Hydrocarbon reservoir potential mapping through Permeability estimation by a CUDNNLSTM Deep Learning Algorithm

Document Type : Research Paper

Authors

School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran.

10.22059/ijmge.2023.356428.595045

Abstract

Potential mapping of Permeability is a crucial factor in determining the productivity of an oil and gas reservoirs. Accurately estimating permeability is essential for optimizing production and reducing operational costs. In this study, we utilized the CUDNNLSTM algorithm to estimate reservoir permeability. The drilling core data were divided into a training pool and a validation pool, with 80% of the data used for training and 20% for validation. Based on the high variation permeability along the formation, we developed the CUDNNLSTM algorithm for estimating permeability. First, due to the highly dispersed signals from the sonic, density, and neutron logs, which are related to permeability, we adjusted the algorithm to train for 1000 epochs. However, once the validation loss value reached 0.0158, the algorithm automatically stopped the training process at epoch number 500. Within 500 epochs of the algorithm, we achieved an impressive accuracy of 98.42%. Using the algorithm, we estimated the permeabilities of the entire set of wells, and the results were highly satisfactory. The CUDNNLSTM algorithm due to the large number of neurons and the ability to solve high-order equations on the GPU is a powerful tool for accurately estimating permeability in oil and gas reservoirs. Its ability to handle highly dispersed signals from various logs makes it a valuable asset in optimizing production and reducing operational costs, because it is much cheaper than the cost of core extraction and has very high accuracy.

Keywords

Main Subjects

References

[1].    M. Arab Amiri, M. Karimi and A. Alimohammadi, "Hydrocarbon resources potential mapping using the evidential belief functions and GIS, Ahvaz/Khuzestan Province, southwest Iran," Arabian Journal of Geosciences, vol. 8, no. 6, pp. 1-13, 2014.
[2]    M. Badawy, T. Abdel Fattah, S. Abou Shagar, A. Diab, M. Rashed and M. Osman, "Identifying the hydrocarbon potential from seismic, geochemical, and wireline data of the Sallum intra-basin, North Western Desert of Egypt," NRIAG Journal of Astronomy and Geophysics, vol. 12, no. 1, pp. 1-18, 2022.
[3]    . C. W. Spencer, "Review of characteristics of low-permeability gas reservoirs in western United States," AAPG, vol. 73, no. 5, pp. 613-629, 1989.
[4]    D. Bennion, R. Bietz, F. Thomas and M. Cimolai, "Reductions In the Productivity of Oil And Low Permeability Gas Reservoirs Due to Aqueous Phase Trapping," journal of canadian petroleum technology, vol. 33, no. 09, 1994.
[5]    Y. D. Wang, M. J. Blunt, R. T. Armstrong and P. Mostaghimi, "Deep learning in pore scale imaging and modeling," Earth-Science Reviews, vol. 215, 2021.
[6]    H. Al Khalifah, P. Glover and P. Lorinczi, "Permeability prediction and diagenesis in tight carbonates using machine learning techniques," Marine and Petroleum Geology, vol. 112, 2020.
[7]    M. Abedini, M. Ziaii and J. Ghiasi-freez, "The application of Committee machine with particle swarm optimization to the assessment of permeability based on thin section image analysis," IJMGE, vol. 52, no. 2, pp. 177-185, 2018.
[8]    F. Feng, P. Wang, Z. Wei, G. Jiang, D. Xu and J. Zhang, "A New Method for Predicting the Permeability of Sandstone in Deep Reservoirs," Geofluids, pp. 1-16, 2020.
[9]    R. Rezaee and J. Ekundayo, "Permeability Prediction Using Machine Learning Methods for the CO2 Injectivity of the Precipice Sandstone in Surat Basin, Australia," Energies, vol. 6, 2022.
[10] M. A. Ahmadi and Z. Chen, "Comparison of machine learning methods for estimating permeability and porosity of oil reservoirs via petro-physical logs," Petroleum, vol. 5, no. 3, 2019.
[11] B. Singh, P. Sihag, S. M. Pandhiani and S. Gautam, "Estimation of permeability of soil using easy measured soil parameters: assessing the artificial intelligence-based models," journal of Hydraulic Engineering, 2019.
[12] N. Alqahtani, R. T. Armstrong and P. Mostaghimi, "Deep Learning Convolutional Neural Networks to Predict Porous Media Properties," in SPE Asia Pacific Oil and Gas Conference and Exhibition, 2018.
[13] Y. D. Wang, T. Chung, R. T. Armstrong and P. Mostaghimi, "ML-LBM: Predicting and Accelerating Steady State Flow Simulation in Porous Media with Convolutional Neural Networks," Transp Porous Med, pp. 49-75, 2021.
[14] S. George W, "Measurement of permeability I. Theory," Journal of Non-Crystalline Solids, vol. 113, no. 2-3, pp. 107-118, 1989.
[15] D. Sundaram, J. Tamás Svidró, A. Diószegi and J. Svidró, "Measurement of Darcian Permeability of foundry sand mixtures," international Journal of Cast Metals Research, vol. 34, no. 2, pp. 97-103, 2021.
[16] R. Baker and j. Doolittle, "Permeability measurement techniques for porous media: A review," Journal of hydrology, vol. 303, pp. 1-4, 2005.
[17] B. Azizzadeh mehmandost olya and R. Mohebian, "Q-FACTOR ESTIMATION FROM VERTICAL SEISMIC PROFILING (VSP) WITH DEEP LEARNING ALGORITHM, CUDNNLSTM," JOURNAL OF SEISMIC EXPLORATION, pp. 89-104, 2023.
[18] A. Chawla, P. Jacob, B. Lee and S. Fallon, "Bidirectional LSTM autoencoder for sequence-based anomaly detection in cyber security," International Journal of Simulation--Systems, Science & Technology, 2019.
[19] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, pp. 1735-1780, 1997.
[20] C. Kyunghyun, M. Bart van, C. Gulcehre, D. Bahdanau, B. Fethi and H. Schwenk, "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation," arXiv, 2014.
[21] T. Stérin, N. Farrugia and V. Gripon, "An intrinsic difference between vanilla rnns and gru models," COGNTIVE, p. 84, 2017.
[22] C. Sharan, W. Cliff, V. Philippe, C. Jonathan, T. John and C. Bryan , "cuDNN: Efficient Primitives for Deep Learning," ARXIV, 2014.
[23] j. Soete, L. Kleipool, H. Claes, S. Claes, H. Hamaekers, S. Kele and M. Özkul, "Acoustic properties in travertines and their relation to porosity and pore types," Marine and Petroleum Geology, vol. 59, pp. 320-335, 2015.
[24] G. Hamada and V. Joseph, "Developed correlations between sound wave velocity and porosity, permeability and mechanical properties of sandstone core samples," Petroleum Research, vol. 5, no. 4, pp. 326-338, 2020.
[25] C. Kyunghyun , B. v. Merrienboer, G. Caglar , B. Dzmitry , B. Fethi and S. Holger , "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation," ARXIV, 2014.
International Journal of Mining and Geo-Engineering
Volume 57, Issue 4
December 2023
Pages 389-396

Files

Share

How to cite

Statistics