Machine Learning and Flow Zone Indicator for Permeability Estimation in Uncored Intervals of a Southern Iraqi Oil Field

Mohammed Rajaa; Ayad A. Al-haleem

doi:10.52716/jprs.v16i3.1075

Authors

Mohammed Rajaa Department of Petroleum Engineering, College of Engineering, University of Baghdad, Baghdad, Iraq.
Ayad A. Al-haleem Department of Petroleum Engineering, College of Engineering, University of Baghdad, Baghdad, Iraq.

DOI:

https://doi.org/10.52716/jprs.v16i3.1075

Keywords:

Flow Zone Indicator, hydraulic flow unit, Machine Learning, Permeability.

Abstract

The precise estimation of permeability is a difficult task due to the nature of heterogeneous reservoirs. Attributable to the high costs of core sampling and the poor accuracy of the linear regression method, the Flow Zone Indicator (FZI) method is regarded as one of the most commonly used techniques in Iraqi fields in recent years to predict permeability. However, this method requires statistical or machine learning to predict FZI in uncored intervals. This study aims to identify the most suitable machine learning model for FZI prediction in uncored intervals using conventional well logs as input. Following this, the reservoir is divided into hydraulic flow units (HFUs) using unsupervised learning. Specifically, AutoGluon is used as an automated machine learning framework to find the best algorithm and optimal hyperparameters for FZI estimation. The k-means algorithm was employed to classify the reservoir into HFUs. This integrated approach was applied to a field case study in southern Iraq. The study utilized both core and log data from three wells. The results demonstrated that the neural network (NN) outperformed the other algorithms within the framework, achieving more than an R² of 90% and a root mean squared error (RMSE) of 1.69 on the test data, and more than an R² of 96% and an RMSE of 0.493 on the training data. By applying the derived correlations for each HFU, the permeability prediction achieved an R² of 85% and an RMSE of approximately 0.37. This demonstrates the effectiveness of the automated machine learning framework in improving FZI estimation and, consequently, permeability predictions.

References

A. M. Ali and A. A. Alhaleem, “Determination of Reservoir Hydraulic Flow Units and Permeability Estimation Using Flow Zone Indicator Method,” Iraqi Journal of Chemical and Petroleum Engineering, vol. 24, no. 2, pp. 89–95, Jun. 2023, doi: https://doi.org/10.31699/IJCPE.2023.2.10.

D. A. Alobaidi, “Permeability Prediction in One of Iraqi Carbonate Reservoir Using Hydraulic Flow Units and Neural Networks,” Iraqi Journal of Chemical and Petroleum Engineering, vol. 17, no. 1, pp. 1–11, Mar. 2016, doi: https://doi.org/10.31699/IJCPE.2016.1.1.

T. Astsauri, M. Habiburrahman, A. F. Ibrahim, and Y. Wang, “Utilizing machine learning for flow zone indicators prediction and hydraulic flow unit classification,” Scientific Reports, vol. 14, no. 1, p. 4223, Feb. 2024, doi: https://doi.org/10.1038/s41598-024-54893-1.

J. O. Amaefule, M. Altunbay, D. Tiab, D. G. Kersey, and D. K. Keelan, “Enhanced Reservoir Description: Using Core and Log Data to Identify Hydraulic (Flow) Units and Predict Permeability in Uncored Intervals/Wells,” in Proc. SPE Annual Technical Conference and Exhibition, Houston, TX, USA, Oct. 3–6, 1993, Paper SPE-26436-MS, doi: https://doi.org/10.2118/26436-MS.

Z. Mahdi and G. Farman, “Estimation of Petrophysical Properties for Zubair Reservoir in Abu-Amood Oil Field,” Iraqi Geological Journal, vol. 56, no. 1B, pp. 32–39, Feb. 2023, doi: https://doi.org/10.46717/igj.56.1B.3ms-2023-2-11.

H. Y. Ali and H. A. Chafet, “Predicting Permeability of the Mishrif Reservoir for Non-Cored Wells by Integrating Conventional Well Logs, Routine Core Analysis, and Drilling Data: A Case Study of Southeastern Iraq,” Iraqi Geological Journal, vol. 57, no. 2C, pp. 84–101, Sep. 2024, doi: https://doi.org/10.46717/igj.57.2C.7ms-2024-9-15.

S. H. Al-Rubiaa and M. F. Al-Shahwan, “Rock typing and prediction permeability using machine learning techniques in Mishrif Formation, southern Iraq,” IOP Conference Series: Earth and Environmental Science, vol. 1300, no. 1, Art. no. 012040, 2024, doi: https://doi.org/10.1088/1755-1315/1300/1/012040.

A. T. Saleh and M. S. Aljawad, “Permeability Estimation for Upper Shale Member in Southern Iraqi Oil Field Using Machine learning and Hydraulic Flow Units Methods,” Iraqi Geological Journal, vol. 56, no. 2B, pp. 90–101, Aug. 2023, doi: https://doi.org/10.46717/igj.56.2B.7ms-2023-8-16.

O. Salman, O. F. Hasan, and S. Al-Jawad, “Permeability Prediction in One of Iraqi Carbonate Reservoir Using Statistical, Hydraulic Flow Units, and ANN Methods,” Iraqi Journal of Chemical and Petroleum Engineering, vol. 23, no. 4, pp. 17–24, Dec. 2022, doi: https://doi.org/10.31699/IJCPE.2022.4.3.

Z. Zhang, H. Zhang, J. Li, and Z. Cai, “Permeability and porosity prediction using logging data in a heterogeneous dolomite reservoir: An integrated approach,” Journal of Natural Gas Science and Engineering, vol. 86, p. 103743, Feb. 2021, doi: https://doi.org/10.1016/j.jngse.2020.103743.

E. Hajibolouri, A. A. Roozshenas, R. Miri, A. Soleymanzadeh, S. Kord, and A. Shafiei, “Permeability modelling in a highly heterogeneous tight carbonate reservoir using comparative evaluating learning-based and fitting-based approaches,” scientific reports, vol. 14, no. 1, Art. no. 10209, May 2024, doi: https://doi.org/10.1038/s41598-024-60995-7.

M. R. Abdul Hameed and S. M. Hamd-Allah, “Studying the Effect of Permeability Prediction on Reservoir History Matching by Using Artificial Intelligence and Flow Zone Indicator Methods,” Iraqi Geological Journal, vol. 56, no. 1E, pp. 9–21, May 2023, doi: https://doi.org/10.46717/igj.56.1E.2ms-2023-5-12.

U. S. Alameedy, A. T. Almomen, and N. Abd, “Evaluating Machine Learning Techniques for Carbonate Formation Permeability Prediction Using Well Log Data,” Iraqi Geological Journal, vol. 56, no. 1D, pp. 175–187, Apr. 2023, doi: https://doi.org/10.46717/igj.56.1D.14ms-2023-4-23.

A. Hussain, M. E. Nasser, and G. Hassan, “Evaluation of Mishrif Reservoir in Abu Amood Oil Field, Southern Iraq,” Iraqi Journal of Science, vol. 62, no. 12, pp. 4758–4768, Dec. 2021, doi: https://doi.org/10.24996/ijs.2021.62.12.14.

M. Q. Abed Talib and M. S. Al-Jawad, “Unveiling the Potential: A Pioneering Investigation into Nahr Umr Formation in Abu Amood Field,” Iraqi Geological Journal, vol. 57, no. 1F, pp. 272–285, Jun. 2024, doi: https://doi.org/10.46717/igj.57.1F.20ms-2024-6-29.

Z. S. Alshammary, A. J. Al-Khafaji, and F. M. Al-Najm, “Characterization of the Yamama Reservoir in the Abu-Amood Oil Field, Nasiriya, Southern Iraq,” Iraqi Geological Journal, vol. 57, no. 1C, pp. 14–28, Mar. 2024, doi: https://doi.org/10.46717/igj.57.1C.2ms-2024-3-14.

M. E. Nasser, S. N. Al-Jawed, and M. F. Hassan, “Geological Modeling for Yamama Formation in Abu Amood Oil Field,” Iraqi Journal of Science, vol. 58, no. 2C, Jun. 2017, doi: https://doi.org/10.24996/ijs.2017.58.2C.9.

Z. A. Mahdi and G. M. Farman, “3D Geological Model for Zubair Reservoir in Abu-Amood Oil Field,” Iraqi Geological Journal, vol. 56, no. 1B, pp. 40–50, Feb. 2023, doi: https://doi.org/10.46717/igj.56.1B.4ms-2023-2-12.

Z. A. Mahdi, “Evaluation of Petrophysical Properties and Construction of a 3D Geological Model for Zubair Formation in Abu-Amood Oil Field,” M.Sc. thesis, Dept. of Petroleum Engineering, Univ. of Baghdad, Baghdad, Iraq, 2022.

B. S. Nabawy, A. M. K. Basal, M. A. Sarhan, and M. G. Safa, “Reservoir zonation, rock typing and compartmentalization of the Tortonian-Serravallian sequence, Temsah Gas Field, offshore Nile Delta, Egypt,” Marine and Petroleum Geology, vol. 92, pp. 609–631, Apr. 2018, doi: https://doi.org/10.1016/j.marpetgeo.2018.03.030.

N. Erickson, J. Mueller, A. Shirkov, H. Zhang, P. Larroy, M. Li, and A. Smola, “AutoGluon-Tabular: Robust and accurate AutoML for structured data,” arXiv preprint arXiv:2003.06505, 2020, doi: https://doi.org/10.48550/arXiv.2003.06505.

M. Baratchi, C. Wang, S. Limmer, J. N. van Rijn, H. H. Hoos, T. Bäck, and M. Olhofer, “Automated machine learning: Past, present and future,” Artificial Intelligence Review, vol. 57, no. 5, Art. no. 122, 2024, doi: https://doi.org/10.1007/s10462-024-10726-1.

J. Blömer, C. Lammersen, M. Schmidt, and C. Sohler, “Theoretical analysis of the k-means algorithm—A survey,” in Algorithm Engineering: Selected Results and Surveys, L. Kliemann and P. Sanders, Eds., vol. 9220, Lecture Notes in Computer Science. Cham, Switzerland: Springer, 2016, pp. 81–116, doi: https://doi.org/10.1007/978-3-319-49487-6_3.

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and É. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, no. 85, pp. 2825–2830, 2011.

X. Ying, “An Overview of Overfitting and its Solutions,” Journal of physics: Conference series, vol. 1168, no. 2, Art. no. 022022, Feb. 2019, doi: https://doi.org/10.1088/1742-6596/1168/2/022022.

R. Rezaee and J. Ekundayo, “Permeability Prediction Using Machine Learning Methods for the CO2 Injectivity of the Precipice Sandstone in Surat Basin, Australia,” Energies (Basel), vol. 15, no. 6, Art. no. 2053, Mar. 2022, doi: https://doi.org/10.3390/en15062053.

M. M. Hashim, G. M. Farman, and A. Askar, “Artificial Neural Network Application to Permeability Prediction from Nuclear Magnetic Resonance Log,” Iraqi Geological Journal, vol. 57, no. 2D, pp. 88–99, Oct. 2024, doi: https://doi.org/10.46717/igj.57.2D.7ms-2024-10-17.