Application of neighborhood information-enhanced MLSTM in reservoir parameter prediction: a case study of heterogeneous carbonate reservoirs

WANG Xin; JIANG Tao; ZHOU Mi; GAO GuoHai; JIANG Wei; MEI QingYan; ZHAO Xiang

doi:10.6038/pg2024HH0153

2024 Vol. 39, No. 2

Article Contents

Article navigation > Progress in Geophysics > 2024 > 39(2): 620-633

Next Article Previous Article

WANG Xin, JIANG Tao, ZHOU Mi, GAO GuoHai, JIANG Wei, MEI QingYan, ZHAO Xiang. 2024. Application of neighborhood information-enhanced MLSTM in reservoir parameter prediction: a case study of heterogeneous carbonate reservoirs. Progress in Geophysics, 39(2): 620-633. doi: 10.6038/pg2024HH0153

Citation:

WANG Xin, JIANG Tao, ZHOU Mi, GAO GuoHai, JIANG Wei, MEI QingYan, ZHAO Xiang. 2024. Application of neighborhood information-enhanced MLSTM in reservoir parameter prediction: a case study of heterogeneous carbonate reservoirs. Progress in Geophysics, 39(2): 620-633. doi: 10.6038/pg2024HH0153

Application of neighborhood information-enhanced MLSTM in reservoir parameter prediction: a case study of heterogeneous carbonate reservoirs

1.
School of Computer Science, Southwest Petroleum University, Chengdu 610500, China
2.
Exploration and Development Research Institute, PetroChina Southwest Oil and Gasfield Company, Chengdu 610043, China
Fund Project:
油气藏地质及开发工程国家重点实验室开放性研究课题(PLN 2022-33)资助

More Information

Corresponding author: ZHOU Mi, E-mail: 1203212378@swpu.edu.cn

Received Date: 28 May 2023

Revised Date: 23 November 2023

Publish Date: 20 April 2024

Abstract

Abstract

Accurately predicting reservoir parameters such as porosity, permeability, and water saturation is a fundamental basis for reservoir fine evaluation and oil and gas exploration. Traditional methods for the prediction of reservoir parameters often rely on empirical formulas or simplified geological models that are built upon well logging data. However, these methods tend to overlook the nonlinear relationships among well logs and exhibit poor generalization ability when applied to complex reservoirs. Facing the strong heterogeneity of carbonate reservoirs and the sequential characteristics of well logs, this paper proposes a Fused Neighborhood information Multi-layer Long Short-Term Memory network (FN-MLSTM) to address the challenge of parameters prediction of carbonate reservoir. Firstly, the Principal Component Analysis (PCA) is employed to extract independent features from well logs. Then, an unsupervised clustering technique based on the K-Means algorithm and its optimization is employed to form well groups. By incorporating the resulting neighborhood information, a Multi-layer Long Short-Term Memory network (MLSTM) is built to predict the reservoir parameters. Experimental results demonstrate that the proposed model outperforms other methods such as Long Short-Term Memory network (LSTM), Deep Neural Network (DNN), eXtreme Gradient Boosting (XGBoost), and Random Forests (RF) in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²) on a test set of 22 wells in a specific region. This highlights the outstanding performance of the model in parameters prediction. Moreover, ablation experiments show that the integration of neighborhood information effectively improves the predictive accuracy of the model.
- Reservoir parameter prediction /
- Well logs /
- Multi-layer Long Short-Term Memory network (MLSTM) /
- Principal component analysis /
- Clustering

FullText(HTML)

References

	Al-Anazi A F, Gates I D. 2010. Support vector regression for porosity prediction in a heterogeneous reservoir: a comparative study. Computers & Geosciences, 36(12): 1494-1503. Google Scholar
	Alizadeh B, Najjari S, Kadkhodaie-Ilkhchi A. 2012. Artificial neural network modeling and cluster analysis for organic facies and burial history estimation using well log data: a case study of the South Pars Gas Field, Persian Gulf, Iran. Computers & Geosciences, 45: 261-269. doi: 10.3970/cmc.2012.028.261 CrossRef Google Scholar
	An P, Cao D P, Zhao B Y, et al. 2019. Reservoir physical parameters prediction based on LSTM recurrent neural network. Progress in Geophysics (in Chinese), 34(5): 1849-1858, doi: 10.6038/pg2019CC0366. CrossRef Google Scholar
	Archie G E. 1942. The electrical resistivity log as an aid in determining some reservoir characteristics. Transactions of the AIME, 146(1): 54-62. doi: 10.2118/942054-G CrossRef Google Scholar
	Bedi J, Toshniwal D. 2019. Deep learning framework to forecast electricity demand. Applied Energy, 238: 1312-1326. doi: 10.1016/j.apenergy.2019.01.113 CrossRef Google Scholar
	Burchette T P. 2012. Carbonate rocks and petroleum reservoirs: a geological perspective from the industry. Geological Society, London, Special Publications, 370: 17-37. doi: 10.1144/SP370.14 CrossRef Google Scholar
	Chen W, Yang L Q, Zha B, et al. 2020. Deep learning reservoir porosity prediction based on multilayer long short-term memory network. Geophysics, 85(4): WA213-WA225. doi: 10.1190/geo2019-0261.1 CrossRef Google Scholar
	Coates G R, Galford J, Mardon D, et al. 1998. A new characterization of bulk-volume irreducible using magnetic resonance. The Log Analyst, 39(1): SPWLA-1998-v39n1a4. Google Scholar
	Ding S, Yang S F, Lu W, et al. 2023. Robust prediction for water saturation based on strategy of light gradient boosting machine. Progress in Geophysics (in Chinese), 38(1): 185-200, doi: 10.6038/pg2023GG0145. CrossRef Google Scholar
	Gu Y F, Bao Z D, Lin Y B, et al. 2017. The porosity and permeability prediction methods for carbonate reservoirs with extremely limited logging data: stepwise regression vs. N-way analysis of variance. Journal of Natural Gas Science and Engineering, 42: 99-119. doi: 10.1016/j.jngse.2017.03.010 CrossRef Google Scholar
	Guan Q Q. 2022. Prediction method of total organic carbon in shale oil reservoir based on PCA-CNN model. Petroleum Geology and Recovery Efficiency (in Chinese), 29(6): 49-57, doi: 10.13673/j.cnki.cn37-1359/te.202109017. CrossRef Google Scholar
	Guo J C, Zhou H Y, Zeng J, et al. 2020. Advances in low-field nuclear magnetic resonance (NMR) technologies applied for characterization of pore space inside rocks: a critical review. Petroleum Science, 17(5): 1281-1297. doi: 10.1007/s12182-020-00488-0 CrossRef Google Scholar
	Han X H, Zhang H, Mao X J, et al. 2021. A method of gas porosity measurement for tight reservoirs based on mechanical analysis of core chamber. Chinese Journal of Geophysics (in Chinese), 64(1): 289-297, doi: 10.6038/cjg2021O0345. CrossRef Google Scholar
	Hu X Y, Yuan W, Tang Z, et al. 2018. Calculation method of shaly sands reservoir water saturation based on petrophysical facies. Progress in Geophysics (in Chinese), 33(2): 808-814, doi: 10.6038/pg2018BB0096. CrossRef Google Scholar
	Karamizadeh S, Abdullah S M, Manaf A A, et al. 2013. An overview of principal component analysis. Journal of Signal and Information Processing, 4(3B): 173-175. Google Scholar
	Kenyon W E, Day P I, Straley C, et al. 1988. A three-part study of NMR longitudinal relaxation properties of water-saturated sandstones. SPE Formation Evaluation, 3(3): 622-636. doi: 10.2118/15643-PA CrossRef Google Scholar
	Khaksar A, Griffiths C M. 1998. Porosity form sonic log in gas-bearing shaly sandstones: field data versus empirical equations. Exploration Geophysics, 29(3-4): 440-446. doi: 10.1071/EG998440 CrossRef Google Scholar
	Kuila U, McCarty D K, Derkowski A, et al. 2014. Total porosity measurement in gas shales by the water immersion porosimetry (WIP) method. Fuel, 117: 1115-1129. doi: 10.1016/j.fuel.2013.09.073 CrossRef Google Scholar
	Liu H Y, Tian Z Y, Liu B, et al. 2018. Pore types, origins and control on reservoir heterogeneity of carbonate rocks in Middle Cretaceous Mishrif Formation of the West Qurna oilfield, Iraq. Journal of Petroleum Science and Engineering, 171: 1338-1349. doi: 10.1016/j.petrol.2018.08.034 CrossRef Google Scholar
	Liu X Y, Chen X H, Li J Y, et al. 2016. Reservoir physical property prediction based on kernel-Bayes discriminant method. Acta Petrolei Sinica, 37(7): 878-886, doi: 10.7623/syxb201607006. CrossRef Google Scholar
	Mukaka M M. 2012. Statistics corner: A guide to appropriate use of correlation coefficient in medical research. Malawi Medical Journal, 24(3): 69-71. Google Scholar
	Otchere D A, Ganat T O A, Gholami R, et al. 2021a. A novel custom ensemble learning model for an improved reservoir permeability and water saturation prediction. Journal of Natural Gas Science and Engineering, 91: 103962, doi: 10.1016/j.jngse.2021.103962. CrossRef Google Scholar
	Otchere D A, Ganat T O A, Gholami R, et al. 2021b. Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties: Comparative analysis of ANN and SVM models. Journal of Petroleum Science and Engineering, 200: 108182, doi: 10.1016/j.petrol.2020.108182. CrossRef Google Scholar
	Pan S W, Zheng Z C, Guo Z, et al. 2022. An optimized XGBoost method for predicting reservoir porosity using petrophysical logs. Journal of Petroleum Science and Engineering, 208: 109520, doi: 10.1016/j.petrol.2021.109520. CrossRef Google Scholar
	Rousseeuw P J. 1987. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20: 53-65. doi: 10.1016/0377-0427(87)90125-7 CrossRef Google Scholar
	Selim S Z, Ismail M A. 1984. K-means-type algorithms: a generalized convergence theorem and characterization of local optimality. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, PAMI-6(1): 81-87. doi: 10.1109/TPAMI.1984.4767478 CrossRef Google Scholar
	Shao R B, Xiao L Z, Liao G Z, et al. 2022. Multitask learning based reservoir parameters prediction with geophysical logs. Chinese Journal of Geophysics (in Chinese), 65(5): 1883-1895, doi: 10.6038/cjg2022P0177. CrossRef Google Scholar
	Song J G, Gao Q S, Li Z. 2016. Application of random forests for regression to seismic reservoir prediction. Oil Geophysical Prospecting (in Chinese), 51(6): 1202-1211, doi: 10.13810/j.cnki.issn.1000-7210.2016.06.021. CrossRef Google Scholar
	Syakur M A, Khotimah B K, Rochman E M S, et al. 2018. Integration k-means clustering method and elbow method for identification of the best customer profile cluster[J]. IOP Conference Series: Materials Science and Engineering, 336: 012017, doi: 10.1088/1757-899X/336/1/012017. CrossRef Google Scholar
	Tian H, Li M, Yang M, et al. 2015. Study on the porosity exponent of fractured-vuggy reservoirs-based on triple porosity model before and after improvement. Progress in Geophysics, 30(4): 1779-1784, doi: 10.6038/pg20150434. CrossRef Google Scholar
	Tibshirani R, Walther G, Hastie T. 2001. Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society Series B: Statistical Methodology, 63(2): 411-423. doi: 10.1111/1467-9868.00293 CrossRef Google Scholar
	Wood D A. 2020. Predicting porosity, permeability and water saturation applying an optimized nearest-neighbour, machine-learning and data-mining network of well-log data. Journal of Petroleum Science and Engineering, 184: 106587, doi: 10.1016/j.petrol.2019.106587. CrossRef Google Scholar
	Yang L, Shami A. 2020. On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing, 415: 295-316. doi: 10.1016/j.neucom.2020.07.061 CrossRef Google Scholar
	Yu C L, Lin C Y. 2007. Advancement of reservoir heterogeneity research. Petroleum Geology and Recovery Efficiency (in Chinese), 14(4): 15-18, 22, doi: 10.3969/j.issn.1009-9603.2007.04.004. CrossRef Google Scholar
	Yu Y, Si X S, Hu C H, et al. 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 31(7): 1235-1270. doi: 10.1162/neco_a_01199 CrossRef Google Scholar
	Zhang Z, Zhang H, Li J, et al. 2021. Permeability and porosity prediction using logging data in a heterogeneous dolomite reservoir: An integrated approach. Journal of Natural Gas Science and Engineering, 86: 103743, doi: 10.1016/j.jngse.2020.103743. CrossRef Google Scholar
	安鹏, 曹丹平, 赵宝银, 等. 2019. 基于LSTM循环神经网络的储层物性参数预测方法研究. 地球物理学进展, 34(5): 1849-1858, doi: 10.6038/pg2019CC0366. CrossRef Google Scholar
	丁圣, 杨尚锋, 路巍, 等. 2023. 基于高效梯度提升策略含水饱和度预测模型. 地球物理学进展, 38(1): 185-200, doi: 10.6038/pg2023GG0145. CrossRef Google Scholar
	管倩倩. 2022. 基于PCA-CNN模型的页岩储层有机碳含量预测方法. 油气地质与采收率, 29(6): 49-57, doi: 10.13673/j.cnki.cn37-1359/te.202109017. CrossRef Google Scholar
	韩学辉, 张浩, 毛新军, 等. 2021. 基于岩心室应力应变和不确定度分析的致密储层氦孔隙度测量方法. 地球物理学报, 64(1): 289-297, doi: 10.6038/cjg2021O0345. CrossRef Google Scholar
	胡向阳, 袁伟, 汤翟, 等. 2018. 基于岩石物理相的泥质砂岩储层含水饱和度计算方法. 地球物理学进展, 33(2): 808-814, doi: 10.6038/pg2018BB0096. CrossRef Google Scholar
	刘兴业, 陈小宏, 李景叶, 等. 2016. 基于核贝叶斯判别法的储层物性参数预测. 石油学报, 37(7): 878-886, doi: 10.7623/syxb201607006. CrossRef Google Scholar
	邵蓉波, 肖立志, 廖广志, 等. 2022. 基于多任务学习的测井储层参数预测方法. 地球物理学报, 65(5): 1883-1895, doi: 10.6038/cjg2022P0177. CrossRef Google Scholar
	宋建国, 高强山, 李哲. 2016. 随机森林回归在地震储层预测中的应用. 石油地球物理勘探, 51(6): 1202-1211, doi: 10.13810/j.cnki.issn.1000-7210.2016.06.021. CrossRef Google Scholar
	田瀚, 李明, 杨敏, 等. 2015. 缝洞型储层孔隙度指数的计算研究: 基于改进前后的三孔隙度模型. 地球物理学进展, 30(4): 1779-1784, doi: 10.6038/pg20150434. CrossRef Google Scholar
	于翠玲, 林承焰. 2007. 储层非均质性研究进展. 油气地质与采收率, 14(4): 15-18, 22, doi: 10.3969/j.issn.1009-9603.2007.04.004. CrossRef Google Scholar