Evaluating the Prediction Performance of Random Forest in Classification of Carbonate Lithology
DOI:
https://doi.org/10.20428/jst.v30i9.3186Keywords:
Carbonate lithology prediction , Random Forest , machine learning in geoscience , reservoir characterization , feature importanceAbstract
Accurate lithology prediction in carbonate reservoirs is essential for hydrocarbon exploration but remains challenging due to their complex heterogeneity. Traditional methods (e.g., seismic and well-log analysis) often fail to capture subtle lithological variations, while machine learning approaches such as Random Forest (RF) remain underexplored for carbonates. Previous research has not sufficiently compared Random Forest with advanced models such as XGBoost and deep learning approaches, nor provided detailed feature importance analyses specific to carbonate lithology classification. This study employs a dataset comprising 4,624 samples characterized by ten petrophysical properties to evaluate the classification performance of RF. Our optimized RF framework demonstrates superior accuracy while reducing dependence on costly core sampling, thereby improving the precision of carbonate reservoir models.
References
A
Abbas, A. M., Al-Mudhafar, W. J., & Wood, D. A. (2024). Integration of electromagnetic, resistivity-based, and production logging data for validating lithofacies and permeability predictive models with tree ensemble algorithms in heterogeneous carbonate reservoirs. Petroleum Geoscience, 30(2), Article petgeo2023-067. https://doi.org/10.1144/petgeo2023-067
Al-Khudafi, A. M., Al-Sharifi, H. A., & Hamada, G. M. (2023). Evaluation of different tree-based machine learning approaches for formation lithology classification. Journal of Geological Sciences, 2(1), Article jgs-2023-0026. https://doi.org/10.56952/jgs-2023-0026
Amaefule, A. E., McColloch, M., Hoummad, T. C., & Keelan, H. D. (1993). Enhanced reservoir description: Using core and log data to identify hydraulic flow units and predict permeability in uncored intervals/wells. SPE Formation Evaluation, 8(2), 221–229. https://doi.org/10.2118/24729-PA
Ao, Y., Li, H., Zhu, L., Ali, S., & Zvi, Z. (2020). The linear random forest algorithm and its advantages in machine learning assisted logging regression classification. Journal of Petroleum Science and Engineering, 194, Article 107550. https://doi.org/10.1016/j.petrol.2020.107550
B
Banerjee, S., Jha, M., & Mittal, S. (2024). Machine learning-based petrographic classification using geophysical well logs: A case study from India’s Bokaro coalfield. Journal of Earth System Science, 133(1), Article 12. https://doi.org/10.1007/s12040-023-02220-4
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Bressan, T. S., de Lima, G. F., & de Almeida, L. B. (2020). Lithology prediction using machine learning algorithms: A case study in the Paraná Basin, Brazil. Journal of Applied Geophysics, 183, Article 104197. https://doi.org/10.1016/j.jappgeo.2020.104197
C
Cracknell, M. J., & Reading, A. M. (2014). Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Computers & Geosciences, 63, 22–33. https://doi.org/10.1016/j.cageo.2013.10.008
F
Farhadi, Z. (2022). An ensemble framework to improve the accuracy of prediction using clustered random-forest and shrinkage methods. Applied Sciences, 12(20), Article 10608. https://doi.org/10.3390/app122010608
G
Gu, Y., Wang, X., & Zhang, J. (2021). The identification of coal and gangue by deep learning and random forest. IEEE Access, 9, 119939–119949. https://doi.org/10.1109/ACCESS.2021.3107935
H
Hamada, G. M., Al-Khudafi, A. M., & Al-Sharifi, H. A. (2024). Characterization of lithofacies properties of carbonate reservoir rocks using machine learning techniques. Journal of Petroleum and Mining Engineering, 26(1), 45–54. https://doi.org/10.21608/jpme.2024.265484.1190
Hamada, G. M., Al-Blehed, M. S., & Al-Awad, M. N. (2024). Reservoir characterization using machine learning techniques: A comprehensive review. Journal of Natural Gas Science and Engineering, 102, Article 104567. https://doi.org/10.1016/j.jngse.2024.104567
Harris, J. R., & Grunsky, E. C. (2015). Predictive lithological mapping of Canada’s North using Random Forest classification applied to geophysical and geochemical data. Computers & Geosciences, 80, 9–25. https://doi.org/10.1016/j.cageo.2015.03.006
K
Karabadji, N. E. I., Seridi, H., Aridhi, S., & Dhifli, W. (2023). Improving decision tree performance by differential evolution-based feature weighting. Knowledge-Based Systems, 241, Article 108246. https://doi.org/10.1016/j.knosys.2022.108246
L
Liaw, A., & Wiener, M. (2002). Classification and regression by random forest. R News, 2(3), 18–22.
Lucia, D. J. (2007). Petrophysical parameters influencing reservoir quality of carbonate rocks. Society of Professional Well Log Analysts.
M
Mukherjee, R., Naik, A., & Srivastava, P. K. (2024). Comparative analysis of machine learning algorithms for lithology classification: A case study from the Cambay Basin. Journal of Petroleum Exploration and Production Technology, 14(2), 345–360. https://doi.org/10.1007/s13202-023-01712-4
Musleh, D., Olatunji, S. O., & Almajed, A. A. (2023). Ensemble learning based sustainable approach to carbonate reservoirs permeability prediction. Sustainability, 15(19), Article 14403. https://doi.org/10.3390/su151914403
N
Nugroho, H., Wikantika, K., & Bijaksana, S. (2023). Integration of remote sensing and geophysical data to enhance lithological mapping utilizing the Random Forest classifier: A case study from Komopa, Papua Province, Indonesia. Journal of Degraded and Mining Lands Management, 10(3), 4417–4429. https://doi.org/10.15243/jdmlm.2023.103.4417
R
Rosid, M. S., Haikel, S., & Haidar, M. W. (2019). Carbonate reservoir rock type classification using comparison of Naive Bayes and Random Forest method in field “S” East Java. Proceedings of the International Conference on Applied Physics. https://doi.org/10.1063/1.5132446
S
Shuvo, M. G. H., Islam, M. S., & Hossain, M. E. (2024). Application of machine learning in lithology prediction: A review. Earth Science Informatics, 17(1), 1–15. https://doi.org/10.1007/s12145-023-01188-0
Singh, B. K., & Rao, G. S. (2023). Random Forest classifier for lithological mapping of the Mundiyawas-Khera mineralized belt of the Alwar basin, India, from remote sensing and potential field data. EGUsphere, Article egu23-8232. https://doi.org/10.5194/egusphere-egu23-8232
T
Tepe, C. (2024). Ensemble learning methods for geoscience applications. Springer. https://doi.org/10.1007/978-3-031-52342-8
Tong, K., Sun, F., & Dong, S. (2024). Method of lithology identification in carbonate reservoirs using well logs based on deep forest. Research Square. https://doi.org/10.21203/rs.3.rs-4422432/v1
W
Wang, G., Carr, T. R., Ju, Y., & Li, C. (2020). Identifying organic-rich Marcellus Shale lithofacies by support vector machine classifier in the Appalachian basin. Computers & Geosciences, 64, 52–60. https://doi.org/10.1016/j.cageo.2013.12.003
Wang, G., Ju, Y., Carr, T. R., Li, C., & Zhang, P. (2019). Machine learning assisted lithofacies classification and reservoir quality prediction in tight shale gas reservoirs. Journal of Petroleum Science and Engineering, 182, Article 106312. https://doi.org/10.1016/j.petrol.2019.106312
Weka Team. (2023). Weka 3: Machine Learning Software in Java (Version 3.9.6) [Computer software]. University of Waikato. https://www.cs.waikato.ac.nz/ml/weka/
X
Xie, Y., Zhu, C., & Wang, X. (2020). Performance evaluation of machine learning methods for lithology classification using imbalanced well log data. Natural Resources Research, 29(3), 1685–1701. https://doi.org/10.1007/s11053-019-09553-w
Xie, Y., Zhu, C., Zhou, W., Li, Z., Liu, X., & Tu, M. (2018). Evaluation of machine learning methods for formation lithology identification: A comparison of tuning processes and model performances. Journal of Petroleum Science and Engineering, 160Trace, 182–193. https://doi.org/10.1016/j.petrol.2017.10.028
Z
Zhang, P., Gao, T., & Li, R. (2024). Advanced machine learning framework for enhanced lithology classification and identification. SPE Journal, 29(4), Article 223312-MS. https://doi.org/10.2118/223312-MS
Zhang, P., Gao, T., & Li, R. (2025). Enhancing lithology classification through a deep learning framework. Paper presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, Houston, TX, USA. https://doi.org/10.15530/urtec-2025-4252996
Zhu, L., Wang, Y., Zhu, Y., Zhang, C., & Zhang, F. (2023). Challenges of machine learning models for lithology prediction in imbalanced datasets: A case study. Journal of Geophysical Research: Solid Earth, 128(4), Article e2022JB025678. https://doi.org/10.1024/2022JB025678
