Petrophysical evaluation of clastic formations in boreholes with incomplete well log dataset by using joint inversion technique and machine learning algorithms
Main Article Content
Abstract
A succesful petrophysical evaluation of shaly-sand formations requieres: 1) the availability of high quality well log data and, 2) a petrophysical model that successfully represents the geological conditions of the rocks. Unfortunately, it is not always possible to fulfill these conditions, and in many cases the set of well logs is incomplete. To determine petrophysical parameters (i.e., volumes of laminar, structural and disperse shale) in clastic rocks from incomplete well log data we followed three approaches which are based on a hierarchical model, and on a joint inversion technique: 1) Available well log data (excluding the incomplete well log) are used to train machine learning algorithms to generate a predictive model; 2) the first step of the second approach machine learning algorithms are used to generate the missing data which are subsequently included a joint inversion; 3) in the third approach, machine learning process is used to estimate the missing data which are subsequently included in the prediction of the petrophysical properties. The supervised learning paradigm we used was in a joint based on different regression models (linear, decision trees, and kernel). A performance analysis of the three approaches is conducted with synthetic data (representing real conditions of clastic formations from an oil field in southern Mexico). We simulated gamma ray, deep resistivity, P-wave travel time, bulk density and neutron porosity logs by means of a hierarchical petrophysical model for clastic rock to accomplish a controlled analysis. The three different approaches were applied without P-wave travel time data to analyze the impact of the missing information. In general, the results indicate an adequate petrophysical parameter determination in each of the approaches. Metric evaluations indicate that the best performance was obtained by the second approach followed by approaches one and three. The correct estimation of the volumes of shale distribution could not be correctly resolved by any of the three applied methods but the total shale content could accurately be predicted which suggests that there is a non-uniqueness problem.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
Alpak, F. O., Torres-Verdín, C., and Habashy, T. M. (2006). Petrophysical inversion of borehole array-induction logs: Part I—Numerical examples. Geophysics, 71(4), F101-F119. Doi: https://doi.org/10.1190/1.2213358
Anemangely, M., Ramezanzadeh, A., Amiri, H., & Hoseinpour, S.-A. (2019). Machine learning technique for the prediction of shear wave velocity using petrophysical logs. Journal of Petroleum Science and Engineering, 174, 306-327. doi: https://doi.org/10.1016/j.petrol.2018.11.032
Aquino, A. (2011). Inversión conjunta de registros de pozos para la evaluación petrofísica en formaciones areno-arcillosas anisótropas. [Tesis de doctorado]. Instituto Mexicano del Petróleo.
Aquino-López, A., Mousatov, A., and 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. doi: https://doi.org/10.1088/1742-2132/8/4/009
Aquino-López, A., Mousatov, A., Markov, M., and Kazatchenko, E. (2015). Modeling and inversion of elastic wave velocities and electrical conductivity in clastic formations with structural and dispersed shales. Journal of Applied Geophysics, 116, 28-42. doi: https://doi.org/10.1016/j.jappgeo.2015.02.013
Archie, G. E. (1942). The electrical resistivity log as an aid in determining some reservoir characteristics. Transactions of the AIME, 146(01), 54-62. doi: https://doi.org/10.2118/942054-G
Bhatt, A., and Helle, H. B. (2002). Determination of facies from well logs using modular neural networks. Petroleum Geoscience, 8(3), 217-228. doi: https://doi.org/10.1144/petgeo.8.3.217
Bishop, C. M., 2006. Pattern Recognition and Machine Learning. Springer, New York, NY.
Bjørlykke, K. and Jahren, J. (2010). Sandstones and sandstone reservoirs. En A. Per Avseth, Jan Inge Faleide, Roy H. Gabrielsen, Nils-Martin Hanken, Kaare Høeg, Jens Jahren, Martin Landrø, Nazmul Haque Mondol, Jenø Nagy and Jesper Kresten Nielsen (Eds.), Petroleum Geoscience: From Sedimentary Environments to Rock Physics. (pp. 113-140). Springer, Berlin, Heidelberg. doi: https://doi.org/10.1007/978-3-642-02332-3_4
Boser, B. E., Guyon, I. M., and Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. [Conference Paper]. Proceedings of the fifth annual workshop on Computational learning theory - COLT ’92, 144-152. doi: https://doi.org/10.1145/130385.130401
Bukar, I., Adamu, M. B., & Hassan, U. (2019). A machine learning approach to shear sonic log prediction. [Conference Paper]. SPE Nigeria Annual International Conference and Exhibition. doi: https://doi.org/10.2118/198764-MS
Bust, V. K., Majid, A. A., Oletu, J. U., and Worthington, P. F. (2013). The petrophysics of shale gas reservoirs: Technical challenges and pragmatic solutions. Petroleum Geoscience, 19(2), 91-103. doi: https://doi.org/10.1144/petgeo2012-031
Chicco, D., Warrens, M. J., and Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, e623. doi: https://doi.org/10.7717/peerj-cs.623
Clavier, C., Coates, G., & Dumanoir, J. (1984). Theoretical and experimental bases for the dual-water model for interpretation of shaly sands. Society of Petroleum Engineers Journal, 24(02), 153-168. doi: https://doi.org/10.2118/6859-PA
Friedl, M. A., and Brodley, C. E. (1997). Decision tree classification of land cover from remotely sensed data. Remote Sensing of Environment, 61(3), 399-409. doi: https://doi.org/10.1016/S0034-4257(97)00049-7
Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and Tensor Flow. (2a ed.). O’Reilly Media, Inc.
Geurts, P., Ernst, D., and Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3-42. doi: https://doi.org/10.1007/s10994-006-6226-1
Ghavami, F. (2011). Developing synthetic logs using artificial neural network: Application to Knox County in Kentucky.
Hajizadeh, A., AL Mudaliar, K., and Tewari, R. D. (2019). Designing a pragmatic solution for complex numerical modeling problem in thinly laminated reservoirs. Journal of Petroleum Exploration and Production Technology, 9(4), 2831-2844. doi: https://doi.org/10.1007/s13202-019-0662-5
Han, D. H. (1986). Effects of porosity and clay content on acoustic properties of sandstones and unconsolidated sediments. [Ph.D. Thesis]., Stanford University, Department of Geophysics, Stanford, USA.
Han, D. H., Nur, A., and Morgan, D. (1986). Effects of porosity and clay content on wave velocities in sandstones. Geophysics, 51(11), 2093-2107. doi: https://doi.org/10.1190/1.1442062
Heidari, Z., & Torres-Verdín, C. (2013). Inversion-based method for estimating total organic carbon and porosity and for diagnosing mineral constituents from multiple well logs in shale-gas formations. Interpretation, 1(1), T113-T123. doi: https://doi.org/10.1190/INT-2013-0014.1
Heidari, Z., and Torres-Verdín, C. (2014). Inversion-based detection of bed boundaries for petrophysical evaluation with well logs: Applications to carbonate and organic-shale formations. Interpretation, 2(3), T129-T142. doi: https://doi.org/10.1190/INT-2013-0172.1
Hoerl, A. E., and Kennard, R. W. (1970). Ridge Regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1), 55-67. doi: https://doi.org/10.1080/00401706.1970.10488634
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to statistical learning. Springer New York. doi: https://doi.org/10.1007/978-1-4614-7138-7
Kazatchenko, E., Markov, M., and Mousatov, A. (2004). Joint inversion of acoustic and resistivity data for carbonate microstructure evaluation. Petrophysics-The SPWLA Journal of Formation Evaluation and Reservoir Description, 45(02).
Kazatchenko, E., Markov, M., Mousatov, A., & Pervago, E. (2007). Joint inversion of conventional well logs for evaluation of double-porosity carbonate formations. Journal of Petroleum Science and Engineering, 56(4), 252-266. doi: https://doi.org/10.1016/j.petrol.2006.09.008
Koza, J. R., Bennett, F. H., Andre, D., and Keane, M. A. (1996). Automated design of both the topology and sizing of analog electrical circuits using genetic programming. In: Gero, J.S., Sudweeks, F. (Eds.). Artificial Intelligence in Design ’96 (pp. 151-170). Springer Netherlands. doi: https://doi.org/10.1007/978-94-009-0279-4_9
Markov, M., Levine, V., Mousatov, A., and Kazatchenko, E. (2005). Elastic properties of double-porosity rocks using the differential effective medium model. Geophysical Prospecting, 53(5), 733-754. doi: https://doi.org/10.1111/j.1365-2478.2005.00498.x
Meju, M. A. (1994). Geophysical data analysis: understanding inverse problem theory and practice. Society of Exploration Geophysicists. doi: https://doi.org/10.1190/1.9781560802570
Mezzatesta, A. G., and Méndez, E. R. (2006) A Novel Approach to Numerical Integration of Conventional, Multi-Component Induction, and Magnetic Resonance Data in Thinly Bedded Sand-Shale Systems. [Sesión de conferencia]. SPWLA Annual Logging Symposium 1, Old CSD Building, KDMIPE Campus, Kaulagarh Road, Dehradun, Uttarakhand, India.
Mezzatesta, A. G., Mollison, R. A., and Frost, E. (June, 2002). Laminated Shaly Sand Reservoirs-An Interpretation Model Incorporating New Measurements. [Presentación de paper]. In SPWLA Annual Logging Symposium, Oiso, Japan.
Minear, J. W. (September, 1982). Clay models and acoustic velocities. [Presentación de paper]. SPE Annual Technical Conference and Exhibition (SPE-11031). SPE. doi: https://doi.org/10.2118/11031-MS
Mitchell, T. (1996). Machine Learning (First). McGraw-Hill Education.
Mitchell, W. K., and Nelson, R. J. (June,1988). A practical approach to statistical log analysis. [Presentación de paper]. In SPWLA Annual Logging Symposium.
Müller, A. C., and Guido, S. (2016). Introduction to machine learning with Python (First edit). O’Reilly Media, Inc.
Nguyen-Sy, T., To, Q.-D., Vu, M.-N., Nguyen, T.-D., and Nguyen, T.-T. (2021). Predicting the electrical conductivity of brine-saturated rocks using machine learning methods. Journal of Applied Geophysics, 184, 104238. doi: https://doi.org/10.1016/j.jappgeo.2020.104238
Pérez-Rosales, C. (1982). On the relationship between formation resistivity factor and porosity. Society of Petroleum Engineers Journal, 22(04), 531-536. doi: https://doi.org/10.2118/10546-PA
Poupon, A., Loy, M. E., and Tixier, M. P. (1954). A contribution to electrical log interpretation in shaly sands. Journal of petroleum Technology, 6(06), 27-34. doi: https://doi.org/10.2118/311-G
Rasmussen, C. E. and Williams, C. K., (2006). Gaussian processes for machine learning. Cambridge, MA: MIT press.
Rolon, L., Mohaghegh, S. D., Ameri, S., Gaskari, R., and McDaniel, B. (2009). Using artificial neural networks to generate synthetic well logs. Journal of Natural Gas Science and Engineering, 1(4-5), 118-133. doi: https://doi.org/10.1016/j.jngse.2009.08.003
Samuel, A. L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of Research and Development, 3(3), 210-229. doi: https://doi.org/10.1147/rd.33.0210
Shalev-Shwartz, S., and Ben-David, S. (2014). Understanding machine learning. Cambridge University Press. doi: https://doi.org/10.1017/CBO9781107298019
Shedid, S. A., and Saad, M. A. (2017). Comparison and sensitivity analysis of water saturation models in shaly sandstone reservoirs using well logging data. Journal of Petroleum Science and Engineering, 156, 536-545. doi: https://doi.org/10.1016/j.petrol.2017.06.005
Simandoux, P. (1963). Measures dielectrique en milieu poreux, application a mesure de saturation en eau, etude des massifs argileaux. Revue de l’Inst. Francais du petrole, 193-215.
Snieder, R., and Trampert, J. (1999). Inverse problems in geophysics. In: Wirgin, A. (Eds.). Wavefield Inversion. International Centre for Mechanical Sciences (pp. 119-190). Springer Vienna. doi: https://doi.org/10.1007/978-3-7091-2486-4_3
Thomas, E.C. and Stieber, S. J. (June, 1975). The distribution of shale in sandstones and its effect on porosity. [Sesión de conferencia]. Trans SPWLA 16th Annual Logging Symp.
Torres-Verdín, C., Alpak, F. O., and Habashy, T. M. (2006). Petrophysical inversion of borehole array-induction logs: Part II—Field data examples. Geophysics, 71(5), G261-G268. doi: https://doi.org/10.1190/1.2335633
Tosaya, C., and Nur, A. (1982). Effects of diagenesis and clays on compressional velocities in rocks. Geophysical Research Letters, 9(1), 5-8. doi: https://doi.org/10.1029/GL009i001p00005
Wang, J., and Hu, J. (2015). A robust combination approach for short-term wind speed forecasting and analysis – Combination of the ARIMA (Autoregressive Integrated Moving Average), ELM (Extreme Learning Machine), SVM (Support Vector Machine) and LSSVM (Least Square SVM) forecasts using a GPR (Gaussian Process Regression) model. Energy, 93, 41-56. doi: https://doi.org/10.1016/j.energy.2015.08.045
Waxman, M. H., and Smits, L. J. M. (1968). Electrical conductivities in oil-bearing shaly-sands. Society of Petroleum Engineers Journal, 8(02), 107-122. doi: https://doi.org/10.2118/1863-A
Wilson, M. D., and Pittman, E. D. (1977). Authigenic clays in sandstones: recognition and influence on reservoir properties and paleoenvironmental analysis. Journal of Sedimentary Research, 47(1), 3-31. doi: https://doi.org/10.1306/212F70E5-2B24-11D7-8648000102C1865D
Winsauer, W. O., Shearin Jr, H. M., Masson, P. Y., and Williams, M. (1952). Resistivity of brine-saturated sands in relation to pore geometry. AAPG Bulletin, 36(2), 253-277. doi: https://doi.org/10.1306/3D9343F4-16B1-11D7-8645000102C1865D
Wolpert, D. H., and Macready, W. G. (1997). No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation, 1(1), 67-82. doi: https://doi.org/10.1109/4235.585893
Worthington, P. F. (2000). Recognition and evaluation of low-resistivity pay. Petroleum geoscience, 6(1), 77-92. doi: https://doi.org/10.1144/petgeo.6.1.77
Worthington, P. F. (2001). The influence of formation anisotropy upon resistivity-porosity relationships. Petrophysics, 42(02).
Worthington, P. F. (2011). The petrophysics of problematic reservoirs. Journal of Petroleum Technology, 63(12), 88-97. doi: https://doi.org/10.2118/144688-JPT
Wyllie, M. R. J. and Gregory, A. R. (1953). Formation factors of unconsolidated porous media: Influence of particle shape and effect of cementation. Journal of petroleum technology, 5(04), 103-110. doi: https://doi.org/10.2118/223-G
Wyllie, M. R. J., Gregory, A. R., and Gardner, G. H. F. (1958). An experimental investigation of factors affecting elastic wave velocities in porous media, Geophysics, 23(3), 459-493. doi: https://doi.org/10.1190/1.1438493
Zeng, L., Yi, S., Zhang, W., Feng, H., Lv, A., Zhao, W., Luo, Y., Wang, Q., and Lu, H. (2020). Provenance of loess deposits and stepwise expansion of the desert environment in NE China since ~1.2 Ma: Evidence from Nd-Sr isotopic composition and grain-size record. Global and Planetary Change, 185, 103087. doi: https://doi.org/10.1016/j.gloplacha.2019.103087
Zhang, Y. L., Bao, Z. D., Zhao, Y., Jiang, L., Zhou, Y. Q., and Gong, F. H. (2017). Origins of authigenic minerals and their impacts on reservoir quality of tight sandstones: Upper Triassic Chang-7 Member, Yanchang Formation, Ordos Basin, China. Australian Journal of Earth Sciences, 64(4), 519-536. doi: https://doi.org/10.1080/08120099.2017.1318168
Zhdanov, M. S. (2002). Geophysical inverse theory and regularization problems (V. 36). Elsevier.
Zwennes, J.W., (2017), Shale distribution quantification in a sandstone reservoir using density porosity and neutron porosity log data [M.S. Thesis]., University of Louisiana at Lafayette.