Reservoir Permeability Prediction Based on Machine Learning
DOI:
https://doi.org/10.62051/ijnres.v3n1.17Keywords:
Machine learning; Permeability prediction; Carbonate reservoir.Abstract
This paper discusses the challenges and solutions of carbonate reservoir permeability prediction. It is difficult to predict the permeability of carbonate reservoir because of its complex pore structure and heterogeneity. Although NMR logging is useful for characterizing pore structure, its high cost limits its wide application. Therefore, in this paper, machine learning technology and petrophysical logging data are used to compare the permeability prediction models. By constructing and testing permeability prediction models based on artificial neural network (ANN), decision tree (DT) and support vector machine (SVM), the advantages and limitations of various methods are analyzed, which provides new tools and methods for oil and gas exploration and development.
References
Wang Hua, Zhang Yushun. Current situation and prospect of artificial intelligence processing and interpretation of logging data [J]. Well Logging Technology, 2021,45 (4): 345-356.
YANG Y, SUN J, LI H, et al. ADMM-CSNet: a deep learning approach for image compressive sensing [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 42 (3): 521-538.
LAM F, LI Y, PENG X. Constrained magnetic resonance spectroscopic imaging by learning nonlinear low dimensional models [J]. IEEE Transactions on Medical Imaging, 2019, 39 (3): 545-555.
Zhang Cymbals, Zhu Jun, Su Hang. Towards the third generation of Artificial Intelligence [J]. Science in China: Information Science, 2020,50 (9) : 1281-1302.
LUO S H, XIAO L Z, JIN Y, et al. A machine learning framework for low-field NMR data processing [J]. Petroleum Science, 2022, 19 (2): 581-593.
HAMADA G M, ELSHAFEI M A. Neural network prediction of porosity and permeability of heterogeneous gas sand reservoirs [C]//SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition, Al-Khobar, Saudi Arabia, 2009.
ZHOU X, SU G, WANG L, et al. The inversion of 2D NMR relaxometry data using L1 regularization [J]. Journal of Magnetic Resonance, 2017, 275: 46-54.
SONG Y Q, KAUSIK R. NMR application in unconven tional shale reservoirs-a new porous media research frontier [J]. Progress in Nuclear Magnetic Resonance Spectroscopy, 2019, 112: 17-33.
XIE R, WU Y, LIU K, et al. De-noising methods for NMR logging echo signals based on wavelet transform [J]. Journal of Geophysics and Engineering, 2014, 11 (3): 035003.
GU M, XIE R, XIAO L. A novel method for NMR data denoising based on discrete cosine transform and variable length windows [J]. Journal of Petroleum Science and Engineering, 2021, 207: 108852.
GE X, FAN Y, LI J, et al. Noise reduction of nuclear magnetic resonance (NMR) transversal data using improved wavelet transform and exponentially weighted moving average (EWMA) [J]. Journal of Magnetic Resonance, 2015, 251: 71-83.
Xiao Lizhi. The integration and interpretability of machine learning data-driven and mechanism model [J]. Geophysical Prospecting for Petroleum, 2022, 61 (2): 205-212.
LUO S, XIAO L, ZONG F, et al. Inside-out azimuth ally selective NMR tool using array coil and capacitive decoupling [J]. Journal of Magnetic Resonance, 2020, 315: 106735.
GUO J, XIE R, XIAO L, et al. Nuclear magnetic resonance T1–T 2 inversion with double objective functions [J]. Journal of Magnetic Resonance, 2019, 308: 106562.
PARASRAM T, DAOUD R, XIAO D. T2 analysis using artificial neural networks [J]. Journal of Magnetic Resonance, 2021, 325: 106930.
Zhang Zhe, Liao Guangzhi, Xiao Lizhi, et al. Prediction of NMR T2 spectrum based on Machine Learning algorithm [J]. Science Technology and Engineering, 2023,23 (17): 7282-7292.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Qi Wang
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
