A real-time intelligent lithology identification method based on a dynamic felling strategy weighted random forest algorithm
), Abstract
Real-time intelligent lithology identification while drilling is vital to realizing downhole closed-loop drilling. The complex and changeable geological environment in the drilling makes lithology identification face many challenges. This paper studies the problems of difficult feature information extraction, low precision of thin-layer identification and limited applicability of the model in intelligent lithologic identification. The author tries to improve the comprehensive performance of the lithology identification model from three aspects: data feature extraction, class balance, and model design. A new real-time intelligent lithology identification model of dynamic felling strategy weighted random forest algorithm (DFW-RF) is proposed. According to the feature selection results, gamma ray and 2 MHz phase resistivity are the logging while drilling (LWD) parameters that significantly influence lithology identification. The comprehensive performance of the DFW-RF lithology identification model has been verified in the application of 3 wells in different areas. By comparing the prediction results of five typical lithology identification algorithms, the DFW-RF model has a higher lithology identification accuracy rate and F1 score. This model improves the identification accuracy of thin-layer lithology and is effective and feasible in different geological environments. The DFW-RF model plays a truly efficient role in the real-time intelligent identification of lithologic information in closed-loop drilling and has greater applicability, which is worthy of being widely used in logging interpretation.
Keywords
References
Abdelhakim, L., Abdellah, E.H., Karima, B., et al., 2020. Mapping specific groundwater vulnerability to nitrate using random forest: case of Sais basin, Morocco. Modeling Earth Systems and Environment 6 (3), 1451–1466. https://doi.org/10.1007/s40808-020-00761-6.
Al-Mudhafar, J.W., 2017. Integrating kernel support vector machines for efficient rock facies classification in the main pay of Zubair formation in South Rumaila oil field, Iraq. Modeling Earth Systems and Environment 3 (1), 1–8. https://doi.org/10.1007/s40808-017-0277-0.
Alzubaidi, F., Mostaghimi, P., Swietojanski, P., et al., 2021. Automated lithology classification from drill core images using convolutional neural networks. J. Petrol. Sci. Eng. 197, 107933. https://doi.org/10.1016/j.petrol.2020.107933.
Amjad, A., Chen, S.C., 2020. Characterization of well logs using K-mean cluster analysis. J. Pet. Explor. Prod. Technol. 10 (6), 2245–2256. https://doi.org/10.1007/s13202-020-00895-4.
Baisakhi, D., Rima, C., 2018. Well log data analysis for lithology and fluid identification in Krishna-Godavari basin, India. Arabian J. Geosci. 11, 1–12. https://doi.org/10.1007/s12517-018-3587-2.
Becerra, D., Pires, D.L.R., Galvis-Portilla, H., et al., 2022. Generating a labeled data set to train machine learning algorithms for lithologic classification of drill cuttings. Interpretation 10 (3), SE85–SE100. https://doi.org/10.1190/INT-2021-0194.1.
Boonen, P., Valant-Spaight, B., de-Andre, C.A., et al., 2005. A comparison of logging-while-drilling and wireline nuclear porosity logs in shales from wells in Brazil. Petrophysics 46 (4), 295–301. https://doi.org/10.1144/1354-079304-636.
Breiman, L., 2001. Random forests. Mach. Learn. 45 (1), 5–32. https://doi.org/10.1023/A:1010933404324.
Chawla, N.V., Bowyer, K.W., Hall, L.O., et al., 2002. Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357. https://doi.org/10.1613/jair.953.
Dong, S.Q., Zeng, L.B., Du, X.Y., et al., 2022. Lithofacies identification in carbonate reservoirs by multiple kernel Fisher discriminant analysis using conventional well logs: a case study in A oilfield, Zagros Basin, Iraq. J. Petrol. Sci. Eng. 210, 110081. https://doi.org/10.1016/j.petrol.2021.110081.
Ghawi, R., Pfeffer, J., 2019. Efficient hyperparameter tuning with grid search for text categorization using kNN approach with BM25 similarity. Open Computer Science 9 (1), 160–180. https://doi.org/10.1515/comp-2019-0011.
Han, X., Feng, F.P., Zhang, X.C., et al., 2023. An unequal fracturing stage spacing optimization model for hydraulic fracturing that considers cementing interface integrity. Petrol. Sci. 20 (4), 2165–2186. https://doi.org/10.1016/j.petsci.2023.05.010.
Hjelm, R.D., Alex, F., Samuel, L.M., et al., 2018. Learning deep representations by mutual information estimation and maximization. Statistics 2, 1-24 http://arxiv.org/abs/1808.06670.
Jorge, A.L., Luis, H.O., Carmen, C.C., 2018. Automatic identification of calcareous lithologies using support vector machines, borehole logs and fractal dimension of borehole electrical imaging. Earth Sci. Res. J. 22 (2), 75–82. https://doi.org/10.15446/esrj.v22n2.68320.
Karimzadeh, S., Tangestani, H.M., 2021. Evaluating the VNIR-SWIR datasets of WorldView-3 for lithological mapping of a metamorphic-igneous terrain using support vector machine algorithm; a case study of Central Iran. Adv. Space Res. 68 (6), 2421–2440. https://doi.org/10.1016/j.asr.2021.05.002.
Kumar, T., Seelam, N.K., Rao, G.S., 2022. Lithology prediction from well log data using machine learning techniques: a case study from Talcher coalfield, Eastern India. J. Appl. Geophys. 199, 104605. https://doi.org/10.1016/j.jappgeo.2022.104605.
Li, S.Q., Chen, Z., Li, W., et al., 2023. An FE simulation of the fracture characteristics of blunt rock indenter under static and harmonic dynamic loadings using cohesive elements. Rock Mech. Rock Eng. 56 (4), 2935–2947. https://doi.org/10.1007/s00603-022-03214-x.
Li, Z., Wu, Y., Kang, Y., et al., 2021. Feature-depth smoothness based semi-supervised weighted extreme learning machine for lithology identification. J. Nat. Gas Sci. Eng. 96, 104306. https://doi.org/10.1016/j.jngse.2021.104306.
Liang, H., Chen, H., Guo, J., et al., 2022. Research on lithology identification method based on mechanical specific energy principle and machine learning theory. Expert Syst. Appl. 189, 116142. https://doi.org/10.1016/j.eswa.2021.116142.
Merembayev, T., Kurmangaliyev, D., Bekbauov, B., et al., 2021. A comparison of machine learning algorithms in predicting lithofacies: case studies from Norway and Kazakhstan. Energies 14 (7), 1896. https://doi.org/10.3390/en14071896.
Miao, T., Henning, O., Xu, H.M., 2021. Inversion of well logs into lithology classes accounting for spatial dependencies by using hidden Markov models and recurrent neural networks. J. Petrol. Sci. Eng. 196, 107598. https://doi.org/10.1016/j.petrol.2020.107598.
Peng, H.C., Long, F.H., Ding, C., 2005. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27 (8), 1226–1238. https://doi.org/10.1109/TPAMI.2005.159.
Phillip, J.H., Trudy, D., John, A.W., et al., 2017. Elemental differences: geochemical identification of aboriginal silcrete sources in the Arcadia Valley, eastern Australia. J. Archaeol. Sci.: Report 15 (15), 570–577. https://doi.org/10.1016/j.jasrep.2016.11.032.
Polat, Ö., Polat, A., Ekici, T., 2021. Automatic classification of volcanic rocks from thin section images using transfer learning networks. Neural Comput. Appl. 33 (18), 11531–11540. https://doi.org/10.1007/s00521-021-05849-3.
Ren, Q., Zhang, D., Zhao, X., et al., 2022. A novel hybrid method of lithology identification based on k-means++ algorithm and fuzzy decision tree. J. Petrol. Sci. Eng. 208, 109681. https://doi.org/10.1016/j.petrol.2021.109681.
Rosid, M.S., Haikel, S., Haidar, M.W., 2019. Carbonate reservoir rock type classification using comparison of Naïve Bayes and Random Forest method in field “S” East Java. AIP Conf. Proc. 2168 (1), 1–9. https://doi.org/10.1063/1.5132446.
Stephen, K., Matthew, J.C., Anya, M.R., 2019. Lithological mapping in the central African Copper Belt using random forests and clustering: strategies for optimized results. Ore Geol. Rev. 112, 103015. https://doi.org/10.1016/j.oregeorev.2019.103015.
Sui, Y., Cao, G.S., Guo, T.Y., et al., 2022. Development of gelled acid system in high-temperature carbonate reservoirs. J. Petrol. Sci. Eng. 216, 110836. https://doi.org/10.1016/j.petrol.2022.110836.
Sun, J., Chen, M., Li, Q., et al., 2021. A new method for predicting formation lithology while drilling at horizontal well bit. J. Petrol. Sci. Eng. 196, 107955. https://doi.org/10.1016/j.petrol.2020.107955.
Sun, J., Li, Q., Chen, M.Q., et al., 2019. Optimization of models for a rapid identification of lithology while drilling-a win-win strategy based on machine learning. J. Petrol. Sci. Eng. 176, 321–341. https://doi.org/10.1016/j.petrol.2019.01.006.
Wang, X.D., Yang, S.C., Zhao, Y.F., et al., 2018. Lithology identification using an optimized KNN clustering method based on entropy-weighed cosine distance in Mesozoic strata of Gaoqing field, Jiyang depression. J. Petrol. Sci. Eng. 166, 157–174. https://doi.org/10.1016/j.petrol.2018.03.034.
Wu, Z.B., Wang, J., Xi, K.K., et al., 2022. Research on control system of small intelligent drilling rig based on lithology identification. J. Phys. Conf. 2181 (1), 012039. https://doi.org/10.1088/1742-6596/2181/1/012039.
Wu, Z.Y., Zhang, X., Zhang, C.L., et al., 2021. Lithology identification based on LSTM recurrent neural network. Lithologic Reservoirs 33 (3), 120–128. https://doi.org/10.12108/yxyqc.20210312 (in Chinese).
Xie, H.M., Zhou, J., Zhang, P.F., 2022. Simulation research on vibration parameters model of drill string. Fuel 315, 122351. https://doi.org/10.1016/j.fuel.2021.122351.
Xu, M.H., Zhu, X.Y., Gao, S.L., et al., 2022. Joint use of multi-seismic information for lithofacies prediction via supervised convolutional neural networks. Geophysics 87 (5), 151–162. https://doi.org/10.1190/GEO2021-0554.1.
Xu, T., Zhang, W.T., Li, J., et al., 2022. Domain generalization using contrastive domain discrepancy optimization for interpretation-while-drilling. J. Nat. Gas Sci. Eng. 105, 104685. https://doi.org/10.1016/j.jngse.2022.104685.
Yao, L., Fang, Z., Xiao, Y., et al., 2021. An intelligent fault diagnosis method for lithium battery systems based on grid search support vector machine. Energy 214, 118866. https://doi.org/10.1016/j.energy.2020.118866.
Zeng, L.L., Ren, W.J., Shan, L.Q., 2020. Attention-based bidirectional gated recurrent unit neural networks for well logs prediction and lithology identification. Neurocomputing 414, 153–171. https://doi.org/10.1016/j.neucom.2020.07.026.
Zhang, J., He, Y., Zhang, Y., et al., 2022. Well logging based lithology classification using machine learning methods for high quality reservoir identification: a case study of Baikouquan formation in Mahu area of Junggar basin, NW China. Energies 15 (10), 3675. https://doi.org/10.3390/en15103675.
Zhao, L.X., Zou, C.F., Chen, Y.Y., et al., 2021. Fluid and lithofacies prediction based on integration of well-log data and seismic inversion: a machine-learning approach. Geophysics 86 (4), 151–165. https://doi.org/10.1190/GEO2020-0521.1.
Zhou, Z.L., Wang, G.W., Ran, Y., et al., 2016. A logging identification method of tight oil reservoir lithology and lithofacies: a case from Chang 7 member of Triassic Yanchang Formation in Heshui area, Ordos Basin, NW China. Petroleum Exploration and Development Online 43 (1), 65–73. https://doi.org/10.1016/S1876-3804(16)30007-6.
Zou, C.F., Zhao, L.X., Xu, M.H., et al., 2021. Porosity prediction with uncertainty quantification from multiple seismic attributes using Random Forest. J. Geophys. Res. Solid Earth 126 (7), e2021JB021826. https://doi.org/10.1029/2021JB021826.
京公网安备11010802044758号