Prediction of Porosity and Permeability Using Well Log and Core Data: A Data-Driven Approach

Md Alamin Islam; Bintun Zaman; Shahria Nayem Ahmed

doi:10.38032/scse.2026.4.308

Authors

Md Alamin Islam Department of Petroleum and Mining Engineering, Chittagong University of Engineering & Technology, Chattogram-4349, Bangladesh
Bintun Zaman Department of Petroleum and Mining Engineering, Chittagong University of Engineering & Technology, Chattogram-4349, Bangladesh
Shahria Nayem Ahmed Department of Petroleum and Mining Engineering, Chittagong University of Engineering & Technology, Chattogram-4349, Bangladesh

DOI:

https://doi.org/10.38032/scse.2026.4.308

Keywords:

Porosity, Permeability, Reservoir Characterization, Machine Learning

Abstract

Accurate prediction of porosity and permeability is very important for reservoir characterization and hydrocarbon extraction. Traditional workflow in the form of empirical correlations is usually difficult, time-consuming, spatially limiting, and entirely dependent on formation geology. The current study examines a different approach, which uses machine learning (ML) regression models based on well-log and core data. Three regression architectures including Random Forest, CatBoost, and K-Nearest Neighbors (KNN) were trained and validated based on a dataset consisting of 340 samples of shaly sand gas reservoirs. The gamma ray (GR), resistivity (RLLD), spontaneous potential (SP), bulk density (RHOB), neutron porosity (NPHI), and depth were used as the input variables with the core-derived porosity (CPHI) and permeability (CKHG) being used as the targets. The quantitative measures of performance of the models included R², Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The findings indicated that KNN regression was better than its counterparts as it achieved R² = 0.8933 and R² = 0.9340 in terms of porosity and permeability prediction, respectively, and more acceptable metrics of errors showed. Comparatively, the traditional empirical methods showed a significantly lower accuracy rate. The findings highlight that machine learning has the potential to provide precise, scalable, and low-cost predictions of the reservoir properties which could lead to better choices for exploration and production activities.

Downloads

PDF

Downloads

Download data is not yet available.

References

[1] Asquith, G.B., Gibson, C.R., Henderson, S. and Krygowski, D., 2004. Basic well log analysis. Tulsa: American Association of Petroleum Geologists. DOI: https://doi.org/10.1306/Mth16823

[2] Aminian, K. and Ameri, S., 2005. Application of artificial neural networks for reservoir characterization with limited data. Journal of Petroleum Science and Engineering, 49(3–4), pp.212–222. DOI: https://doi.org/10.1016/j.petrol.2005.05.007

[3] Urang, J.G., Ebong, E.D., Akpan, A.E. and Akaerue, E.I., 2020. A new approach for porosity and permeability prediction from well logs using artificial neural network and curve fitting techniques: A case study of Niger Delta, Nigeria. Journal of Applied Geophysics, 183, p.104210. DOI: https://doi.org/10.1016/j.jappgeo.2020.104207

[4] Zargari, H., Poordad, S. and Kharrat, R., 2013. Porosity and permeability prediction based on computational intelligence methods including artificial neural networks and adaptive neuro-fuzzy inference systems in a southern carbonate reservoir of Iran. Petroleum Science and Technology, 31(10), pp.1066–1077. DOI: https://doi.org/10.1080/10916466.2010.536805

[5] Ghargan, H.M., Al-Fatlawi, O. and Bashir, Y., 2024. Reservoir permeability prediction based on artificial intelligence techniques. Iraqi Journal of Chemical and Petroleum Engineering, 25(4), pp.49–60. DOI: https://doi.org/10.31699/IJCPE.2024.4.5

[6] Aïfa, T., Baouche, R. and Baddari, K., 2014. Neuro-fuzzy system to predict permeability and porosity from well log data: A case study of the Hassi R’Mel gas field, Algeria. Journal of Petroleum Science and Engineering, 123, pp.217–229. DOI: https://doi.org/10.1016/j.petrol.2014.09.019

[7] Lim, J.S., 2005. Reservoir properties determination using fuzzy logic and neural networks from well data in offshore Korea. Journal of Petroleum Science and Engineering, 49(3–4), pp.182–192. DOI: https://doi.org/10.1016/j.petrol.2005.05.005

[8] Nugroho, I.D.R., Trisna, M.D., and Saroji, S., 2024. An implementation of XGBoost and Random Forest algorithms to estimate effective porosity and permeability using well log data from the Fajar Field, South Sumatera Basin, Indonesia. Indonesian Journal of Applied Physics, 14(2), pp.271–279. DOI: https://doi.org/10.13057/ijap.v14i2.82901

[9] Tam, T.N.T. and Thanh, D.H.T., 2023. Estimation of petrophysical properties using machine learning methods. In: Environmental Science and Engineering. Cham: Springer, pp.475–486. DOI: https://doi.org/10.1007/978-3-031-17808-5_29

[10] Mahesh, B., 2020. Machine learning algorithms: A review. International Journal of Science and Research, 9(1), pp.381–386. DOI: https://doi.org/10.21275/ART20203995

[11] Ho, T.K., 1995. Random decision forests. Technical Report. Murray Hill, NJ: AT&T Bell Laboratories.

[12] Dorogush, A.V., Ershov, V. and Gulin, A., 2018.CatBoost: Gradient boosting with categorical features support. Available at: https://arxiv.org/abs

/1810.11363 [Accessed 21 July 2025].

[13] GeeksforGeeks, 2025. CatBoost in machine learning.

Available at: https://www.geeksforgeeks.org/machine-learning/catboost-ml/ [Accessed 5 August 2025].

[14] Sui, X., He, S., Vilsen, S.B., Meng, J., Teodorescu, R., and Stroe, D.I., 2021. A review of non-probabilistic machine learning-based state-of-health estimation techniques for lithium-ion batteries. Applied Energy, 300, p.117346. DOI: https://doi.org/10.1016/j.apenergy.2021.117346

[15] GeoLOil, 2025. Import core data. Available at: https://geoloil.com/importCoreData.php [Accessed 12 July 2025].