Neural Network for Porosity Prediction in Carbonate Formation: A Case Study of the South of Iraq

Huda F. Alsaad; Safa J. Al-Kamil; Mohammed S.  Al-Radhi; Najm A.  Fadhih

doi:10.52716/jprs.v13i3.697

Authors

Huda F. Alsaad Basra Oil Company, Studies and Planning Division, Basra, Iraq
Safa J. Al-Kamil Southern Technical University, Basra, Iraq
Mohammed S. Al-Radhi Basra Oil Company, Basra, Iraq
Najm A. Fadhih Basra Oil Company, Basra, Iraq

DOI:

https://doi.org/10.52716/jprs.v13i3.697

Keywords:

: Porosity prediction, Faihaa oil field, Yamamma formation, Recurrent neural network, Seq2Seq, LSTM

Abstract

This study presents the application of a Sequence-to-Sequence (Seq2Seq) recurrent neural network for estimating porosity log data by leveraging information from other logs. The effectiveness of this technique in simulating porosity for heterogeneous reservoirs is demonstrated by employing data from the Yamama Formation in the Faihaa Oil field in southern Iraq. Four wells in the field were used for the model training and evaluation, where input data comprised density, neutron, gamma-ray, and porosity logs. The model's performance was assessed using absolute percentage, and root means squared errors, and the results were compared against actual data, revealing a significant correlation. These results establish the Seq2Seq recurrent neural network model as a superior option for predicting reservoir porosity from other good log data. They could have practical implications in estimating porosity for petroleum calculations.

.

References

Asquith G.B., Gibosn CH.R., "Basic Well Log Analysis for Geologists American Association of Petroleum Geologists," American Association of Petroleum Geologists, vol. 3, 1982. https://doi.org/10.1306/Mth3425

T. O. Abdullah, S. S. Ali, N. A Al-Ansari, and S. Knutsson, "Groundwater Vulnerability Mapping Using Lineament Density on Standard DRASTIC Model: Case Study in Halabja Saidsadiq Basin, Kurdistan. Region, Iraq", Engineering, vol. 07, no. 10, pp. 644-667, 2015. https://doi.org/10.4236/eng.2015.710057

Buday T., "The regional geology of Iraq", Stratigraphy and Paleogeography, Kassab, I. I. and Jassim, S.Z., (eds), Dar Al-Kutib Publ. House, Mosul, Iraq, 1980.

Basra Oil Company, "Seismic interpretation and inversion report of faihaa oil field," 2019.

Basra Oil Company, "Final well report of Faihaa-1, 2, 3, 4, 5 and Faihaa 6", respectively 2014, 2016, 2016, 2017, 2018 and 2018.

Basra Oil Company, "Final well reports of Faihaa-1, 2,3 , 4,5 and 6", 2020.

N. M. Nawi, W. H. Atomi, and M. Z. Rehman, "The Effect of Data Pre-Processing on Optimized Training of Artificial Neural Networks", Procedia Technology, vol. 11, pp. 32-39, 2013. https://doi.org/10.1016/j.protcy.2013.12.159

J. Brownlee, "Data Preparation for Machine Learning: Data Cleaning, Feature Selection, and Data Transforms in Python", Machine Learning Mastery, 2020.

S. Maetschke, R. Tennakoon, C. Vecchiola, and R. Garnavi, "nuts-flow/ml : data pre-processing for deep learning", arXiv:1708.06046, vol. 2, pp. 1-11, 2018. https://doi.org/10.48550/arXiv.1708.06046

M. S. H. Al-Radhi, S. J. D. Al-Kamil, and S. Tamás, “A model-based machine learning to develop a PLC control system for Rumaila degassing stations”, Journal of Petroleum Research and Studies, vol. 10, no. 4, pp. 1-18, Dec. 2020. https://doi.org/10.52716/jprs.v10i4.364

M. Z. Rehman, and N. M. Nawi, "The Effect of Adaptive Momentum in Improving the Accuracy of Gradient Descent Back Propagation Algorithm on Classification Problems", International Conference on Software Engineering and Computer Systems, Springer, Berlin, Heidelberg, vol. 179, no. 6, p. 380–390, 2011. https://doi.org/10.1007/978-3-642-22170-5_33

G. Lera and M. Pinzolas, "Neighborhood based Levenberg-Marquardt algorithm for neural network training", in IEEE Transactions on Neural Networks, vol. 13, no. 5, pp. 1200-1203, Sept. 2002. https://doi.org/10.1109/TNN.2002.1031951.

Diederik P. Kingma, Jimmy Lei Ba, "Adam: A Method for Stochastic Optimization", arXiv:1412.6980, vol. 9, 2015. https://doi.org/10.48550/arXiv.1412.6980

S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory", Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735

H. Sak, A. Senior, and F. Beaufays, "Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling", Interspeech conference, pp. 338-342, 2014.

A. Graves, "Generating Sequences With Recurrent Neural Networks," arXiv preprint arXiv:1308.0850, 2013. https://doi.org/10.48550/arXiv.1308.0850

I. Sutskever, O. Vinyals, and Q. V. Le, "Sequence to sequence learning with neural networks," Advances in Neural Information Processing Systems, vol. 27, pp. 3104– 3112, 2014.

A. Graves, "Generating sequences with recurrent neural networks", In ArXiv preprint arXiv:1308.0850, 2013. https://doi.org/10.48550/arXiv.1308.0850

A. M. Handhal, H. A. Chafeet, and N. A. Dahham, "Microfacies, Depositional Environments and Diagenetic Processes of the Mishrif and Yamama Formations at Faiha and Sindibad Fields, South Iraq", Iraqi Bulletin of Geology and Mining," Iraqi Bulletin of Geology and Mining, vol. 16, no. 2, pp. 51-74, 2020.

M. Al-Hassani, and S. Al-Dulaimi, "Biostratigraphy of Yamama Formation in Faihaa Oil Field, Southern Iraq," Iraqi Journal of Science, vol. 62, no. 5, pp. 1570-1586, 2021. https://doi.org/10.24996/ijs.2021.62.5.20

M. A. Ahmed, M. E. Nasser, and S. N. AL-Jawad, "Diagenesis Processes Impact on Reservoir Quality in Carbonate Yamama Formation /Faihaa Oil Field", Iraqi Journal of Science, vol. 61, no. 1, pp. 92-102, 2020. https://doi.org/10.24996/ijs.2020.61.1.10

Zuhoor J. Younis Al-Aani, Fahad M. Al-Najm and Zainab A. Khalaf, "Geological model Construction for Yamama Formation at Faihaa Oil Field- South of Iraq", Basrah Journal of Science, vol. 38, no. 3, pp. 521–543, 2020. https://doi.org/10.29072/basjs.2020310

B. Rafik and B. Kamel, "Predicion of permapility and porosity from well log data using the nonparametric regression with multivariat analysis and neural net wok", Egyptian Journal of Petroleum, vol. 26, no. 3, pp. 763-778, 2017. https://doi.org/10.1016/j.ejpe.2016.10.013

O. D. Saputro, Z. L. Maulana and F. D. E. Latief, "Porosity Log Prediction Using Artificial Neural Network", Journal of Physics: Conference Series, vol. 739, 2016. https://doi.org/10.1088/1742-6596/739/1/012092

Ernest N. Mbia, Ida L. Fabricius, Anette Krogsbøll, Peter Frykman, and Finn Dalhoff, "Permeability, compressibility and porosity of Jurassic shale from theNorwegian–Danish Basin", Petroleum Geoscience, vol. 20, pp. 257-281, 2014. https://doi.org/10.1144/petgeo2013-035

G. M. Hamada, A. Elsakka and C. Y. Nyein, "Artificial Neural Network (ANN) Prediction of Porosity and Water Saturation of Shaly Sandstone Reservoirs", Advances in Applied Science Research, vol. 9, no. 2, pp. 26-31, 2018.

M. S. H. Al-Radhi, S. J. D. Al-Kamil, and S. Tamás, “A model-based machine learning to develop a PLC control system for Rumaila degassing stations”, Journal of Petroleum Research and Studies, vol. 10, no. 4, pp. 1-18, Dec. 2020. https://doi.org/10.52716/jprs.v10i4.364