USING THE METHOD OF SUPPORT VECTORS ON THE EXAMPLE OF PREDICTING THE PROPERTIES OF HYDROCARBON DEPOSITS
DOI:
https://doi.org/10.34185/1991-7848.itmm.2024.01.040Keywords:
oil, gas, machine learning, support vector machine, reservoir properties, reservoir management.Abstract
. Permeability stands as a crucial parameter in characterizing any hydrocarbon reservoir, rendering it indispensable for accurate solutions to numerous petroleum engineering challenges. Conventional methods for determining permeability, such as core analysis and well test techniques, are notably costly and time-consuming. Hence, efforts have been directed towards leveraging artificial neural networks to establish correlations between well log data and core permeability. Recent advancements in artificial intelligence techniques have introduced a robust machine learning methodology known as support vector machine (SVM). This study aims to employ SVM in predicting the permeability of three gas wells within the Southern Pars field. The results obtained from SVM demonstrated a correlation coefficient of 0.97 between core and predicted permeability for the testing dataset.
References
Nello Cristianini, John Shawe-Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. — Cambridge University
Press, 2000. — ISBN 978-1-139-64363-4.
L. Wang, Support Vector Machines: Theory and Applications, Springer,
Berlin, Germany, 2005.
V. N. Vapnik, The Nature of Statistical Learning Theory, Springer, New York, NY,
USA, 2nd edition, 2000.
R. Gholami, A. R. Shahraki, M. Jamali Paghaleh, "Prediction of Hydrocarbon Reservoirs Permeability Using Support Vector Machine", Mathematical Problems in Engineering,
vol. 2012, Article ID 670723, 18 pages, 2012. https://doi.org/10.1155/2012/670723
A. Bhatt, Reservoir properties from well logs using neural networks, Ph.D. thesis, Department of Petroleum Engineering and Applied Geophysics, Norwegian University of Science and Technology, A dissertation for the partial fulfillment of requirements, 2002.
S. Mohaghegh, S. Ameri, and K. Aminian, “A methodological approach for reservoir heterogeneity characterization using artificial neural networks,” Journal of Petroleum Science and Engineering, vol. 16, pp. 263–274, 1996.
