Quantitative prediction of tight sandstone sweet spots based on deep learning method with prior information constraints
WANG Di1,2, ZHANG Yiming1,2, ZHANG Fanchang3, DING Jicai1,2, NIU Cong1,2
1. CNOOC Research Institute Co., Ltd., Beijing 100028, China; 2. National Engineering Research Center of Offshore Oil and Gas Exploration, Beijing 100028, China; 3. School of Geosciences, China University of Petroleum (East China), Qingdao, Shandong 266580, China
Abstract:The Permian Shihezi Formation is located at the LX block at the eastern margin of the Ordos Basin, and it develops tight sandstone reservoirs with fluvial facies. Reservoirs with high gas production feature a porosity of larger than 12%, a permeability of higher than 1 mD, and a gas saturation of more than 50%, and the quantitative evaluation of reservoir parameters shall be urgently carried out to find sweet spots with high production. However, the accuracy of indirectly predicting porosity and other parameters by traditional seismic inversion is low. In addition, the seismic data and well-logging curves of the LX block have inconsistent corresponding relations, and a lot of conflict samples exist, which makes conventional convolutional neural networks difficult to be applied. Therefore, a fully connected network architecture is added to the conventional convolutional neural network, and the seismic data and well-logging data are connected through local Toeplitz network architecture, so as to deal with the indirect correlation between reservoir parameters and seismic data. The fully connected network architecture can address the conflict samples by introducing prior information including the line/channel number, horizon, and seismic facies. Furthermore, a deep learning network model suitable for tight reservoirs is established by introducing prior constraint information such as stratigraphic framework and seismic facies, and a geo-oriented method for selecting the best sample well is developed, so as to quantitatively predict reservoir parameters and describe the plane distribution of the sweet spots in reservoirs with high gas production. The actual application results show that the predicted results of porosity, permeability, and gas saturation are in good agreement with the well-logging data, and the newly deployed five wells are tested and achieve an open-flow capacity of more than 10,000 m3/d during drilling, which effectively promotes the efficient development of tight gas.
张国生,赵文智,杨涛,等.我国致密砂岩气资源潜力、分布与未来发展地位[J].中国工程科学,2012,14(6):87-93.ZHANG Guosheng,ZHAO Wenzhi,YANG Tao,et al.Resource evaluation,position and distribution of tight sandstone gas in China[J]. Strategic Study of CAE,2012, 14(6):87-93.
[2]
侯加根,唐颖,刘钰铭,等.鄂尔多斯盆地苏里格气田东区致密储层分布模式[J].岩性油气藏,2014,26(3):1-6 HOU Jiagen,TANG Ying,LIU Yuming,et al.Distribution patterns of tight reservoirs in eastern Sulige gas field,Ordos basin[J]. Lithologic Reservoirs,2014,26(3):1-6.
[3]
张林清,张会星,姜效典,等.弹性参数反演与属性融合技术在“甜点”预测中的应用[J].天然气地球科学,2017,28(4):582-589.ZHANG Linqing,ZHANG Huixing,JIANG Xiaodian,et al.Application of elastic parameters inversion and attribute fusion technology in the “sweet spot” prediction[J].Natural Gas Geoscience,2017,28(4):582-589.
[4]
李岳桐,卢宗盛,吴振东,等.沧东凹陷孔二段细粒沉积岩致密油甜点预测[J].石油地球物理勘探,2018,53(5):1059-1066.LI Yuetong,LU Zongsheng,WU Zhendong,et al.Sweet spot prediction for fine-grain sediment reservoirs in the Cangdong Sag[J].Oil Geophysical Prospecting,2018,53(5):1059-1066.
[5]
李久娣,孙莉,魏水建,等.东海海域深层HG组低渗储层“甜点”预测方法及应用[J].石油物探,2019,58(5):758-765.LI Jiudi,SUN Li,WEI Shuijian,et al.“Sweet spot” prediction and its application in the low permeability reservoir of the deep HG formation in the East China Sea[J].Geophysical Prospecting for Petroleum,2019,58(5):758-765.
[6]
孙文举,王应斌,徐文军.鄂尔多斯东缘雷家碛地区盒8段致密储层“甜点”预测[J].岩性油气藏,2019,31(1):69-77.SUN Wenju,WANG Yingbin,XU Wenjun.Sweet spot prediction of tight reservoir of He 8 member in Leijiaqi area,eastern margin of Ordos Basin[J].Lithologic Reservoirs,2019,31(1):69-77.
[7]
韩刚,高红艳,龙凡,等.叠前反演在西湖凹陷致密砂岩储层“甜点”预测中的应用[J].石油物探,2021,60(3):471-478.HAN Gang,GAO Hongyan,LONG Fan,et al.Prestack elastic inversion for sweet-spot prediction in tight reservoirs in Xihu Sag[J].Geophysical Prospecting for Petroleum,2021,60(3):471-478.
[8]
韩飞鹏,宋光建,吴振坤,等.致密油“甜点”多属性融合预测技术[J].特种油气藏,2019,26(1):94-99.HAN Feipeng,SONG Guangjian,WU Zhenkun,et al.Multi-attribute fusion prediction technique for tight oil “sweets” [J].Special Oil & Gas Reservoirs,2019,26(1):94-99.
[9]
朱永才,姜懿洋,吴俊军,等.吉木萨尔凹陷致密油储层物性定量预测[J].特种油气藏,2017,24(4):42-47.ZHU Yongcai,JIANG Yiyang,WU Junjun,et al.Quantitative prediction of tight oil reservoir properties in Jumusar depression[J].Special Oil & Gas Reservoirs,2017,24(4):42-47.
[10]
王迪,张益明,刘志斌,等.AVO定量解释模版在LX地区致密气“甜点”预测中的应用[J].石油物探,2020,59(6):936-948.WANG Di,ZHANG Yiming,LIU Zhibin,et al.Application of an AVO template to identify sweet spots in a tight sandstone reservoir in the LX area [J].Geophysical Prospecting for Petroleum,2020,59(6):936-948.
[11]
汪关妹,张万福,张宏伟,等.致密砂岩气地震预测关键技术及效果[J].石油地球物理勘探,2020,55(增刊1):72-79.WANG Guanmei,ZHANG Wanfu,ZHANG Hongwei,et al.Key technology and effect of prediction of tight sandstone gas based on seismic data[J].Oil Geophysical Prospecting,2020,55(S1):72-79.
[12]
JAISWAL P,VARACCHI B,EBRAHIMI P,et al.Can seismic velocities predict sweet spots in the Woodford Shale?A case study from McNeff 2-28 Well,Grady County,Oklahoma[J].Journal of Applied Geophysics,2014,104(5):26-34.
[13]
SREEDURGA S,BINEET M,RAJESH S,et al.Seismic attribute analysis for fracture detection and poro-sity prediction:A case study from tight volcanic reservoirs,Barmer Basin,India[J].The Leading Edge,2017,36(11):947b1-947b7.
[14]
宋磊,印兴耀,宗兆云,等.基于先验约束的深度学习地震波阻抗反演方法[J].石油地球物理勘探,2021,56(4):716-727.SONG Lei,YIN Xingyao,ZONG Zhaoyun,et al.Deep learning seismic impedance inversion based on prior constraints[J].Oil Geophysical Prospecting,2021,56(4):716-727.
[15]
张玉玺,刘洋,张浩然,等.基于深度学习的多属性盐丘自动识别方法[J].石油地球物理勘探,2020,55(3):475-483.ZHANG Yuxi,LIU Yang,ZHANG Haoran,et al.Multi-attribute automatic interpretation of salt domes based on deep learning[J].Oil Geophysical Prospecting,2020,55(3):475-483.
[16]
朱剑兵,王兴谋,冯德永,等.基于双向循环神经网络的河流相储层预测方法及应用[J].石油物探,2020,59(2):250-257.ZHU Jianbing,WANG Xingmou,FENG Deyong,et al.Predicting fluvial reservoirs using seismic data based on a Bi-recurrent neural network[J].Geophysical Prospecting for Petroleum,2020,59(2):250-257.
[17]
杜昕,范廷恩,董建华,等.基于多层感知机网络的薄储层预测[J].石油地球物理勘探,2020,55(6):1178-1187.DU Xin,FAN Ting’en,DONG Jianhua,et al.Characterization of thin sand reservoirs based on a multi-layer perceptron deep neural network[J].Oil Geophysical Prospecting,2020,55(6):1178-1187.
[18]
丁燕,杜启振,YASIN Qamar,等.基于深度学习的裂缝预测在S区潜山碳酸盐岩储层中的应用[J].石油物探,2020,59(2):267-275.DING Yan,DU Qizhen,YASIN Q,et al.Fracture prediction based on deep learning:Application to a buried hill carbonate reservoir in the S area[J].Geophysical Prospecting for Petroleum,2020,59(2):267-275.
[19]
杨柳青,查蓓,陈伟.基于深度神经网络的砂岩储层孔隙度预测方法[J].中国科技论文,2020,15(1):73-80.YANG Liuqing,ZHA Bei,CHEN Wei.Prediction method of reservoir porosity based on deep neural network[J].China Science Paper,2020,15(1):73-80.
[20]
陈康,狄贵东,张佳佳,等.基于改进U-Net卷积神经网络的储层预测[J].CT理论与应用研究,2021,30(4):403-416.CHEN Kang,DI Guidong,ZHANG Jiajia,et al.Reservoir prediction based on improved U-Net convolutional neural network[J].CT Theory and Applications,2021,30(4):403-416.
[21]
闫星宇,顾汉明,罗红梅,等.基于改进深度学习方法的地震相智能识别[J].石油地球物理勘探,2020,55(6):1169-1177.YAN Xingyu,GU Hanming,LUO Hongmei,et al.Intelligent seismic facies classification based on an improved deep learning method[J].Oil Geophysical Prospecting,2020,55(6):1169-1177.
[22]
王俊,曹俊兴,尤加春,等.基于门控循环单元神经网络的储层孔渗饱参数预测[J].石油物探,2020,59(4):616-627.WANG Jun,CAO Junxing,YOU Jiachun,et al.Prediction of reservoir porosity,permeability,and saturation based on a gated recurrent unit neural network[J].Geophysical Prospecting for Petroleum,2020,59(4):616-627.
[23]
刘力辉,陆蓉,杨文魁.基于深度学习的地震岩相反演方法[J].石油物探,2019,58(1):123-129.LIU Lihui,LU Rong,YANG Wenkui.Seismic lithofacies inversion based on deep learning[J].Geophysical Prospecting for Petroleum,2019,58(1):123-129.
[24]
张益明,张繁昌,丁继才,等.基于混合深度学习网络的致密砂岩甜点预测[J].石油物探,2021,60(6):995-1002.ZHANG Yiming,ZHANG Fanchang,DING Jicai,et al. Sweet spot prediction in tight sand reservoirs by a hybrid deep-learning network[J].Geophysical Prospecting for Petroleum,2021,60(6):995-1002.