Method and practice of deep favorable shale reservoir prediction based on machine learning

CHENG Bingjie, XU Tianji, LUO Shiyi, CHEN Tianjie, LI Yongsheng

doi:10.11698/PED.20220185

Petroleum Exploration and Development >

0 20221016 - 20221016

DOI: https://doi.org/10.11698/PED.20220185

Method and practice of deep favorable shale reservoir prediction based on machine learning

Expand

1. State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, Chengdu 610059, China;
2. College of Geophysics, Chengdu University of Technology, Chengdu 610059, China;
3. School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China;
4. Yangtze Delta Region Institute of University of Electronic Science and Technology of China, Huzhou 313000, China

Received date: 2022-06-20

Revised date: 2022-07-18

Online published: 2022-08-15

Fold

Abstract

A set of method for predicting the favorable reservoir of deep shale gas based on machine learning is proposed through research of parameter correlation feature analysis principle, intelligent calculation method based on convolution neural network (CNN), and integrated fusion characterization method based on KPCA nonlinear dimension reduction principle. (1) High-dimensional correlation characteristics of core and logging data are analyzed based on Pearson correlation coefficient. (2) The nonlinear dimension reduction method of kernal principal component analysis (KPCA) is used to characterize complex high-dimensional data, so as to efficiently and accurately understand the core and logging response laws to favorable reservoirs. (3) CNN and logging data are used to train and verify the model similar to the underground reservoir. (4) CNN and seismic data are used to intelligently predict favorable reservoir parameters such as organic carbon content, gas content, brittleness and in-situ stress to effectively solve the problem of nonlinear and complex feature extraction in reservoir prediction. (5) KPCA is used to eliminate complex redundant information, mine big data characteristics of favorable reservoirs, and integrate and characterize various parameters to realize the comprehensive evaluation of reservoirs. This method has been used to predict the spatial distribution of favorable shale reservoirs in the Ordovician Wufeng Formation to Silurian Longmaxi Formation of Weirong shale gas field in Sichuan Basin. The predicted results are highly consistent with the actual core, logging, productivity data, proving that this method can provide effective support for the exploration and development of deep shale gas.

Key words： Pearson correlation coefficient; kernel principal component analysis; convolution neural network; machine learning; deep shale gas; favorable reservoir prediction; Ordovician- Silurian; Weirong shale gas field; Sichuan Basin

Cite this article

CHENG Bingjie, XU Tianji, LUO Shiyi, CHEN Tianjie, LI Yongsheng . Method and practice of deep favorable shale reservoir prediction based on machine learning[J]. Petroleum Exploration and Development, 0 : 20221016 -20221016 . DOI: 10.11698/PED.20220185

References

[1] 马新华, 谢军, 雍锐, 等. 四川盆地南部龙马溪组页岩气储集层地质特征及高产控制因素[J]. 石油勘探与开发, 2020, 47(5): 841-855.
MA Xinhua, XIE Jun, YONG Rui, et al.Geological characteristics and high production control factors of shale gas reservoirs in Silurian Longmaxi Formation, southern Sichuan Basin, SW China[J]. Petroleum Exploration and Development. 2020, 47(5): 841-855.
[2] 戴金星, 倪云燕, 刘全有, 等. 四川超级气盆地[J]. 石油勘探与开发, 2021, 48(6): 1081-1088.
DAI Jinxing, NI Yunyan, LIU Quanyou, WU Xiaoqi, et al.Sichuan super gas basin in southwest China[J]. Petroleum Exploration and Development. 2021, 48(6): 1081-1088.
[3] 邹才能, 赵群, 丛连铸, 等. 中国页岩气开发进展、潜力及前景[J]. 天然气工业, 2021, 41(1): 1-14.
ZOU Caineng, ZHAO Qun, CONG Lianzhu, et al.Development progress, potential and prospect of shale gas in China[J]. Natural Gas Industry, 2021, 41(1): 1-14.
[4] 郭彤楼. 深层页岩气勘探开发进展与攻关方向[J]. 油气藏评价与开发, 2021, 11(1): 1-6.
GUO Tonglou.Progress and research direction of deep shale gas exploration and development[J]. Reservoir Evaluation and Development, 2021, 11(1): 1-6.
[5] WOOD D, SCHMIT B E, RIGGINS L, et al.Cana Woodford stimulation practices—a case history[R]. SPE 143960-MS, 2011.
[6] FARINAS M, FONSECA E.Hydraulic fracturing simulation case study and post frac analysis in the Haynesville shale[R]. SPE 163847-MS, 2013.
[7] 徐中华, 郑马嘉, 刘忠华, 等. 四川盆地南部地区龙马溪组深层页岩岩石物理特征[J]. 石油勘探与开发. 2020, 47(6): 1100-1110.
XU Zhonghua, ZHENG Majia, LIU Zhonghua, et al.Petrophysical properties of deep Longmaxi Formation shales in the southern Sichuan Basin, SW China[J]. Petroleum Exploration and Development. 2020, 47(6): 1100-1110.
[8] 张金川, 陶佳, 李振, 等. 中国深层页岩气资源前景和勘探潜力[J]. 天然气工业, 2021, 41(1): 15-28.
ZHANG Jinchuan, TAO Jia, LI Zhen, et al.Prospect of deep shale gas resources in China[J]. Natural Gas Industry, 2021, 41(1): 15-28.
[9] ZOU C N, YANG Z, ZHU R K, et al.Geologic significance and optimization technique of sweet spots in unconventional shale systems[J]. Journal of Asian Earth Sciences, 2019, 178: 3-19.
[10] 唐建明, 徐天吉, 程冰洁, 等. 四川盆地深层页岩气“甜点”预测与钻井工程辅助设计技术[J]. 石油物探, 2021, 60(3): 479-487.
TANG Jianming, XU Tianji, CHENG Bingjie, et al.Sweet-spot prediction and aided design for drilling engineering: Application to deep shale gas reservoirs in the Sichuan Basin[J]. Geophysical Prospecting for Petroleum, 2021, 60(3): 479-487.
[11] 马永生, 张建宁, 赵培荣, 等. 物探技术需求分析及攻关方向思考: 以中国石化油气勘探为例[J]. 石油物探, 2016, 55(1): 1-9.
MA Yongsheng, ZHANG Jianning, ZHAO Peirong, et al.Requirement analysis and research direction for the geophysical prospecting technology of Sinopec[J]. Geophysical Prospecting for Petroleum, 2016, 55(1): 1-9.
[12] 刘瑞合, 赵金玉, 印兴耀, 等. VTI介质各向异性参数层析反演策略与应用[J]. 石油地球物理勘探, 2017, 52(3): 484-490, 3.
LIU Ruihe, ZHAO Jinyu, YIN Xingyao, et al.Strategy of anisotropic parameter tomography inversion in VTI medium[J]. Oil Geophysical Prospecting, 2017, 52(3): 484-490, 3.
[13] SONG Y H, CHEN H, WANG X M.Stepwise inversion method for determining anisotropy parameters in a horizontal transversely isotropic formation[J]. Applied Geophysics, 2019, 16(2): 233-242.
[14] 许杰, 何治亮, 董宁, 等. 含气页岩有机碳含量地球物理预测[J]. 石油地球物理勘探, 2013, 48(S1): 64-68, 202, 7.
XU Jie, HE Zhiliang, DONG Ning, et al. Total organic carbon content prediction of gas-bearing shale with geophysical methods[J]. Oil Geophysical Prospecting, 2013, 48(S1): 64-68, 202, 7.
[15] 徐天吉, 程冰洁, 胡斌, 等. 基于VTI介质弹性参数的页岩脆性预测方法及其应用[J]. 石油与天然气地质, 2016, 37(6): 971-978.
XU Tianji, CHENG Bingjie, HU Bin, et al.Shale brittleness prediction based on elastic parameters of VTI media[J]. Oil & Gas Geology, 2016, 37(6): 971-978.
[16] HE J M, ZHANG Z B, LI X.Numerical analysis on the formation of fracture network during the hydraulic fracturing of shale with pre-existing fractures[J]. Energies, 2017, 10(6): 736.
[17] KRESSE O, WENG X W.Numerical modeling of 3D hydraulic fractures interaction in complex naturally fractured formations[J]. Rock Mechanics and Rock Engineering, 2018, 51(12): 3863-3881.
[18] LI S B, ZHANG D X.A fully coupled model for hydraulic-fracture growth during multiwell-fracturing treatments: Enhancing fracture complexity[J]. SPE Production & Operations, 2018, 33(2): 235-250.
[19] 沈骋, 郭兴午, 陈马林, 等. 深层页岩气水平井储层压裂改造技术[J]. 天然气工业, 2019, 39(10): 68-75.
SHEN Cheng, GUO Xingwu, CHEN Malin, et al.Horizontal well fracturing stimulation technology for deep shale gas reservoirs[J]. Natural Gas Industry, 2019, 39(10): 68-75.
[20] 刘清友, 朱海燕, 陈鹏举. 地质工程一体化钻井技术研究进展及攻关方向: 以四川盆地深层页岩气储层为例[J]. 天然气工业, 2021, 41(1): 178-188.
LIU Qingyou, ZHU Haiyan, CHEN Pengju.Research progress and direction of geology-engineering integrated drilling technology: A case study on the deep shale gas reservoirs in the Sichuan Basin[J]. Natural Gas Industry, 2021, 41(1): 178-188.
[21] 孙焕泉, 周德华, 赵培荣, 等. 中国石化地质工程一体化发展方向[J]. 油气藏评价与开发, 2021, 11(3): 269-280.
SUN Huanquan, ZHOU Dehua, ZHAO Peirong, et al.Geology- engineering integration development direction of Sinopec[J]. Reservoir Evaluation and Development, 2021, 11(3): 269-280.
[22] 张艳, 张春雷, 成育红, 等. 基于机器学习的多地震属性沉积相分析[J]. 特种油气藏, 2018, 25(3): 13-17.
ZHANG Yan, ZHANG Chunlei, CHENG Yuhong, et al.Multi-attribute seismic sedimentary facies analysis based on machine learning[J]. Special Oil & Gas Reservoirs, 2018, 25(3): 13-17.
[23] DAS V, MUKERJI T.Petrophysical properties prediction from pre-stack seismic data using convolutional neural networks[M]// BEVC D, NEDORUB O. SEG Technical Program Expanded Abstracts 2019. Houston: Society of Exploration Geophysicists, 2019: 2328-2332.
[24] 吴正阳, 莫修文, 柳建华, 等. 裂缝性储层分级评价中的卷积神经网络算法研究与应用[J]. 石油物探, 2018, 57(4): 618-626.
WU Zhengyang, MO Xiuwen, LIU Jianhua, et al.Convolutional neural network algorithm for classification evaluation of fractured reservoirs[J]. Geophysical Prospecting for Petroleum, 2018, 57(4): 618-626.
[25] AL-ANAZI A F, GATES I D. Support vector regression to predict porosity and permeability: Effect of sample size[J]. Computers & Geosciences, 2012, 39: 64-76.
[26] 安鹏, 曹丹平, 赵宝银, 等. 基于LSTM循环神经网络的储层物性参数预测方法研究[J]. 地球物理学进展, 2019, 34(5): 1849-1858.
AN Peng, CAO Danping, ZHAO Baoyin, et al.Reservoir physical parameters prediction based on LSTM recurrent neural network[J]. Progress in Geophysics, 2019, 34(5): 1849-1858.
[27] ALFARRAJ M, ALREGIB G.Semi-supervised learning for acoustic impedance inversion[M]//BEVC D, NEDORUB O. SEG Technical Program Expanded Abstracts 2019. Houston: Society of Exploration Geophysicists, 2019: 2298-2302.
[28] 黄旭日, 代月, 徐云贵, 等. 基于深度学习算法不同数据集的地震反演实验[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 16-25.
HUANG Xuri, DAI Yue, XU Yungui, et al.Seismic inversion experiments based on deep learning algorithm using different datasets[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2020, 42(6): 16-25.
[29] BOLANDI V, KADKHODAIE A, FARZI R.Analyzing organic richness of source rocks from well log data by using SVM and ANN classifiers: A case study from the Kazhdumi Formation, the Persian Gulf Basin, offshore Iran[J]. Journal of Petroleum Science and Engineering, 2017, 151: 224-234.
[30] 王惠君, 赵桂萍, 李良, 等. 基于卷积神经网络(CNN)的泥质烃源岩TOC预测模型: 以鄂尔多斯盆地杭锦旗地区为例[J]. 中国科学院大学学报, 2020, 37(1): 103-112.
WANG Huijun, ZHAO Guiping, LI Liang, et al.TOC prediction model for muddy source rocks based on convolutional neural network (CNN): A case study of the Hangjinqi area of the Ordos Basin[J]. Journal of University of Chinese Academy of Sciences, 2020, 37(1): 103-112.
[31] 李硕, 韩迎东, 王双, 等. 基于Pearson相关系数的图像误匹配点剔除算法[J]. 激光与光电子学进展, 2021, 58(8): 0810025.
LI Shuo, HAN Yingdong, WANG Shuang, et al.Algorithm for eliminating mismatched points based on Pearson correlation coefficient[J]. Laser & Optoelectronics Progress, 2021, 58(8): 0810025.
[32] YANG X B, YU H Z, WANG D, et al.Road identification system based on CNN[J]. Journal of Physics: Conference Series, 2020, 1486: 042024.
[33] CHICCO D, WARENS M J, JURMAN G.The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. PeerJ Computer Science, 2021, 7: e623.
[34] 赵亚楠, 郭华玲, 郑宾, 等. 基于KPCA和LSSVM的表面缺陷深度识别[J]. 激光杂志, 2021, 42(3): 74-78.
ZHAO Yanan, GUO Hualing, ZHENG Bin, et al.Research on the surface defect depth recognition based on KPCA and LSSVM[J]. Laser Journal, 2021, 42(3): 74-78.

Options

Abstract

Outlines

模态框（Modal）标题

Abstract

Cite this article

References