOI:

https://doi.org/10.24028/gj.v47i3.309312

Keywords:

petrophysics, terrigenous oil and gas reservoirs, multiple regression, machine learning, neural networks

Abstract

An important problem in the search for oil and gas fields is the ability to predict key petrophysical properties such as porosity, permeability, etc. Along with traditional regression analysis, neural network methods and deep learning technologies are becoming increasingly common. All of them require verification of the efficiency of the petrophysical model, i.e. the ability to correctly predict the desired value with the least errors based on selected sets of independent petrophysical data.

The object of study was samples of Lower Carboniferous sandstones of deep horizons (interval 4931—5879 m) from 14 wells of promising formations of the northwestern part of the Dnipro-Donetsk Basin (Bakumivska, Zorkivska, Voloshkivska, Komyshnyanska, Chervonozavodska, Lutsenkivska, Piskivska and Chervonolutska areas). Nine families of geological and petrophysical characteristics were used as independent search features, for which effective approximations of multiple regression were obtained, and their informative weight was determined. In total, 38 empirical regression equations were obtained that can be used to predict the key reservoir characteristics of terrigenous reservoir rocks (effective porosity, permeability, residual water saturation, etc.).

The residual water saturation ratio and effective porosity are traditionally effectively predicted by a simple linear regression model using petrodensity, petroelectric, petro-velocity and geochemical attributes. Carbonate and structural features can only be used in a piecewise linear regression model for predicting the residual water saturation factor. All these regression equations usually have small errors.

Practical analysis of the behavior of the composition features indicates the importance of using Na2O, TiO2 and Fe2O3 oxides, which most likely convey the influence of mineralized solutions, chemical composition of the cement aggregate and films on the surface of mica minerals — siderite, iron oxides-hydroxides and ore mineral.

Three families of features in the predictive model of the residual water saturation coefficient: petrodensity, carbonate content, and structural, give a close value of the critical point of the predictive response (kc.v=0.39), which is probably critical for these terrigenous reservoirs, since this value indicates the limit of impact of conditional bound water.

The authors have formed regression relationships in all selected models between all families of traits and the permeability coefficient. It was found that the use of a nonlinear regression model significantly increases the level of its reliability compared to the reliability of traditional linear models. For example, the geochemical predictors in the linear regression model for predicting effective porosity have a low value of the explained variance (75 %), which is on the verge of statistical reliability. At the same time, the SVM provides a reliable correlation of geochemical characteristics and permeability at the level of 90 %; the active role of SiO2, sodium and chlorine was established.

All implementations of linear regression models of the porosity parameter in reservoir conditions and the proportion of supercapillary pores in the total volume of voids have increased and/or high modeling errors, except for the family of petroelectric and geochemical features.

The preliminary results showed that neural network and deep learning methods outperform traditional regression analysis in terms of prediction accuracy and can effectively cope with uncertainty in test results, making it one of the most effective tools for petrophysical modeling and prediction.

References

Bezrodna, I., & Shynkarenko, A. (2015). Estimation of void space structure of zarichna area poor-porous rocks based on petrophysical and geophysical studies. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 2(69), 53—58. https://doi.org/10.17721/1728-2713. 69.08.53-58 (in Ukrainian).

Vyzhva, S., & Bezrodna, I. (2016). Determination of the void space structure of complex rocks using the petroacoustic studies data from the semyrenkivska area. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 3(74), 11—17. https://doi.org/10.17721/1728-2713.74.02 (in Ukrainian).

Vyzhva, S.A., Bezrodna, I.M., & Kozionova, O.O. (2012). Analysis of the capacitive properties of carbonate rocks of the Lower Carboniferous of the Rudenkivsko-Proletarskaya NGR based on the results of GDS and petrophysics. In Collection of scientific works «Theoretical and applied aspects of geoinformatics» (pp. 16á27) (in Ukrainian).

Vyzhva, S., Onyshchuk, V., Onyshchuk, І., Reva, М., & Shabatura, О. (2022а). Electric and elastic properties of deep-seated consolidated rocks of carboniferous period of the central graben of the Dnieper-Donetsk Depression. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 2(97), 29—38. https://doi.org/10.17721/1728-2713.97.04 (in Ukrainian).

Vyzhva, S., Onyshchuk, V., Onyshchuk, І., Reva, М., & Shabatura, О. (2023). Electric and elastic properties of consolidated terrigenous rocks of Cambrian period of the southern slope of the Lviv palaeozoic trough. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 2(101), 15—24. https://doi.org/10.17721/ 1728-2713.101.02 (in Ukrainian).

Vyzhva, S., Onyshchuk, V., Onyshchuk, I., Reva, M., & Shabatura, O. (2022б). Reservoir properties of deep-seated consolidated rocks of carboniferous period of the central graben of the Dnieper-Donetsk Depression. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 1(96), 11—19. https://doi.org/10. 17721/1728-2713.96.02 (in Ukrainian).

Vyzhva, S., Onyshchuk, V., Onyshchuk, I., Reva, M., & Shabatura, O. (2022в). Reservoir properties of consolidated terrigenous rocks of cambrian period of the eastern slope of the lviv paleozoic depression. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 3(98), 33—41. https://doi.org/10.17721/1728-2713.98.04 (in Ukrainian).

Vyzhva, S., Onyshchuk, V., Onyshchuk, I., Reva, M., & Shabatura, О. (2021а). Porosity and permeability properties of consolidated rocks of the northern near edge zone of the dnieper-donetsk depression. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 3(94), 37—45. https://doi.org/10.17721/1728-2713.94. 04 (in Ukrainian).

Vyzhva, S., Onyshchuk, V., Orlyuk, М., Onyshchuk, І., Reva, М., & Shabatura, О. (2021б). Electric and elastic parameters of carbonic period terrigenous rocks of the eastern part of the northern edge of the dnieper-donets depression. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 4(95), 25—33. https://doi.org/10.17721/1728-2713.95.03 (in Ukrainian).

Vyzhva, S., Shynkarenko, A., Bezrodna, I., Shchurov, I., Gafych, I., & Solodkyi, I. (2017). Influence of variable pressure on acoustic and volumetric properties of terrigenous reservoir rocks (on the example of semyrenkivska area samples). Visnyk of Taras Shevchenko National University of Kyiv. Geology, 1(76), 19—26. https://doi.org/10.17721/1728-2713.76.03 (in Ukrainian).

Sobol, V., & Karpenko, O. (2025). A new model of permeability of terrigenous granular reservoirs on the example of turney deposits of yablunivske oil and gas condensate field of the dnieper-donets basin. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 1(92), 61—66. https://doi.org/10.17721/1728-2713.92.09 (in Ukrainian).

Shynkarenko, А. (2018). Modern approaches to determine the permeability of reservoir rocks based on the results of geophysical investigations. Visnyk of Taras Shevchenko National University of Kyiv. Geology, 3(82), 45—54. https://doi.org/10.17721/17282713.82.06 (in Ukrainian).

Al-Anazi, A., & Gates, I.D. (2010). Support-vector regression for permeability predictionin a heterogeneous reservoir: a comparative study. SPE Reservoir Evaluation & Engineering, 13, 485—495. http://doi.org/10.2118/126339-PA.

Al-Anazi, A.F., & Gates, I.D. (2012). Support vector regression to predict porosity and permeability: Effect of sample size. Computers & Geosciences, 39, 64—76. https://doi.org/10.1016/j.cageo.2011.06.011.

Al-Bulushi, N., Araujo, M., & Kraaijveld, M. (2007). Predicting water saturation using artificial neural networks (ANNs). SPWLA Middle East Regional Symposium, Abu Dhabi, UAE, April 2007 (pp. 65—71).

Al-Dousari, M., Garrouch, A.A., & Al-Omair, O. (2016). Investigating the dependence of shear wave velocity on petrophysical parameters. Journal of Petroleum Science and Engineering, 146, 286—296. https://doi.org/10.1016/j.petrol. 2016.04.036.

Alfarraj, M., & AlRegib, G. (2018). Petrophysical property estimation from seismic data using recurrent neural networks. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists (pp. 2141—2146). https://doi.org/10.1190/segam2018-2995752.1.

Al-Mudhafar, W. (2014). Using generalized linear regression of multiple attributes for modeling and prediction the formation permeability in sandstone reservoir. Offshore Technology Conference, Houston, Texas, May 2014. https://doi.org/10.4043/25158-MS.

Al-Mudhafar, W., & Rostami, A. (2014). Comparative applied multivariate geostatistical algorithms for formation permeability modeling. SPWLA 20th Formation Evaluation Symposium of Japan, Chiba, Japan, October 2014. https://doi.org/10.13140/2.1.1700.2566.

Aquino-López, A., Mousatov, A., & Markov, M. (2011). Model of sand formations for joint simulation of elastic moduli and electrical conductivity. Journal of Geophysics and Engineering, 8(4), 568—578. https://doi.org/10.1088/1742-2132/8/4/009.

Baziar, S., Tadayoni, M., Nabi-Bidhendi, M., & Khalili, M. (2014). Prediction of permeability in a tight gas reservoir by using three soft computing approaches: A comparative study. Journal of Natural Gas Science and Engineering, 21, 718—724. https://doi.org/10.1016/j.jngse. 2014.09.037.

Ben-Awuah, J., & Padmanabhan, E. (2017). An enhanced approach to predict permeability in reservoir sandstones using artificial neural networks (ANN). Arabian Journal of Geosciences, 10, 173. https://doi.org/10.1007/s12517-017-2955-7.

Benaafi, M., Hariri, M., Al-Shaibani, A., Abdullatif, O., & Makkawi, M. (2018). Integrated geomechanical, petrographical and petrophysical study of the sandstones of the Wajid Group, SW Saudi Arabia. Journal of African Earth Sciences, 143, 162—177. https://doi.org/10.1016/j.jafrearsci.2018.03.011.

Civan, F. (2018). Effect of stress shock and pressurization/depressurization hysteresis on petrophysical properties of naturally-fractured reservoir formations. SPE Western Regional Meeting, Garden Grove, California, USA, April 2018. https://doi.org/10.2118/190081-MS.

El Sharawy, M.S., & Nabawy, B.S. (2018). Determining the porosity exponent m and lithology factor a for sandstones and their control by overburden pressure: A case study from the Gulf of Suez, Egypt. AAPG Bulletin, 102, 1893—1910. https://doi.org/10.1306/ 03141817262.

Feng, X., & Jimenez, R. (2014). Bayesian prediction of elastic modulus of intact rocks using their uniaxial compressive strength. Engineering Geology, 173, 32—40, https://doi.org/10.1016/j.enggeo.2014.02.005.

Goldberg, I., & Gurevich, B. (1998). A semi-em-

pirical velocity-porosity-clay model for petrophysical interpretation of P- and S-velocities. Geophysical Prospecting, 46, 271—285. https://doi.org/10.1046/j.1365-2478.1998.00095.x.

Han, T., Best, A., Sothcott, J., & MacGregor, L. (2011). Pressure effects on the joint elastic-electrical properties of reservoir sandstones. Geophysical Prospecting, 59, 506—517. https://doi.org/10.1111/j.1365-2478.2010.00939.x.

Hawkins, A.B., & McConnell, B.J. (1992). Sensitivity of sandstone strength and deformability to changes in moisture content. Quarterly Journal of Engineering Geology and Hydrogeology, 25(2), 115—130. https://doi.org/10.1144/GSL.QJEG.1992.025.02.05.

Joshi, D., Patidar, A.K., Mishra, A., Agarwal, S., Pandey, A., Dewangan, B.K., & Choudhury, T. (2021). Prediction of sonic log and correlation of lithology by comparing geophysical well log data using machine learning principles. GeoJournal, 88, 47—68. https://doi.org/10.1007/s10708-021-10502-6.

Koesoemadinata, A.P., & McMechan, G.A. (2023). Correlations between seismic parameters, EM parameters, and petrophysical/petrological properties for sandstone and carbonate at low water saturations. Geophysics, 68(3), 870—883. https://doi.org/10.1190/1.1581039.

Lai, J., Wang, G., Cao, J., Xiao, C., Wang, S., Pang, X., Dai, Q., He, Z., Fan, X., Yang, L., & Qin, Z. (2018). Investigation of pore structure and petrophysical property in tight sandstones. Marine and Petroleum Geology, 91, 179—189. https://doi.org/10.1016/j.marpetgeo.2017. 12.024.

Lala, A.M.S., & El-Sayed, N.A.A. (2015). Effect of pore framework and radius of pore throats on permeability estimation. Journal of African Earth Sciences, 110, 64—74. https://doi.org/10.1016/j.jafrearsci.2015.05.019.

Stück, H., Koch, R., & Siegesmund, S. (2012). Petrographical and petrophysical properties of sandstones: Statistical analysis as an approach to predict material behaviour and construction suitability. Environmental Earth Sciences, 9. https://doi.org/10.1007/s12665-012-2008-1.

Török, Á., & Vásárhelyi, B. (2010). The influence of fabric and water content on selected rock mechanical parameters of travertine, examples from Hungary. Engineering Geology, 115, 237—245. https://doi.org/10.1016/j.enggeo.2010.01.005.

Vásárhelyi, B. (2005). Statistical Analysis of the Influence of Water Content on the Strength of the Miocene Limestone. Rock Mechanics and Rock Engineering, 38(1), 69—76. https://doi.org/10.1007/s00603-004-0034-3.

Wang, H., Kou, Z., Bagdonas, D.A., Phillips, E.H.W.,

Alvarado, V., Johnson, A.C., Jiao, Z., McLaughlin, J.F., & Quillinan, S.A. (2022). Multiscale petrophysical characterization and flow unit classification of the Minnelusa eolian sandstones. Journal of Hydrology, 607, 127466. https://doi.org/10.1016/j.jhydrol. 2022.127466.

Wang, M., Liu, W., Liu, H., Xie, T., Wang, Q., & Xu, W. (2024). Comparative study on convolutional neural network and regression analysis to evaluate uniaxial compressive strength of Sandy Dolomite. Scientific Report, 14, 9880. https://doi.org/10.1038/s41598-024-60085-8.

Zhao, X., Chen, X., Huang, Q., Lan, Z., Wang, X., & Yao, G. (2022). Logging-data-driven permeability prediction in low-permeable sandstones based on machine learning with pattern visualization: a case study in Wenchang A Sag, Pearl River Mouth Basin. Journal of Petroleum Science and Engineering, 214, 110517. https://doi.org/10.1016/j.petrol.2022.110517.